A method and system for generating work orders for full-area monitoring of optical cables

Abstract

This application relates to the field of optical cable operation and maintenance management, specifically to a method and system for generating optical cable full-domain monitoring work orders. The method includes: collecting pending fault data from optical cable full-domain monitoring; acquiring historical similar fault data similar to the pending fault data; performing semantic analysis on the pending fault data and historical similar fault data to obtain a pending fault logical sequence and a historical similar fault logical sequence; using the historical similar fault logical sequence to enhance the features of the pending fault logical sequence, obtaining fault enhancement sequence features; using a fault detection model to identify the fault enhancement sequence features to obtain fault information, and generating a fault work order based on the fault information. Compared with existing technologies, this application utilizes historical fault information to semantically and logically enhance the current pending fault data, thereby enabling the effective acquisition of fault information from the pending fault data to construct fault work orders, facilitating maintenance personnel in their work.

Description

Technical Field

[0001] This invention relates to the field of optical cable operation and maintenance management, and more specifically, to a method and system for generating optical cable full-area monitoring work orders. Background Technology

[0002] With the widespread adoption of 5G, cloud computing, and the Internet of Things, fiber optic communication has become the core of modern information infrastructure. Fiber optic networks have evolved from early short-distance point-to-point connections to a network architecture covering the entire network, undertaking the task of data transmission throughout the entire path from central nodes to end customers.

[0003] A global fiber optic network covers a large area and includes numerous optical cables and optical path devices. Therefore, various faults may occur during the daily operation and maintenance of a global fiber optic network. To effectively resolve these faults, corresponding fault tickets need to be generated to provide maintenance personnel with a basis for troubleshooting. Existing fault tickets typically only contain a partial description of the fault, while detailed information requires maintenance personnel to conduct on-site investigations, leading to reduced troubleshooting efficiency and ultimately impacting the customer's user experience. Summary of the Invention

[0004] This invention provides a method and system for generating optical cable full-area monitoring work orders, which are used to generate fault work orders containing fault information based on the description of the fault problem, so that maintenance personnel can quickly handle the fault problem and improve the efficiency of fault problem resolution.

[0005] According to a first aspect of this application, a method for generating a fiber optic cable full-area monitoring work order is provided, the method comprising:

[0006] Collect data on unprocessed faults from the full-area monitoring of optical cables;

[0007] Obtain historical similar fault data that are similar to the fault data to be processed from a preset historical fault database;

[0008] Semantic analysis is performed on the fault data to be processed to obtain a logical sequence of faults to be processed, and semantic analysis is performed on the historical similar fault data to obtain a logical sequence of historical similar faults.

[0009] The fault logic sequence to be processed is enhanced with the historical similar fault logic sequence to obtain fault enhancement sequence features.

[0010] The fault type is obtained by identifying the fault enhancement sequence features using a pre-trained fault detection model, the fault information of the fault data to be processed is obtained based on the fault type, and a fault work order is generated based on the fault information.

[0011] Optionally, the step of performing semantic analysis on the fault data to be processed to obtain a logical sequence of faults to be processed, and performing semantic analysis on the historical similar fault data to obtain a logical sequence of historical similar faults, includes:

[0012] The fault data to be processed and the historical similar fault data are respectively segmented into words based on semantics to obtain the first semantic word segmentation of the fault data to be processed and the second semantic word segmentation of the historical similar fault data.

[0013] Obtain the first logical relationship between the first semantic word segments, and obtain the second logical relationship between the second semantic word segments;

[0014] The fault logic sequence to be processed is obtained based on the first semantic word segmentation and the first logical relationship, and the historical similar fault logic sequence is obtained based on the second semantic word segmentation and the second logical relationship.

[0015] Optionally, obtaining the first logical relationship between the first semantic segments and obtaining the second logical relationship between the second semantic segments includes:

[0016] The first semantic word is queried in the preset fault knowledge graph to obtain the first fault knowledge entity corresponding to the first semantic word;

[0017] The second semantic word is queried in the preset fault knowledge graph to obtain the second fault knowledge entity corresponding to the second semantic word;

[0018] Extract the first fault relationship corresponding to the first fault knowledge entity from the fault knowledge graph as the first logical relationship.

[0019] The second fault relationship corresponding to the second fault knowledge entity is extracted from the fault knowledge graph and used as the second logical relationship.

[0020] Optionally, the step of using the historical similar fault logic sequence to enhance the features of the fault logic sequence to obtain fault-enhanced sequence features includes:

[0021] Feature identification is performed on the historical similar fault logic sequence and the fault logic sequence to be processed respectively to obtain the first logical feature of the historical similar fault logic sequence and the second logical feature of the fault logic sequence to be processed.

[0022] The first logical feature and the second logical feature are fused through a cross-attention mechanism to obtain fault enhancement sequence features.

[0023] Optionally, the fault information of the fault data to be processed is obtained according to the fault type, including:

[0024] Based on the fault type and the fault data to be processed, the associated third fault knowledge entity is extracted from the preset fault knowledge graph.

[0025] The fault information is obtained based on the third fault knowledge entity and the fault data to be processed.

[0026] Optionally, after the step of generating a fault work order based on the fault information, the method further includes:

[0027] Obtain the impact information of the fault corresponding to the fault information in the optical cable, and set the priority level of the fault work order according to the impact information.

[0028] Optionally, obtaining the impact information of the fault corresponding to the fault information in the optical cable includes:

[0029] Based on the fault information, the location of the fault is determined to be the fault topology location in the optical cable topology network corresponding to the optical cable;

[0030] The number of optical paths affected by the fault and their corresponding optical path attributes are obtained based on the fault topology location.

[0031] The extent of damage caused by the fault is determined based on the fault information.

[0032] The impact information of the fault on the optical cable is obtained based on the number of optical paths affected by the fault, the corresponding optical path attributes, and the degree of damage caused by the fault.

[0033] According to a second aspect of this application, a system for generating work orders for comprehensive optical cable monitoring is provided, the system comprising:

[0034] The data acquisition module is used to collect fault data to be processed for the full-area monitoring of optical cables;

[0035] The historical data extraction module is used to obtain historical similar fault data that is similar to the fault data to be processed from a preset historical fault database;

[0036] The logical sequence extraction module is used to perform semantic analysis on the fault data to be processed to obtain the logical sequence of the fault to be processed, and to perform semantic analysis on the historical similar fault data to obtain the logical sequence of the historical similar fault.

[0037] The sequence enhancement module is used to enhance the features of the fault logic sequence to be processed using the historical similar fault logic sequence to obtain fault enhancement sequence features.

[0038] The work order generation module is used to identify the fault type by using a pre-trained fault detection model to identify the fault enhancement sequence features, obtain the fault information of the fault data to be processed according to the fault type, and generate a fault work order according to the fault information.

[0039] According to a third aspect of this application, an electronic device is provided, comprising:

[0040] Memory, used to store one or more computer programs;

[0041] A processor, when the one or more computer programs are executed by the processor, implements the method for generating a fiber optic cable full-area monitoring work order as described in the first aspect above.

[0042] According to a fourth aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions, the computer instructions being configured to cause a processor to execute and implement the method for generating a fiber optic cable full-area monitoring work order as described in the first aspect.

[0043] Based on any of the above aspects, the embodiments of this application provide a method, system, electronic device, and computer storage medium for generating optical cable full-area monitoring work orders. This involves querying the fault data to be processed in a historical fault database, extracting historical similar fault data matching the fault data to be processed, extracting the logical sequence of the fault to be processed from the fault data to be processed, and extracting historical similar fault logical sequences from the historical similar fault data. The logical sequences contain event details and logical relationships of the corresponding faults. The historical similar fault logical sequences are used to enhance the features of the logical sequence of the fault to be processed. The detailed event details and logical relationships of the faults in the historical similar fault logical sequences are used to supplement and enhance the logical sequence of the fault to be processed. This enables the fault detection model to effectively identify the features of the supplemented and enhanced fault sequence, accurately obtain the fault information of the fault data to be processed, and then generate detailed fault work orders based on the fault information. This allows maintenance personnel to respond quickly based on the fault information in the fault work orders, improving the efficiency of fault problem handling. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 This is a flowchart illustrating the steps of the generation method provided in this embodiment.

[0046] Figure 2 This is a flowchart illustrating the steps for obtaining the fault logic sequence to be processed and the historical similar fault logic sequence provided in this embodiment.

[0047] Figure 3 This is a flowchart illustrating the steps for obtaining the first and second logical relationships provided in this embodiment.

[0048] Figure 4 This is a flowchart illustrating the steps for obtaining fault information provided in this embodiment.

[0049] Figure 5 This is a schematic diagram of the functional modules of the generation system provided in this embodiment.

[0050] Figure 6 This is a schematic diagram of the device structure of the electronic device provided in this embodiment. Detailed Implementation

[0051] The accompanying drawings are for illustrative purposes only and should not be construed as limiting the scope of this application. To better illustrate the following embodiments, some components in the drawings may be omitted, enlarged, or reduced, and do not represent the actual dimensions of the product; it is understandable to those skilled in the art that some well-known structures and their descriptions may be omitted in the drawings.

[0052] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0053] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0054] A global fiber optic network covers a large area and includes a large number of optical cables and optical path equipment. Therefore, various faults may occur during the daily operation and maintenance of a global fiber optic network.

[0055] However, existing fault tickets are usually generated after customers complain about fault problems. Since customers usually lack relevant knowledge in the field of optical cables, the fault problems they describe are often one-sided, usually only describing some simple symptoms. As a result, maintenance personnel cannot obtain accurate fault information based on fault tickets alone. They need to conduct on-site physical inspections to confirm the fault information, which reduces the efficiency of fault problem resolution and affects the customer's user experience.

[0056] This embodiment provides a technical solution that can solve the above problems. The specific implementation of this application will be described in detail below with reference to the accompanying drawings.

[0057] like Figure 1 As shown in the figure, this embodiment provides a method for generating a fiber optic cable full-area monitoring work order, which may include the following steps:

[0058] S1: Collect unprocessed fault data for full-area monitoring of optical cables;

[0059] In this embodiment, fault text descriptions reported by customers or maintenance personnel during the full-area monitoring of the optical cable can be collected, or fault alarm information from the full-area monitoring of the optical cable can be obtained, and the fault alarm information can be organized into natural language description text as the fault text description.

[0060] For example, the fault text description could be "Optical power suddenly drops by 15dB at a distance of 33.2 kilometers from the computer room A0, while the temperature rises by 8°C", or it could be "The signal is intermittent, but the router's signal indicator light is normal".

[0061] Understandably, since the fault text description includes descriptions reported by the customer, the cause and solution of the fault problem cannot often be directly determined based solely on the description provided by the customer. Therefore, further processing of the fault text description provided by the user is required.

[0062] S2: Obtain historical similar fault data that is similar to the fault data to be processed from the preset historical fault database;

[0063] In this embodiment, the historical fault database contains a number of historical fault data; the historical fault data includes historical fault text descriptions, historical fault information and historical fault solutions for the historical faults of the optical cable full-area monitoring.

[0064] In one embodiment, the historical fault data can be encoded using an embedded encoder to obtain a historical fault encoding vector corresponding to the historical fault data, and the historical fault encoding vector can be stored in the historical fault database. In this embodiment, obtaining historical similar fault data similar to the fault data to be processed from the preset historical fault database may include:

[0065] The fault data to be processed is encoded using an embedded encoder to obtain a query vector. The vector similarity between the query vector and the historical fault encoding vectors stored in the historical fault database is calculated. Based on the vector similarity, at least one historical fault data is extracted from the historical fault database as the historical similar fault data. Preferably, the historical fault data in the historical fault database can be sorted in descending order of vector similarity, and a predetermined number of historical fault data with the highest vector similarity can be extracted as the historical similar fault data.

[0066] S3: Perform semantic analysis on the fault data to be processed to obtain a logical sequence of faults to be processed, and perform semantic analysis on the historical similar fault data to obtain a logical sequence of historical similar faults;

[0067] In this embodiment, as Figure 2 As shown, step S3 may include the following steps:

[0068] S31: The fault data to be processed and the historical similar fault data are respectively segmented into words based on semantics to obtain the first semantic word segmentation of the fault data to be processed and the second semantic word segmentation of the historical similar fault data;

[0069] In this embodiment, the fault data to be processed and the historical similar fault data can be processed using a professional dictionary and named entity recognition model based on the field of optical cable operation and maintenance. The fault text description in the fault data to be processed and the historical fault text description in the historical similar fault data are identified and segmented to obtain the first semantic segmentation and the second semantic segmentation, which respectively represent the semantic information with logical relationships in the fault data to be processed and the historical similar fault data.

[0070] For example, assuming the fault text description of the fault data to be processed is "the optical power suddenly drops by 15dB at a distance of 33.2 km from the equipment room A0, while the temperature rises by 8°C", then the first semantic segmentation obtained can be ["at a distance of 33.2 km from the equipment room A0", "the optical power suddenly drops by 15dB", "the temperature rises by 8°C"]. Assuming the historical fault text description of the historical similar fault data is "the optical power suddenly decreases by 10dB at a distance of 45.8 km from the equipment room B0, and the local temperature rises by 6°C, the cause of the fault is damage to the outer sheath of the optical cable caused by third-party mechanical excavation", then the second semantic segmentation can be ["at a distance of 45.8 km from the equipment room B0", "the optical power suddenly decreases by 10dB", "the local temperature rises by 6°C", "the cause of the fault is damage to the outer sheath of the optical cable caused by third-party mechanical excavation"].

[0071] S32: Obtain the first logical relationship between the first semantic word segments, and obtain the second logical relationship between the second semantic word segments;

[0072] Understandably, although the first semantic segment and the second semantic segment have separate semantic descriptions, the logical relationships between the first semantic segment and between the second semantic segment are not clear. For example, regarding the first semantic segment "optical power suddenly drops by 15dB" and "temperature rises by 8°C" mentioned above, it is unclear whether they are parallel or causally related, with the decrease in optical power due to the increase in temperature, and the causal order is also unclear. Therefore, it is necessary to determine the first logical relationship between the first semantic segment and the second logical relationship between the second semantic segment to achieve synchronization between the logical relationships, facilitating subsequent feature enhancement processing.

[0073] In one implementation, such as Figure 3 As shown, step S32 may include the following sub-steps:

[0074] A1: Query the first semantic word in the preset fault knowledge graph to obtain the first fault knowledge entity corresponding to the first semantic word;

[0075] A2: Query the second semantic word in the preset fault knowledge graph to obtain the second fault knowledge entity corresponding to the second semantic word;

[0076] A3: Extract the first fault relationship corresponding to the second fault knowledge entity from the fault knowledge graph as the first logical relationship;

[0077] A4: Extract the second fault relationship corresponding to the second fault knowledge entity from the fault knowledge graph as the second logical relationship.

[0078] In this embodiment, the fault knowledge graph is pre-built and stores standardized entities in the field of optical cable faults and their interrelationships. For example, the fault knowledge graph includes entity types such as fault location, fault phenomenon (e.g., "sudden drop in optical power" and "temperature rise"), fault-related components (e.g., "outer sheath of optical cable" and "optical cable frame"), fault mode (e.g., "external damage"), and fault cause. Corresponding specific instances are recorded under the corresponding entity type, as well as predefined entity logical relationship types such as "cause", "located in", "manifests as", and "accompanying".

[0079] Therefore, by using precise matching or semantic similarity matching, the first and second semantic segments can be mapped to the corresponding first and second fault knowledge entities in the fault knowledge graph. Then, the corresponding entity logical relationships can be extracted from the fault knowledge graph using the first and second fault knowledge entities, respectively, to obtain the corresponding first and second logical relationships.

[0080] Taking the first semantic segmentation ["distance from computer room A033.2 km", "optical power suddenly drops by 15dB", "temperature rises by 8℃"] as an example, "distance from computer room A033.2 km" can be classified as the entity type of the fault location, "optical power suddenly drops by 15dB" can be classified as the entity type of the fault phenomenon, and "temperature rises by 8℃" can be classified as the entity type of the fault phenomenon. After determining the entity types of each first semantic segmentation, "distance from computer room A033.2 km" has a location relationship with "optical power suddenly drops by 15dB" and "temperature rises by 8℃", and "optical power suddenly drops by 15dB" and "temperature rises by 8℃" have a parallel relationship.

[0081] S33: Obtain the fault logic sequence to be processed based on the first semantic word segmentation and the first logical relationship, and obtain the historical similar fault logic sequence based on the second semantic word segmentation and the second logical relationship.

[0082] In one implementation, the pending fault logic sequence and the historical similar fault logic sequence can be set according to the specific relationships in the first and second logical relationships. It is understood that because the pending fault data and historical similar fault data corresponding to the first and second logical relationships are similar, the first and second logical relationships are also similar. Therefore, the logical order of the first semantic word segmentation can be determined based on the first logical relationship, and then the first semantic word segmentation can be sorted according to the logical order to obtain the pending fault logic sequence. Simultaneously, the second semantic word segmentation can be sorted according to the logical order to obtain the historical similar fault logic sequence. Specifically, for the second semantic word segmentation, the parts matching the logical order are first identified and arranged in the same order; for second semantic word segmentation exceeding the logical order range, they are placed at the end of the sorted sequence, thereby generating the complete historical similar fault logic sequence. If there is a first logical relation that does not match the second logical relation, when sorting the second semantic word, the second semantic word at the position that does not match the second logical relation in the sorted fault logic sequence to be processed is removed from the sorted fault logic sequence to be processed, and the removed second semantic word is placed after the sorted fault logic sequence to be processed.

[0083] Taking the first semantic segmentation ["distance from equipment room A033.2 km", "optical power suddenly drops by 15 dB", "temperature rises by 8 °C"] and the second semantic segmentation ["distance from equipment room B045.8 km", "optical power abruptly decreases by 10 dB", "local temperature rises by 6 °C", "fault cause is damage to the outer sheath of the optical cable caused by third-party mechanical excavation"] as an example, the logical order can be: the first word is the fault location, the second word is related to the first word in terms of location, and the third word is related to the second word in terms of parallel relationship. Then the logical sequence of the fault to be processed can be {"distance from equipment room A033.2 km", "optical power suddenly drops by 15 dB", "temperature rises by 8 °C"}. Since the second logical relationship is different from the first logical relationship... It also includes the entity logic relationship of the causal relationship between "the fault was caused by third-party mechanical excavation resulting in damage to the outer sheath of the optical cable" and "the optical power suddenly decreased by 10dB" and "the local temperature rise was 6℃". Therefore, "distance from B045.8km", "the optical power suddenly decreased by 10dB" and "the local temperature rise was 6℃" can be sorted according to the logical order first. Then, "the fault was caused by third-party mechanical excavation resulting in damage to the outer sheath of the optical cable" can be set after the sorted sequence. Finally, the logical sequence of the historical similar fault is {"distance from B045.8km", "the optical power suddenly decreased by 10dB", "the local temperature rise was 6℃", "the fault was caused by third-party mechanical excavation resulting in damage to the outer sheath of the optical cable"}.

[0084] It is understood that if the historical similar fault data contains multiple data points, each of the historical similar fault data points can be processed according to the above steps to obtain the corresponding historical similar fault logic sequence, which will not be elaborated further here.

[0085] In this embodiment, the fault data to be processed and the historical similar fault data are transformed into structured, comparable, and inferable fault logic sequences and historical similar fault logic sequences by using semantic word segmentation and logical relations. This makes the fault logic sequences to be processed and the historical similar fault logic sequences mutually aligned, so that the historical similar fault logic sequences can be used to enhance the features of the fault logic sequences to be processed.

[0086] S4: Use the historical similar fault logic sequence to enhance the features of the fault logic sequence to be processed, and obtain the fault enhancement sequence features;

[0087] In this embodiment, step S4 may include the following steps:

[0088] Feature identification is performed on the historical similar fault logic sequence and the fault logic sequence to be processed respectively to obtain the first logical feature of the historical similar fault logic sequence and the second logical feature of the fault logic sequence to be processed.

[0089] The first logical feature and the second logical feature are fused using a cross-attention mechanism to obtain the fault enhancement sequence feature.

[0090] In this embodiment, step S4 described above can be implemented using a pre-trained feature enhancement model.

[0091] In one implementation, the feature enhancement model may include a historical sequence branch, a sequence branch to be processed, and a feature fusion module. The historical sequence branch and the sequence branch to be processed are equipped with LSTM (Long Short-Term Memory) networks. The LSTM networks in the historical sequence branch and the sequence branch to be processed can share weights, ensuring that the processed first logical feature and second logical feature are in the same semantic space. The LSTM network captures the contextual dependencies between ordered events in the historical similar fault logical sequence and the sequence to be processed fault logical sequence, extracting logical features from the sequences to obtain the first logical feature of the historical similar fault logical sequence and the second logical feature of the sequence to be processed fault logical sequence. The feature fusion module includes a cross-attention mechanism, which fuses the first and second logical features to obtain the fault-enhanced sequence features.

[0092] It should be noted that before the historical similar fault logic sequences are input into the historical sequence branches, the second semantic segments of the preset entity types need to be removed. For example, the second semantic segments of the entity types related to fault causation need to be removed to prevent the LSTM network from misinterpreting the second semantic segments of the preset entity types during recognition, and to facilitate alignment with the fault logic sequences to be processed. Furthermore, multiple historical sequence branches can be set. If there are multiple historical similar fault logic sequences, the multiple historical similar fault logic sequences are input into multiple historical sequence branches for processing. The first logical features obtained from each historical sequence branch are integrated to obtain a first logical feature set. The first logical feature set and the second logical features are then fused using a cross-attention mechanism.

[0093] S5: Use a pre-trained fault detection model to identify the fault enhancement sequence features to obtain the fault type, obtain the fault information of the fault data to be processed according to the fault type, and generate a fault work order according to the fault information.

[0094] In this embodiment, as Figure 4 As shown, the fault information obtained from the fault data to be processed according to the fault type in step S5 may include the following steps:

[0095] S51: Extract the associated third fault knowledge entity from the preset fault knowledge graph according to the fault type and the fault data to be processed.

[0096] S52: Obtain the fault information based on the third fault knowledge entity and the fault data to be processed.

[0097] In this embodiment, by utilizing a pre-trained fault detection model to accurately identify the enhanced fault sequence features, a more granular third fault knowledge entity, centered on the fault type, can be retrieved from the fault knowledge graph based on the fault type identified by the fault detection model and the fault data to be processed. It is understood that the fault data to be processed often consists of textual descriptions of faults provided to customers, which may contain inaccuracies or missing parts. Therefore, the third fault knowledge entity, extracted from the fault knowledge graph and associated with the fault data to be processed, can supplement and improve the data. This third fault knowledge entity may also contain solutions to the fault, ultimately yielding fault information containing more knowledge features and solutions. This allows maintenance personnel to understand more about the fault situation, reducing the time spent on on-site troubleshooting and effectively improving fault handling efficiency.

[0098] In this embodiment, the fault detection model can be built based on a multilayer perceptron. The fault detection model utilizes the strong fitting ability of the multilayer perceptron to high-dimensional nonlinear features to identify the fault enhancement sequence features, effectively extracting discriminative semantic features that are highly correlated with the fault type, thereby accurately predicting different fault categories.

[0099] Understandably, the training of the fault detection model may include the following:

[0100] Complete fault data samples with labeled fault types from history are collected. The fault data samples are segmented into words based on semantics to obtain training semantic words. The training semantic words are then constructed into training logical sequences based on different training logical orders. The training logical sequences are used to extract features through a pre-trained LSTM network to obtain training logical sequence features. The training logical sequence features are used to train the fault detection model to be trained, and the loss is calculated using the labeled fault types. Finally, the trained fault detection model is obtained.

[0101] Understandably, although the fault work order obtained after step S5 contains relatively complete fault information, it is usually not possible to determine whether the fault is urgent based solely on the fault information. For example, the fault of fiber optic signal interruption is obviously more serious when it occurs in the fiber optic cable segment of an important facility than when it occurs in an idle fiber optic cable segment. Therefore, after obtaining the fault work order containing fault information, it is also necessary to determine the priority level of the fault work order so that maintenance personnel can arrange the processing based on the priority level of the work order.

[0102] Therefore, in this embodiment, after executing step S5 and obtaining a fault work order containing fault information, it is also possible to obtain the impact information of the fault corresponding to the fault information in the optical cable, and set the work order priority level of the fault work order according to the impact information.

[0103] In one implementation, obtaining the influence information may include:

[0104] Based on the fault information, determine the fault location in the optical cable topology network corresponding to the optical cable; obtain the number of optical paths affected by the fault and their corresponding optical path attributes based on the fault topology location; obtain the degree of damage of the fault based on the fault information; and obtain the impact information of the fault in the optical cable based on the number of optical paths affected by the fault, their corresponding optical path attributes, and the degree of damage of the fault.

[0105] In this embodiment, the fiber optic topology network is pre-constructed based on the distribution of optical cables. The network uses optical cable devices as nodes and connecting optical fibers between these devices as edges, enabling comprehensive monitoring of the entire optical cable network. By mapping the optical cable topology network to actual locations, the location of the fault contained in the fault information is transformed into a fault topology location within the network. This allows for the identification of the associated optical cable device or segment. Furthermore, based on the network, the optical path attributes of the fault location are obtained, determining the importance of the affected services. Simultaneously, the number of optical paths affected by the fault is determined, defining the scope of the impact. Combined with the degree of damage reflected in the fault information, the impact information of the fault can be effectively determined, and the priority level of the corresponding fault work order can be determined using this impact information.

[0106] In this embodiment, by querying the fault data to be processed in the historical fault database, historical similar fault data matching the fault data to be processed is extracted. The logical sequence of the fault to be processed and the logical sequence of the historical similar fault data are also extracted. The logical sequence contains the event details and logical relationships of the corresponding fault. The historical similar fault logical sequence is used to enhance the features of the logical sequence of the fault to be processed. The detailed event details and logical relationships of the fault in the historical similar fault logical sequence are used to supplement and enhance the logical sequence of the fault to be processed. This enables the fault detection model to effectively identify the features of the enhanced fault sequence, accurately obtain the fault information of the fault data to be processed, and generate a detailed fault work order based on the fault information. This allows maintenance personnel to respond quickly based on the fault information in the fault work order, improving the efficiency of fault problem handling.

[0107] like Figure 5 As shown in the illustration, this application also provides a system for generating optical cable full-area monitoring work orders. Optionally, the generation system may include:

[0108] Data acquisition module 11 is used to collect unprocessed fault data for full-area monitoring of optical cables;

[0109] In this embodiment, the data acquisition module 11 can be used to perform... Figure 1 For a detailed description of the data acquisition module 11 shown in step S1, please refer to the description of step S1.

[0110] The historical data extraction module 12 is used to obtain historical similar fault data that is similar to the fault data to be processed from a preset historical fault database;

[0111] In this embodiment, the historical data extraction module 12 can be used to perform... Figure 1 For a detailed description of the historical data extraction module 12 shown in step S2, please refer to the description of step S2.

[0112] The logical sequence extraction module 13 is used to perform semantic analysis on the fault data to be processed to obtain the logical sequence of the fault to be processed, and to perform semantic analysis on the historical similar fault data to obtain the logical sequence of the historical similar fault.

[0113] In this embodiment, the logical sequence extraction module 13 can be used to perform... Figure 1 For a detailed description of the logical sequence extraction module 13 shown in step S3, please refer to the description of step S3.

[0114] Sequence enhancement module 14 is used to enhance the features of the fault logic sequence to be processed using the historical similar fault logic sequence to obtain fault enhancement sequence features;

[0115] In this embodiment, the sequence enhancement module 14 can be used to perform... Figure 1 For a detailed description of the sequence enhancement module 14 shown in step S4, please refer to the description of step S4.

[0116] The work order generation module 15 is used to identify the fault type by using a pre-trained fault detection model to identify the fault enhancement sequence features, obtain the fault information of the fault data to be processed according to the fault type, and generate a fault work order according to the fault information.

[0117] In this embodiment, the work order generation module 15 can be used to execute... Figure 1 For a detailed description of the work order generation module 15, please refer to the description of step S5 shown in step S5.

[0118] This application provides an electronic device with the following structure: Figure 6 As shown.

[0119] The electronic device includes a memory 21, a processor 22, a communication module 23, and an input / output interface 24, etc. Optionally, the memory 21, the processor 22, the communication module 23, and the input / output interface 24 can be connected and communicate with each other through a bus 25.

[0120] The memory 21 is used to store one or more computer programs and transmit the code of the computer programs to the processor 22; when the one or more computer programs are executed by the processor 22, a method for generating a fiber optic cable full-area monitoring work order is implemented in this embodiment of the application.

[0121] Optionally, the electronic device can be connected to a network via communication module 23 to communicate with other devices, such as terminals or servers, to achieve data interaction. The electronic device can be various forms of digital computers, exemplarily such as desktop computers, servers, workbenches, mainframes, or other types of computers. The electronic device can also be various forms of mobile terminals, exemplarily such as smartphones, tablets, wearable devices (such as helmets, glasses, watches, etc.), and other similar mobile terminals.

[0122] Optionally, the electronic device can connect to required input / output devices, such as a keyboard or display device, via the input / output interface 24. The electronic device itself may have a display device, and other display devices can also be connected externally via the input / output interface 24. Optionally, a storage device, such as a hard disk, can also be connected via the input / output interface 24 to store data from the electronic device, read data from the storage device, or store data from the storage device in the memory 21. It is understood that the input / output interface 24 can be a wired interface or a wireless interface. Depending on the actual application scenario, the device connected to the input / output interface 24 can be a component of the electronic device or an external device connected to the electronic device when needed.

[0123] Optionally, the memory 21 may be a volatile memory and / or a non-volatile memory. The volatile memory may be a random access memory, etc., and the non-volatile memory may be a read-only memory, a programmable read-only memory, an erasable programmable read-only memory, an electrically erasable programmable read-only memory, or a flash memory, etc.

[0124] Optionally, the computer program stored in the processor 22 can be divided into one or more modules, which are stored in the memory 21 and executed by the processor 22 to perform the method provided in this embodiment. The one or more modules can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in the electronic device.

[0125] Optionally, the processor 22 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 22 include, but are not limited to, a central processing unit, a graphics processing unit, a digital signal processor, various special-purpose artificial intelligence computing chips, various processors running machine learning model algorithms, and can also be any suitable controller, microcontroller, processor, etc. The processor 22 executes the various methods and processes of this embodiment, exemplarily, such as a method for generating a fiber optic cable full-area monitoring work order according to an embodiment of this application.

[0126] Optionally, the bus 25 may include a path for transmitting information. Depending on its function, the bus 25 may be divided into an address bus, a data bus, a control bus, etc.

[0127] In an optional implementation, this application embodiment also provides a computer storage medium storing a computer program thereon. When executed by a computer, the computer program enables the computer to perform the methods described in the above-described method embodiments. Part or all of the computer program can be loaded and / or installed on the memory 21 of an electronic device. When the computer program is executed by the processor 22, one or more steps of a method for generating a fiber optic cable full-area monitoring work order according to an embodiment of this application can be performed.

[0128] Optionally, the computer-readable storage medium may be a random access memory, a read-only memory, a programmable read-only memory, an erasable programmable read-only memory, an electrically erasable programmable read-only memory, etc.

[0129] Obviously, the above embodiments of this application are merely examples for clearly illustrating the technical solution of this application, and are not intended to limit the specific implementation of this application. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the claims of this application should be included within the protection scope of the claims of this application.

Claims

1. A method for generating a work order for full-area monitoring of optical cables, characterized in that, The method includes: Collect data on unprocessed faults from the full-area monitoring of optical cables; Obtain historical similar fault data that are similar to the fault data to be processed from a preset historical fault database; The fault data to be processed and the historical similar fault data are respectively segmented into words based on semantics to obtain the first semantic word segmentation of the fault data to be processed and the second semantic word segmentation of the historical similar fault data. Obtain the first logical relationship between the first semantic word segments, and obtain the second logical relationship between the second semantic word segments; The fault logic sequence to be processed is obtained based on the first semantic word segmentation and the first logical relationship, and the historical similar fault logic sequence is obtained based on the second semantic word segmentation and the second logical relationship. The fault logic sequence to be processed is enhanced by using the historical similar fault logic sequence to obtain fault enhancement sequence features; The fault type is obtained by identifying the fault enhancement sequence features using a pre-trained fault detection model, the fault information of the fault data to be processed is obtained based on the fault type, and a fault work order is generated based on the fault information.

2. The method for generating a fiber optic cable full-area monitoring work order according to claim 1, characterized in that, The step of obtaining the first logical relationship between the first semantic segments and obtaining the second logical relationship between the second semantic segments includes: The first semantic word is queried in the preset fault knowledge graph to obtain the first fault knowledge entity corresponding to the first semantic word; The second semantic word is queried in the preset fault knowledge graph to obtain the second fault knowledge entity corresponding to the second semantic word; Extract the first fault relationship corresponding to the first fault knowledge entity from the fault knowledge graph as the first logical relationship. The second fault relationship corresponding to the second fault knowledge entity is extracted from the fault knowledge graph and used as the second logical relationship.

3. The method for generating a fiber optic cable full-area monitoring work order according to claim 1, characterized in that, The step of using the historical similar fault logic sequence to enhance the features of the fault logic sequence to be processed, resulting in fault-enhanced sequence features, includes: Feature identification is performed on the historical similar fault logic sequence and the fault logic sequence to be processed respectively to obtain the first logical feature of the historical similar fault logic sequence and the second logical feature of the fault logic sequence to be processed. The first logical feature and the second logical feature are fused using a cross-attention mechanism to obtain the fault enhancement sequence feature.

4. The method for generating a fiber optic cable full-area monitoring work order according to claim 1, characterized in that, The fault information obtained based on the fault type includes: Based on the fault type and the fault data to be processed, the associated third fault knowledge entity is extracted from the preset fault knowledge graph. The fault information is obtained based on the third fault knowledge entity and the fault data to be processed.

5. A method for generating a fiber optic cable full-area monitoring work order according to any one of claims 1-4, characterized in that, After the step of generating a fault work order based on the fault information, the method further includes: Obtain the impact information of the fault corresponding to the fault information in the optical cable, and set the priority level of the fault work order according to the impact information.

6. The method for generating a fiber optic cable full-area monitoring work order according to claim 5, characterized in that, The step of obtaining the impact information of the fault corresponding to the fault information in the optical cable includes: Based on the fault information, the location of the fault is determined to be the fault topology location in the optical cable topology network corresponding to the optical cable; The number of optical paths affected by the fault and their corresponding optical path attributes are obtained based on the fault topology location. The extent of damage caused by the fault is determined based on the fault information. The impact information of the fault on the optical cable is obtained based on the number of optical paths affected by the fault, the corresponding optical path attributes, and the degree of damage caused by the fault.

7. A system for generating work orders for comprehensive optical cable monitoring, characterized in that, The system includes: The data acquisition module is used to collect fault data to be processed for the full-area monitoring of optical cables; The historical data extraction module is used to obtain historical similar fault data that is similar to the fault data to be processed from a preset historical fault database; The logical sequence extraction module is used to perform semantic segmentation on the fault data to be processed and the historical similar fault data to obtain a first semantic segmentation of the fault data to be processed and a second semantic segmentation of the historical similar fault data; obtain a first logical relationship between the first semantic segments and a second logical relationship between the second semantic segments; obtain a logical sequence of the fault to be processed based on the first semantic segments and the first logical relationship, and obtain a logical sequence of the historical similar faults based on the second semantic segments and the second logical relationship. The sequence enhancement module is used to enhance the features of the fault logic sequence to be processed using the historical similar fault logic sequence to obtain fault enhancement sequence features. The work order generation module is used to identify the fault type by using a pre-trained fault detection model to identify the fault enhancement sequence features, obtain the fault information of the fault data to be processed according to the fault type, and generate a fault work order according to the fault information.

8. The system for generating optical cable full-area monitoring work orders according to claim 7, characterized in that, The step of obtaining the first logical relationship between the first semantic segments and obtaining the second logical relationship between the second semantic segments includes: The first semantic word is queried in the preset fault knowledge graph to obtain the first fault knowledge entity corresponding to the first semantic word; The second semantic word is queried in the preset fault knowledge graph to obtain the second fault knowledge entity corresponding to the second semantic word; Extract the first fault relationship corresponding to the first fault knowledge entity from the fault knowledge graph as the first logical relationship. The second fault relationship corresponding to the second fault knowledge entity is extracted from the fault knowledge graph and used as the second logical relationship.

9. An electronic device, characterized in that, include: Memory, used to store one or more computer programs; A processor, when the one or more computer programs are executed by the processor, implements a method for generating a fiber optic cable full-area monitoring work order as described in any one of claims 1-6.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute a method for generating a fiber optic cable full-area monitoring work order as described in any one of claims 1-6.

Images