A method for querying and diagnosing communication optical path performance data based on a maintenance intelligent agent
By using a maintenance-based intelligent agent method, optical path performance parameters can be automatically queried and diagnosed, solving the problems of low efficiency and large errors in optical path maintenance, and realizing efficient and accurate optical path performance data query and anomaly diagnosis.
Patent Information
- Application Number
- CN202611302310.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-08-26
- Publication Date
- 2026-11-17
AI Technical Summary
In the existing technology, during the optical path maintenance process, the efficiency of querying optical path performance parameters is low, the communication cost is high and errors are easy to occur. Human performance diagnosis requires a lot of manpower and wastes time, and the diagnosis results are prone to subjective errors.
The method based on maintenance intelligent agents is adopted. By acquiring the query conditions input by users, semantic analysis and key item information are extracted, fuzzy matching and localization of network element entities are performed, communication optical path performance parameters are obtained, key item performance parameters are screened and anomalies are automatically diagnosed, and a performance assessment report is generated.
It improves the efficiency of optical path performance parameter query, reduces manual intervention, lowers fault diagnosis errors, and improves the accuracy and efficiency of maintenance decisions.
Smart Images

Figure CN123122653A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the technical field of communication optical path maintenance, and in particular to a method for querying communication optical path performance data and diagnosing anomalies based on a maintenance intelligent agent. Background Technology
[0002] Currently, during optical path maintenance, on-site maintenance personnel cannot obtain the current optical path performance and need to repeatedly call the communication dispatch center for inquiries. The staff at the communication dispatch center receive the calls, operate the network management system as required to query the optical path performance, and then verbally relay the query results to the on-site maintenance personnel over the phone. The on-site maintenance personnel manually verify the information before conducting manual performance diagnosis and maintenance. In the traditional maintenance method, optical path performance parameters are queried manually and subjective performance judgments are made for optical path maintenance. This process requires a lot of manpower and is time-consuming. Furthermore, optical path performance parameters include, but are not limited to, the attenuation coefficient, dispersion characteristics, applicable wavelength range, bending performance, and other performance parameters of various optical cables. The manual search method is inefficient and prone to errors.
[0003] Regarding the aforementioned technologies, the inventors believe that there are drawbacks such as low communication efficiency and easy error in manually querying optical path performance parameters, the need for a large amount of manpower for manual performance diagnosis which is time-consuming, and the easy for subjective errors in the diagnosis results. Summary of the Invention
[0004] To address the problems of low efficiency, high communication costs, high anomaly diagnosis errors, and lack of unified anomaly diagnosis standards in existing technologies for querying communication optical path performance data, this application provides a communication optical path performance data query and anomaly diagnosis method based on a maintenance intelligent agent. This method can replace manual querying of optical path performance parameters and perform automatic optical path fault diagnosis, providing data reference for on-site maintenance personnel to make maintenance decisions, thereby improving parameter query efficiency and reducing fault diagnosis errors.
[0005] Firstly, the above-mentioned inventive objective of this application is achieved through the following technical solution: A method for querying and diagnosing communication optical path performance data based on a maintenance intelligent agent, the method comprising: The system acquires query condition information input by the user to the maintenance intelligent agent and performs semantic analysis and key item information extraction. Based on the key item information, it performs user intent recognition and network element entity annotation processing to obtain a set of key query information. Based on the key query information set, network element entity fuzzy matching is performed in all communication optical paths. Based on the fuzzy matching results, the target network element entity is located and the corresponding communication optical path performance parameters are obtained across regions and fed back to the maintenance intelligent agent. The maintenance intelligent agent performs key item performance parameter screening and automatic anomaly diagnosis processing on the communication optical path performance parameters based on the key items in the key query information set, and obtains the communication optical path anomaly diagnosis result. The key performance parameters and the communication optical path anomaly diagnosis results are mapped to preset report templates to generate a communication optical path performance assessment report, and the communication optical path performance assessment report is fed back to the user terminal for maintenance decision processing.
