CN120017489B - Fault analysis method and device for FTTR equipment, equipment and medium - Google Patents
Fault analysis method and device for FTTR equipment, equipment and mediumInfo
- Publication number
- CN120017489B CN120017489B CN202510465808.5A CN202510465808A CN120017489B CN 120017489 B CN120017489 B CN 120017489B CN 202510465808 A CN202510465808 A CN 202510465808A CN 120017489 B CN120017489 B CN 120017489B
- Authority
- CN
- China
- Prior art keywords
- fault
- data
- semantic
- semantic representation
- fttr
- 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.)
- Active
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0631—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B10/00—Transmission systems employing electromagnetic waves other than radio-waves, e.g. infrared, visible or ultraviolet light, or employing corpuscular radiation, e.g. quantum communication
- H04B10/07—Arrangements for monitoring or testing transmission systems; Arrangements for fault measurement of transmission systems
- H04B10/075—Arrangements for monitoring or testing transmission systems; Arrangements for fault measurement of transmission systems using an in-service signal
- H04B10/079—Arrangements for monitoring or testing transmission systems; Arrangements for fault measurement of transmission systems using an in-service signal using measurements of the data signal
- H04B10/0793—Network aspects, e.g. central monitoring of transmission parameters
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/149—Network analysis or design for prediction of maintenance
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/16—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Test And Diagnosis Of Digital Computers (AREA)
Abstract
本申请提供的FTTR设备的故障分析方法和装置、设备及介质，涉及人工智能技术领域。在本申请中，首先，获取对目标FTTR设备进行数据采集得到的多个故障相关数据；其次，对多个故障相关数据进行语义挖掘，形成目标故障语义表示；然后，基于目标故障语义表示，对目标FTTR设备进行故障分析，输出目标FTTR设备对应的故障预测数据。基于上述内容，可以改善现有技术中存在的难以对LAN口故障进行有效分析的问题。
This application provides a method and apparatus, device, and medium for analyzing FTTR equipment failures, relating to the field of artificial intelligence technology. First, multiple fault-related data are acquired through data collection on a target FTTR device. Second, semantic mining is performed on the multiple fault-related data to form a semantic representation of the target failure. Finally, based on the semantic representation of the target failure, a fault analysis is performed on the target FTTR device, outputting fault prediction data corresponding to the target FTTR device. This approach can improve the existing difficulty in effectively analyzing LAN port failures.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to a method, a device, equipment and a medium for analyzing faults of FTTR equipment.
Background
FTTR (Fiber to the Room) is a network access technology that lays optical fibers directly into the user's room in order to increase network bandwidth and stability. FTTR devices typically involve hardware such as fiber optic modems (ONUs), wireless routers, etc. In FTTR networks, the LAN port (Local Area Network port) is a critical interface for connecting local devices (e.g., computers, televisions, printers, etc.). If FTTR equipment causes LAN port damage, a series of effects can occur. Therefore, the damage or faults of the LAN port are required to be analyzed or predicted, so that corresponding maintenance can be performed in time, and the effective work of the equipment is ensured. However, in the prior art, since maintenance is generally performed after the failure of the LAN port, there is a problem in that it is difficult to efficiently analyze the failure of the LAN port.
Disclosure of Invention
In view of the above, the present application aims to provide a method, an apparatus, a device and a medium for analyzing a fault of FTTR devices, so as to solve the problem that it is difficult to effectively analyze a fault of a LAN port in the prior art.
In order to achieve the above purpose, the application adopts the following technical scheme:
A method of fault analysis of FTTR devices, comprising:
Acquiring a plurality of fault related data obtained by data acquisition of target FTTR equipment, wherein the fault related data are data contributing to the occurrence of faults of a LAN (local area network) port of the target FTTR equipment, and at least one time series data exist in the plurality of fault related data;
performing semantic mining on the plurality of fault related data to form a target fault semantic representation, wherein in the process of semantic mining, data fluctuation semantics in the time series data are mined from at least two time change directions for each time series data;
and performing fault analysis on the target FTTR equipment based on the target fault semantic representation, and outputting fault prediction data corresponding to the target FTTR equipment, wherein the fault prediction data is used for reflecting whether the LAN port of the target FTTR equipment is faulty or not.
In a preferred option of the present application, in the fault analysis method of FTTR devices, the step of performing semantic mining on the plurality of fault-related data to form a target fault semantic representation includes:
for each time series data in the plurality of fault related data, mining data fluctuation semantics in the time series data from at least two time change directions, and outputting corresponding local fault semantic representations;
When at least one piece of fault related data which does not belong to time series data exists in the plurality of pieces of fault related data, carrying out semantic mining on the fault related data aiming at each piece of fault related data in the at least one piece of fault related data, and outputting corresponding local fault semantic representation;
And fusing the local fault semantic representations corresponding to each piece of fault related data to form a target fault semantic representation, wherein the target fault semantic representation is used for representing global semantic information of the plurality of pieces of fault related data.
