CN117729119A - Equipment operation data processing method and system for edge computing gateway - Google Patents
Equipment operation data processing method and system for edge computing gateway Download PDFInfo
- Publication number
- CN117729119A CN117729119A CN202311454902.8A CN202311454902A CN117729119A CN 117729119 A CN117729119 A CN 117729119A CN 202311454902 A CN202311454902 A CN 202311454902A CN 117729119 A CN117729119 A CN 117729119A
- Authority
- CN
- China
- Prior art keywords
- activity data
- equipment operation
- operation activity
- template
- data
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 12
- 230000000694 effects Effects 0.000 claims abstract description 234
- 238000003745 diagnosis Methods 0.000 claims abstract description 63
- 238000000605 extraction Methods 0.000 claims abstract description 59
- 230000005856 abnormality Effects 0.000 claims abstract description 58
- 230000002159 abnormal effect Effects 0.000 claims abstract description 16
- 238000012549 training Methods 0.000 claims description 35
- 238000000034 method Methods 0.000 claims description 30
- 238000012545 processing Methods 0.000 claims description 18
- 238000004891 communication Methods 0.000 claims description 12
- 230000009467 reduction Effects 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 10
- 238000013256 Gubra-Amylin NASH model Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000002405 diagnostic procedure Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 238000000547 structure data Methods 0.000 description 1
Abstract
The embodiment of the invention provides a device operation data processing method and a system for an edge computing gateway. And then, carrying out self-attention feature extraction on the operation activity data of each template device, and acquiring a device operation directed graph of the operation activity data of each template device according to the determined self-attention feature sequence. This device operational directed graph reflects abnormal attention nodes of the template device operational activity data. Finally, the device operation directed graph of the plurality of template device operation activity data is utilized to train and generate a device abnormality diagnosis network, so that device abnormality conditions in the edge computing gateway can be effectively detected and diagnosed.
Description
Technical Field
The invention relates to the technical field of edge computing gateways, in particular to a device operation data processing method and system for an edge computing gateway.
Background
In edge computing networks, device anomaly issues become a critical challenge due to the large number of devices and complex operating environments. Current equipment anomaly detection and diagnostic methods rely primarily on traditional methods based on rules, statistical models, or machine learning, which often require a large number of manually defined rules or features, and may be inaccurate or poorly adapted for complex edge computing environments.
Accordingly, a new method capable of automatically learning and effectively detecting and diagnosing abnormality of the apparatus is required. The edge computing gateway is used as a key node for connecting the terminal equipment and the cloud platform, and plays an important role in the whole edge computing architecture. Therefore, the detection and diagnosis of equipment anomalies for edge computing gateways has important research value and practical application requirements.
In recent years, techniques such as self-attention mechanisms and graph neural networks have made remarkable progress in the fields of sequence data and graph data processing. The self-attention mechanism can extract key features from the sequence data, and the graph neural network can effectively model and analyze the graph structure data. However, a method for comprehensively utilizing a self-attention mechanism and a graph neural network to solve the problem of anomaly detection and diagnosis of the edge computing gateway device is not yet available.
Disclosure of Invention
In view of the above, an object of the embodiments of the present invention is to provide a method and a system for processing device operation data of an edge computing gateway, which first obtain a sequence of template device operation activity data of a target edge computing gateway, wherein the sequence includes a plurality of template device operation activity data. And then, carrying out self-attention feature extraction on the operation activity data of each template device, and acquiring a device operation directed graph of the operation activity data of each template device according to the determined self-attention feature sequence. This device operational directed graph reflects abnormal attention nodes of the template device operational activity data. Finally, the device operation directed graph of the plurality of template device operation activity data is utilized to train and generate a device abnormality diagnosis network, so that device abnormality conditions in the edge computing gateway can be effectively detected and diagnosed.
According to an aspect of the embodiment of the present invention, there is provided a method and a system for processing device operation data of an edge computing gateway, where the method includes:
acquiring a template equipment operation activity data sequence of a target edge computing gateway, wherein the template equipment operation activity data sequence comprises a plurality of template equipment operation activity data;
respectively extracting self-attention characteristics of each piece of template equipment operation activity data, and acquiring equipment operation directed graphs of each piece of template equipment operation activity data according to the determined self-attention characteristic sequences, wherein the equipment operation directed graphs reflect abnormal attention nodes of the template equipment operation activity data;
training and generating the equipment abnormality diagnosis network according to the equipment operation directed graph of the plurality of template equipment operation activity data.
In an alternative embodiment, the extracting self-attention characteristics of each piece of template device operation activity data, and obtaining a device operation directed graph of each piece of template device operation activity data according to the determined self-attention characteristic sequence includes:
for each template equipment operation activity data, carrying out self-attention feature extraction on the template equipment operation activity data according to a preset self-attention network, determining a self-attention positioning operation link of the template equipment operation activity data, and storing the self-attention positioning operation link as self-attention positioning data;
loading the template equipment operation activity data into a preset graph self-encoder, generating encoded data of the preset graph self-encoder, and taking the encoded data as first encoded directed graph data of the template equipment operation activity data;
loading the self-attention positioning data into the preset graph self-encoder, generating encoded data of the preset graph self-encoder, and taking the encoded data as second encoded directed graph data of the self-attention positioning data;
and fusing the first coding directed graph data and the second coding directed graph data to generate a device operation directed graph of the template device operation activity data.
In an alternative embodiment, the training to generate the device anomaly diagnostic network according to the device operation directed graph of the plurality of template device operation activity data includes:
according to the equipment operation directed graph of the plurality of template equipment operation activity data, updating weight parameters of a preset GAN model to generate the equipment abnormality diagnosis network;
the GAN model comprises a feature extraction network and a prediction network, wherein the feature extraction network comprises a feature extraction unit and a feature reduction unit;
the process for updating the weight parameters of the preset GAN model according to the device operation directed graph of the operation activity data of the plurality of template devices comprises the following steps:
according to a preset reconstruction loss function, carrying out weight parameter updating on the equipment operation directed graph of the plurality of template equipment operation activity data, determining first weight information of the feature extraction unit and first weight information of the feature reduction unit, and obtaining depth coding directed graph data generated after the feature extraction unit carries out feature extraction on the equipment operation directed graph of the plurality of template equipment operation activity data according to the first weight information of the feature extraction unit;
and updating weight parameters of the depth coding directed graph data according to a preset training supervision cost function, determining second weight information of the prediction network, determining second weight information of the feature extraction unit and second weight information of the feature reduction unit.
In an alternative embodiment, the plurality of template device operational activity data includes active device operational activity data and passive device operational activity data;
the training and generating the equipment abnormality diagnosis network according to the equipment operation directed graph of the plurality of template equipment operation activity data comprises the following steps:
when the weight of the passive equipment operation activity data in the template equipment operation activity data sequence is larger than that of the active equipment operation activity data, traversing the passive equipment operation activity data in the template equipment operation activity data sequence in the current training stage of training the equipment abnormality diagnosis network to generate a plurality of traversed passive equipment operation activity data, wherein the number of the traversed passive equipment operation activity data is the same as that of the active equipment operation activity data;
training in the training stage according to the device operation directed graph of the active device operation activity data and the device operation directed graph of the traversal passive device operation activity data;
traversing the rest passive equipment operation activity data except the traversed passive equipment operation activity data in the template equipment operation activity data sequence to generate a plurality of new traversed passive equipment operation activity data in the next training stage of the equipment abnormality diagnosis network, wherein the number of the new traversed passive equipment operation activity data is the same as that of the active equipment operation activity data;
and carrying out the next training stage according to the device operation directed graph of the active device operation activity data and the new device operation directed graph traversing the passive device operation activity data.
In an alternative embodiment, the method further comprises:
acquiring candidate equipment operation activity data;
extracting self-attention characteristics of the candidate equipment operation activity data, and acquiring equipment operation directed graphs of the candidate equipment operation activity data according to the determined self-attention characteristic sequence, wherein the equipment operation directed graphs of the candidate equipment operation activity data reflect abnormal attention nodes of the candidate equipment operation activity data;
and carrying out abnormality diagnosis on the candidate equipment operation activity data according to the equipment operation directed graph of the candidate equipment operation activity data and a preset equipment abnormality diagnosis network, and determining an abnormality diagnosis result of the candidate equipment operation activity data.
In an alternative embodiment, the preset device abnormality diagnosis network includes a feature extraction network and a prediction network; the feature extraction network comprises a feature extraction unit and a feature reduction unit;
performing abnormality diagnosis on the candidate equipment operation activity data according to the equipment operation directed graph of the candidate equipment operation activity data and a preset equipment abnormality diagnosis network, wherein determining an abnormality diagnosis result of the candidate equipment operation activity data comprises the following steps:
loading the device operation directed graph of the candidate device operation activity data into the feature extraction network, and obtaining depth coding directed graph data generated after feature extraction is carried out on the device operation directed graph by a feature extraction unit of the feature extraction network;
and loading the depth coding directed graph data into the prediction network, and determining an abnormality diagnosis result of the candidate equipment operation activity data.
According to another aspect of the embodiment of the present invention, there is provided a method and a system for processing device operation data of an edge computing gateway, where the system includes:
the first acquisition module is used for acquiring a template equipment operation activity data sequence, wherein the template equipment operation activity data sequence comprises a plurality of template equipment operation activity data;
the first extraction module is used for extracting self-attention characteristics of each piece of template equipment operation activity data respectively, and acquiring equipment operation directed graphs corresponding to each piece of template equipment operation activity data according to the determined self-attention characteristic sequences, wherein the equipment operation directed graphs reflect abnormal attention nodes of the template equipment operation activity data;
and the training module is used for training and generating the equipment abnormality diagnosis network according to the equipment operation directed graph of the equipment operation activity data of the plurality of template equipment.
In an alternative embodiment, the system further comprises:
the second acquisition module is used for acquiring candidate equipment operation activity data;
the second extraction module is used for extracting self-attention characteristics of the candidate equipment operation activity data, and acquiring equipment operation directed graphs of the candidate equipment operation activity data according to the determined self-attention characteristic sequences, wherein the equipment operation directed graphs of the candidate equipment operation activity data reflect abnormal attention nodes of the candidate equipment operation activity data;
the diagnosis module is used for carrying out abnormality diagnosis on the candidate equipment operation activity data according to the equipment operation directed graph of the candidate equipment operation activity data and a preset equipment abnormality diagnosis network, and determining an abnormality diagnosis result of the candidate equipment operation activity data.
According to another aspect of an embodiment of the present invention, there is provided a server including: the device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus; the memory is used for storing a computer program; the processor is configured to implement the method steps of running data processing for an edge computing gateway according to any one of the above when executing the computer program.
According to another aspect of the embodiments of the present invention, there is provided a readable storage medium having stored thereon a computer program which, when executed by a processor, can perform the steps of the apparatus-running data processing method for an edge computing gateway described above.
The foregoing objects, features and advantages of embodiments of the invention will be more readily apparent from the following detailed description of the embodiments taken in conjunction with the accompanying drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 shows a schematic diagram of components of a server provided by an embodiment of the present invention;
fig. 2 is a schematic flow chart of a method for processing data for device operation of an edge computing gateway according to an embodiment of the present invention;
FIG. 3 illustrates a functional block diagram of a data processing system operating in accordance with an apparatus for an edge computing gateway, provided by an embodiment of the present invention.
Detailed Description
In order to enable those skilled in the art to better understand the present invention, a technical solution of the present embodiment of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiment of the present invention, and it is apparent that the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. All other embodiments, which can be made by those skilled in the art without the benefit of the teachings of this invention, are intended to fall within the scope of the invention.
The terms first, second, third and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar elements 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 the embodiments of the invention described herein may be implemented, for example, 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.
Fig. 1 shows an exemplary component diagram of a server 100. The server 100 may include one or more processors 104, such as one or more Central Processing Units (CPUs), each of which may implement one or more hardware threads. The server 100 may also include any storage medium 106 for storing any kind of information such as code, settings, data, etc. For example, and without limitation, storage medium 106 may include any one or more of the following combinations: any type of RAM, any type of ROM, flash memory devices, hard disks, optical disks, etc. More generally, any storage medium may store information using any technique. Further, any storage medium may provide volatile or non-volatile retention of information. Further, any storage medium may represent fixed or removable components of server 100. In one case, the server 100 may perform any of the operations of the associated instructions when the processor 104 executes the associated instructions stored in any storage medium or combination of storage media. The server 100 also includes one or more drive units 108, such as a hard disk drive unit, an optical disk drive unit, etc., for interacting with any storage media.
The server 100 also includes input/output 110 (I/O) for receiving various inputs (via input unit 112) and for providing various outputs (via output unit 114). One particular output mechanism may include a presentation device 116 and an associated Graphical User Interface (GUI) 118. The server 100 may also include one or more network interfaces 120 for exchanging data with other devices via one or more communication units 122. One or more communication buses 124 couple the components described above together.
The communication unit 122 may be implemented in any manner, for example, via a local area network, a wide area network (e.g., the internet), a point-to-point connection, etc., or any combination thereof. The communication unit 122 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers 100, etc., governed by any protocol or combination of protocols.
Fig. 2 is a schematic flow chart of a method and a system for processing device operation data of an edge computing gateway according to an embodiment of the present invention, where the method and the system for processing device operation data of an edge computing gateway may be executed by the server 100 shown in fig. 1, and detailed steps of the method for processing device operation data of an edge computing gateway are described below.
Step S110, a template equipment operation activity data sequence of a target edge computing gateway is obtained, wherein the template equipment operation activity data sequence comprises a plurality of template equipment operation activity data;
step S120, extracting self-attention characteristics of each piece of template equipment operation activity data respectively, and acquiring equipment operation directed graphs of each piece of template equipment operation activity data according to the determined self-attention characteristic sequences, wherein the equipment operation directed graphs reflect abnormal attention nodes of the template equipment operation activity data;
and step S130, training and generating the equipment abnormality diagnosis network according to the equipment operation directed graph of the plurality of template equipment operation activity data.
In an alternative embodiment, the method further comprises:
step S140, acquiring candidate equipment operation activity data;
step S150, extracting self-attention characteristics of the candidate equipment operation activity data, and acquiring equipment operation directed graphs of the candidate equipment operation activity data according to the determined self-attention characteristic sequences, wherein the equipment operation directed graphs of the candidate equipment operation activity data reflect abnormal attention nodes of the candidate equipment operation activity data;
step S160, performing abnormality diagnosis on the candidate equipment operation activity data according to the equipment operation directed graph of the candidate equipment operation activity data and a preset equipment abnormality diagnosis network, and determining an abnormality diagnosis result of the candidate equipment operation activity data.
Based on the above steps, the embodiment first obtains a template device operation activity data sequence of the target edge computing gateway, where the sequence includes a plurality of template device operation activity data. And then, carrying out self-attention feature extraction on the operation activity data of each template device, and acquiring a device operation directed graph of the operation activity data of each template device according to the determined self-attention feature sequence. This device operational directed graph reflects abnormal attention nodes of the template device operational activity data. Finally, the device operation directed graph of the plurality of template device operation activity data is utilized to train and generate a device abnormality diagnosis network, so that device abnormality conditions in the edge computing gateway can be effectively detected and diagnosed.
In an alternative embodiment, the extracting self-attention characteristics of each piece of template device operation activity data, and obtaining a device operation directed graph of each piece of template device operation activity data according to the determined self-attention characteristic sequence includes:
for each template equipment operation activity data, carrying out self-attention feature extraction on the template equipment operation activity data according to a preset self-attention network, determining a self-attention positioning operation link of the template equipment operation activity data, and storing the self-attention positioning operation link as self-attention positioning data;
loading the template equipment operation activity data into a preset graph self-encoder, generating encoded data of the preset graph self-encoder, and taking the encoded data as first encoded directed graph data of the template equipment operation activity data;
loading the self-attention positioning data into the preset graph self-encoder, generating encoded data of the preset graph self-encoder, and taking the encoded data as second encoded directed graph data of the self-attention positioning data;
and fusing the first coding directed graph data and the second coding directed graph data to generate a device operation directed graph of the template device operation activity data.
In an alternative embodiment, the training to generate the device anomaly diagnostic network according to the device operation directed graph of the plurality of template device operation activity data includes:
according to the equipment operation directed graph of the plurality of template equipment operation activity data, updating weight parameters of a preset GAN model to generate the equipment abnormality diagnosis network;
the GAN model comprises a feature extraction network and a prediction network, wherein the feature extraction network comprises a feature extraction unit and a feature reduction unit;
the process for updating the weight parameters of the preset GAN model according to the device operation directed graph of the operation activity data of the plurality of template devices comprises the following steps:
according to a preset reconstruction loss function, carrying out weight parameter updating on the equipment operation directed graph of the plurality of template equipment operation activity data, determining first weight information of the feature extraction unit and first weight information of the feature reduction unit, and obtaining depth coding directed graph data generated after the feature extraction unit carries out feature extraction on the equipment operation directed graph of the plurality of template equipment operation activity data according to the first weight information of the feature extraction unit;
and updating weight parameters of the depth coding directed graph data according to a preset training supervision cost function, determining second weight information of the prediction network, determining second weight information of the feature extraction unit and second weight information of the feature reduction unit.
In an alternative embodiment, the plurality of template device operational activity data includes active device operational activity data and passive device operational activity data;
the training and generating the equipment abnormality diagnosis network according to the equipment operation directed graph of the plurality of template equipment operation activity data comprises the following steps:
when the weight of the passive equipment operation activity data in the template equipment operation activity data sequence is larger than that of the active equipment operation activity data, traversing the passive equipment operation activity data in the template equipment operation activity data sequence in the current training stage of training the equipment abnormality diagnosis network to generate a plurality of traversed passive equipment operation activity data, wherein the number of the traversed passive equipment operation activity data is the same as that of the active equipment operation activity data;
training in the training stage according to the device operation directed graph of the active device operation activity data and the device operation directed graph of the traversal passive device operation activity data;
traversing the rest passive equipment operation activity data except the traversed passive equipment operation activity data in the template equipment operation activity data sequence to generate a plurality of new traversed passive equipment operation activity data in the next training stage of the equipment abnormality diagnosis network, wherein the number of the new traversed passive equipment operation activity data is the same as that of the active equipment operation activity data;
and carrying out the next training stage according to the device operation directed graph of the active device operation activity data and the new device operation directed graph traversing the passive device operation activity data.
In an alternative embodiment, the method further comprises:
acquiring candidate equipment operation activity data;
extracting self-attention characteristics of the candidate equipment operation activity data, and acquiring equipment operation directed graphs of the candidate equipment operation activity data according to the determined self-attention characteristic sequence, wherein the equipment operation directed graphs of the candidate equipment operation activity data reflect abnormal attention nodes of the candidate equipment operation activity data;
and carrying out abnormality diagnosis on the candidate equipment operation activity data according to the equipment operation directed graph of the candidate equipment operation activity data and a preset equipment abnormality diagnosis network, and determining an abnormality diagnosis result of the candidate equipment operation activity data.
In an alternative embodiment, the preset device abnormality diagnosis network includes a feature extraction network and a prediction network; the feature extraction network comprises a feature extraction unit and a feature reduction unit;
performing abnormality diagnosis on the candidate equipment operation activity data according to the equipment operation directed graph of the candidate equipment operation activity data and a preset equipment abnormality diagnosis network, wherein determining an abnormality diagnosis result of the candidate equipment operation activity data comprises the following steps:
loading the device operation directed graph of the candidate device operation activity data into the feature extraction network, and obtaining depth coding directed graph data generated after feature extraction is carried out on the device operation directed graph by a feature extraction unit of the feature extraction network;
and loading the depth coding directed graph data into the prediction network, and determining an abnormality diagnosis result of the candidate equipment operation activity data.
Fig. 3 illustrates a functional block diagram of a data processing system 200 according to an embodiment of the present invention, where the steps performed by the method may correspond to the functions performed by the data processing system 200 according to the device operation for an edge computing gateway. The data processing system 200 may be understood as the above-mentioned server 100 or the processor of the server 100, or may be understood as a component which is independent from the above-mentioned server 100 or the processor and implements the functions of the present invention under the control of the server 100, as shown in fig. 3, and the functions of the functional modules of the data processing system 200 are described in detail below.
A first obtaining module 210, configured to obtain a template device operation activity data sequence, where the template device operation activity data sequence includes a plurality of template device operation activity data;
a first extraction module 220, configured to extract self-attention features of each piece of template device operation activity data, and obtain a device operation directed graph corresponding to each piece of template device operation activity data according to the determined self-attention feature sequence, where the device operation directed graph reflects abnormal attention nodes of the template device operation activity data;
the training module 230 is configured to train and generate the device abnormality diagnosis network according to the device operation directed graph of the plurality of template device operation activity data.
In an alternative embodiment, the system further comprises:
a second obtaining module 240, configured to obtain candidate device operation activity data;
a second extraction module 250, configured to perform self-attention feature extraction on the candidate device operation activity data, and obtain a device operation directed graph of the candidate device operation activity data according to the determined self-attention feature sequence, where the device operation directed graph of the candidate device operation activity data reflects an abnormal attention node of the candidate device operation activity data;
and the diagnosis module 260 is configured to perform an anomaly diagnosis on the candidate equipment operation activity data according to the equipment operation directed graph of the candidate equipment operation activity data and a preset equipment anomaly diagnosis network, and determine an anomaly diagnosis result of the candidate equipment operation activity data.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.
Claims (10)
1. A method of device operation data processing for an edge computing gateway, the method comprising:
acquiring a template equipment operation activity data sequence of a target edge computing gateway, wherein the template equipment operation activity data sequence comprises a plurality of template equipment operation activity data;
respectively extracting self-attention characteristics of each piece of template equipment operation activity data, and acquiring equipment operation directed graphs of each piece of template equipment operation activity data according to the determined self-attention characteristic sequences, wherein the equipment operation directed graphs reflect abnormal attention nodes of the template equipment operation activity data;
training and generating the equipment abnormality diagnosis network according to the equipment operation directed graph of the plurality of template equipment operation activity data.
2. The device operation data processing method for an edge computing gateway according to claim 1, wherein the respectively performing self-attention feature extraction on each of the template device operation activity data, and obtaining a device operation directed graph of each of the template device operation activity data according to the determined self-attention feature sequence comprises:
for each template equipment operation activity data, carrying out self-attention feature extraction on the template equipment operation activity data according to a preset self-attention network, determining a self-attention positioning operation link of the template equipment operation activity data, and storing the self-attention positioning operation link as self-attention positioning data;
loading the template equipment operation activity data into a preset graph self-encoder, generating encoded data of the preset graph self-encoder, and taking the encoded data as first encoded directed graph data of the template equipment operation activity data;
loading the self-attention positioning data into the preset graph self-encoder, generating encoded data of the preset graph self-encoder, and taking the encoded data as second encoded directed graph data of the self-attention positioning data;
and fusing the first coding directed graph data and the second coding directed graph data to generate a device operation directed graph of the template device operation activity data.
3. The device operation data processing method for an edge computing gateway according to claim 1 or 2, wherein the training to generate the device anomaly diagnosis network according to the device operation directed graph of the plurality of template device operation activity data comprises:
according to the equipment operation directed graph of the plurality of template equipment operation activity data, updating weight parameters of a preset GAN model to generate the equipment abnormality diagnosis network;
the GAN model comprises a feature extraction network and a prediction network, wherein the feature extraction network comprises a feature extraction unit and a feature reduction unit;
the process for updating the weight parameters of the preset GAN model according to the device operation directed graph of the operation activity data of the plurality of template devices comprises the following steps:
according to a preset reconstruction loss function, carrying out weight parameter updating on the equipment operation directed graph of the plurality of template equipment operation activity data, determining first weight information of the feature extraction unit and first weight information of the feature reduction unit, and obtaining depth coding directed graph data generated after the feature extraction unit carries out feature extraction on the equipment operation directed graph of the plurality of template equipment operation activity data according to the first weight information of the feature extraction unit;
and updating weight parameters of the depth coding directed graph data according to a preset training supervision cost function, determining second weight information of the prediction network, determining second weight information of the feature extraction unit and second weight information of the feature reduction unit.
4. The device operational data processing method for an edge computing gateway of claim 1, wherein the plurality of template device operational activity data comprises active device operational activity data and passive device operational activity data;
the training and generating the equipment abnormality diagnosis network according to the equipment operation directed graph of the plurality of template equipment operation activity data comprises the following steps:
when the weight of the passive equipment operation activity data in the template equipment operation activity data sequence is larger than that of the active equipment operation activity data, traversing the passive equipment operation activity data in the template equipment operation activity data sequence in the current training stage of training the equipment abnormality diagnosis network to generate a plurality of traversed passive equipment operation activity data, wherein the number of the traversed passive equipment operation activity data is the same as that of the active equipment operation activity data;
training in the training stage according to the device operation directed graph of the active device operation activity data and the device operation directed graph of the traversal passive device operation activity data;
traversing the rest passive equipment operation activity data except the traversed passive equipment operation activity data in the template equipment operation activity data sequence to generate a plurality of new traversed passive equipment operation activity data in the next training stage of the equipment abnormality diagnosis network, wherein the number of the new traversed passive equipment operation activity data is the same as that of the active equipment operation activity data;
and carrying out the next training stage according to the device operation directed graph of the active device operation activity data and the new device operation directed graph traversing the passive device operation activity data.
5. The device-specific data processing method for an edge computing gateway of claim 1, further comprising:
acquiring candidate equipment operation activity data;
extracting self-attention characteristics of the candidate equipment operation activity data, and acquiring equipment operation directed graphs of the candidate equipment operation activity data according to the determined self-attention characteristic sequence, wherein the equipment operation directed graphs of the candidate equipment operation activity data reflect abnormal attention nodes of the candidate equipment operation activity data;
and carrying out abnormality diagnosis on the candidate equipment operation activity data according to the equipment operation directed graph of the candidate equipment operation activity data and a preset equipment abnormality diagnosis network, and determining an abnormality diagnosis result of the candidate equipment operation activity data.
6. The device operation data processing method for an edge computing gateway according to claim 5, wherein the preset device abnormality diagnosis network includes a feature extraction network and a prediction network; the feature extraction network comprises a feature extraction unit and a feature reduction unit;
performing abnormality diagnosis on the candidate equipment operation activity data according to the equipment operation directed graph of the candidate equipment operation activity data and a preset equipment abnormality diagnosis network, wherein determining an abnormality diagnosis result of the candidate equipment operation activity data comprises the following steps:
loading the device operation directed graph of the candidate device operation activity data into the feature extraction network, and obtaining depth coding directed graph data generated after feature extraction is carried out on the device operation directed graph by a feature extraction unit of the feature extraction network;
and loading the depth coding directed graph data into the prediction network, and determining an abnormality diagnosis result of the candidate equipment operation activity data.
7. A device-running data processing system for an edge computing gateway, comprising:
the first acquisition module is used for acquiring a template equipment operation activity data sequence, wherein the template equipment operation activity data sequence comprises a plurality of template equipment operation activity data;
the first extraction module is used for extracting self-attention characteristics of each piece of template equipment operation activity data respectively, and acquiring equipment operation directed graphs corresponding to each piece of template equipment operation activity data according to the determined self-attention characteristic sequences, wherein the equipment operation directed graphs reflect abnormal attention nodes of the template equipment operation activity data;
and the training module is used for training and generating the equipment abnormality diagnosis network according to the equipment operation directed graph of the equipment operation activity data of the plurality of template equipment.
8. The device-running data processing system for an edge computing gateway of claim 7, further comprising:
the second acquisition module is used for acquiring candidate equipment operation activity data;
the second extraction module is used for extracting self-attention characteristics of the candidate equipment operation activity data, and acquiring equipment operation directed graphs of the candidate equipment operation activity data according to the determined self-attention characteristic sequences, wherein the equipment operation directed graphs of the candidate equipment operation activity data reflect abnormal attention nodes of the candidate equipment operation activity data;
the diagnosis module is used for carrying out abnormality diagnosis on the candidate equipment operation activity data according to the equipment operation directed graph of the candidate equipment operation activity data and a preset equipment abnormality diagnosis network, and determining an abnormality diagnosis result of the candidate equipment operation activity data.
9. A server, comprising: the device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus; the memory is used for storing a computer program; the processor, when configured to execute the computer program, implements the device-specific data processing method steps of any one of claims 1-6 for an edge computing gateway.
10. A computer readable storage medium having stored thereon a computer program, which when executed by a processor performs the apparatus-running data processing method steps for an edge computing gateway according to any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311454902.8A CN117729119A (en) | 2023-11-03 | 2023-11-03 | Equipment operation data processing method and system for edge computing gateway |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311454902.8A CN117729119A (en) | 2023-11-03 | 2023-11-03 | Equipment operation data processing method and system for edge computing gateway |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117729119A true CN117729119A (en) | 2024-03-19 |
Family
ID=90209610
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311454902.8A Pending CN117729119A (en) | 2023-11-03 | 2023-11-03 | Equipment operation data processing method and system for edge computing gateway |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117729119A (en) |
-
2023
- 2023-11-03 CN CN202311454902.8A patent/CN117729119A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6706321B2 (en) | Method and device for service call information processing | |
| US10373065B2 (en) | Generating database cluster health alerts using machine learning | |
| CN112416643A (en) | Unsupervised anomaly detection method and unsupervised anomaly detection device | |
| CN113222554A (en) | Intelligent office cooperation method and system based on big data | |
| CN111277427B (en) | Data center network equipment inspection method and system | |
| CN110490132B (en) | Data processing method and device | |
| CN117729119A (en) | Equipment operation data processing method and system for edge computing gateway | |
| CN111695880B (en) | Production flow monitoring method and system | |
| CN112100844B (en) | Internet of vehicles information configuration simulation method and system | |
| CN111948967B (en) | Power data acquisition method and system based on big data | |
| CN113298622A (en) | Method and system for processing e-commerce business orders based on machine learning | |
| CN113905407B (en) | Terminal equipment monitoring information acquisition method and system in distributed wireless networking | |
| CN117272207A (en) | Data center anomaly analysis method and system | |
| CN113282482A (en) | Compatibility test method and system for software package | |
| CN117033052A (en) | Object abnormality diagnosis method and system based on model identification | |
| CN111368413A (en) | Tracking management method and system for clothing production plan | |
| CN117216701B (en) | Intelligent bridge monitoring and early warning method and system | |
| CN117952252A (en) | Intelligent scheduling early warning method and system for hardware processing | |
| CN117519034A (en) | Abnormality monitoring method and system applied to corrugated board production control system | |
| CN113641095B (en) | Active safety machine leaning control method and system based on laser radar | |
| CN117077809A (en) | Abnormal data analysis method and system based on wind control decision and visualization | |
| CN115514620B (en) | Anomaly detection method and cloud network platform | |
| CN117914734A (en) | Gateway equipment switching method and system based on data analysis | |
| CN117401179A (en) | Unmanned aerial vehicle-based flight performance testing method and system | |
| CN117110782A (en) | Method and system for testing network-related performance of energy storage power station |
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 |