[0006] In a preferred embodiment, this application can be further configured as follows: performing fuzzy matching of network element entities across all communication optical paths based on the key query information set, locating the target network element entity based on the fuzzy matching result, and obtaining the corresponding communication optical path performance parameters across regions and feeding them back to the maintenance intelligent agent. Specifically, this includes: Obtain the network element entity names from the key query information set and perform standardized preprocessing. Then, perform similar string sequence matching and sorting on the preprocessed network element entity information with all network element entities in the communication optical path to generate a candidate set of network element entities. The candidate set of network element entities is subjected to multi-dimensional similarity scoring processing. The target network element entity is located by combining the preset multi-level network element screening conditions. A cross-regional performance query request carrying the target network element entity identifier is sent to the cross-regional collaborative controller. The cross-regional collaborative controller identifies the target network element entity's region and forwards the request based on a preset resource location table, and receives the communication optical path performance parameters fed back by the corresponding query region. The cross-regional collaborative controller integrates the communication optical path performance parameters of all target network element entities across regions and feeds back the integrated communication optical path performance parameters to the maintenance intelligent agent.
[0007] In a preferred embodiment, this application can be further configured as follows: the multi-dimensional similarity scoring process of performing multi-dimensional similarity scoring on the candidate set of network element entities, locating the target network element entity in combination with preset multi-level network element screening conditions, and sending a cross-regional performance query request carrying the identifier of the target network element entity to the cross-regional collaborative controller specifically includes: The calculation expression for the multidimensional similarity score is as follows: in, Indicates candidate network element entities With communication optical path network element entity The overall similarity score between them Indicates semantic similarity. Indicating word similarity, Indicates character structural similarity. Indicates the similarity of structured metadata. , , , These represent the weighting coefficients, .
[0008] In a preferred embodiment, this application can be further configured as follows: the step of performing fuzzy matching processing of network element entities in all communication optical paths based on the key query information set, locating the target network element entity based on the fuzzy matching result, and obtaining the corresponding communication optical path performance parameters across regions and feeding them back to the maintenance intelligent agent, further includes: When there are candidate network elements with the same similarity score in the candidate network element entity set, the candidate network element entity is fed back to the user terminal and the user confirmation result of the candidate network element entity is obtained to obtain the target network element entity. According to the multi-level network element screening conditions, when the multi-dimensional similarity score is within the manual review range, the corresponding candidate network element entity is fed back to the user terminal for manual review and processing, and the target network element entity confirmed by the user is obtained.
[0009] In a preferred embodiment, this application can be further configured as follows: obtaining query condition information input by the user to the maintenance agent and performing semantic analysis and key item information extraction, and performing user intent recognition and network element entity annotation processing based on the key item information to obtain a set of key query information, specifically includes: By combining the preset power standard knowledge base, semantic analysis is performed on the query condition information, and functional keyword identification and word segmentation are performed according to the word and sentence sequence to obtain the key item information of the optical path to be queried; Based on the key information, user intent is identified, and all network element entities that match the user intent are standardized and transformed, and the user intent direction is located, to obtain a set of key query information.
[0010] In a preferred embodiment, this application can be further configured as follows: the maintenance agent performs key item performance parameter screening and automatic anomaly diagnosis processing on the communication optical path performance parameters based on key items in the key query information set, to obtain communication optical path anomaly diagnosis results, specifically including: Based on the board number and port number in the key query information set, the communication optical path performance parameters are further filtered to obtain key performance parameters corresponding to the board number and port number; Obtain historical alarm information of the target network element entity, and perform abnormal threshold determination and abnormal determination logic analysis on the board number and the port number based on the historical alarm information to obtain dual abnormal diagnosis indicators; The key performance parameters are compared with the dual anomaly diagnostic indicators. Based on the comparison results, it is determined whether the current optical path state of the target network element entity is abnormal, and the optical path anomaly state determination result is obtained. Historical proximity performance parameters of the target network element entity are obtained for proximity health trend analysis and proximity health status assessment. The results of the optical path anomaly status determination are then corrected to obtain the communication optical path anomaly diagnosis results.
[0011] In a preferred embodiment, this application can be further configured as follows: mapping the key performance parameters and the communication optical path anomaly diagnosis results to preset report templates to generate a communication optical path performance assessment report, and feeding the communication optical path performance assessment report back to the user terminal for maintenance decision processing, specifically including: Based on the user intent, report templates are filtered, and the key performance parameters and the communication optical path anomaly diagnosis results are mapped to the filtered report templates respectively to generate a communication optical path performance assessment report. The communication optical path performance assessment report is fed back to the user terminal to obtain the human performance analysis results of the communication optical path and optimize and update the abnormal diagnosis results of the communication optical path to obtain the maintenance decision of the target network element entity.