In a preferred option of the present application, in the fault analysis method of FTTR devices, the step of mining, for each time-series data of the plurality of fault-related data, data fluctuation semantics in the time-series data from at least two time-varying directions, and outputting a corresponding local fault semantic representation includes:
Loading the time series data into corresponding semantic mining branches, wherein each time series data corresponds to one semantic mining branch;
For each sequence sub-data in the time sequence data, performing semantic space mapping on the sequence sub-data to form a corresponding first fault semantic representation, taking the sequence sub-data as a starting point, cutting out a first sequence data fragment corresponding to the sequence sub-data in the time sequence data according to a first time change direction through a target window carried by the semantic mining branch, and cutting out a second sequence data fragment corresponding to the sequence sub-data in the time sequence data according to a second time change direction through the target window by taking the sequence sub-data as the starting point, wherein the size of the target window is used as a network parameter of the semantic mining branch and is formed in training;
Respectively carrying out semantic space mapping on the first sequence data segment and the second sequence data segment to form a corresponding second fault semantic representation and a corresponding third fault semantic representation;
And fusing the first fault semantic representation, the second fault semantic representation and the third fault semantic representation corresponding to each sequence sub-data to form a corresponding local fault semantic representation.
In a preferred option of the present application, in the fault analysis method of FTTR devices, the step of performing semantic space mapping on the first sequence data segment and the second sequence data segment to form a second fault semantic representation and a third fault semantic representation, includes:
Performing dispersion calculation on the first sequence data segment to obtain a first dispersion, and performing dispersion calculation on the second sequence data segment to obtain a second dispersion, wherein the time sequence data belongs to time-value sequence data comprising temperature, voltage or network flow;
and respectively carrying out semantic space mapping on the first dispersion and the second dispersion to form a corresponding second fault semantic representation and a corresponding third fault semantic representation, wherein the semantic space mapping comprises word embedding processing.
In a preferred option of the present application, in the fault analysis method of FTTR devices, the step of fusing the first fault semantic representation, the second fault semantic representation and the third fault semantic representation corresponding to each sequence sub-data to form a corresponding local fault semantic representation includes:
for each sequence sub-data, splicing the first fault semantic representation, the second fault semantic representation and the third fault semantic representation corresponding to the sequence sub-data to form a spliced fault semantic representation corresponding to the sequence sub-data;
Splicing the spliced fault semantic representations corresponding to each sequence sub-data to form spliced fault semantic representations corresponding to the time sequence data, and respectively rolling and pooling the spliced fault semantic representations corresponding to the time sequence data to realize different semantic feature extraction and form corresponding convolution fault semantic representations and pooling fault semantic representations, wherein the spliced fault semantic representations corresponding to each sequence sub-data, the convolution fault semantic representations and the pooling fault semantic representations have the same size;
For each sequence sub-data, focus mining is carried out on the convolution fault semantic representation and the pooling fault semantic representation respectively based on the splicing fault semantic representation corresponding to the sequence sub-data to form a corresponding first focus semantic representation and a second focus semantic representation Jiao Yuyi representation, and the first focus semantic representation and the second focus semantic representation Jiao Yuyi representation are overlapped to form a corresponding fusion focus semantic representation;
and splicing the fusion focusing semantic representations corresponding to each sequence sub-data to form a splicing focusing semantic representation, and determining a local fault semantic representation based on the splicing focusing semantic representation.
In a preferred option of the present application, in the fault analysis method of FTTR devices, when at least one fault-related data that does not belong to time-series data is included in the plurality of fault-related data, for each fault-related data in the at least one fault-related data, performing semantic mining on the fault-related data, and outputting a corresponding local fault semantic representation, the method includes:
When at least one piece of fault related data which does not belong to time series data exists in the plurality of pieces of fault related data, carrying out semantic space mapping on the fault related data aiming at each piece of fault related data in the at least one piece of fault related data to obtain corresponding fault mapping semantic representation;
When the number of the obtained fault mapping semantic representations is larger than a preset number, clustering each fault mapping semantic representation to form at least one corresponding semantic representation cluster;
Aiming at each fault mapping semantic representation, focusing and mining the fault mapping semantic representation according to the clustering center of the semantic representation cluster corresponding to the fault mapping semantic representation to form local fault semantic representation corresponding to the fault mapping semantic representation.
In a preferred option of the present application, in the fault analysis method of FTTR devices, the fault analysis method of FTTR device further includes:
Performing semantic mining on a plurality of training fault related data by using a semantic mining unit included in a candidate fault analysis network to form training fault semantic representation, wherein the candidate fault analysis network belongs to a neural network, the plurality of training fault related data comprise at least one training time sequence data, and in the process of semantic mining, mining data fluctuation semantics in the training time sequence data from at least two time variation directions for each training time sequence data;
Performing fault analysis based on the training fault semantic representation by utilizing a semantic analysis unit included in the candidate fault analysis network, and outputting training fault prediction data;
and updating the network parameters of the candidate fault analysis network according to the training loss index between the training fault prediction data and the fault label data corresponding to the plurality of training fault related data to form a target fault analysis network.
