CN117633495A - Alarm handling determination method, device, equipment and storage medium - Google Patents
Alarm handling determination method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN117633495A CN117633495A CN202311638923.5A CN202311638923A CN117633495A CN 117633495 A CN117633495 A CN 117633495A CN 202311638923 A CN202311638923 A CN 202311638923A CN 117633495 A CN117633495 A CN 117633495A
- Authority
- CN
- China
- Prior art keywords
- alarm
- maintenance
- treatment
- information
- prediction model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 68
- 238000011282 treatment Methods 0.000 claims abstract description 197
- 238000012423 maintenance Methods 0.000 claims abstract description 188
- 238000012549 training Methods 0.000 claims abstract description 60
- 230000002787 reinforcement Effects 0.000 claims abstract description 27
- 238000003062 neural network model Methods 0.000 claims abstract description 13
- 238000004590 computer program Methods 0.000 claims description 16
- 238000004140 cleaning Methods 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 6
- 230000007246 mechanism Effects 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 5
- 238000011418 maintenance treatment Methods 0.000 abstract 1
- 230000000875 corresponding effect Effects 0.000 description 48
- 238000012545 processing Methods 0.000 description 19
- 230000008569 process Effects 0.000 description 11
- 238000004891 communication Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 238000013473 artificial intelligence Methods 0.000 description 4
- 230000005856 abnormality Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000003058 natural language processing Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000014509 gene expression Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 241000282412 Homo Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/211—Selection of the most significant subset of features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/092—Reinforcement learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Entrepreneurship & Innovation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Business, Economics & Management (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Educational Administration (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The embodiment of the invention discloses an alarm handling determining method, an alarm handling determining device, alarm handling determining equipment and a storage medium, wherein the method comprises the following steps: acquiring target treatment requirements and operation and maintenance alarm information to be processed; constructing a prompt word instruction according to the target handling requirement; inputting the operation and maintenance alarm information to be processed into a pre-trained alarm treatment prediction model based on the prompt word instruction, and determining alarm treatment operation corresponding to the operation and maintenance information to be processed according to the output result of the alarm treatment prediction model; the alarm treatment prediction model is a neural network model trained based on a human feedback reinforcement learning method. The alarm treatment prediction model is obtained by training based on a human feedback reinforcement learning method and is suitable for a neural network model for alarm operation and maintenance treatment determination, so that operation and maintenance alarm information generated in a large amount for a banking system can be automatically and rapidly and accurately treated, the alarm treatment determination speed is improved, the manual participation degree is reduced, and the operation and maintenance quality and the system operation safety are further improved.
Description
Technical Field
The present invention relates to the field of language processing technologies, and in particular, to a method, an apparatus, a device, and a storage medium for determining alarm handling.
Background
In the field of network security, alarms generally refer to an alert of a possible security breach or attack. When the system detects an alarm, measures need to be taken in time to treat so as to prevent the security hole from being attacked or utilized by people.
With the rapid development of banking, resource objects such as application systems, servers and devices of the data center internet technology (Internet Technology, IT) are geometrically increased, application system architecture is continuously evolved, association relations between applications and infrastructure are also increasingly complicated, and the number of monitoring resource objects and the alarm amount accessed by a monitoring platform are increased.
Because the alarm information is generally complex and needs to be judged and processed according to actual conditions, the traditional alarm treatment method often needs a large amount of manual intervention, and has low efficiency. For large-scale national banks, the number of resource objects and the number of daily alarms are extremely large, if the total alarms are manually and rapidly treated, a large amount of operation and maintenance personnel and labor cost are required to be consumed, unavoidable treatment errors exist in the manual treatment process, the operation and maintenance quality is reduced, and the requirements of the banks on high system safety are difficult to meet.
Disclosure of Invention
The invention provides an alarm treatment determining method, an alarm treatment determining device, alarm treatment determining equipment and a storage medium, which are used for automatically and quickly treating a large amount of alarm information generated by operation through an alarm treatment prediction model trained based on a human feedback reinforcement learning method, so that the alarm treatment determining speed is improved, the human participation degree is reduced, and the operation and maintenance quality and the system operation safety are improved.
In a first aspect, an alarm handling determination method provided by an embodiment of the present invention includes:
acquiring target treatment requirements and operation and maintenance alarm information to be processed;
constructing a prompt word instruction according to the target handling requirement;
inputting the operation and maintenance alarm information to be processed into a pre-trained alarm treatment prediction model based on the prompt word instruction, and determining alarm treatment operation corresponding to the operation and maintenance information to be processed according to the output result of the alarm treatment prediction model;
the alarm treatment prediction model is a neural network model trained based on a human feedback reinforcement learning method.
In a second aspect, an embodiment of the present invention provides an alarm handling determination apparatus, including:
the information acquisition module is used for acquiring target treatment requirements and operation and maintenance alarm information to be processed;
The instruction construction module is used for constructing a prompt word instruction according to the target handling requirement;
the alarm treatment determining module is used for inputting the operation and maintenance alarm information to be processed into the pre-trained alarm treatment prediction model based on the prompt word instruction, and determining alarm treatment operation corresponding to the operation and maintenance information of the alarm to be processed according to the output result of the alarm treatment prediction model;
the alarm treatment prediction model is a neural network model trained based on a human feedback reinforcement learning method.