[0012] Secondly, the above-mentioned inventive objective of this application is achieved through the following technical solutions: A communication optical path performance data query and anomaly diagnosis system based on a maintenance intelligent agent, the system comprising: The information acquisition and preprocessing module is used to acquire the query condition information input by the user to the maintenance intelligent agent and perform semantic analysis and key item information extraction. Based on the key item information, user intent recognition and network element entity annotation processing are performed to obtain a set of key query information. The network element location and performance parameter query module is used to perform fuzzy matching processing of network element entities in all communication optical paths based on the key query information set, locate the target network element entity based on the fuzzy matching result, and obtain the corresponding communication optical path performance parameters across regions and feed them back to the maintenance intelligent agent. The key item screening and anomaly diagnosis module is used to control the maintenance intelligent agent to perform key item performance parameter screening and automatic anomaly diagnosis processing on the communication optical path performance parameters based on the key items in the key query information set, and to obtain the communication optical path anomaly diagnosis result. The assessment report and maintenance decision module is used to map the key performance parameters and the communication optical path anomaly diagnosis results to preset report templates to generate a communication optical path performance assessment report, and to feed the communication optical path performance assessment report back to the user terminal for maintenance decision processing.
[0013] Thirdly, the above-mentioned objectives of this application are achieved through the following technical solutions: A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-described method for querying and diagnosing communication optical path performance data based on a maintenance intelligent agent.
[0014] Fourthly, the above-mentioned objectives of this application are achieved through the following technical solutions: A computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-described method for querying and diagnosing communication optical path performance data based on a maintenance intelligent agent.
[0015] In summary, this application includes at least one of the following beneficial technical effects: 1. This application replaces the manual work of querying optical path performance parameters by setting up an intelligent agent. It reduces the workload of querying optical path performance parameters by replacing the traditional three-times telephone inquiry for each optical path with intelligent agent query. The intelligent agent can also query more comprehensive optical cable performance data related to the optical path to be repaired from the managed resource system. 2. This application uses multi-dimensional scoring and multi-level network element screening conditions to screen the closest network element items, thereby improving the comprehensiveness and accuracy of network element item screening. When multiple network element candidates appear, a manual confirmation mechanism is used for manual review, which not only ensures the accuracy of the query results but also improves the user's interactive experience, and can flexibly respond to the user's query needs in various scenarios. 3. By comparing the key performance indicators obtained from the screening with the anomaly judgment thresholds and judgment logic in the alarm information, the intelligent agent performs network element anomaly judgment, providing data reference for users to make network element operation and maintenance decisions, further reducing the analysis time for users to judge network element faults, and improving the efficiency of fault analysis and maintenance decision-making. Attached Figure Description
[0016] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the accompanying drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. The elements or parts in the drawings are not necessarily drawn to scale.
[0017] Figure 1 This is an overall schematic diagram of the communication optical path performance data query and anomaly diagnosis method in this embodiment.
[0018] Figure 2 This is a structural block diagram of the communication optical path performance data query and anomaly diagnosis system in this embodiment.
[0019] Figure 3 This is a schematic diagram of the internal structure of a computer device used to implement methods for querying and diagnosing the performance data of communication optical paths. Detailed Implementation
[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0021] It should be understood that, when used in this specification, the terms “comprising” and “including” indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.
[0022] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification, unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “the” are intended to include the plural forms.
[0023] It should also be further understood that the term "and / or" as used in this specification refers to any combination of one or more of the associated listed items, as well as all possible combinations, and includes such combinations.
[0024] In one embodiment, such as Figure 1 As shown, this application discloses a method for querying and diagnosing communication optical path performance data based on a maintenance intelligent agent, which specifically includes the following steps: S1: Obtain the query conditions input by the user to the maintenance agent and perform semantic analysis and key item information extraction. Based on the key item information, perform user intent recognition and network element entity annotation processing to obtain a set of key query information.
[0025] Specifically, step S1 includes: S11: Combining the preset power standard knowledge base, perform semantic analysis on the query condition information and perform functional keyword identification and word segmentation according to the word and sentence sequence to obtain the key item information of the optical path to be queried.
[0026] Specifically, by combining the power specification knowledge base preset by the maintenance intelligent agent and decomposing the query conditions entered by the user according to the text word sequence, multiple power-specific terms conforming to the power specification knowledge base are obtained, such as equipment model: ZTE, component: optical module, performance index: received optical power, etc. In this embodiment, the network element entity name, board number and port number are used as functional key items, and the specific information of the network element entity name, board number and port number are used as key item information, thereby obtaining the key item information of the optical path to be queried.
[0027] S12: Based on key item information, identify user intent, and perform standardized transformation and user intent direction positioning on all network element entities that match the user intent to obtain a set of key query information.
[0028] Specifically, based on the pre-built intent classification system for the optical cable field by the maintenance intelligent agent, it includes, but is not limited to, intents for performance parameter query, intents for fault phenomenon delineation, intents for operation process guidance, and intents for comparative analysis. For example, fault phenomenon delineation aims to diagnose the current anomaly, such as the abnormal reason for a sudden spike in the bit error rate of this link or a sudden drop in received optical power to -30dBm. The intent classification system performs preliminary intent classification on key information items, and deep semantic analysis is conducted using an LLM large language model to confirm user intent. All network element entities that match the user intent are standardized and converted, such as changing the network element model "652" to "G.652". The direction of the user intent is located, such as clarifying whether it is "receiving optical light" or "emitting optical light", and whether it is "near end" or "far end", resulting in a set of key query information, including but not limited to network element name, board number, and port number.
[0029] S2: Based on the key query information set, perform fuzzy matching of network element entities in all communication optical paths, locate the target network element entity based on the fuzzy matching results, and obtain the corresponding communication optical path performance parameters across regions and feed them back to the maintenance intelligent agent.
[0030] Specifically, step S2 combines the multidimensional similarity scores and multi-level network element screening conditions of all candidate network element entities in the candidate network element entity set to select target network element entities from the candidate network element entity set and perform network element entity localization. It then obtains all communication optical path performance parameters from the target network element entity's managed system and feeds them back to the maintenance intelligent agent. Step S2 specifically includes: S21: Obtain the network element entity names in the key query information set and perform standardized preprocessing. Then, perform similar string sequence matching and sorting processing on the preprocessed network element entity information and all network element entities in the communication optical path to generate a candidate set of network element entities.
[0031] Specifically, the network element entity names obtained from the key query information set are standardized and preprocessed, including but not limited to converting letters to lowercase, restoring abbreviations to full names, converting full-width / half-width symbols, and converting Chinese and English characters. Common prefixes / suffixes in network element entity names, such as NE- and -SYS, are uniformly removed to reduce the interference of irrelevant characters on the matching of network element entity names. The preprocessed network element entity information is then compared with the network element entity information stored in all managed systems using LCS similarity calculation. After normalizing the string length of the preprocessed network element entity information and the network element entity information stored in all managed systems, the longer the length of the subsequence that appears in both strings and has the same order, the more similar the preprocessed network element entity information is to the network element entity information in the managed system. The network element entity candidate set is obtained by sorting them from high to low similarity.
[0032] S22: Perform multi-dimensional similarity scoring on the candidate set of network element entities, locate the target network element entity by combining the preset multi-level network element screening conditions, and send a cross-regional performance query request carrying the target network element entity identifier to the cross-regional collaborative controller.
[0033] Specifically, the calculation expression for the multidimensional similarity score is as follows: in, Indicates candidate network element entities With communication optical path network element entity The overall similarity score between them Indicates semantic similarity. Indicating word similarity, Indicates character structural similarity. Indicates the similarity of structured metadata. , , , These represent the weighting coefficients, .
[0034] The expression for calculating lexical similarity in this embodiment is as follows: in, , Indicates the regulating factor. , This is a constant, and in this embodiment, it is taken as 0.75. This represents the average character length of all network element entities in the communication optical path. Represents the communication optical path network element entity Name length, Indicates the first Terms for candidate network element entities Network element entities in communication optical path management systems Frequency of occurrence in Indicates the number of candidate network element entities. Indicates the first Candidate network element entities Inverse document frequency.
[0035] The expression for calculating character structure similarity in this embodiment is as follows: in, Indicates the candidate network element entity Converted into communication optical network element entities Minimum number of character transformations required These represent the character lengths of the candidate network element entity and the communication optical path network element entity, respectively.
[0036] The expression for calculating the similarity of structured metadata in this embodiment is as follows: in, Indicates the judgment of the first Candidate network element entities With the Each communication optical path network element entity The value is 1 if the fields are the same, and 0 if they are different. Indicates the importance of the corresponding network element entity. , They represent the first Candidate network element entities metadata fields and the first Each communication optical path network element entity Metadata fields.
[0037] The multi-level network element screening criteria in this embodiment are as follows: when a candidate network element entity is completely identical to a network element entity in the communication optical path, the similarity score is 100; when the multi-dimensional similarity score is higher than 95, the candidate network element entity is directly determined to be the target network element entity; when the multi-dimensional similarity score is between 80 and 95, manual review is required to confirm the target network element entity; when the multi-dimensional similarity score is lower than 80, the corresponding candidate network element entity is determined not to be the target network element entity. It should be noted that the similarity score range of the multi-level network element screening criteria in this embodiment can be set according to actual conditions and is not limited to one method in this embodiment.
[0038] Based on the target network element entity location, a cross-regional performance query request carrying the target network element entity identifier is generated and sent to the cross-regional collaborative controller.
[0039] S23: The cross-regional collaborative controller identifies the region to which the target network element belongs and forwards the request for cross-regional performance query based on the preset resource location table, and receives the communication optical path performance parameters fed back by the corresponding query region.
[0040] Specifically, in this embodiment, a cross-regional collaborative controller is used to perform cross-regional data calls on network element entities in different regions. The cross-regional collaborative controller has a preset real-time updated resource location table to record the management or mapping relationship between each network element entity and the regional controller. Through the resource location table, the region where the target network element entity is located can be quickly determined, and the corresponding parameter query and call request is routed to the corresponding regional controller for cross-regional performance query. The cross-regional collaborative controller identifies the region to which the target network element entity belongs in the cross-regional performance query request and forwards the request to the corresponding regional controller for querying communication optical path performance parameters, including parameters such as bandwidth, latency, and optical power.
[0041] S24: The cross-regional collaborative controller integrates the communication optical path performance parameters of all target network element entities across regions and feeds back the integrated communication optical path performance parameters to the maintenance intelligent agent.
[0042] Specifically, the cross-regional collaborative controller centrally integrates the communication optical path parameters of all target network elements and feeds back the integrated communication optical path performance parameters to the maintenance intelligent agent based on a preset standard interface.
[0043] This embodiment also includes: S221: When there are candidate network elements with the same similarity score in the candidate network element entity set, the candidate network element entity is fed back to the user terminal and the user confirmation result of the candidate network element entity is obtained to obtain the target network element entity.
[0044] Specifically, when there are multiple candidate network element entities with the same similarity score in the candidate network element entity set, the candidate network element entities are fed back to the user terminal for manual review through the maintenance intelligent agent, and the user confirmation result of the candidate network element entities is obtained to obtain the target network element entity confirmed by the user.
[0045] S222: According to the multi-level network element screening conditions, when the multi-dimensional similarity score is within the manual review range, the corresponding candidate network element entity is fed back to the user terminal for manual review and processing to obtain the target network element entity confirmed by the user.
[0046] Specifically, according to the multi-level network element screening conditions, that is, when the multi-dimensional similarity score is in the manual review range, i.e., in the range of 80-95 points, the corresponding candidate network element entities are fed back to the user end for manual review through the maintenance intelligent agent, and the final candidate network element entities selected by the human are obtained, thus obtaining the target network element entity.
[0047] By manually reviewing the target network element entities, the accuracy of the selection of target network element entities is further ensured, and the participation of on-site maintenance personnel is also improved.
[0048] S3: The maintenance agent performs key item performance parameter screening and automatic anomaly diagnosis processing on the communication optical path performance parameters based on the key items in the key query information set, and obtains the communication optical path anomaly diagnosis results.
[0049] Specifically, step S3 includes: S31: Based on the board number and port number in the key query information set, the performance parameters of the communication optical path are further filtered to obtain the key performance parameters corresponding to the board number and port number.
[0050] Specifically, based on the board number and port number in the key query information set, the target board information and port information are filtered in the communication optical path performance parameters to obtain the key performance parameters corresponding to the board number and port number, including but not limited to light emission power, light reception power, link utilization and unavailable seconds.
[0051] S32: Obtain historical alarm information of the target network element entity, and perform abnormal threshold judgment and abnormal judgment logic analysis on the board number and port number based on the historical alarm information to obtain dual abnormal diagnosis indicators.
[0052] Specifically, historical alarm information of the target network element entity is obtained, and the performance parameter thresholds and corresponding anomaly judgment logic of the target network element entity in the historical alarm information are analyzed, including but not limited to the parameter anomaly thresholds and anomaly judgment logic of each board and port, to obtain dual anomaly diagnostic indicators.
[0053] S33: Compare the key performance parameters with the dual anomaly diagnostic indicators, and determine whether the current optical path status of the target network element entity is abnormal based on the comparison results, so as to obtain the optical path anomaly status determination result.
[0054] Specifically, the key performance parameters are compared with the dual anomaly diagnostic indicators. If the relevant parameters of the corresponding board number or port number in the key performance parameters meet one of the dual anomaly diagnostic indicators, the current optical path status of the target network element entity is determined to be abnormal. If it does not meet the requirements, it indicates that the current optical path status is normal, thus obtaining the optical path anomaly status determination result.
[0055] S34: Obtain the historical proximity performance parameters of the target network element entity, perform proximity health trend analysis and proximity health status assessment, correct the optical path abnormality judgment results, and obtain the communication optical path abnormality diagnosis results.
[0056] Specifically, the system acquires the historical and proximity performance parameters of the target network element entity, analyzes its proximity health trend (e.g., a declining or stabilizing health status), and performs proximity health status analysis. If the performance parameters of the target network element entity conform to the steady-state health trend, it is determined to be in a healthy state. If the performance parameters do not conform to the steady-state health trend (e.g., sudden changes, discrete values, or reaching extreme values), it is determined to be in an unhealthy state. The system analyzes whether the optical path anomaly status determination result conforms to the proximity health trend and proximity health status. If both conform, the communication optical path anomaly diagnosis result is directly output. If one does not conform, the optical path anomaly status determination result is corrected, and the corrected communication optical path anomaly diagnosis result is output.
[0057] S4: Map the key performance parameters and communication optical path anomaly diagnosis results to the preset report templates to generate a communication optical path performance assessment report, and feed the communication optical path performance assessment report back to the user end for maintenance decision processing.
[0058] Specifically, step S4 includes: S41: Based on user intent, the report template is filtered, and the key performance parameters and communication optical path anomaly diagnosis results are mapped to the filtered report templates respectively to generate a communication optical path performance assessment report.
[0059] Specifically, based on user intent, the system filters the preset report templates in the maintenance agent and maps the key performance parameters and communication optical path anomaly diagnosis results to the corresponding positions in the report template according to the format of the filtered report template, thereby generating a standardized communication optical path performance assessment report.
[0060] S42: Feed back the communication optical path performance assessment report to the user end, obtain the human performance analysis results of the communication optical path, optimize and update the communication optical path anomaly diagnosis results, and obtain the maintenance decision of the target network element entity.
[0061] Specifically, the communication optical path performance assessment report is fed back to the user terminal for visualization and display. The system also obtains the user's human performance analysis results based on the communication optical path performance assessment report. When the two assessment results are consistent, the communication optical path performance assessment report is confirmed. When the two assessment results are different, the communication optical path anomaly diagnosis results are optimized and updated based on the difference items. The system continues until the assessment results are consistent, at which point the maintenance decision for the target network element entity is output.
[0062] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.
[0063] In one embodiment, a communication optical path performance data query and anomaly diagnosis system based on a maintenance intelligent agent is provided. This system corresponds one-to-one with the communication optical path performance data query and anomaly diagnosis method based on a maintenance intelligent agent described in the above embodiments. For example... Figure 2 As shown, the communication optical path performance data query and anomaly diagnosis system based on maintenance intelligent agents includes an information acquisition and preprocessing module, a network element location and performance parameter query module, a key item screening and anomaly diagnosis module, and an analysis report and maintenance decision module. Detailed descriptions of each functional module are as follows: The information acquisition and preprocessing module is used to acquire the query conditions input by the user to the maintenance intelligent agent and perform semantic analysis and key item information extraction. Based on the key item information, user intent recognition and network element entity annotation processing are performed to obtain a set of key query information.
[0064] The network element location and performance parameter query module is used to perform fuzzy matching of network element entities in all communication optical paths based on the key query information set, locate the target network element entity based on the fuzzy matching result, and obtain the corresponding communication optical path performance parameters across regions and feed them back to the maintenance intelligent agent.
[0065] The key item screening and anomaly diagnosis module is used to control the maintenance agent to screen and automatically diagnose anomalies in the communication optical path performance parameters based on key items in the key query information set, and obtain communication optical path anomaly diagnosis results.
[0066] The assessment report and maintenance decision module is used to map key performance parameters and communication optical path anomaly diagnosis results to preset report templates to generate a communication optical path performance assessment report, and then feed the communication optical path performance assessment report back to the user terminal for maintenance decision processing.
[0067] Specific limitations regarding the communication optical path performance data query and anomaly diagnosis system based on maintenance intelligent agents can be found in the limitations of the communication optical path performance data query and anomaly diagnosis method based on maintenance intelligent agents mentioned above, and will not be repeated here. Each module in the aforementioned communication optical path performance data query and anomaly diagnosis system based on maintenance intelligent agents can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.
[0068] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 3As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides the environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores data related to communication optical path performance data querying, anomaly diagnosis, and maintenance. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements a method for communication optical path performance data querying and anomaly diagnosis based on a maintenance intelligent agent.
[0069] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements a method for querying and diagnosing communication optical path performance data based on a maintenance intelligent agent.
[0070] Those skilled in the art will recognize that the units of the various examples described in connection with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application of the technical solution and the constraints involved. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of the invention.
[0071] In the embodiments provided by the present invention, it should be understood that the division of units is only a logical functional division. In actual implementation, there may be other division methods, such as multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored.
[0072] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0073] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.
[0074] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the present invention specification.
Claims
1. A method for querying and diagnosing communication optical path performance data based on a maintenance intelligent agent, characterized in that, The method includes: The system acquires query condition information input by the user to the maintenance intelligent agent and performs semantic analysis and key item information extraction. Based on the key item information, it performs user intent recognition and network element entity annotation processing to obtain a set of key query information. Based on the key query information set, network element entity fuzzy matching is performed in all communication optical paths. Based on the fuzzy matching results, the target network element entity is located and the corresponding communication optical path performance parameters are obtained across regions and fed back to the maintenance intelligent agent. The maintenance intelligent agent performs key item performance parameter screening and automatic anomaly diagnosis processing on the communication optical path performance parameters based on the key items in the key query information set, and obtains the communication optical path anomaly diagnosis result. The key performance parameters and the communication optical path anomaly diagnosis results are mapped to preset report templates to generate a communication optical path performance assessment report, and the communication optical path performance assessment report is fed back to the user terminal for maintenance decision processing.
2. The method for querying and diagnosing communication optical path performance data based on a maintenance intelligent agent according to claim 1, characterized in that, The process of performing fuzzy matching of network element entities across all communication optical paths based on the key query information set, locating the target network element entity based on the fuzzy matching results, and obtaining the corresponding communication optical path performance parameters across regions and feeding them back to the maintenance intelligent agent specifically includes: Obtain the network element entity names from the key query information set and perform standardized preprocessing. Then, perform similar string sequence matching and sorting on the preprocessed network element entity information with all network element entities in the communication optical path to generate a candidate set of network element entities. The candidate set of network element entities is subjected to multi-dimensional similarity scoring processing. The target network element entity is located by combining the preset multi-level network element screening conditions. A cross-regional performance query request carrying the target network element entity identifier is sent to the cross-regional collaborative controller. The cross-regional collaborative controller identifies the target network element entity's region and forwards the request based on a preset resource location table, and receives the communication optical path performance parameters fed back by the corresponding query region. The cross-regional collaborative controller integrates the communication optical path performance parameters of all target network element entities across regions and feeds back the integrated communication optical path performance parameters to the maintenance intelligent agent.
3. The method for querying and diagnosing communication optical path performance data based on a maintenance intelligent agent according to claim 2, characterized in that, The process of performing multi-dimensional similarity scoring on the candidate set of network element entities, locating the target network element entity by combining preset multi-level network element screening conditions, and sending a cross-regional performance query request carrying the target network element entity identifier to the cross-regional collaborative controller specifically includes: The calculation expression for the multidimensional similarity score is as follows: in, Indicates candidate network element entities With communication optical path network element entity The overall similarity score between them Indicates semantic similarity. Indicating word similarity, Indicates character structural similarity. Indicates the similarity of structured metadata. , , , These represent the weighting coefficients, .
4. The method for querying and diagnosing communication optical path performance data based on a maintenance intelligent agent according to claim 2, characterized in that, The process of performing fuzzy matching of network element entities across all communication optical paths based on the key query information set, locating the target network element entity based on the fuzzy matching result, and obtaining the corresponding communication optical path performance parameters across regions and feeding them back to the maintenance intelligent agent also includes: When there are candidate network elements with the same similarity score in the candidate network element entity set, the candidate network element entity is fed back to the user terminal and the user confirmation result of the candidate network element entity is obtained to obtain the target network element entity. According to the multi-level network element screening conditions, when the multi-dimensional similarity score is within the manual review range, the corresponding candidate network element entity is fed back to the user terminal for manual review and processing, and the target network element entity confirmed by the user is obtained.
5. The method for querying and diagnosing communication optical path performance data based on a maintenance intelligent agent according to claim 1, characterized in that, The process of acquiring query condition information input by the user to the maintenance intelligent agent, performing semantic analysis and extracting key item information, and then performing user intent recognition and network element entity annotation based on the key item information to obtain a set of key query information specifically includes: By combining the preset power standard knowledge base, semantic analysis is performed on the query condition information, and functional keyword identification and word segmentation are performed according to the word and sentence sequence to obtain the key item information of the optical path to be queried; Based on the key information, user intent is identified, and all network element entities that match the user intent are standardized and transformed, and the user intent direction is located, to obtain a set of key query information.
6. The method for querying and diagnosing communication optical path performance data based on a maintenance intelligent agent according to claim 1, characterized in that, The maintenance intelligent agent performs key item performance parameter screening and automatic anomaly diagnosis processing on the communication optical path performance parameters based on key items in the key query information set, and obtains communication optical path anomaly diagnosis results, specifically including: Based on the board number and port number in the key query information set, the communication optical path performance parameters are further filtered to obtain key performance parameters corresponding to the board number and port number; Obtain historical alarm information of the target network element entity, and perform abnormal threshold determination and abnormal determination logic analysis on the board number and the port number based on the historical alarm information to obtain dual abnormal diagnosis indicators; The key performance parameters are compared with the dual anomaly diagnostic indicators. Based on the comparison results, it is determined whether the current optical path state of the target network element entity is abnormal, and the optical path anomaly state determination result is obtained. Historical proximity performance parameters of the target network element entity are obtained for proximity health trend analysis and proximity health status assessment. The results of the optical path anomaly status determination are then corrected to obtain the communication optical path anomaly diagnosis results.
7. The method for querying and diagnosing communication optical path performance data based on a maintenance intelligent agent according to claim 1, characterized in that, The process of mapping the key performance parameters and the communication optical path anomaly diagnosis results to preset report templates to generate a communication optical path performance assessment report, and then feeding the communication optical path performance assessment report back to the user terminal for maintenance decision-making, specifically includes: Based on the user intent, report templates are filtered, and the key performance parameters and the communication optical path anomaly diagnosis results are mapped to the filtered report templates respectively to generate a communication optical path performance assessment report. The communication optical path performance assessment report is fed back to the user terminal to obtain the human performance analysis results of the communication optical path and optimize and update the abnormal diagnosis results of the communication optical path to obtain the maintenance decision of the target network element entity.
8. A communication optical path performance data query and anomaly diagnosis system based on a maintenance intelligent agent, characterized in that, The system includes: The information acquisition and preprocessing module is used to acquire the query condition information input by the user to the maintenance intelligent agent and perform semantic analysis and key item information extraction. Based on the key item information, user intent recognition and network element entity annotation processing are performed to obtain a set of key query information. The network element location and performance parameter query module is used to perform fuzzy matching processing of network element entities in all communication optical paths based on the key query information set, locate the target network element entity based on the fuzzy matching result, and obtain the corresponding communication optical path performance parameters across regions and feed them back to the maintenance intelligent agent. The key item screening and anomaly diagnosis module is used to control the maintenance intelligent agent to perform key item performance parameter screening and automatic anomaly diagnosis processing on the communication optical path performance parameters based on the key items in the key query information set, and to obtain the communication optical path anomaly diagnosis result. The assessment report and maintenance decision module is used to map the key performance parameters and the communication optical path anomaly diagnosis results to preset report templates to generate a communication optical path performance assessment report, and to feed the communication optical path performance assessment report back to the user terminal for maintenance decision processing.
9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the communication optical path performance data query and anomaly diagnosis method based on maintenance intelligent agent as described in any one of claims 1 to 7.
10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the communication optical path performance data query and anomaly diagnosis method based on maintenance intelligent agent as described in any one of claims 1 to 7.