The application also provides a fault analysis device of FTTR equipment, which comprises:
The fault related data acquisition module is used for acquiring a plurality of fault related data obtained by data acquisition of the target FTTR equipment, wherein the fault related data is data contributing to the occurrence of faults of the LAN port of the target FTTR equipment, and at least one time series data exists in the plurality of fault related data;
The data semantic mining module is used for carrying out semantic mining on the plurality of fault related data to form target fault semantic representation, wherein in the process of semantic mining, data fluctuation semantics in the time sequence data are mined from at least two time change directions for each time sequence data;
The fault analysis module is configured to perform fault analysis on the target FTTR device based on the target fault semantic representation, and output fault prediction data corresponding to the target FTTR device, where the fault prediction data is used to reflect whether a LAN port of the target FTTR device will fail.
On the basis of the above, the application also provides an electronic device, comprising:
a memory for storing a computer program;
and the processor is connected with the memory and is used for executing the computer program stored in the memory so as to realize the fault analysis method of the FTTR equipment.
On the basis of the above, the present application also provides a computer readable storage medium, in which a computer program is stored, the computer program executing the steps of the fault analysis method of FTTR devices.
The method, the device, the equipment and the medium for analyzing the faults of FTTR equipment are characterized in that firstly, a plurality of fault related data obtained by data acquisition of target FTTR equipment are obtained, secondly, semantic mining is carried out on the plurality of fault related data to form target fault semantic representation, then, fault analysis is carried out on target FTTR equipment based on the target fault semantic representation, and fault prediction data corresponding to target FTTR equipment are output. On the basis of the above, on one hand, semantic mining is performed on a plurality of fault related data, so that semantic information carried by the formed target fault semantic representation can be richer, and on the other hand, in the process of semantic mining, for each time series data, at least two time change directions are used for mining the data fluctuation semantics, so that the representation reliability of the mined semantic information is higher, the reliability of fault prediction data output based on the target fault semantic representation is ensured, and the problem that effective analysis on LAN (local area network) port faults is difficult in the prior art is solved.
Drawings
In order to make the above objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Fig. 1 is a block diagram of an electronic device according to an embodiment of the present application.
Fig. 2 is a flow chart of a fault analysis method of FTTR equipment according to an embodiment of the present application.
FIG. 3 is a schematic diagram showing the fusion of semantic representations of sub-data of each sequence according to an embodiment of the present application.
Fig. 4 is a block schematic diagram of a fault analysis device of FTTR equipment according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, but not all embodiments of the present application. The components of the embodiments of the present application generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
As shown in fig. 1, an embodiment of the present application provides an electronic device. The electronic device may include a memory, a processor, and a fault analysis device of FTTR devices.
In detail, the memory and the processor are electrically connected directly or indirectly to realize transmission or interaction of data. For example, the memory and the processor may be electrically connected by one or more communication buses or signal lines. The fault analysis means of the FTTR device comprises at least one software function module stored in the memory in the form of software or firmware. The processor is configured to execute an executable computer program stored in the memory, for example, a software functional module and a computer program included in the fault analysis device of the FTTR device, so as to implement the fault analysis method of the FTTR device provided by the embodiment of the present application.
Alternatively, the Memory may be, but is not limited to, random access Memory (Random Access Memory, RAM), read Only Memory (ROM), programmable Read Only Memory (Programmable Read-Only Memory, PROM), erasable Read Only Memory (Erasable Programmable Read-Only Memory, EPROM), electrically erasable Read Only Memory (Electric Erasable Programmable Read-Only Memory, EEPROM), etc.
And the processor may be a general-purpose processor including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), a System on Chip (SoC), etc., a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components.
It will be appreciated that the architecture shown in fig. 1 is merely illustrative, and that the electronic device may also include more or fewer components than shown in fig. 1, or may have a different configuration than shown in fig. 1, for example, may also include a communication unit for information interaction with other devices.
With reference to fig. 2, the embodiment of the application further provides a fault analysis method of FTTR devices applicable to the electronic device. Wherein, the method steps defined by the flow related to the fault analysis method of the FTTR device can be implemented by the electronic device. The specific flow shown in fig. 2 will be described in detail.
Step S110, acquiring a plurality of fault related data obtained by data acquisition on the target FTTR device.
In the embodiment of the application, the electronic device can acquire a plurality of fault related data obtained by data acquisition of the target FTTR device. The fault related data refers to data that may have a contribution to the occurrence of a fault in the LAN port of the target FTTR device (i.e., some factors that may cause the occurrence of a fault in the LAN port), and at least one time-series data exists in the plurality of fault related data, for example, part of the fault related data in the plurality of fault related data belongs to the time-series data, or all of the fault related data in the plurality of fault related data belongs to the time-series data, and in addition, the time-series data refers to a data set collected sequentially according to a chronological order, such as data at time point 1, data at time point 2, data at time point 3, and so on. In addition, the specific application scenario of the target FTTR device may be FTTR-B (Business FTTR), i.e. a business all-optical networking scheme, which is a Wi-Fi scheme specially created for enterprises and oriented to the business scenario. And the Wi-Fi is covered at each corner of the enterprise by using an all-optical networking scheme of optical fiber access, photoelectric composite cable and Wi-Fi6, so that network services are provided for networking work of enterprise staff, such as live broadcast, online conference and other activities.
And step S120, carrying out semantic mining on the plurality of fault related data to form a target fault semantic representation.
In the embodiment of the application, after the plurality of fault related data are obtained, the electronic device can perform semantic mining on the plurality of fault related data to form a target fault semantic representation. In the process of semantic mining, for each time series data, mining the data fluctuation semantics in the time series data from at least two time variation directions. In addition, semantic mining means that potential semantic information is mined from the plurality of fault related data, and the potential semantic information is represented in a vector or matrix form, so that corresponding semantic representation is obtained.
And step S130, performing fault analysis on the target FTTR equipment based on the target fault semantic representation, and outputting fault prediction data corresponding to the target FTTR equipment.
In the embodiment of the present application, after the target fault semantic representation is obtained, the electronic device may perform fault analysis on the target FTTR device based on the target fault semantic representation, and output fault prediction data corresponding to the target FTTR device. The failure prediction data is used for reflecting whether the LAN port of the target FTTR device fails. For example, the target fault semantic representation may be subjected to full connection processing to obtain a corresponding full connection fault semantic representation, and then the full connection fault semantic representation may be processed by a classification function (such as softmax, etc.) to obtain a corresponding probability distribution, such as (a, b), where a may refer to a probability that the LAN port of the target FTTR device fails, b may refer to a probability that the LAN port of the target FTTR device does not fail, and then a type with a probability having a larger value may be determined as corresponding fault prediction data, and if a is greater than b, a fault may occur.
On the basis of the above, on one hand, semantic mining is performed on a plurality of fault related data, so that semantic information carried by the formed target fault semantic representation can be richer, and on the other hand, in the process of semantic mining, for each time series data, at least two time change directions are used for mining the data fluctuation semantics, so that the representation reliability of the mined semantic information is higher, the reliability of fault prediction data output based on the target fault semantic representation is ensured, and the problem that effective analysis on LAN (local area network) port faults is difficult in the prior art is solved.
It should be noted that, in step S120, a specific manner of performing semantic mining on the plurality of fault-related data is not limited, and corresponding selection may be performed according to actual requirements.
For example, in an alternative embodiment, in order to improve the efficiency of semantic mining, after semantic space mapping (such as word embedding) is performed on the multiple fault-related data, the semantic space mapping results corresponding to the fault-related data are spliced, and then convolution, pooling, activation, attention and other processes may be performed to obtain corresponding target fault semantic information.
For another example, in another alternative embodiment, in order to improve the accuracy of semantic mining, so that the obtained target fault semantic information can represent more semantic information, the step S120 may further include a step S121, a step S122, and a step S123, which are described below.
Step S121, for each time series data of the plurality of fault related data, mining data fluctuation semantics in the time series data from at least two time variation directions, and outputting a corresponding local fault semantic representation.
In the embodiment of the application, for each time series data in the plurality of fault related data, the data fluctuation semantics in the time series data can be mined from at least two time variation directions, and the corresponding local fault semantic representation can be output. It should be noted that, for time series data, the fluctuation of the data generally plays an important role, at least for faults of the device, so that a corresponding semantic mining can be performed.
Step S122, when at least one fault-related data not belonging to the time-series data is included in the plurality of fault-related data, semantic mining is performed on each fault-related data in the at least one fault-related data, and a corresponding local fault semantic representation is output.
In the embodiment of the application, when at least one piece of fault related data which does not belong to time series data exists in the plurality of pieces of fault related data, semantic mining is performed on each piece of fault related data in the at least one piece of fault related data, and corresponding local fault semantic representation is output, namely semantic information of the fault related data is mined.
Step S123, fusing the local fault semantic representations corresponding to each fault related data to form a target fault semantic representation.
In the embodiment of the present application, after obtaining the local fault semantic representation corresponding to each fault related data (including the local fault semantic representation corresponding to each time series data), the local fault semantic representations corresponding to each fault related data may be fused to form the target fault semantic representation. Wherein the target fault semantic representation is used to characterize global semantic information possessed by the plurality of fault related data. Illustratively, the local fault semantic representations corresponding to each fault related data may be spliced to obtain corresponding spliced semantic representations, and then convolution, pooling and activation processing may be performed on the spliced semantic representations, so as to obtain target fault semantic information capable of characterizing global semantic information of the plurality of fault related data.
It should be understood that, in the above embodiment, the implementation manner of step S121 is not limited, that is, the specific manner of mining the data fluctuation semantics in the time-series data is not limited, for example, in an alternative embodiment, in order to fully mine the semantic information of the data fluctuation semantics and ensure the semantic richness of the obtained local fault semantic representation, step S121 may further include the following steps S121a, S121b, S121c and S121d.
Step S121a, loading the time-series data into a corresponding semantic mining branch.
In the embodiment of the application, the time series data can be loaded into the corresponding semantic mining branch. Each of the time series data corresponds to one semantic mining branch, and in addition, the semantic mining branch belongs to a part of a corresponding neural network model, such as a part of a network structure of a target fault analysis network in the following, and is used for semantic mining.
Step S121b, for each sequence sub-data in the time series data, performing semantic space mapping on the sequence sub-data to form a corresponding first fault semantic representation, taking the sequence sub-data as a starting point, cutting out a first sequence data segment corresponding to the sequence sub-data in the time series data according to a first time change direction through a target window carried by the semantic mining branch, and cutting out a second sequence data segment corresponding to the sequence sub-data in the time series data according to a second time change direction through the target window with the sequence sub-data as a starting point.
In the embodiment of the application, for each sequence sub-data (such as data at a time point) in the time sequence data, semantic space mapping (such as word embedding processing) is performed on the sequence sub-data to form a corresponding first fault semantic representation, a target window carried by the semantic mining branch is used as a starting point, a first sequence data fragment corresponding to the sequence sub-data is cut out in the time sequence data according to a first time change direction (such as a time from the early to the late direction) by taking the sequence sub-data as a starting point, and a second sequence data fragment corresponding to the sequence sub-data is cut out in the time sequence data according to a second time change direction (such as a time from the late to the early direction) by taking the sequence sub-data as a starting point. The size of the target window is used as a network parameter of the semantic mining branch and is formed in training. For example, when the size of the target window is equal to 4, it means that the number of sequence sub-data included in the first sequence data segment is less than or equal to 4 and the number of sequence sub-data included in the second sequence data segment is less than or equal to 4. For example, for a first sequence sub-data, a first sequence data segment includes the first sequence sub-data, a second sequence sub-data, a third sequence sub-data, and a fourth sequence sub-data, and a second sequence data segment includes the first sequence sub-data. For the second sequence sub-data, the first sequence data segment includes the second sequence sub-data, the third sequence sub-data, the fourth sequence sub-data, and the fifth sequence sub-data, and the second sequence data segment includes the first sequence sub-data and the second sequence sub-data. For the fourth sequence sub-data, the first sequence data segment includes the first sequence sub-data, the second sequence sub-data, the third sequence sub-data, and the fourth sequence sub-data, the second sequence data segment includes the fourth sequence sub-data, the fifth sequence sub-data, the sixth sequence sub-data, and the seventh sequence sub-data, and the other sequence data segments and the like, which are not exemplified herein.
And step 121c, performing semantic space mapping on the first sequence data segment and the second sequence data segment respectively to form a corresponding second fault semantic representation and a corresponding third fault semantic representation.
In the embodiment of the application, after the first sequence data segment and the second sequence data segment are obtained, semantic space mapping can be respectively carried out on the first sequence data segment and the second sequence data segment to form a corresponding second fault semantic representation and a corresponding third fault semantic representation.
Step S121d, fusing the first fault semantic representation, the second fault semantic representation and the third fault semantic representation corresponding to each sequence sub-data to form a corresponding local fault semantic representation.
In the embodiment of the application, after the first fault semantic representation, the second fault semantic representation and the third fault semantic representation corresponding to each sequence sub-data are obtained, the first fault semantic representation, the second fault semantic representation and the third fault semantic representation corresponding to each sequence sub-data can be fused to form the corresponding local fault semantic representation. In this way, in the local fault semantic representation, the semantic information of the sequence sub-data itself is carried, the semantic information of the fluctuation condition of the previous sequence sub-data is carried, and the semantic information of the fluctuation condition of the subsequent sequence sub-data is carried, so that the local fault semantic representation has better semantic representation capability. In addition, as the target window is formed in training, the adaptive target window can be determined for different time series data, so that the reliable capture of the potential semantic information in the fluctuation condition is realized.
It will be appreciated that in the above embodiment, the implementation of step S121c is not limited, i.e. the specific way of performing semantic space mapping on the first sequence data segment and the second sequence data segment, respectively, for example, in an alternative embodiment, in order to be able to reliably capture the latent semantic information in the corresponding fluctuation situation, step S121c may further include the following:
Firstly, performing dispersion calculation on the first sequence data segment to obtain a first dispersion, performing dispersion calculation on the second sequence data segment to obtain a second dispersion, wherein the time sequence data belongs to time-value sequence data including temperature, voltage or network flow, such as temperature at time point 1, temperature at time point 2, temperature at time point 3 and the like;
Secondly, semantic space mapping is conducted on the first dispersion and the second dispersion respectively to form corresponding second fault semantic representation and third fault semantic representation, wherein the semantic space mapping comprises word embedding processing, namely word embedding processing is conducted on the corresponding dispersion to obtain corresponding semantic representation, and word embedding processing can be achieved through a corresponding word embedding model.
It will be appreciated that in the above embodiment, the embodiment of step S121d is not limited, i.e. the specific manner of forming the corresponding local fault semantic representation is not limited, for example, in an alternative embodiment, in order to achieve sufficient fusion of multiple semantic representations of each sequence of sub-data, step S121d may further include the following (shown in connection with fig. 3):
Firstly, for each sequence sub-data, splicing the first fault semantic representation, the second fault semantic representation and the third fault semantic representation corresponding to the sequence sub-data to form a spliced fault semantic representation corresponding to the sequence sub-data;
Secondly, splicing the spliced fault semantic representations corresponding to each sequence sub-data to form spliced fault semantic representations corresponding to the time sequence data, respectively carrying out convolution and pooling (which can be respectively realized through a corresponding convolution network and pooling network) on the spliced fault semantic representations corresponding to the time sequence data so as to realize different semantic feature extraction and form corresponding convolution fault semantic representations and pooling fault semantic representations, wherein the spliced fault semantic representations corresponding to each sequence sub-data, the convolution fault semantic representations and the pooling fault semantic representations have the same size, namely important semantic features in the spliced fault semantic representations are respectively extracted through convolution and pooling, and compression of the semantic representations is realized, so that the sizes of the spliced fault semantic representations corresponding to each sequence sub-data are the same, and further, the subsequent processing is convenient while the capturing of the important semantic features is realized;
Then, for each sequence sub-data, based on the spliced fault semantic representation corresponding to the sequence sub-data, focus mining is performed on the convolution fault semantic representation and the pooled fault semantic representation to form a corresponding first focus semantic representation and a second focus semantic representation Jiao Yuyi, and the first focus semantic representation and the second focus semantic representation Jiao Yuyi are overlapped to form a corresponding fused focus semantic representation; that is, on one hand, semantic information having an association relationship with the convolution fault semantic representation can be mined from the spliced fault semantic representation corresponding to the sequence sub-data, and on the other hand, semantic information having an association relationship with the pooling fault semantic representation can be mined from the spliced fault semantic representation corresponding to the sequence sub-data, so that, as the convolution fault semantic representation and the pooling fault semantic representation are obtained by respectively coiling and pooling the spliced fault semantic representation capable of representing global semantic information, the convolution fault semantic representation and the pooling fault semantic representation can pay attention to different semantic features when representing global semantic information, and therefore focus mining can be performed respectively, so that mining of different associated semantic features, namely mining of more associated semantic features, can be realized, and the semantics of the overlapped and integrated focus semantic representation is richer;
Secondly, the fusion focusing semantic representations corresponding to each sequence sub-data can be spliced to form a splicing focusing semantic representation, and local fault semantic representation is determined based on the splicing focusing semantic representation; the stitched focus semantic representation may be used as a corresponding local fault semantic representation, or may be convolved, pooled, and activated to obtain a corresponding local fault semantic representation.
It will be appreciated that in the above embodiment, the implementation manner of step S122 is not limited, that is, the specific manner of performing semantic mining on the fault-related data is not limited, for example, in an alternative embodiment, in order to make the semantic representation of the mined local fault semantic representation better, step S122 may further include the following:
Firstly, when at least one fault related data which does not belong to time series data exists in the plurality of fault related data, semantic space mapping is carried out on the fault related data aiming at each fault related data in the at least one fault related data to obtain corresponding fault mapping semantic representation, and word embedding processing can be carried out through a word embedding model to obtain corresponding semantic space mapping by way of example, in addition, the fault related data can refer to the number of times of not carrying out electrostatic protection when carrying out port connection operation, such as not wearing an antistatic bracelet, because electrostatic discharge usually occurs when connecting or operating equipment, hardware damage can be caused to a certain extent when a LAN port of the equipment contacts an electrostatic source, or the fault related data can refer to the condition of electromagnetic interference, such as whether the fault related data is in a strong magnetic environment, such as being placed near a high-power electric appliance (such as a microwave oven, an air conditioner and the like), and the like, because frequent electromagnetic interference can influence the work of a LAN port and possibly cause damage;
Secondly, when the number of the obtained fault mapping semantic representations is larger than a preset number (such as 3, 5, 7, 10 and the like), clustering is carried out on each fault mapping semantic representation (a clustering specific algorithm of clustering is not limited, such as a clustering algorithm of KNN (K-Nearest Neighbors, K nearest neighbor) and the like), and at least one corresponding semantic representation cluster is formed (namely at least one clustering center is obtained);
and then, aiming at each fault mapping semantic representation, carrying out focusing mining on the fault mapping semantic representation according to the clustering center of the semantic representation cluster corresponding to the fault mapping semantic representation to form local fault semantic representation corresponding to the fault mapping semantic representation.
Based on the method, the clustering is performed first and then the focusing excavation is performed, so that the focusing excavation precision can be ensured, and the problem that the accuracy of the excavated semantic representation is not high due to the focusing excavation based on irrelevant semantic representation is avoided. In addition, embodiments of focused mining may employ cross-attention.
It should be further noted that, in the above-mentioned step S120 and step S130, in order to ensure reliable execution of step S120 and step S130, the implementation may be performed by a corresponding neural network model, such as a target fault analysis network. Based on this, the fault analysis method of FTTR devices may further include a step of training to form the target fault analysis network, specifically as follows:
firstly, semantic mining is performed on a plurality of training fault related data by using a semantic mining unit included in a candidate fault analysis network to form training fault semantic representation, wherein the candidate fault analysis network belongs to a neural network, the plurality of training fault related data comprise at least one training time sequence data, in the process of semantic mining, for each training time sequence data, data fluctuation semantics in the training time sequence data are mined from at least two time variation directions, and the related explanation of the step S120 can be referred to;
Secondly, a semantic analysis unit included in the candidate fault analysis network may be utilized to perform fault analysis based on the training fault semantic representation, and training fault prediction data may be output, which may refer to the explanation related to step S130;
Then, according to the training loss index (such as cross entropy loss) between the training fault prediction data and the fault label data (i.e. information about whether the marked representation will generate faults or not, such as manual marking or recognition by adopting other neural network models) corresponding to the plurality of training fault related data, the network parameters of the candidate fault analysis network may be updated to form the target fault analysis network, for example, the network parameters may be updated along the direction of reducing the training loss index until the training loss index converges, so as to form the target fault analysis network.
Referring to fig. 4, the embodiment of the application further provides a fault analysis device of FTTR equipment, which can be applied to the electronic equipment. The fault analysis device of FTTR equipment can comprise a fault related data acquisition module, a data semantic mining module and a fault analysis module.
In detail, the fault related data obtaining module may be configured to obtain a plurality of fault related data obtained by performing data collection on the target FTTR device, where the fault related data is data that may have a contribution to a failure of the LAN port of the target FTTR device, and at least one time series data exists in the plurality of fault related data. In an embodiment of the present application, the fault related data acquisition module may be used to perform step S110 shown in fig. 2, and the description of step S110 may be referred to above for the relevant content of the fault related data acquisition module.
In detail, the data semantic mining module may be configured to perform semantic mining on the plurality of fault related data to form a target fault semantic representation, where, in the process of semantic mining, for each time-series data, data fluctuation semantics in the time-series data are mined from at least two time-varying directions. In an embodiment of the present application, the data semantic mining module may be used to perform step S120 shown in fig. 2, and the description of step S120 may be referred to above for the relevant content of the data semantic mining module.
In detail, the fault analysis module may be configured to perform fault analysis on the target FTTR device based on the target fault semantic representation, and output fault prediction data corresponding to the target FTTR device, where the fault prediction data is used to reflect whether a LAN port of the target FTTR device will fail. In an embodiment of the present application, the fault analysis module may be used to perform step S130 shown in fig. 2, and the description of step S130 may be referred to for the relevant content of the fault analysis module.
In an embodiment of the present application, corresponding to the above-mentioned fault analysis method applied to the FTTR devices of the electronic device, a computer readable storage medium is further provided, where a computer program is stored in the computer readable storage medium, and the computer program executes each step of the fault analysis method of the FTTR device when running. The steps executed when the computer program runs are not described in detail herein, and reference may be made to the explanation of the fault analysis method of the FTTR apparatus.
In summary, the method, the device, the equipment and the medium for analyzing the faults of FTTR equipment provided by the application firstly acquire a plurality of fault related data obtained by data acquisition of target FTTR equipment, secondly perform semantic mining on the plurality of fault related data to form target fault semantic representation, and then perform fault analysis on target FTTR equipment based on the target fault semantic representation to output fault prediction data corresponding to target FTTR equipment. On the basis of the above, on one hand, semantic mining is performed on a plurality of fault related data, so that semantic information carried by the formed target fault semantic representation can be richer, and on the other hand, in the process of semantic mining, for each time series data, at least two time change directions are used for mining the data fluctuation semantics, so that the representation reliability of the mined semantic information is higher, the reliability of fault prediction data output based on the target fault semantic representation is ensured, and the problem that effective analysis on LAN (local area network) port faults is difficult in the prior art is solved.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. The apparatus and method embodiments described above are merely illustrative, for example, flow diagrams and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present application may be integrated together to form a single part, or each module may exist alone, or two or more modules may be integrated to form a single part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, an electronic device, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. The storage medium includes a U disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, an optical disk, or other various media capable of storing program codes. It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.
The above description is only of the preferred embodiments of the present application and is not intended to limit the present application, but various modifications and variations can be made to the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (9)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510465808.5A CN120017489B (en) | 2025-04-15 | 2025-04-15 | Fault analysis method and device for FTTR equipment, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510465808.5A CN120017489B (en) | 2025-04-15 | 2025-04-15 | Fault analysis method and device for FTTR equipment, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN120017489A CN120017489A (en) | 2025-05-16 |
| CN120017489B true CN120017489B (en) | 2025-08-05 |
Family
ID=95668605
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510465808.5A Active CN120017489B (en) | 2025-04-15 | 2025-04-15 | Fault analysis method and device for FTTR equipment, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN120017489B (en) |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10127901B2 (en) * | 2014-06-13 | 2018-11-13 | Microsoft Technology Licensing, Llc | Hyper-structure recurrent neural networks for text-to-speech |
| US10497366B2 (en) * | 2018-03-23 | 2019-12-03 | Servicenow, Inc. | Hybrid learning system for natural language understanding |
| CN112131673B (en) * | 2020-09-30 | 2021-09-28 | 西南石油大学 | Engine surge fault prediction system and method based on fusion neural network model |
| US12272148B2 (en) * | 2020-11-09 | 2025-04-08 | Nvidia Corporation | Scalable semantic image retrieval with deep template matching |
| CN115617609B (en) * | 2022-10-18 | 2025-05-27 | 支付宝(杭州)信息技术有限公司 | A monitoring data processing method and device |
| CN119477188B (en) * | 2024-09-30 | 2025-08-29 | 国网四川省电力公司宜宾供电公司 | A method for generating standardized test reports for SCD files based on correctness checking |
| CN119396096A (en) * | 2024-10-29 | 2025-02-07 | 宜科树人(苏州)教育科技有限公司 | Digital factory operation virtual simulation teaching method and system |
-
2025
- 2025-04-15 CN CN202510465808.5A patent/CN120017489B/en active Active
Non-Patent Citations (1)
| Title |
|---|
| 基于时间序列数据挖掘的故障检测方法;李海林等;《数据采集与处理》;20160430;第1-4节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN120017489A (en) | 2025-05-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US12124326B2 (en) | Automatic correlation of dynamic system events within computing devices | |
| EP3251298B1 (en) | Data extraction | |
| US20160055044A1 (en) | Fault analysis method, fault analysis system, and storage medium | |
| CN111078513B (en) | Log processing method, device, equipment, storage medium and log alarm system | |
| CN111949480B (en) | A Component Awareness-Based Log Anomaly Detection Method | |
| CN113239365B (en) | Vulnerability repairing method based on knowledge graph | |
| CN120632770B (en) | Software defect information fusion method and system based on multi-source data | |
| CN117667479A (en) | Diagnostic methods, devices, storage media and electronic equipment for server faults | |
| CN111191335A (en) | Wind turbine failure cause tracing method, device, equipment and storage medium | |
| CN120017489B (en) | Fault analysis method and device for FTTR equipment, equipment and medium | |
| CN113434404B (en) | Automated business verification method and device for verifying disaster recovery system reliability | |
| CN113342861B (en) | Data management method and device in service scene | |
| US20240119090A1 (en) | Methods and systems for automated template mining for observability | |
| CN114422392B (en) | Intelligent risk monitoring system and risk monitoring method | |
| CN118568067A (en) | Provenance graph compression method, device, electronic device and storage medium | |
| CN117667688A (en) | Software call link extraction method and device | |
| CN119991086B (en) | Electrical equipment operation data management method and system | |
| US12326783B2 (en) | Method, electronic device, and computer program product for collecting training data | |
| WO2015184750A1 (en) | Data maintenance method and device of network element device | |
| CN118363781B (en) | A method and terminal for microservice fault prediction | |
| CN119377064A (en) | Method, device, equipment and storage medium for system anomaly detection | |
| CN121239750A (en) | Data processing, computing equipment, computer storage media and software products | |
| CN118041759A (en) | Method, device and equipment for locating fault root cause of server cluster | |
| CN120353662A (en) | Database fault detection and recovery method and related equipment | |
| CN119440601A (en) | An operation and maintenance method and system based on big data automated operation and maintenance platform |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |