A big data-based intelligent alarm platform coordination optimization operation method and system

Abstract

The application provides a big data-based intelligent alarm platform coordination optimization operation method and system, relates to the technical field of data processing, and comprises the following steps: according to monitored enterprise information, node information and node association information, establishing a node abnormal monitoring association framework corresponding to a to-be-monitored enterprise on an intelligent alarm platform; based on a pre-constructed node abnormality detection alarm model, performing abnormality detection on the running state data of the node, and outputting the detection result of the node; if the detection result of the node is abnormal, identifying whether the node sends alarm information in the node abnormal monitoring association framework, if the node does not send alarm information, marking the node abnormality in the node abnormal monitoring association framework and sending alarm information, and if the node has sent alarm information, no alarm information needs to be sent again. The application avoids repeated alarms caused by the abnormality of a certain node, processes the alarms in time, and improves the abnormal event processing efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and particularly relates to a big data-based intelligent alarm platform coordination optimization operation method and system. BACKGROUND

[0002] The intelligent alarm platform is an operation and maintenance tool based on artificial intelligence technology and big data analysis, aiming to help enterprises quickly and accurately identify and respond to system failures and abnormal situations. It can monitor and analyze various data such as server performance indicators, network traffic, log files, etc. in real time, so as to automatically detect potential failure signs and generate corresponding alarm information.

[0003] The intelligent alarm platform has many powerful functions. It can not only monitor various data, but also automatically learn and optimize alarm rules based on historical data and machine learning algorithms to improve the accuracy and credibility of alarms. In addition, it also supports custom alarm strategies and flexible notification methods to meet the actual needs of different operation and maintenance teams.

[0004] However, in large-scale systems, a large number of abnormal events may occur, each of which triggers alarm notification, which will cause a great burden to system managers, and may even cause alarm information overload. At present, the intelligent alarm platform is prone to abnormal event errors, frequent alarms or a large number of repeated alarms, resulting in inaccurate or repeated alarm data, and unable to find and handle the real abnormal events in time and accurately, thus leading to low efficiency of abnormal event handling.

[0005] Therefore, the technical problem to be solved at present is how to provide a big data-based intelligent alarm platform coordination optimization operation method and system to find and handle the real abnormal events in time and accurately, and improve the efficiency of abnormal event handling. SUMMARY

[0006] The present application aims to provide a big data-based intelligent alarm platform coordination optimization operation method and system to avoid repeated alarms for abnormal nodes, handle alarms in time, and improve the efficiency of abnormal event handling.

[0007] To achieve the above object, the application provides a big data-based intelligent alarm platform coordination optimization operation method, which comprises the following steps: in response to abnormal monitoring of a node of an enterprise, obtaining enterprise information, node information and node association information; according to the monitored enterprise information, node information and node association information, establishing a node abnormal monitoring association framework corresponding to the enterprise to be monitored on the intelligent alarm platform; receiving the running state data of the node of the enterprise, performing abnormal detection on the running state data of the node based on a pre-constructed node abnormal detection alarm model, and outputting the detection result of the node; if the detection result of the node is abnormal, identifying whether the node sends an alarm information in the node abnormal monitoring association framework, if the node does not send an alarm information, marking the abnormal node in the node abnormal monitoring association framework and sending an alarm information, if the node has sent an alarm information, no alarm information needs to be sent again; according to the type of the abnormal node, selecting other normal nodes with the same type as the current abnormal node from the enterprise to replace the abnormal node.

[0008] The big data-based intelligent alarm platform coordination optimization operation method as described above, wherein the method further comprises: collecting service performance data of the selected normal node; calculating a service reliability value of the normal node according to the type of the normal node and the service performance data; and replacing the abnormal node in the node abnormal monitoring association framework with the normal node with the largest service reliability value and the same type as the current abnormal node.

[0009] The big data-based intelligent alarm platform coordination optimization operation method as described above, wherein the method further comprises: predicting whether a task being executed by the enterprise can be completed on time, evaluating a predicted completion reliability value of the task being executed by the enterprise; comparing the predicted completion reliability value of the task being executed by the enterprise with a preset reliability threshold value, if the predicted completion reliability value of the task being executed by the enterprise is greater than the preset reliability threshold value, continuing to evaluate other tasks of the enterprise, otherwise, optimizing resources for the task being executed by the enterprise.

[0010] The big data-based intelligent alarm platform coordination optimization operation method as described above, wherein the method of establishing the node abnormal monitoring association framework corresponding to the enterprise to be monitored on the intelligent alarm platform comprises the following steps: establishing a basic framework of point-line connection according to the enterprise information; filling the node information on multiple points of the basic framework; and connecting the associated points through lines according to the node association information, and deleting the lines between the unassociated points.

[0011] The method for coordinating and optimizing the operation of the intelligent alarm platform based on big data, wherein the method for predicting whether the task being performed by the enterprise can be completed on time and evaluating the predicted completion reliability value of the task being performed by the enterprise comprises: collecting attribute feature data and use feature data of the task being performed by the enterprise; and calculating the predicted completion reliability value of the task being performed by the enterprise according to the collected attribute feature data and use feature data of the task.

[0012] The method for coordinating and optimizing the operation of the intelligent alarm platform based on big data, wherein the method for pre-building a node anomaly detection alarm model comprises: obtaining abnormal operation state data of the nodes of the enterprise as a training set; inputting the training set into a neural network basic learning model for training to obtain a trained model as the node anomaly detection alarm model.

[0013] The method for coordinating and optimizing the operation of the intelligent alarm platform based on big data, wherein after the resource optimization of the task being performed by the enterprise, the predicted completion reliability value of the task being performed by the enterprise is recalculated until the predicted completion reliability value of the task being performed by the enterprise is greater than a preset reliability threshold, and then the resource optimization of the task being performed by the enterprise is not needed, otherwise, the resource optimization of the task being performed by the enterprise is continued.

[0014] As a second aspect of the present application, the present application provides a system for coordinating and optimizing the operation of an intelligent alarm platform based on big data, which comprises: an acquisition module configured to acquire enterprise information, node information and node association information in response to abnormal monitoring of nodes of a certain enterprise; a construction module configured to establish a node abnormal monitoring association framework corresponding to the enterprise to be monitored on the intelligent alarm platform according to the acquired enterprise information, node information and node association information; an anomaly detection module configured to receive operation state data of the nodes of the enterprise, perform anomaly detection on the operation state data of the nodes based on a pre-built node anomaly detection alarm model, and output a detection result of the nodes; an alarm module configured to identify whether the node sends an alarm information in the node abnormal monitoring association framework if the detection result of the node is abnormal, mark the node as abnormal in the node abnormal monitoring association framework and send the alarm information if the node does not send the alarm information, and not send the alarm information again if the node has sent the alarm information; and a selection module configured to select other normal nodes of the same type as the current abnormal node from the enterprise to replace the abnormal node according to the type of the abnormal node.

[0015] The intelligent alarm platform based on big data coordinates and optimizes the operation system as described above, wherein the system further comprises: a data acquisition module configured to acquire service performance data of selected normal nodes; a data processor configured to calculate service reliability values of the normal nodes according to types of the normal nodes and the service performance data; and a data comparator configured to replace an abnormal node in the node abnormality monitoring correlation framework with a normal node having the largest service reliability value and the same type as the current abnormal node.

[0016] The intelligent alarm platform based on big data coordinates and optimizes the operation system as described above, wherein the system further comprises: the data processor is further configured to predict whether a task being performed by the enterprise can be completed on time, and evaluate a predicted completion reliability value of the task being performed by the enterprise; and the data comparator is further configured to compare the predicted completion reliability value of the task being performed by the enterprise and a preset reliability threshold value, if the predicted completion reliability value of the task being performed by the enterprise is greater than the preset reliability threshold value, the other tasks of the enterprise are continuously evaluated, otherwise, the task being performed by the enterprise is optimized in terms of resources.

[0017] The beneficial effects achieved by the present application are as follows:

[0018] (1) The application of the intelligent alarm platform of the present application brings many benefits. First, it greatly shortens the troubleshooting and recovery time, so that the operation and maintenance personnel can take action more quickly. Second, by reducing the false positive rate, the intelligent alarm platform can avoid unnecessary interference and improve overall operation and maintenance efficiency. In addition, the intelligent alarm platform also has the advantages of reducing fault handling cost, improving team communication and cooperation efficiency, and through seamless integration with various monitoring tools, it realizes integrated centralized management and provides a more perfect alarm solution for enterprises.

[0019] (2) The present application avoids repeated alarms for the abnormality of a certain node, and timely handles the alarms to improve the efficiency of handling abnormal events. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments described in the present application, and other drawings can also be obtained by those skilled in the art based on these drawings.

[0021] Figure 1 A flowchart of a big data-based intelligent alarm platform coordination and optimization operation method according to an embodiment of the present application.

[0022] Figure 2 A structural schematic diagram of a big data-based intelligent alarm platform coordination and optimization operation system according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of the present application.

[0024] Embodiment one

[0025] As shown in the drawings, the present application provides a method for coordinating and optimizing operation of an intelligent alarm platform based on big data, which comprises the following steps: Figure 1

[0026] Step S1, in response to abnormal monitoring of a node of an enterprise, obtaining enterprise information, node information and node association information of the monitoring.

[0027] The enterprise information includes the type (production enterprise, financial enterprise, sales enterprise, etc.), name, address and number of the enterprise. The nodes of the enterprise include production equipment, network equipment, storage equipment, data acquisition equipment, sales equipment (such as vending machines, etc.) and management equipment, etc. The node information includes the type, name, number, location, etc. of the node. The node association information includes that the production equipment is connected with the management equipment through the network equipment, the data acquisition equipment is connected with the management equipment and the storage equipment through the network equipment, the data acquisition equipment sends the collected node operation state data to the management equipment and / or the storage equipment through the network equipment, the sales equipment is connected with the storage equipment and the management equipment through the network equipment, etc., and the sales equipment sends the sales data to the storage equipment and / or the management equipment through the network equipment.

[0028] Step S2, according to the monitored enterprise information, node information and node association information, establishing a node abnormal monitoring association framework corresponding to the enterprise to be monitored on the intelligent alarm platform.

[0029] The method for establishing a node abnormal monitoring association framework corresponding to the enterprise to be monitored on the intelligent alarm platform comprises:

[0030] Step S210, according to the enterprise information, establishing a basic framework of point-line connection.

[0031] Step S220, filling the node information on multiple points of the basic framework.

[0032] Step S230, according to the node association information, connecting the associated points through lines, and deleting the lines between the unassociated points.

[0033] ​Step S3, receiving the running state data of the nodes of the enterprise, performing abnormality detection on the running state data of the nodes based on the pre-constructed node abnormality detection alarm model, and outputting the detection result of the nodes.

[0034] As a specific embodiment of the present application, the computing unit of the intelligent alarm platform receives the data collected by the data collection device (i.e., the running state data of the nodes of the enterprise), the node abnormality detection alarm model pre-constructed on the computing unit, analyzes and processes the data collected by the data collection device through the pre-constructed node abnormality detection alarm model, obtains an analysis and processing result, and then sends the processing result to the auditing unit for auditing and stores the auditing result in the storage unit.

[0035] As a specific embodiment of the present application, the pre-constructed node abnormality detection alarm model is used to perform abnormality detection on the running state data of the nodes, without the need for manual investigation of the abnormality of each node, greatly shortening the troubleshooting and recovery time, and enabling the operation and maintenance personnel to take action more quickly. Secondly, the node abnormality detection alarm model is periodically optimized (using an existing model optimization method), and the optimized node abnormality detection alarm model can reduce the false alarm rate, the intelligent alarm platform can avoid unnecessary interference, and the overall operation and maintenance efficiency is improved.

[0036] The method for pre-constructing the node abnormality detection alarm model comprises:

[0037] Step S310, obtaining the abnormal running state data of the nodes of the enterprise as a training set.

[0038] Step S320, inputting the training set into the neural network basic learning model for training, and obtaining the trained model as the node abnormality detection alarm model.

[0039] The node abnormality detection alarm model is used to detect the running state data of the nodes and output the detection result of the nodes. The node abnormality detection alarm model of the present application uses an existing training method, which will not be described here.

[0040] Step S4, if the detection result of the node is abnormal, identifying whether the node has sent alarm information in the node abnormality monitoring association framework, if not, marking the node as abnormal in the node abnormality monitoring association framework and sending alarm information, and if so, no need to send alarm information again.

[0041] Specifically, the method for identifying whether the node has sent alarm information in the node abnormality monitoring association framework is, for example, identifying whether the node has been marked as abnormal or has been marked as alarming in the node abnormality monitoring association framework, if so, the node has sent alarm information, otherwise, the node has not sent alarm information.

[0042] Step S5, according to the type of the abnormal node, selecting other normal nodes with the same type as the current abnormal node from the enterprise to replace the abnormal node.

[0043] Specifically, according to the type of the abnormal node, selecting other normal nodes with the same type as the current abnormal node from the enterprise, and collecting service performance data of the selected normal nodes at the current time.

[0044] Step S6, collecting service performance data of the selected normal nodes.

[0045] The service performance data of the normal node includes: the number of remaining connectable devices, the average delay time of responding to instructions, the proportion of non-responding instructions, working state data (working current, working voltage, power, etc.), and the like.

[0046] Step S7, according to the type and service performance data of the normal node, calculating the service reliability value of the normal node.

[0047] The type of the normal node includes: production equipment, network equipment, storage equipment, data acquisition equipment, sales equipment (such as vending machines, etc.), and management equipment, etc.

[0048] The service reliability value of the normal node is calculated according to the following formula:

[0049]

[0050] Wherein, JF represents the service reliability value of the normal node; S1 represents the influence weight of the number of remaining connectable devices of the normal node on the service reliability value; LS represents the number of remaining connectable devices of the normal node; LZ represents the total number of connectable devices of the normal node; S2 represents the influence weight of the average delay time of responding to instructions of the normal node on the service reliability value; TPx represents the average delay time of responding to instructions of the normal node; Tb represents the theoretical delay time of responding to instructions of the normal node; S3 represents the influence weight of the proportion of non-responding instructions of the normal node on the service reliability value; θw represents the proportion of non-responding instructions of the normal node; S4 represents the influence weight of the working state data of the normal node on the service reliability value; V represents the total number of types of working state data of the normal node; GZ h represents the measured value of the collection data time of the hth type of working state data of the normal node; GB h represents the standard value of the hth type of working state data of the normal node; represents the allowable deviation value of the hth type of working state data of the normal node.

[0051] The application calculates the service reliability value of the normal node according to the type and service performance data of the normal node, improves the calculation accuracy of the service reliability value of the normal node, and selects the normal node with the maximum service reliability value to replace the abnormal node, so that the abnormal node is replaced by the normal node with the maximum service reliability value in time, the enterprise can execute the corresponding task in time, the enterprise production suspension, failure and other phenomena caused by the abnormal node are avoided, the enterprise loss is reduced, and after the abnormal node is repaired, a reminder of the completion of the repair of the abnormal node is sent to the enterprise, so that the repaired node can be used again.

[0052] Step S8, the abnormal node in the node abnormality monitoring association framework is replaced by the normal node with the maximum service reliability value of the same type as the current abnormal node.

[0053] Step S9, whether the task being executed by the enterprise can be completed on time is predicted, and the predicted completion reliability value of the task being executed by the enterprise is evaluated.

[0054] Step S9 includes the following steps:

[0055] Step S910, attribute feature data and use feature data of the task being executed by the enterprise are collected.

[0056] Step S920, the predicted completion reliability value of the task being executed by the enterprise is calculated according to the collected attribute feature data and use feature data of the task.

[0057] The attribute feature data of the task includes: task type, task requirement deadline, task execution start time, total task amount (or total data amount), executed task amount, percentage of the remaining unexecuted part of the current task in the total task, etc. The task type is, for example, reading task, writing task, deleting task, etc.

[0058] The use feature data of the task includes: resource feature data used in the executed process of the task. The resource feature data includes: negative index data (CPU occupancy rate, memory occupancy rate, network response speed), positive index data (network data transmission bandwidth, number of parallel processable processes, etc.

[0059] The calculation formula of the predicted completion reliability value of the task being executed by the enterprise is as follows:

[0060]

[0061] wherein YK represents a predicted completion reliability value of a task being performed by the enterprise; RY represents an amount of tasks already performed; RZ represents a total amount of tasks; Td represents a current time; Tz represents a task execution start time; TJ represents a task requirement deadline; M represents a total number of types of negative indicator data used in resource characteristic data used in the task already performed process; QRL i represents an influence weight of the i-th negative indicator data on a completion reliability value of a current task type; FU maxi represents a maximum value of the i-th negative indicator data in the task already performed process; DQ i represents a measured value of the i-th negative indicator data at a current time; δt i represents a fluctuation factor of the i-th negative indicator data in the task already performed process; N represents a total number of types of positive indicator data used in resource characteristic data used in the task already performed process; WRL j represents an influence weight of the j-th positive indicator data on a completion reliability value of a current task type; XI j represents a measured value of the j-th positive indicator data at a current time; ZHE minj represents a minimum value of the j-th positive indicator data in the task already performed process; βt j represents a fluctuation factor of the j-th positive indicator data in the task already performed process.

[0062] wherein,

[0063] wherein FU i represents an average value of the i-th negative indicator data in the task already performed process; FU maxi represents a maximum value of the i-th negative indicator data in the task already performed process; FU mini represents a minimum value of the i-th negative indicator data in the task already performed process.

[0064] wherein,

[0065] wherein ZHE j represents an average value of the j-th positive indicator data in the task already performed process; ZHE maxj represents a maximum value of the j-th positive indicator data in the task already performed process; ZHE minj represents a minimum value of the j-th positive indicator data in the task already performed process.

[0066] It needs to be explained that different negative index data has different influence weights on the completion reliability value of different task types. For example, for read operation and write operation, the influence weight of memory occupancy rate on write operation is greater than that on read operation, for example, the influence weight of memory occupancy rate on write operation is 0.6, and the influence weight on read operation is 0.2. The influence weights of other negative index data on the completion reliability value of different task types are set according to requirements, which will not be repeated here.

[0067] It needs to be explained that the present application calculates the predicted completion reliability value of the task being executed by the enterprise according to the collected attribute feature data and use feature data of the task, and different negative index data has different influence weights on the completion reliability value of different task types, which improves the calculation accuracy of the predicted completion reliability value of the task being executed by the enterprise.

[0068] Step S10, compare the size of the predicted completion reliability value of the task being executed by the enterprise and the preset reliability threshold value, if the predicted completion reliability value of the task executed by the enterprise is greater than the preset reliability threshold value, continue to evaluate other tasks of the enterprise, otherwise, optimize the resources of the task being executed by the enterprise.

[0069] It needs to be explained that the present application compares the size of the predicted completion reliability value of the task being executed by the enterprise and the preset reliability threshold value through the predicted completion reliability value of the task being executed by the enterprise, if the predicted completion reliability value of the task executed by the enterprise is greater than the preset reliability threshold value, continue to evaluate other tasks of the enterprise, otherwise, optimize the resources of the task being executed by the enterprise, realize the evaluation of whether the task of the enterprise can be completed within the deadline, for the task executed by the enterprise, the predicted completion reliability value of which is less than the preset reliability threshold value, optimize the resources of the task, for example, increase the required resources of the task, so that the task being executed by the enterprise can be completed within the deadline, and improve the completion reliability of the task executed by the enterprise.

[0070] As a preferred embodiment of the present application, after optimizing the resources of the task being executed by the enterprise, the predicted completion reliability value of the task being executed by the enterprise is recalculated until the predicted completion reliability value of the task being executed by the enterprise is greater than the preset reliability threshold value, then the resources of the task being executed by the enterprise do not need to be optimized, otherwise, continue to optimize the resources of the task being executed by the enterprise, so as to ensure that the task can be completed within the deadline.

[0071] As a specific embodiment of the present application, the method for optimizing the resources of the task being executed by the enterprise is to increase new resources for the task being executed by the enterprise.

[0072] The application of the intelligent alarm platform brings many benefits. First, it greatly shortens the troubleshooting and recovery time, enabling the operation and maintenance personnel to take action more quickly. Second, by reducing the false positive rate, the intelligent alarm platform can avoid unnecessary interference and improve overall operational efficiency. Finally, the intelligent alarm platform can also help the operation and maintenance team better manage workloads, optimize resource utilization, and respond to user feedback and needs in a timely manner. In addition, the intelligent alarm platform also has the advantages of reducing fault handling costs, improving team communication and collaboration efficiency, and seamlessly integrating with various monitoring tools to achieve integrated centralized management, providing a more complete alarm solution for enterprises.

[0073] Embodiment Two

[0074] As shown in Figure 2 The present application provides an intelligent alarm platform based on big data coordination optimization running system 100, which comprises:

[0075] The acquisition module 10 is configured to acquire enterprise information, node information and node association information in response to abnormal monitoring of nodes of an enterprise.

[0076] The construction module 20 is configured to establish a node abnormal monitoring association framework corresponding to the enterprise to be monitored on the intelligent alarm platform according to the monitored enterprise information, node information and node association information.

[0077] The abnormality detection module 30 is configured to receive the running state data of the nodes of the enterprise, perform abnormality detection on the running state data of the nodes based on the pre-constructed node abnormality detection alarm model, and output the detection result of the nodes.

[0078] The alarm module 40 is configured to identify whether the node sends an alarm information in the node abnormal monitoring association framework if the detection result of the node is abnormal, and if no alarm information is sent, mark the abnormal node in the node abnormal monitoring association framework and send an alarm information, and if the alarm information has been sent, no alarm information needs to be sent again.

[0079] The selection module 50 is configured to select other normal nodes with the same type as the current abnormal node from the enterprise to replace the abnormal node according to the type of the abnormal node.

[0080] The data acquisition module 60 is configured to acquire service performance data of the selected normal nodes.

[0081] The data processor 70 is configured to calculate the service reliability value of the normal nodes according to the type and service performance data of the normal nodes.

[0082] The data comparator 80 is configured to replace the abnormal node in the node abnormality monitoring and association framework with a normal node having the maximum service reliability value of the same type as the current abnormal node.

[0083] The data processor 70 is further configured to predict whether the task being executed by the enterprise can be completed on time, and evaluate the predicted completion reliability value of the task being executed by the enterprise.

[0084] The data comparator 80 is further configured to compare the predicted completion reliability value of the task being executed by the enterprise with a preset reliability threshold value, and if the predicted completion reliability value of the task being executed by the enterprise is greater than the preset reliability threshold value, continue to evaluate other tasks of the enterprise, otherwise, optimize resources for the task being executed by the enterprise.

[0085] The service reliability value of the normal node is calculated according to the following formula:

[0086]

[0087] The service reliability value of the normal node is calculated according to the following formula: h The service reliability value of the normal node is calculated according to the following formula: h The service reliability value of the normal node is calculated according to the following formula: The service reliability value of the normal node is calculated according to the following formula:

[0088] The attribute characteristic data of the task includes: task type, task requirement deadline, task execution start time, total task amount (or total task data amount), executed task amount, and percentage of the remaining unexecuted part of the current task in the total task.

[0089] The usage characteristic data of the task includes: resource characteristic data used in the executed process of the task. The resource characteristic data includes: negative index data (CPU occupancy rate, memory occupancy rate, network response speed), and positive index data (network data transmission bandwidth, and number of parallel processable processes).

[0090] The calculation formula of the predicted completion reliability value of the task being performed by the enterprise is as follows:

[0091]

[0092] wherein YK represents the predicted completion reliability value of the task being performed by the enterprise; RY represents the executed task amount; RZ represents the total task amount; Td represents the current time; Tz represents the task execution start time; TJ represents the task requirement deadline; M represents the total number of negative index data in the resource characteristic data used in the task execution process; QRL i represents the influence weight of the i-th negative index data on the completion reliability value of the current task type; FU maxi represents the maximum value of the i-th negative index data in the task execution process; DQ i represents the measured value of the i-th negative index data at the current time; δt i represents the fluctuation factor of the i-th negative index data in the task execution process; N represents the total number of positive index data in the resource characteristic data used in the task execution process; WRL j represents the influence weight of the j-th positive index data on the completion reliability value of the current task type; XI j represents the measured value of the j-th positive index data at the current time; ZHE minj represents the minimum value of the j-th positive index data in the task execution process; βt j represents the fluctuation factor of the j-th positive index data in the task execution process.

[0093] wherein,

[0094] wherein FU i represents the average value of the i-th negative index data in the task execution process; FU maxi represents the maximum value of the i-th negative index data in the task execution process; FU mini represents the minimum value of the i-th negative index data in the task execution process.

[0095] wherein,

[0096] wherein ZHE j represents the average value of the j-th positive index data in the task execution process; ZHE maxj represents the maximum value of the j-th positive index data in the task execution process; ZHE minj represents the minimum value of the j-th positive index data in the task execution process.

[0097] The application further provides a computer storage medium storing computer instructions, which are invoked to execute the address mapping method of the large-capacity solid state disk.

[0098] The disclosed embodiment provides a computer readable storage medium storing computer program instructions, which, when executed on a computer, cause the computer to execute the above-mentioned large data-based intelligent alarm platform coordination optimization running method.

[0099] The embodiment of the application provides a processor for processing the above-mentioned large data-based intelligent alarm platform coordination optimization running method.

[0100] In the embodiment of the application, the processor can be an integrated circuit chip with signal processing capability. The processor can be a general processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0101] The disclosed methods, steps and logic block diagrams in the embodiments of the application can be implemented or executed. The general processor can be a microprocessor or any conventional processor. The steps of the method disclosed in combination with the embodiments of the application can be directly embodied as hardware code processor execution or executed by a combination of hardware and software modules in the code processor. The software module can be located in a random memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register or other mature storage medium in the art. The processor reads the information in the storage medium and combines the hardware to complete the steps of the above method.

[0102] The storage medium can be a memory, for example, a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories.

[0103] The non-volatile memory can be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically EPROM (EEPROM), or a flash memory. The volatile memory can be a Random Access Memory (RAM) used as an external cache. By way of example, and not limitation, many forms of RAM are available, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous Dynamic RAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DRRAM).

[0104] The beneficial effects achieved by the present application are as follows:

[0105] (1) The application of the intelligent alarm platform brings many benefits. First of all, it greatly shortens the troubleshooting and recovery time, so that the operation and maintenance personnel can take action more quickly. Secondly, by reducing the false positive rate, the intelligent alarm platform can avoid unnecessary interference and improve overall operation and maintenance efficiency. In addition, the intelligent alarm platform also has the advantages of reducing fault handling cost, improving team communication and cooperation efficiency, etc., and through seamless docking with various monitoring tools, it realizes integrated centralized management and provides a more perfect alarm solution for enterprises.

[0106] (2) The present application avoids repeated alarms for the abnormality of a certain node, and timely handles the alarms to improve the efficiency of abnormal event handling.

[0107] In the description of the present application, the terms "first", "second" are only for the purpose of description, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features. In the description of the present application, the meaning of "multiple" is two or more, unless otherwise specifically limited.

[0108] In the description of the present application, the word "exemplary" is used to mean "serving as an example, instance, or illustration." Any implementation described as "exemplary" is not necessarily to be construed as preferred or advantageous over other implementations. The following description is presented to enable any person skilled in the art to make and use the application. Details are set forth in the following description for purpose of explanation. It should be appreciated that one of ordinary skill in the art would realize that the application can be practiced without the use of these specific details. In other instances, well-known structures and processes are not elaborated as they would be understood by one of ordinary skill in the art. Thus, the present application is not intended to be limited by the embodiments shown, but is to be accorded with the widest scope consistent with the principles and features disclosed.

[0109] The above description is merely illustrative of the embodiments of the present application and is not intended to limit the scope of the application. Variations and modifications as can be obvious to those skilled in the art do not, however, part from the spirit and scope of the application. What is claimed is:

Claims

1. A method for coordinating and optimizing operation of an intelligent alarm platform based on big data, characterized in that, The method comprises: In response to the abnormal monitoring of the nodes of a certain enterprise, obtaining the monitored enterprise information, node information and node association information; According to the monitored enterprise information, node information and node association information, an abnormal node monitoring association framework corresponding to the to-be-monitored enterprise is established on the intelligent alarm platform; Receive the running state data of the nodes of the enterprise, and based on the pre-constructed node abnormality detection alarm model, perform abnormality detection on the running state data of the nodes, and output the detection result of the nodes; If the detection result of the node is abnormal, identify whether the node sends an alarm information in the node abnormality monitoring association framework, if no alarm information is sent, mark the abnormal node in the node abnormality monitoring association framework, and send an alarm information, if the alarm information has been sent, no alarm information needs to be sent again; According to the type of the abnormal node, select other normal nodes with the same type as the current abnormal node from the enterprise to replace the abnormal node; Collect the service performance data of the selected normal node; According to the type and service performance data of the normal node, calculate the service reliability value of the normal node; Replace the abnormal node in the node abnormality monitoring association framework with the normal node with the largest service reliability value of the same type as the current abnormal node. 2.The big data based intelligent alarm platform coordination optimization operation method according to claim 1, characterized in that, The method further comprises: Predict whether the task being performed by the enterprise can be completed on time, and evaluate the predicted completion reliability value of the task being performed by the enterprise; Compare the predicted completion reliability value of the task being performed by the enterprise with the preset reliability threshold value, if the predicted completion reliability value of the task being performed by the enterprise is greater than the preset reliability threshold value, continue to evaluate other tasks of the enterprise, otherwise, optimize the resources of the task being performed by the enterprise.

3. The intelligent alarm platform coordination optimization operation method based on big data according to claim 1, characterized in that, The method of establishing an abnormal node monitoring association framework corresponding to the to-be-monitored enterprise on the intelligent alarm platform comprises: According to the enterprise information, establish a basic framework connected by points and lines; Fill the node information on multiple points of the basic framework; According to the node association information, connect the associated points through lines, and delete the lines between the unassociated points. 4.The big data based intelligent alarm platform coordination optimization operation method according to claim 2, characterized in that, The method of predicting whether the task being performed by the enterprise can be completed on time, and evaluating the predicted completion reliability value of the task being performed by the enterprise comprises: Collect attribute feature data and usage feature data of the task being performed by the enterprise; According to the collected attribute feature data and usage feature data of the task, calculate the predicted completion reliability value of the task being performed by the enterprise. 5.The big data based intelligent alarm platform coordination optimization operation method according to claim 1, characterized in that, The method of pre-constructing the node abnormality detection alarm model comprises: Obtain the abnormal running state data of the enterprise nodes as a training set; Input the training set into a neural network basic learning model for training, and obtain the trained model as the node abnormality detection alarm model. 6.The big data based intelligent alarm platform coordination optimization operation method according to claim 2, characterized in that, After optimizing the resources of the task being performed by the enterprise, recalculate the predicted completion reliability value of the task being performed by the enterprise until the predicted completion reliability value of the task being performed by the enterprise is greater than the preset reliability threshold value, then no further resource optimization is needed for the task being performed by the enterprise, otherwise, continue to optimize the resources of the task being performed by the enterprise.

7. A big data-based intelligent alarm platform coordination optimization operation system, characterized in that, The method of any one of claims 1-6 is performed, and the system comprises: an acquisition module configured to acquire monitored enterprise information, node information, and node association information in response to abnormal monitoring of a node of an enterprise; a construction module configured to establish a node abnormal monitoring association framework corresponding to the enterprise to be monitored on an intelligent alarm platform according to the monitored enterprise information, node information, and node association information; an abnormality detection module configured to receive running state data of a node of an enterprise, perform abnormality detection on the running state data of the node based on a pre-constructed node abnormality detection alarm model, and output a detection result of the node; an alarm module configured to identify whether the node sends alarm information in the node abnormal monitoring association framework if the detection result of the node is abnormal, mark the node as abnormal in the node abnormal monitoring association framework and send alarm information if the node does not send alarm information, and not send alarm information again if the node has sent alarm information; a selection module configured to select other normal nodes of the same type as a current abnormal node from the enterprise to replace the abnormal node according to the type of the abnormal node. 8.The big data based intelligent alarm platform coordination optimization running system according to claim 7, wherein, The system further comprises: a data acquisition module configured to acquire service performance data of the selected normal node; a data processor configured to calculate a service reliability value of the normal node according to the type of the normal node and the service performance data; a data comparator configured to replace the abnormal node in the node abnormal monitoring association framework with a normal node of the same type as the current abnormal node and having the largest service reliability value. 9.The big data based intelligent alarm platform coordination optimization running system according to claim 7, wherein, The system further comprises: the data processor is further configured to predict whether a task being performed by the enterprise can be completed on time and evaluate a predicted completion reliability value of the task being performed by the enterprise; the data comparator is further configured to compare the predicted completion reliability value of the task being performed by the enterprise with a preset reliability threshold value, continue to evaluate other tasks of the enterprise if the predicted completion reliability value of the task being performed by the enterprise is greater than the preset reliability threshold value, and otherwise, perform resource optimization on the task being performed by the enterprise.

Images