In a third aspect, an embodiment of the present invention further provides an alarm handling determination device, including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the alarm handling determination method provided by the embodiments of the present invention.
In a fourth aspect, embodiments of the present invention also provide a storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform the alarm handling determination method provided by embodiments of the present invention.
The embodiment of the invention provides an alarm handling method, an alarm handling device, alarm handling equipment and a storage medium, wherein the alarm handling device, the alarm handling equipment and the storage medium are used for acquiring target handling requirements and operation and maintenance alarm information to be processed; constructing a prompt word instruction according to the target handling requirement; inputting the operation and maintenance alarm information to be processed into a pre-trained alarm treatment prediction model based on the prompt word instruction, and determining alarm treatment operation corresponding to the operation and maintenance information to be processed according to the output result of the alarm treatment prediction model; the alarm treatment prediction model is a neural network model trained based on a human feedback reinforcement learning method. By adopting the technical scheme, aiming at massive operation and maintenance alarm information acquired in real time in a system, a prompt word instruction constructed according to target treatment requirements is used, the prompt word instruction is input into a pre-trained alarm treatment prediction model for processing, the alarm treatment prediction model is used for automatically processing the alarm treatment information to be processed, alarm treatment operation corresponding to the operation and maintenance alarm information to be processed is obtained, and because the alarm treatment prediction model is trained based on a human feedback reinforcement learning method, the alarm treatment prediction model is suitable for a neural network model for determining the alarm operation and maintenance, has high-specialized operation and maintenance alarm operation determining capability, enables the operation and maintenance alarm information generated in a large number for a bank system to be automatically and rapidly treated, improves the alarm treatment determining speed, reduces the manual participation degree, and further improves the operation and maintenance quality and the system operation safety.
It should be understood that the description of this section is not intended to identify key or critical features of the embodiments of the application or to delineate the scope of the application. Other features of the present application will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of an alarm handling determination method according to a first embodiment of the present invention;
fig. 2 is a flowchart of a method for determining alarm handling according to a second embodiment of the present invention;
FIG. 3 is a flowchart illustrating an example of data preprocessing for determining operation and maintenance alarm feature information for operation and maintenance alarm information to be processed according to a second embodiment of the present invention;
FIG. 4 is a training flowchart of an alarm handling prediction model according to a second embodiment of the present invention;
fig. 5 is a schematic structural diagram of an alarm handling determining device according to a third embodiment of the present invention;
Fig. 6 is a schematic structural diagram of an alarm handling determining device according to a fourth embodiment of the present invention.
Detailed Description
In order to make the present application solution better understood by those skilled in the art, the following description will be made in detail and with reference to the accompanying drawings in the embodiments of the present application, it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
Fig. 1 is a flowchart of an alarm handling determination method according to a first embodiment of the present invention, where the embodiment of the present invention is applicable to fast handling of massive operation and maintenance alarm information generated by a large number of resource objects and complex systems, so as to determine a required handling operation for the alarm information. The method may be performed by an alert treatment determining apparatus, which may be configured in an alert treatment determining device. Alternatively, the alert handling determining device may be a notebook, a desktop computer, a smart tablet, etc., which the embodiments of the present invention do not limit.
As shown in fig. 1, the alarm handling determining method provided by the embodiment of the invention specifically includes the following steps:
s101, acquiring target treatment requirements and operation and maintenance alarm information to be processed.
In this embodiment, the target treatment requirement may be specifically understood as a requirement preset according to an actual situation or set and input according to an actual situation, so as to explicitly change from different types of operation and maintenance alarms to alarm treatment operation. The operation and maintenance alarm instruction to be processed can be specifically understood as alarm information generated by faults occurring in the operation process and acquired by an application system, and exemplary operation and maintenance alarm information to be processed can include server downtime, insufficient disk space, network abnormality and the like, which is not limited by the embodiment of the invention.
Specifically, based on a continuously evolving system architecture and an association relation between an application and an infrastructure, in the daily operation and maintenance process of a banking system, operation abnormality may occur in different nodes of the system, and due to different treatment requirements for abnormality under different architectures and association relations, requirements of different types of operation and maintenance alarms to alarm treatment operation can be set or acquired in a targeted manner, and simultaneously operation and maintenance alarm information occurring in the system is monitored and acquired in real time, and the acquired operation and maintenance alarm information is determined to be operation and maintenance alarm information to be processed. The operation and maintenance alarm information to be processed can be obtained through a monitoring platform in the system, and can be reported and obtained actively by different applications, and the embodiment of the invention is not limited to the above.
S102, constructing a prompt word instruction according to the target handling requirement.
In this embodiment, the prompt word instruction may be specifically understood as an artificial intelligence prompt word (prompt) that uses natural language to instruct or excite the artificial intelligence model to complete a specific task, and in this embodiment, may be understood as an instruction constructed according to a target treatment requirement to prompt the content and type of operation and maintenance alarm information input to the artificial intelligence model, and prompt the output content of the alarm treatment prediction model.
Specifically, according to the acquired target treatment requirement, an input content of the alarm treatment prediction model and an output content of the alarm treatment prediction model are expected to be input, and then a preset template can be utilized to construct a problem, a description or a specific mark sequence, and the instruction writing of the prompt word for the alarm treatment prediction model is completed by using a common vocabulary on the basis of considering the context and the context.
It should be clear that the construction of the promt should be straightforward, easy to understand, and relevant to the task description.
S103, inputting the operation and maintenance alarm information to be processed into a pre-trained alarm treatment prediction model based on the prompt word instruction, and determining alarm treatment operation corresponding to the operation and maintenance information to be processed according to the output result of the alarm treatment prediction model.
The alarm treatment prediction model is a neural network model trained based on a human feedback reinforcement learning method.
In the present embodiment, the alarm handling prediction model can be understood as specifically a neural network model for predicting an alarm handling operation corresponding to an operation and maintenance alarm based on operation and maintenance alarm information input therein. Alternatively, the alert treatment prediction model may be a natural language processing model trained based on a human feedback reinforcement learning (Reinforcement Learning from Human Feedback, RLHF) method. The alert handling prediction model may be an InstructGPT model, or may be another natural language processing model that may implement RLHF, as the embodiments of the present invention are not limited in this respect.
Specifically, since the prompt word instruction can help the model to better understand the meaning and task requirement of the input data, the prompt word instruction corresponding to the to-be-processed operation and maintenance alarm information can be selected, the to-be-processed operation and maintenance alarm information is input into the pre-trained alarm treatment prediction model, the alarm treatment prediction model is enabled to process based on the input to-be-processed operation and maintenance alarm information, and the output result of the model is determined to be an alarm treatment operation corresponding to the to-be-processed alarm operation and maintenance information. Alternatively, a plurality of alert handling operations may be included in the output result of the alert handling prediction model, and probability values corresponding to the alert handling operations, respectively, and the alert handling operation in which the probability value is highest may be determined as the alert handling operation corresponding to the alert operation and dimension information to be processed.
According to the technical scheme, the target treatment requirement and the operation and maintenance alarm information to be processed are acquired; constructing a prompt word instruction according to the target handling requirement; inputting the operation and maintenance alarm information to be processed into a pre-trained alarm treatment prediction model based on the prompt word instruction, and determining alarm treatment operation corresponding to the operation and maintenance information to be processed according to the output result of the alarm treatment prediction model; the alarm treatment prediction model is a neural network model trained based on a human feedback reinforcement learning method. By adopting the technical scheme, aiming at massive operation and maintenance alarm information acquired in real time in a system, a prompt word instruction constructed according to target treatment requirements is used, the prompt word instruction is input into a pre-trained alarm treatment prediction model for processing, the alarm treatment prediction model is used for automatically processing the alarm treatment information to be processed, alarm treatment operation corresponding to the operation and maintenance alarm information to be processed is obtained, and because the alarm treatment prediction model is trained based on a human feedback reinforcement learning method, the alarm treatment prediction model is suitable for a neural network model for determining the alarm operation and maintenance, has high-specialized operation and maintenance alarm operation determining capability, enables the operation and maintenance alarm information generated in a large number for a bank system to be automatically and rapidly treated, improves the alarm treatment determining speed, reduces the manual participation degree, and further improves the operation and maintenance quality and the system operation safety.
Example two
Fig. 2 is a flowchart of an alarm handling determination method provided by a second embodiment of the present invention, where the technical solution of the second embodiment of the present invention is further optimized based on the above-mentioned alternative technical solutions, and the construction of a prompt word instruction is completed through a target prompt problem template corresponding to a target handling requirement, so that after the to-be-handled operation and maintenance alarm information is obtained, preprocessing such as data cleaning, normalization, feature extraction, feature screening, etc. is performed on the to-be-handled operation and maintenance alarm information, so as to screen out features in the to-be-handled operation and maintenance alarm information that are not related to the operation and maintenance alarm, and improve the accuracy of subsequent alarm handling operation prediction according to an alarm handling prediction model. Meanwhile, after the alarm treatment operation is determined, a target treatment node for executing the alarm treatment operation is automatically determined according to the operation and maintenance alarm information to be processed, so that faults corresponding to the operation and maintenance alarm information to be processed can be timely and automatically treated, the alarm treatment determination speed is improved, meanwhile, in the training process of the alarm treatment prediction model, besides training sample sets constructed by using historical operation and maintenance alarm data and the historical alarm treatment operation, a reward model for carrying out intensive training on the alarm treatment prediction model is constructed based on human satisfaction corresponding to each historical alarm treatment operation, the alarm treatment prediction model subjected to intensive fine adjustment by using guiding dialogue data can generate more accurate and detailed alarm treatment operation, the human participation degree is reduced on the basis of keeping the influence of the human satisfaction degree, and the operation and maintenance quality and the system operation safety are further improved.
As shown in fig. 2, a method for determining alarm handling provided in a second embodiment of the present invention specifically includes the following steps:
s201, acquiring target treatment requirements and pending operation and maintenance alarm information.
S202, determining a corresponding target prompt problem template according to the target treatment requirement.
The target prompt problem template is used for prompting input and output targets from operation and maintenance alarm information to alarm treatment operation.
Specifically, the type of the operation and maintenance alarm information required to be input into the alarm processing prediction model is determined according to specific target treatment requirements, and the output of the alarm processing operation, which is obtained by aiming at the operation and maintenance alarm information of the input operation and maintenance alarm information type, of the alarm processing prediction model is hoped to be carried out, and a target prompt problem template corresponding to the target treatment requirements is determined according to the operation and maintenance alarm information type, the output of the alarm processing operation and the required operation and used for prompting the input and output targets from the operation and maintenance alarm information to the alarm processing operation.
Optionally, the target treatment requirement may be preset according to different operation and maintenance alarm information types, or may be determined in real time according to the operation and maintenance alarm information type of the operation and maintenance alarm information to be processed obtained each time, which is not limited in the embodiment of the present invention. If a plurality of different types of treatment requirements are preset, when the to-be-processed operation and maintenance alarm information is acquired, the treatment requirement corresponding to the type of the to-be-processed operation and maintenance alarm information can be selected from the prestored plurality of treatment requirements as a target treatment requirement.
For example, assuming that the operation and maintenance alarm information type is a server capacity alarm type, the target hint problem template may be expressed as: the pending operation and maintenance alarm information of the type of which the server capacity fault is known to occur is shown as the following { } please generate an output result containing feasible alarm handling operation and corresponding to a small probability according to the pending operation and maintenance alarm information. The target prompt problem template is only one example provided in the embodiment of the present invention, and the specific implementation manner may be adaptively set according to actual situations, which is not limited in the embodiment of the present invention.
S203, determining the target prompt question template as a prompt word instruction.
S204, carrying out data preprocessing on the operation and maintenance alarm information to be processed, and determining operation and maintenance alarm characteristic information.
In this embodiment, the operation and maintenance alarm feature information may be specifically understood as a feature that has a higher association relationship with an operation and maintenance alarm event in the operation and maintenance alarm information to be processed, and may affect the judgment of the handling operation.
Specifically, since the to-be-processed operation and maintenance alarm information directly obtained from the system is a complete natural language expression, and contains many fuzzy statement expressions which are irrelevant to the operation and maintenance alarm and easily influence the alarm treatment operation to determine, before the to-be-processed operation and maintenance alarm information is input into the pre-trained alarm treatment prediction model according to the prompt word instruction, the to-be-processed operation and maintenance alarm information is subjected to data preprocessing so as to filter phrase with lower association relation with the operation and maintenance alarm, and simultaneously, the phrase is subjected to feature extraction so as to retain the features relevant to the operation and maintenance alarm and input into the alarm treatment prediction model for the alarm treatment operation prediction.
Optionally, fig. 3 is a flowchart illustrating a process of preprocessing data of the operation and maintenance alarm information to be processed and determining the operation and maintenance alarm feature information, as shown in fig. 3, and specifically includes the following steps:
s2041, carrying out data cleaning and normalization on the operation and maintenance alarm information to be processed, and determining the cleaning operation and maintenance alarm information.
In this embodiment, the cleaning operation and maintenance alarm information may be specifically understood as the to-be-processed operation and maintenance alarm information after the statement information irrelevant to the operation and maintenance alarm has been removed.
S2042, carrying out feature extraction and feature screening on the cleaning operation and maintenance alarm information, and determining the operation and maintenance alarm feature information.
The operation and maintenance alarm characteristic information at least comprises characteristic information for representing alarm types, alarm levels and alarm time.
The method comprises the steps of carrying out word segmentation, feature extraction and the like on the clean operation and maintenance alarm information through a natural language processing method, carrying out feature screening on each extracted feature according to the degree of correlation with the operation and maintenance alarm, and determining the obtained feature information correlated with the operation and maintenance alarm as operation and maintenance alarm feature information. Optionally, the operation and maintenance alarm feature information at least comprises feature information for representing alarm type, alarm level and alarm time.
S205, inputting the operation and maintenance alarm feature information into a pre-trained alarm treatment prediction model according to a target prompt problem template, and determining an obtained model output result as alarm treatment operation corresponding to the alarm operation and maintenance information to be processed.
S206, determining a target treatment node according to the operation and maintenance alarm information to be processed.
In this embodiment, the target handling node may be specifically understood as a system node that has a fault in the system that issues the operation and maintenance alarm. It will be appreciated that the system node that issues the operation and maintenance alarm may not be the only system node that has a failure, which may be due to abnormal synthesis of the preceding or following related nodes.
Specifically, when the operation and maintenance alarm information to be processed is obtained, the system nodes which are related to the operation and maintenance alarm information to be processed and possibly have faults in the system can be definitely determined, and each determined system node is used as a target treatment node related to the operation and maintenance alarm information to be processed.
It may be understood that, according to the alarm handling prediction model, the alarm handling operation obtained by processing the alarm operation and maintenance information may not include all the determined target handling nodes, where the determined target handling nodes in the embodiment of the present invention are only nodes that may need to perform the alarm handling operation, and for a part of target handling nodes that are not included in the alarm handling operation, it may be considered that the association relationship between the part of target handling nodes and the current alarm problem is determined to be low according to the alarm handling prediction model, and the association relationship between the subsequent operation and maintenance alarm information and the target handling nodes may be adjusted according to the association relationship, which is not limited in the embodiment of the present invention.
S207, executing alarm handling operation on the target handling node.
Specifically, according to the alarm handling operation, a handling node which needs to correspondingly execute the operation is determined in the target handling node, and corresponding alarm handling operation is executed in each determined node, so that quick automatic handling of the to-be-processed operation and maintenance alarm information is realized.
By way of example, alarm handling operations may include automatic recovery, automatic restart, automatic configuration modification, and the like, to which embodiments of the present invention are not limited.
It can be understood that before the alarm treatment prediction model is put into use, the training operation for the model needs to be completed first, and fig. 4 is a training flowchart of the alarm treatment prediction model provided in the second embodiment of the present invention, as shown in fig. 4, specifically including the following steps:
s301, acquiring a historical operation and maintenance alarm data set, historical alarm treatment operations corresponding to the historical operation and maintenance alarm data, and human satisfaction corresponding to the historical alarm treatment operations.
In this embodiment, the historical operation and maintenance alarm data set may be specifically understood as a set of various types of historical operation and maintenance alarm data generated in a system within a preset period of time, which is acquired by a bank management system. The historical alert handling operation may be specifically understood as an alert handling operation actually performed for the historical operation alert at a corresponding historical moment when the system gives the historical operation alert data. Human satisfaction is specifically understood as satisfaction of a person with respect to a treatment result brought about by a historical alert treatment operation, that is, information about whether the alert treatment operation meets the treatment expectation of a worker with respect to a problem corresponding to the operation and maintenance alert.
S302, constructing a training sample set according to the historical operation and maintenance alarm data set and the historical alarm operation corresponding to each historical operation and maintenance alarm data.
Specifically, for each historical operation and maintenance alarm data in the historical operation and maintenance alarm data set, the corresponding historical alarm operation is used as the corresponding label, the historical operation and maintenance alarm data and the corresponding label are combined to be used as a training sample, further, training sample generation is carried out for each historical operation and maintenance alarm data in the historical operation and maintenance alarm data set, and the obtained set is determined to be a training sample set.
S303, constructing a human preference training sample set according to the training sample set and the human satisfaction corresponding to each training sample.
In this embodiment, the human preference training sample set may be specifically understood as a labeling corpus sample set including human preference information for model output, which may be used to describe whether the model output is a discriminant language model that appears to be good to humans.
Specifically, according to historical operation and maintenance alarm data contained in a training sample set, a historical prompt word instruction corresponding to the historical operation and maintenance alarm data is constructed, a historical alarm operation corresponding to the historical operation and maintenance alarm data is used as a model answer corresponding to the historical prompt word instruction, human satisfaction is used as a historical prompt word instruction and a label of the historical alarm operation to generate human preference training samples, and then a set of human preference training samples is determined to be a human preference training sample set.
By way of example, the human preference training samples may be expressed as: [ x= [ sample, model answer ], y = human satisfaction ], which the embodiment of the invention is not limited to.
S304, training the initial alarm treatment prediction model by using the training sample set, and determining an intermediate alarm treatment prediction model.
In this embodiment, the initial alert treatment prediction model may be specifically understood as an alert treatment prediction model that is not subjected to weight parameter adjustment. Alternatively, the initial alert handling prediction model may be a pre-trained GPT3 model, or may be another type of natural language model, as embodiments of the invention are not limited in this respect.
Specifically, the historical operation and maintenance alarm data in the training sample set is used as the input of an initial alarm treatment prediction model, a loss function is constructed according to the output of the initial alarm treatment prediction model and the historical alarm treatment operation corresponding to the historical operation and maintenance alarm data, the weight parameters of each neural network layer in the initial alarm treatment prediction model are adjusted based on the loss function, and the obtained model is determined to be an intermediate alarm treatment prediction model when the preset convergence condition is met.
S305, training the intermediate alarm treatment prediction model by using the human preference training sample set to determine a reward model.
Specifically, data in the human preference training sample set is input into the intermediate alarm treatment prediction model for training, the alarm treatment prediction results are calculated by the reward model obtained by training, and whether the alarm treatment prediction results conform to the loss value of human preference or not is calculated by the reward model, wherein the training target is to enable the human satisfaction degree corresponding to the alarm treatment prediction results to be higher, so that the accuracy rate of the alarm treatment prediction model output results conforming to human expectations obtained by training according to the reward model is ensured.
S306, based on a human feedback reinforcement learning mechanism, performing reinforcement training on the intermediate alarm treatment prediction model through the reward model, and determining the alarm treatment prediction model.
Specifically, in order to ensure that the alarm treatment prediction model obtained by training meets the expected requirement, strategy constraint information in the model training process is predetermined according to actual conditions, and after training of the reward model is completed, a reward function can be determined according to the reward model and preset strategy constraint; and further performing reinforcement training on the intermediate alarm treatment prediction model according to the reward function to determine an alarm treatment prediction model.
According to the technical scheme, the construction of the prompt word instruction is completed through the target prompt problem template corresponding to the target treatment requirement, and further, after the to-be-treated operation and maintenance alarm information is obtained, preprocessing such as data cleaning, normalization, feature extraction, feature screening and the like is carried out on the to-be-treated operation and maintenance alarm information, so that features irrelevant to the operation and maintenance alarm in the to-be-treated operation and maintenance alarm information are screened out, and the accuracy of subsequent alarm treatment operation prediction according to an alarm treatment prediction model is improved. Meanwhile, after the alarm treatment operation is determined, a target treatment node for executing the alarm treatment operation is automatically determined according to the operation and maintenance alarm information to be processed, so that faults corresponding to the operation and maintenance alarm information to be processed can be timely and automatically treated, the alarm treatment determination speed is improved, meanwhile, in the training process of the alarm treatment prediction model, besides training sample sets constructed by using historical operation and maintenance alarm data and the historical alarm treatment operation, a reward model for carrying out intensive training on the alarm treatment prediction model is constructed based on human satisfaction corresponding to each historical alarm treatment operation, the alarm treatment prediction model subjected to intensive fine adjustment by using guiding dialogue data can generate more accurate and detailed alarm treatment operation, the human participation degree is reduced on the basis of keeping the influence of the human satisfaction degree, and the operation and maintenance quality and the system operation safety are further improved.
Example III
Fig. 5 is a schematic structural diagram of an alarm handling determining device according to a third embodiment of the present invention, and as shown in fig. 5, the alarm handling determining device may include an information acquisition module 41, an instruction construction module 42, and an alarm handling determining module 43.
The information acquisition module 41 is configured to acquire a target treatment requirement and operation and maintenance alarm information to be processed; an instruction construction module 42, configured to construct a hint word instruction according to a target disposition requirement; the alarm handling determining module 43 is configured to input the to-be-processed operation and maintenance alarm information into a pre-trained alarm handling prediction model based on the prompt word instruction, and determine an alarm handling operation corresponding to the to-be-processed alarm operation and maintenance information according to an output result of the alarm handling prediction model; the alarm treatment prediction model is a neural network model trained based on a human feedback reinforcement learning method.
According to the technical scheme of the embodiment of the invention, aiming at massive operation and maintenance alarm information acquired in real time in a system, a prompt word instruction constructed according to target treatment requirements is used, the prompt word instruction is input into a pre-trained alarm treatment prediction model for processing, the alarm treatment prediction model is used for automatically processing the alarm treatment information to be processed, so that alarm treatment operation corresponding to the operation and maintenance alarm information to be processed is obtained.
Optionally, the instruction construction module 42 includes:
the target template determining unit is used for determining a corresponding target prompt problem template according to the target treatment requirement; the target prompt problem template is used for prompting input and output targets from operation and maintenance alarm information to alarm treatment operation.
And the instruction determining unit is used for determining the target prompt question template as a prompt word instruction.
Optionally, the alarm handling determination module 43 includes:
the feature information determining unit is used for carrying out data preprocessing on the operation and maintenance alarm information to be processed and determining the operation and maintenance alarm feature information.
The treatment operation determining unit is used for inputting the operation and maintenance alarm feature information into the pre-trained alarm treatment prediction model according to the target prompt problem template, and determining the obtained model output result as alarm treatment operation corresponding to the alarm operation and maintenance information to be processed.
Optionally, the feature information determining unit is specifically configured to:
carrying out data cleaning and normalization on the operation and maintenance alarm information to be processed, and determining clean operation and maintenance alarm information;
performing feature extraction and feature screening on the cleaning operation and maintenance alarm information to determine the operation and maintenance alarm feature information;
the operation and maintenance alarm characteristic information at least comprises characteristic information for representing alarm types, alarm levels and alarm time.
Optionally, the alarm handling determining device further includes: the operation execution module is used for:
after alarm treatment operation corresponding to the alarm operation and maintenance information to be processed is determined according to the output result of the alarm treatment prediction model, a target treatment node is determined according to the alarm operation and maintenance information to be processed; an alert handling operation is performed on the target handling node.
Optionally, the alarm handling determining device further includes: the model training module is specifically used for:
before acquiring target treatment requirements and to-be-processed operation and maintenance alarm information, acquiring a historical operation and maintenance alarm data set, historical alarm treatment operations corresponding to each historical operation and maintenance alarm data, and human satisfaction corresponding to each historical alarm treatment operation;
according to the historical operation and maintenance alarm data set and the historical alarm operation corresponding to each historical operation and maintenance alarm data, constructing a training sample set;
constructing a human preference training sample set according to the training sample set and the human satisfaction corresponding to each training sample;
training the initial alarm treatment prediction model by using a training sample set, and determining an intermediate alarm treatment prediction model;
training the intermediate alarm handling prediction model by using a human preference training sample set to determine a reward model;
Based on a human feedback reinforcement learning mechanism, the intermediate alarm handling prediction model is reinforcement trained through the reward model, and the alarm handling prediction model is determined.
Optionally, based on a human feedback reinforcement learning mechanism, performing reinforcement training on the intermediate alarm handling prediction model through the reward model, determining the alarm handling prediction model includes:
determining a reward function according to the reward model and a preset strategy constraint;
and performing intensive training on the intermediate alarm treatment prediction model according to the reward function to determine an alarm treatment prediction model.
The alarm treatment determining device provided by the embodiment of the invention can execute the alarm treatment determining method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the executing method.
Example IV
Fig. 6 is a schematic structural diagram of an alarm handling determining device according to a fourth embodiment of the present invention. The alarm handling determination device 50 may be an electronic device intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 6, the alarm handling determination device 50 includes at least one processor 51, and a memory, such as a Read Only Memory (ROM) 52, a Random Access Memory (RAM) 53, etc., communicatively connected to the at least one processor 51, in which the memory stores a computer program executable by the at least one processor, and the processor 51 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 52 or the computer program loaded from the storage unit 58 into the Random Access Memory (RAM) 53. In the RAM 53, various programs and data required for the operation of the alarm handling determination device 50 may also be stored. The processor 51, the ROM 52 and the RAM 53 are connected to each other via a bus 54. An input/output (I/O) interface 55 is also connected to bus 54.
The various components in the alarm handling determination device 50 are connected to the I/O interface 55, including: an input unit 56 such as a keyboard, a mouse, etc.; an output unit 57 such as various types of displays, speakers, and the like; a storage unit 58 such as a magnetic disk, an optical disk, or the like; and a communication unit 59 such as a network card, modem, wireless communication transceiver, etc. The communication unit 59 allows the alarm handling determination device 50 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The processor 51 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 51 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 51 performs the various methods and processes described above, such as the alert handling determination method.
In some embodiments, the alert handling determination method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as the storage unit 58. In some embodiments, part or all of the computer program may be loaded and/or installed onto the alarm handling determination device 50 via the ROM 52 and/or the communication unit 59. When the computer program is loaded into RAM 53 and executed by processor 51, one or more steps of the alert handling determination method described above may be performed. Alternatively, in other embodiments, the processor 51 may be configured to perform the alert handling determination method by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method of alert handling determination, comprising:
acquiring target treatment requirements and operation and maintenance alarm information to be processed;
constructing a prompt word instruction according to the target handling requirement;
inputting the operation and maintenance alarm information to be processed into a pre-trained alarm treatment prediction model based on the prompt word instruction, and determining alarm treatment operation corresponding to the operation and maintenance information to be processed according to an output result of the alarm treatment prediction model;
The alarm treatment prediction model is a neural network model trained based on a human feedback reinforcement learning method.
2. The method of claim 1, wherein the constructing a hint word instruction according to the target treatment requirement comprises:
determining a corresponding target prompt problem template according to the target treatment requirement;
determining the target prompt question template as a prompt word instruction;
the target prompt problem template is used for prompting input and output targets from operation and maintenance alarm information to alarm treatment operation.
3. The method according to claim 2, wherein the inputting the pending alarm operation and maintenance information into a pre-trained alarm treatment prediction model based on the prompt word instruction, determining an alarm treatment operation corresponding to the pending alarm operation and maintenance information according to an output result of the alarm treatment prediction model, includes:
carrying out data preprocessing on the operation and maintenance alarm information to be processed, and determining operation and maintenance alarm characteristic information;
and inputting the operation and maintenance alarm characteristic information into a pre-trained alarm treatment prediction model according to the target prompt problem template, and determining an obtained model output result as alarm treatment operation corresponding to the alarm operation and maintenance information to be processed.
4. A method according to claim 3, wherein the data preprocessing the pending operation and maintenance alarm information to determine operation and maintenance alarm feature information includes:
carrying out data cleaning and normalization on the operation and maintenance alarm information to be processed, and determining clean operation and maintenance alarm information;
performing feature extraction and feature screening on the cleaning operation and maintenance alarm information to determine operation and maintenance alarm feature information;
the operation and maintenance alarm characteristic information at least comprises characteristic information for representing alarm types, alarm levels and alarm time.
5. The method according to claim 1, further comprising, after the determining, according to the output result of the alert treatment prediction model, an alert treatment operation corresponding to the alert operation and maintenance information to be processed:
determining a target treatment node according to the operation and maintenance alarm information to be processed;
the alert handling operation is performed on the target handling node.
6. The method of any of claims 1-5, further comprising, prior to the obtaining the target treatment requirement and the pending operation and maintenance alert information:
acquiring a historical operation and maintenance alarm data set, historical alarm treatment operations corresponding to each historical operation and maintenance alarm data, and human satisfaction corresponding to each historical alarm treatment operation;
According to the historical operation and maintenance alarm data set and the historical alarm operation corresponding to each historical operation and maintenance alarm data, a training sample set is constructed;
constructing a human preference training sample set according to the training sample set and human satisfaction corresponding to each training sample;
training an initial alarm treatment prediction model by using the training sample set, and determining an intermediate alarm treatment prediction model;
training the intermediate alarm treatment prediction model by using the human preference training sample set to determine a reward model;
based on a human feedback reinforcement learning mechanism, performing reinforcement training on the intermediate alarm treatment prediction model through the reward model, and determining an alarm treatment prediction model.
7. The method of claim 6, wherein the human feedback reinforcement learning mechanism-based reinforcement training the intermediate alarm handling prediction model with the reward model to determine an alarm handling prediction model comprises:
determining a reward function according to the reward model and a preset strategy constraint;
and performing reinforcement training on the intermediate alarm treatment prediction model according to the reward function, and determining an alarm treatment prediction model.
8. An alert handling determining apparatus, comprising:
the information acquisition module is used for acquiring target treatment requirements and operation and maintenance alarm information to be processed;
the instruction construction module is used for constructing a prompt word instruction according to the target handling requirement;
the alarm treatment determining module is used for inputting the to-be-processed operation and maintenance alarm information into a pre-trained alarm treatment prediction model based on the prompt word instruction, and determining alarm treatment operation corresponding to the to-be-processed alarm operation and maintenance information according to an output result of the alarm treatment prediction model;
the alarm treatment prediction model is a neural network model trained based on a human feedback reinforcement learning method.
9. An alert handling determining apparatus, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the alarm handling determination method of any of claims 1-7.
10. A storage medium containing computer executable instructions which, when executed by a computer processor, are for performing the alarm handling determination method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311638923.5A CN117633495A (en) | 2023-12-01 | 2023-12-01 | Alarm handling determination method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311638923.5A CN117633495A (en) | 2023-12-01 | 2023-12-01 | Alarm handling determination method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117633495A true CN117633495A (en) | 2024-03-01 |
Family
ID=90033493
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311638923.5A Pending CN117633495A (en) | 2023-12-01 | 2023-12-01 | Alarm handling determination method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117633495A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118337422A (en) * | 2024-03-29 | 2024-07-12 | 北京火山引擎科技有限公司 | Alarm information processing method, system, equipment and medium |
| CN118658278A (en) * | 2024-08-16 | 2024-09-17 | 南京南自华盾数字技术有限公司 | Alarm information processing method, device, electronic equipment and storage medium |
-
2023
- 2023-12-01 CN CN202311638923.5A patent/CN117633495A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118337422A (en) * | 2024-03-29 | 2024-07-12 | 北京火山引擎科技有限公司 | Alarm information processing method, system, equipment and medium |
| CN118658278A (en) * | 2024-08-16 | 2024-09-17 | 南京南自华盾数字技术有限公司 | Alarm information processing method, device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117633495A (en) | Alarm handling determination method, device, equipment and storage medium | |
| CN109544399B (en) | Power transmission equipment state evaluation method and device based on multi-source heterogeneous data | |
| CN110287316A (en) | A kind of Alarm Classification method, apparatus, electronic equipment and storage medium | |
| CN111290922B (en) | Service operation health monitoring method and device | |
| CN103744977A (en) | Monitoring method and monitoring system for cloud computing system platform | |
| CN116089231B (en) | Fault alarm method and device, electronic equipment and storage medium | |
| CN114124460B (en) | Industrial control system intrusion detection method and device, computer equipment and storage medium | |
| CN117649115A (en) | Risk assessment method and device, electronic equipment and storage medium | |
| CN118210670A (en) | Log abnormality detection method and device, electronic equipment and storage medium | |
| CN116755974A (en) | Cloud computing platform operation and maintenance method and device, electronic equipment and storage medium | |
| CN113554280A (en) | Training method, device, equipment and storage medium for power grid system scheduling model | |
| CN116703109A (en) | Method, device, equipment and storage medium for selecting power distribution network project | |
| CN115146997A (en) | Evaluation method and device based on power data, electronic equipment and storage medium | |
| CN116523249A (en) | Production line determining method, device, equipment and storage medium | |
| CN115829160A (en) | Time sequence abnormity prediction method, device, equipment and storage medium | |
| CN115601042A (en) | Information identification method and device, electronic equipment and storage medium | |
| CN115328621A (en) | Transaction processing method, device and equipment based on block chain and storage medium | |
| CN114912541A (en) | Classification method, classification device, electronic equipment and storage medium | |
| CN114861831A (en) | Index set-based novel suspicion classification model training method and equipment | |
| CN117873891A (en) | Abnormal page detection method, device, equipment and storage medium | |
| CN115344459A (en) | Inspection method, inspection device, storage medium and electronic equipment | |
| CN115689707A (en) | Safety monitoring method and device for service program and electronic equipment | |
| CN117523746A (en) | Service type prompting method, device, equipment and medium of cash recycling integrated machine | |
| CN116468076A (en) | Driving behavior analysis method and device, electronic equipment and storage medium | |
| CN116933088A (en) | Secondary equipment fault data generation method and device, electronic equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |