Method, device, equipment, storage medium and product for determining repair information

Abstract

The application discloses a method and device for determining repair information, equipment, a storage medium and a product. The method comprises: obtaining a network availability rate of a service in a preset time period; obtaining service quality index data of the service in the preset time period when the network availability rate is less than a preset value; identifying a fault link section according to the service quality index data; detecting output optical power of an optical module in the fault link section and optical cable loss of an optical cable in the fault link section to obtain a target detection result; and determining target repair information corresponding to the target detection result as repair information of the fault link section according to relationship information of the preset detection result and the preset repair information. Through hierarchical positioning of network element level and port level, the network element level is quickly delimited, then the search area is narrowed, the fault position is accurately found through the port level accurate positioning, and the corresponding repair information is determined, so that the fault can be repaired in time.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a method, apparatus, device, storage medium and product for determining repair information. Background Technology

[0002] With the rapid development of communication technology and the rapid expansion of the number of user terminal devices connected, the scale and complexity of network services are increasing daily. Users are also becoming more sensitive to service perception and have higher demands for service quality. Therefore, in order to improve user experience, accurate and dynamic analysis of service status and timely fault repair are crucial.

[0003] Existing technologies typically use network availability time periods to calculate network availability, which can only determine whether the network used by the service is available. The range of faults identified is relatively wide, requiring users to spend a lot of time to troubleshoot the location of the fault and then repair it, making it difficult to repair the fault in a timely manner. Summary of the Invention

[0004] This application provides a method, apparatus, device, storage medium, and product for determining repair information, which can promptly repair faults.

[0005] In a first aspect, embodiments of this application provide a method for determining repair information, including:

[0006] Obtain the network availability rate of the service within a preset time period;

[0007] When the network availability is less than a preset value, obtain the service quality index data of the service within a preset time period. The service quality index data includes at least one of optical power, bit error rate and latency.

[0008] Identify faulty link segments based on business quality indicator data;

[0009] The output optical power of the optical module in the faulty link segment and the optical cable attenuation in the faulty link segment are detected to obtain the target detection results;

[0010] Based on the relationship between the preset detection results and the preset repair information, the target repair information corresponding to the target detection results is determined to be the repair information for the faulty link segment.

[0011] In one possible implementation, obtaining the network availability of a service over a preset time period includes:

[0012] Obtain the actual bandwidth traffic and alarm information of the service within a preset time period;

[0013] Determine the first time period during which the ratio of actual bandwidth traffic to the service's required bandwidth traffic is less than the traffic threshold.

[0014] Determine the alarm time period corresponding to the alarm information;

[0015] Cyclic Redundancy Check (CRC) is used to determine the error time period;

[0016] The second time period is obtained by combining the first time period, the alarm time period, and the error time period.

[0017] The second ratio between the duration of the second time period and the duration of the preset time period is determined as the network availability rate for the preset time period.

[0018] In one possible implementation, the optical power includes the optical power of the service across multiple link segments; identifying faulty link segments based on service quality index data includes:

[0019] If the optical power of the first target link segment is greater than a first optical power threshold or less than a second optical power threshold, the first target link segment is determined to be a faulty link segment. The first optical power threshold is less than a first preset optical power when the optical power is highly degraded, and the second optical power threshold is greater than a second preset optical power when the optical power is low.

[0020] And / or, if the duration during which the bit error rate is greater than the bit error rate threshold exceeds a first preset duration, obtain the sub-bit error rate of the service in multiple link segments;

[0021] If the sub-bit error rate of the second target link segment meets the first preset condition, the second target link segment is determined to be a faulty link segment.

[0022] And / or, if the duration of the delay being greater than the delay threshold exceeds the second preset duration, obtain the sub-delay of the service in multiple link segments;

[0023] If the sub-delay of the third target link segment meets the second preset condition, the third target link segment is determined to be a faulty link segment.

[0024] In one possible implementation, the method further includes:

[0025] If the duration of continuous decrease in optical power of the fourth target link segment exceeds the third preset duration, the fourth target link segment is determined to be a faulty link segment.

[0026] In one possible implementation embodiment, after obtaining the service quality indicator data for a preset time period, the method further includes:

[0027] Displays business quality indicator data.

[0028] In one possible implementation, the method further includes:

[0029] Obtain network log data for the service within a preset time period;

[0030] The network log data is input into the fault link identification model, and the fault link segment is identified by using the relationship information between the preset network log data and the preset fault link segment in the fault link identification model.

[0031] The fault link identification model is trained using historical network log data of historical problematic link segments.

[0032] In one possible implementation, identifying faulty link segments based on service quality indicator data includes:

[0033] Obtain the shared link segment for the service within a preset time period;

[0034] Based on service quality index data, identify faulty link segments from the shared link segments.

[0035] In one possible implementation, based on the relationship information between preset detection results and preset repair information, the target repair information corresponding to the target detection result is determined as the repair information for the faulty link segment, including:

[0036] If the target detection result includes the first target output optical power of the optical module of the target device being greater than the first optical power threshold or less than the second optical power threshold, an optical power adjustment command is sent to the target device. The optical power adjustment command is used to instruct the target device to adjust the first target output optical power to an output optical power that is less than the first optical power threshold and greater than the second optical power threshold.

[0037] The second target output optical power of the optical module of the target device is detected;

[0038] If the output optical power of the second target is greater than the first optical power threshold, the first repair information is determined to be the repair information of the faulty link segment.

[0039] In one possible implementation, the method further includes:

[0040] If the output optical power of the second target is less than the second optical power threshold, the second repair information is determined to be the repair information of the faulty link segment.

[0041] In one possible implementation embodiment, after determining that the first repair information is the repair information for the faulty link segment when the second target output optical power is greater than the first optical power threshold, the method further includes:

[0042] If the output optical power of the second target is greater than the first optical power threshold, the status of the optical module of the target device is detected;

[0043] If the optical module status of the target device does not meet the third preset condition, the second repair information is determined to be the repair information of the faulty link segment.

[0044] In one possible implementation, based on the relationship information between preset detection results and preset repair information, the target repair information corresponding to the target detection result is determined as the repair information for the faulty link segment, including:

[0045] If the target detection results include optical cable attenuation greater than the attenuation threshold, the third repair information is determined to be the repair information for the faulty link segment.

[0046] In one possible implementation, the method further includes:

[0047] If the sub-bit error rate of the faulty link segment meets the first preset condition, the output optical power of the optical module of the faulty link segment is adjusted to be less than the first optical power threshold and greater than the second optical power threshold.

[0048] In one possible implementation, the method further includes:

[0049] If the sub-bit error rate of the faulty link segment meets the first preset condition, and a virtual connection alarm is detected in the optical module of the faulty link segment, the fourth repair information is determined to be the repair information of the faulty link segment.

[0050] In one possible implementation, the method further includes:

[0051] If the sub-bit error rate of the faulty link segment meets the first preset condition, and the temperature of the optical module of the faulty link segment is detected to be greater than the preset temperature threshold, the heat dissipation device is activated.

[0052] In one possible implementation, the method further includes:

[0053] If the sub-delay of the faulty link segment meets the second preset condition, the output optical power of the optical module of the faulty link segment is adjusted to be less than the first optical power threshold and greater than the second optical power threshold.

[0054] In one possible implementation, the faulty link segment includes a first device and a second device; the method further includes:

[0055] If the sub-delay of the faulty link segment meets the second preset condition, the network topology information of the service is obtained, including the path information from the first device to the second device.

[0056] Based on the path information, the detour link segments between the first device and the second device, excluding the faulty link segments, are determined to meet the fourth preset condition.

[0057] Switch services on the faulty link segment to the detour link segment.

[0058] Secondly, embodiments of this application provide a device for determining repair information, comprising:

[0059] The acquisition module is used to acquire the network availability of services within a preset time period;

[0060] The acquisition module is also used to acquire service quality indicator data of the service within a preset time period when the network availability is less than a preset value. The service quality indicator data includes at least one of optical power, bit error rate and latency.

[0061] The identification module is used to identify faulty link segments based on business quality indicator data;

[0062] The detection module is used to detect the output optical power of the optical module in the faulty link segment and the optical cable attenuation in the faulty link segment, and obtain the target detection result.

[0063] The determination module is used to determine the target repair information corresponding to the target detection result as the repair information for the faulty link segment based on the relationship information between the preset detection results and the preset repair information.

[0064] Thirdly, embodiments of this application provide an electronic device, the device comprising:

[0065] Processor and memory storing computer program instructions;

[0066] A method for determining repair information that enables any of the above-mentioned functions when a processor executes computer program instructions.

[0067] Fourthly, embodiments of this application provide a computer storage medium storing computer program instructions, wherein when the computer program instructions are executed by a processor, a method for determining repair information that implements any of the above-mentioned items is provided.

[0068] Fifthly, embodiments of this application provide a computer program product in which instructions are executed by a processor of an electronic device, enabling the electronic device to perform any of the above-mentioned methods for determining repair information.

[0069] The method, apparatus, device, storage medium, and product for determining repair information in this application embodiment obtain the network availability rate of a service within a preset time period; when the network availability rate is less than a preset value, obtain service quality index data of the service within the preset time period, the service quality index data including at least one of optical power, bit error rate, and latency; identify faulty link segments based on the service quality index data; detect the output optical power of the optical module in the faulty link segment and the optical cable attenuation of the optical cable in the faulty link segment to obtain target detection results; and determine the target repair information corresponding to the target detection results as the repair information of the faulty link segment based on the relationship information between the preset detection results and preset repair information. The identification of faulty link segments is triggered by the network availability rate. After identifying the faulty link segment, the repair information of the faulty link segment is determined by detecting the optical module and optical cable in the faulty link segment. That is, through hierarchical positioning at the network element level and then at the port level, the network element level is quickly delimited to rapidly determine the approximate range of the problem, and then the investigation area is narrowed down. Precise port-level positioning accurately locates the fault location and determines the corresponding repair information, so that the fault can be repaired in a timely manner. Attached Figure Description

[0070] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0071] Figure 1 This is a flowchart illustrating a method for determining repair information provided in one embodiment of this application;

[0072] Figure 2 This is a flowchart illustrating a method for determining repair information provided in another embodiment of this application;

[0073] Figure 3 This is a flowchart illustrating a method for determining repair information provided in another embodiment of this application;

[0074] Figure 4 This is a flowchart illustrating a method for determining repair information provided in another embodiment of this application;

[0075] Figure 5 This is a flowchart illustrating a method for determining repair information provided in another embodiment of this application;

[0076] Figure 6 This is a flowchart illustrating a method for determining repair information provided in another embodiment of this application;

[0077] Figure 7 This is a schematic diagram of the structure of a device for determining repair information provided in another embodiment of this application;

[0078] Figure 8 This is a schematic diagram of the structure of an electronic device provided in another embodiment of this application. Detailed Implementation

[0079] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0080] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0081] With the rapid development of communication technology and the rapid expansion of the number of user terminal devices connected, the scale and complexity of network services are increasing daily. Users are also becoming more sensitive to service perception and have higher demands for service quality. Therefore, in order to improve user experience, accurate and dynamic analysis of service status and timely fault repair are crucial.

[0082] Existing technologies typically calculate network availability using network availability time periods or mean time between failures. This only considers one factor and can only determine whether the network used by the service is available. The range of faults identified is relatively wide, requiring users to spend a lot of time to locate the fault and then repair it, making it difficult to repair faults in a timely manner.

[0083] To address the problems of existing technologies, embodiments of this application provide a method, apparatus, device, storage medium, and product for determining repair information. Embodiments of this application trigger the identification of faulty link segments based on network availability. After identifying the faulty link segment, repair information is determined by detecting the optical modules and optical cables within the faulty link segment. Specifically, through hierarchical positioning at the network element level followed by the port level, the approximate scope of the problem is quickly determined at the network element level, then the investigation area is narrowed down. Precise port-level positioning accurately locates the fault location and determines the corresponding repair information, enabling timely fault repair.

[0084] This application embodiment can be based on the operator scenario, applied to the network management system, to dynamically analyze services and assist AI in repair, thereby improving user perception and user satisfaction.

[0085] The method for determining repair information provided in the embodiments of this application will be described in detail below.

[0086] like Figure 1 As shown, the method for determining repair information provided in this application embodiment includes the following steps S110 to S150.

[0087] S110. Obtain the network availability rate of the service within a preset time period.

[0088] The preset time period is a historical time period.

[0089] S120. When the network availability is less than a preset value, obtain the service quality indicator data for the service within a preset time period. The service quality indicator data includes at least one of optical power, bit error rate, and latency.

[0090] The preset values ​​are pre-set.

[0091] In some embodiments, when the network availability is less than a preset value, the real-time service flow data analysis engine is used to obtain the service quality indicator data of the service within a preset time period.

[0092] Specifically, when network availability is lower than a preset value, the data sources are first integrated. A message queue (such as Kafka) is used as a data buffer and transmission layer to collect raw data such as traffic logs and performance metrics from network devices (such as routers, switches, firewalls, etc.) and servers within a preset time period. This raw data may include, but is not limited to, optical power, bit error rate, and latency.

[0093] Next, Apache Flink is used for real-time data processing. Apache Flink is an open-source, distributed, stream-batch integrated big data processing framework that supports high throughput and low latency Complex Event Processing (CEP). Apache Flink processes the raw data according to a preset window strategy (such as sliding window or scrolling window), and filters out the business quality indicator data for a preset time period from the raw data. The business quality indicator data includes at least one of optical power, bit error rate, and latency.

[0094] S130. Identify faulty link segments based on business quality indicator data.

[0095] Among them, the faulty link segment is the transmission link used in the service transmission process.

[0096] In some embodiments, a faulty link segment can be identified based on at least one of optical power, bit error rate, and latency.

[0097] In some embodiments, the Traceroute tool, which has been developed or integrated and extended, is used to record the transmission path of service flows. Traceroute is a tool for network diagnostics and analysis, primarily used to trace the router path that data packets take from the source host to the destination host, and to display relevant information for each router, helping users understand the network topology and locate network faults. In this embodiment, the Traceroute tool supports complex network environments such as Multi-Protocol Label Switching (MPLS) and Software Defined Networking (SDN), has multi-protocol support capabilities, and can penetrate network structures such as Network Address Translation (NAT) and Virtual Private Networks (VPNs) to accurately record the transmission path of data packets.

[0098] In some embodiments, for the transmission links of the business flow recorded using the developed or integrated Traceroute tool, all transmission links are analyzed using a big data analytics platform (such as Hadoop or Spark), and abnormal traffic patterns are identified based on business quality index data, thereby identifying faulty link segments.

[0099] S140. Detect the output optical power of the optical module in the faulty link segment and the optical cable attenuation in the faulty link segment to obtain the target detection result.

[0100] In some embodiments, the target detection result includes at least one of the optical module detection result and the optical cable detection result.

[0101] In some embodiments, the target detection result is that the output optical power is too high or too low, or the optical cable attenuation is too high.

[0102] S150. Based on the relationship between the preset detection results and the preset repair information, determine the target repair information corresponding to the target detection results as the repair information for the faulty link segment.

[0103] The relationship between the preset detection results and the preset repair information is pre-defined.

[0104] In some embodiments, after determining that the target repair information corresponding to the target detection result is the repair information of the faulty link segment, the repair information of the faulty link segment is displayed for use during repair, providing an effective reference for adjusting circuits and routing, improving network availability and user experience in actual applications.

[0105] In some embodiments, a fault case library and a repair information library are established to record the experience and knowledge accumulated during each fault handling process, providing reference and guidance for future fault handling.

[0106] This application embodiment triggers the identification of faulty link segments based on network availability. After identifying the faulty link segment, the repair information is determined by detecting the optical modules and optical cables within the faulty link segment. That is, through hierarchical positioning at the network element level and then at the port level, the network element level is quickly delineated to determine the approximate scope of the problem, and then the investigation area is narrowed down. At the port level, precise positioning is used to accurately locate the fault location and determine the corresponding repair information, so that the fault can be repaired in a timely manner.

[0107] Based on this, in some embodiments, such as Figure 2 As shown, S110 may specifically include S111 to S116.

[0108] S111. Obtain the actual bandwidth traffic and alarm information of the service within a preset time period.

[0109] In some embodiments, network availability is determined based on bandwidth usage and overall service performance over a preset time period. For example, a one-month preset time period can be used to analyze network availability within that month. Here, "network" can refer to a leased line.

[0110] In some embodiments, the actual bandwidth traffic and alarm information of the service within a preset time period can be obtained from the user's request.

[0111] S112. Determine the first time period during which the first ratio of actual bandwidth traffic to the service's required bandwidth traffic is less than the traffic threshold.

[0112] The traffic threshold and the bandwidth requirements of the service are pre-set. The bandwidth requirements can be based on the service itself, and different services can have different bandwidth requirements.

[0113] In some embodiments, a first ratio of actual bandwidth traffic to service-required bandwidth traffic is calculated at the minute level, and a first time period in which the first ratio is less than a traffic threshold is determined.

[0114] As an example, the first ratio is 1%.

[0115] It should be noted that actual bandwidth traffic and required bandwidth traffic refer to the total bandwidth under the aggregated port.

[0116] S113. Determine the alarm time period corresponding to the alarm information.

[0117] In some embodiments, by monitoring relevant alarms of the service, when a service interruption alarm such as user-side R_LOS or Ethernet port loss occurs, the alarm is displayed in minutes, with the default alarm time period. User-side R_LOS refers to Receive Loss of Signal, a common alarm signal in communication transmission equipment.

[0118] S114. Use Cyclic Redundancy Check (CRC) to determine the error time period.

[0119] In some embodiments, by monitoring the performance of the service and analyzing the real-time performance data reported by the service, the time period of CRC error can be found with a granularity of minutes.

[0120] S115. Combine the first time period, the alarm time period, and the error time period to obtain the second time period.

[0121] In some embodiments, a second time period is obtained by combining all unavailable time periods, i.e., combining the first time period, the alarm time period, and the error time period.

[0122] It is understandable that the first time period, the alarm time period, and the error time period may overlap.

[0123] S116. Determine the second ratio of the duration of the second time period to the duration of the preset time period, which is the network availability rate of the preset time period.

[0124] It is understandable that the sum of the duration of the first time period, the duration of the alarm time period, and the duration of the error time period is greater than or equal to the duration of the second time period.

[0125] In some embodiments, a second ratio of the duration of the second time period to the duration of the preset time period is calculated, and the second ratio is used as the network availability rate of the preset time period.

[0126] This application embodiment obtains unavailable time periods generated from different dimensions based on data such as bandwidth traffic, related alarms, and current network status, and then calculates the network availability rate. It comprehensively considers multiple factors to determine the network availability rate, thereby improving the accuracy of the network availability rate calculation.

[0127] Based on this, in some embodiments, the optical power includes the optical power of the service across multiple link segments; the above-mentioned S130 may specifically include:

[0128] If the optical power of the first target link segment is greater than a first optical power threshold or less than a second optical power threshold, the first target link segment is determined to be a faulty link segment. The first optical power threshold is less than a first preset optical power when the optical power is highly degraded, and the second optical power threshold is greater than a second preset optical power when the optical power is low.

[0129] And / or, if the duration during which the bit error rate is greater than the bit error rate threshold exceeds a first preset duration, obtain the sub-bit error rate of the service in multiple link segments;

[0130] If the sub-bit error rate of the second target link segment meets the first preset condition, the second target link segment is determined to be a faulty link segment.

[0131] And / or, if the duration of latency greater than the latency threshold exceeds the second preset duration, obtain the sub-latency of the service in multiple link segments;

[0132] If the sub-delay of the third target link segment meets the second preset condition, the third target link segment is determined to be a faulty link segment.

[0133] The first optical power threshold, the second optical power threshold, the bit error rate threshold, and the delay threshold can all be preset. The first preset duration and the second preset duration are also preset.

[0134] In some embodiments, when network availability fails to meet user expectations (i.e., preset values), a service degradation analysis is initiated to identify potential faulty link segments. By collecting and analyzing real-time network service quality indicator data, degraded links are identified, and potential problems are promptly discovered. The main causes of performance degradation in links include three aspects: degraded optical power, excessively high bit error rate, and excessive latency.

[0135] In some embodiments, based on real-time optical power analysis, the actual optical power of each link segment is compared with a first optical power threshold and a second optical power threshold. A first target link segment whose actual optical power is greater than the first optical power threshold is defined as a highly degraded optical link segment; a first target link segment whose actual optical power is less than the second optical power threshold is defined as a poorly degraded optical link segment.

[0136] It is understood that setting the first optical power threshold to be less than the first preset optical power when optical degradation is high, and setting the second optical power threshold to be greater than the second preset optical power when optical degradation is low, can detect potentially faulty link segments in advance. In the embodiments of this application, the faulty link segment can be a link segment that is about to fail.

[0137] As an example, the difference between the second optical power threshold and the second preset optical power at low optical degradation is greater than 2 dB.

[0138] In some embodiments, the Bit Error Rate (BER) is a key performance indicator reflecting the accuracy and reliability of data transmission. When the BER of a service flow exceeds a threshold (e.g., more than 1 / 1,000,000), it typically indicates a problem in the network, which could be due to degraded link quality, equipment failure, interference, or other causes. For rapid localization, service-based flow detection can be used to detect and locate faulty links segment by segment. This allows for the accurate identification and location of potential problematic links or nodes leading to an increased BER, which may stem from various factors such as line aging, equipment failure, and external interference.

[0139] Specifically, the system tracks the bit error rate (BER) of the service flow in real time. If the BER of the service flow continuously exceeds the BER threshold for multiple consecutive sampling periods, the flow-following detection function is activated. This function performs segmented detection on the links traversed by the service flow, comprehensively collecting and deeply analyzing key performance indicators such as BER and packet loss rate for each link segment. By comparing the BER of each link segment, if the BER of the second target link segment meets a first preset condition, the second target link segment is determined to be a faulty link segment. The BER threshold can be set according to the specific requirements of the service and the current state of the network. For example, the BER threshold could be 1 / 1,000,000.

[0140] The first preset condition includes the maximum sub-error rate.

[0141] In some embodiments, latency is another crucial performance metric in network communication, directly impacting data transmission speed and user experience. When the latency of a service flow exceeds a latency threshold (e.g., over 100 milliseconds), it typically indicates a bottleneck or problem in the network, such as network congestion, excessive device load, excessively long transmission paths, or improper network configuration. To quickly identify problems, a service-based flow detection function segments the network for inspection, accurately pinpointing faulty links causing increased latency and ensuring efficient data transmission and a smooth user experience.

[0142] Specifically, when the detected latency of a service flow continuously exceeds a latency threshold for a duration exceeding a second preset duration, a segment-by-segment detection mechanism is initiated. This mechanism can meticulously analyze each link segment traversed by the service flow during transmission, compare the latency of different link segments, and determine the third target link segment as a faulty link segment if its sub-latency meets the second preset condition. This allows for precise identification of the potentially problematic link causing the increased latency. The second preset duration is pre-set; for example, it might be 50 milliseconds.

[0143] The second preset condition includes the maximum sub-delay.

[0144] The embodiments of this application can accurately identify key points of service degradation. By using three important factors affecting service availability—optical power, bit error rate, and latency—to identify faulty link segments, the accuracy of faulty link segment identification is improved.

[0145] Based on this, in some embodiments, the method may further include:

[0146] If the duration of continuous decrease in optical power of the fourth target link segment exceeds the third preset duration, the fourth target link segment is determined to be a faulty link segment.

[0147] As an example, historical optical power is analyzed by comparing the current optical power of the link segment used by the service with the optical power of the previous day. If it decreases, the count is 1. The current optical power is continuously compared with the optical power of the previous day for 7 consecutive days. If the current optical power decreases in all comparisons, it indicates optical degradation and can be identified as a faulty link segment.

[0148] In this application embodiment, link segments with continuously decreasing optical power are also identified as faulty link segments, thus improving the accuracy of faulty link segment identification.

[0149] Based on this, in some embodiments, after S120 described above, the method may further include:

[0150] Displays business quality indicator data.

[0151] As an example, business quality indicator data can be visualized using Grafana or a custom web interface. Real-time charts and alert notifications can be displayed to provide operations personnel with a clear understanding of network health. Grafana is an open-source data analysis and visualization tool.

[0152] This application embodiment achieves second-level end-to-end perception and real-time visualization of business quality by displaying real business flow data, thereby improving user experience.

[0153] It should be noted that E2E perception can refer to the network's comprehensive perception of its own status, business traffic, user needs, and other information from one end to the other.

[0154] Based on this, in some embodiments, corresponding to S130 above, the method may further include:

[0155] Obtain network log data for the service within a preset time period;

[0156] The network log data is input into the fault link identification model, and the fault link segment is identified by using the relationship information between the preset network log data and the preset fault link segment in the fault link identification model.

[0157] The fault link identification model is trained using historical network log data of historical problematic link segments.

[0158] In some embodiments, a high-risk link intelligent analysis platform is constructed. The high-risk link intelligent analysis platform includes a fault link identification model. The construction process of the high-risk link intelligent analysis platform includes:

[0159] (1) Data preprocessing: Clean and transform the collected historical fault records, network logs and other data, and extract network log data that is useful for model training;

[0160] (2) Model training: Supervised or unsupervised learning methods (depending on data availability) are used to train the machine learning model to determine the relationship between the preset network log data and the preset faulty link segment; the model needs to be updated regularly to adapt to changes in the network environment;

[0161] (3) Prediction and Alarm: The model outputs the prediction results of high-risk links.

[0162] In some embodiments, a preset condition is used to determine whether an alarm needs to be triggered. Alarm information can be sent to relevant personnel through various channels such as email, SMS, and Slack.

[0163] This application embodiment, through the collection of historical fault data and model training, can use the fault link identification model to determine more complex fault link segments, thereby improving the accuracy of fault link segment identification.

[0164] Based on this, in some embodiments, such as Figure 3 As shown, the above S130 may specifically include S131 to S132.

[0165] S131. Obtain the shared link segment of the service within a preset time period.

[0166] In some embodiments, when a sudden batch of packet loss or mass service failure occurs simultaneously in the network, deep learning and pattern recognition are used to perform cluster analysis on the affected services to determine the commonalities of the affected services, i.e., to identify shared links.

[0167] S132. Based on the service quality index data, identify the faulty link segment from the shared link segment.

[0168] In some embodiments, if a large number of services are experiencing problems, then the problem must be with the shared link. In this case, it is only necessary to identify the faulty link segment from the shared link segment.

[0169] This application's embodiments, through big data analysis and correlation analysis, can quickly identify common problem points such as faulty link segments, nodes, or regions, and determine their scope. Once the common problem points are identified, the scope of the fault is narrowed, improving the efficiency of faulty link segment identification.

[0170] This application proposes a series of efficient and automated solutions to address network service degradation issues of different fault types. The specific optimizations and intelligent adjustments are as follows.

[0171] Based on this, in some embodiments, such as Figure 4 As shown, the above S150 may specifically include S151 to S153.

[0172] S151. If the target detection result includes the first target output optical power of the optical module of the target device being greater than the first optical power threshold or less than the second optical power threshold, an optical power adjustment command is sent to the target device. The optical power adjustment command is used to instruct the target device to adjust the first target output optical power to an output optical power that is less than the first optical power threshold and greater than the second optical power threshold.

[0173] In some embodiments, the output optical power of the optical module of a device in a faulty link is monitored and recorded. If the target detection result indicates that the first target output optical power of the target device's optical module is greater than a first optical power threshold or less than a second optical power threshold, an optical power adjustment command is sent to the target device to attempt to adjust its output optical power to a reasonable range.

[0174] S152, Detect the second target output optical power of the optical module of the target device.

[0175] The second target output optical power is the adjusted output optical power.

[0176] S153. If the output optical power of the second target is greater than the first optical power threshold, the first repair information is determined to be the repair information of the faulty link segment.

[0177] In some embodiments, if the output optical power of the second target is greater than the first optical power threshold, it indicates that the adjustment is ineffective, and the first repair information is determined to be the repair information of the faulty link segment.

[0178] In some embodiments, the first repair information is information prompting the user to configure an appropriate optical attenuator.

[0179] In some embodiments, after determining that the first repair information is the repair information for the faulty link segment, the repair information for the faulty link segment is displayed.

[0180] In this embodiment, the output optical power of the faulty optical module in the faulty link can be adjusted by the optical power adjustment command. If it cannot be adjusted, the user is prompted for manual intervention. The user can repair the faulty link in a timely manner by using the repair information.

[0181] Based on this, in some embodiments, corresponding to S153 above, the method may further include:

[0182] If the output optical power of the second target is less than the second optical power threshold, the second repair information is determined to be the repair information of the faulty link segment.

[0183] In some embodiments, if the output optical power of the second target is less than the second optical power threshold, it indicates that the adjustment is ineffective and the output optical power still does not meet the standard. In this case, the second repair information is determined to be the repair information of the faulty link segment.

[0184] In some embodiments, the second repair information is a message prompting the user to replace the optical module.

[0185] In this embodiment, after adjusting the output optical power of the faulty optical module in the faulty link using the optical power adjustment command, if the adjustment is ineffective, the user is prompted for manual intervention. The user can then repair the faulty link in a timely manner using the repair information.

[0186] Based on this, in some embodiments, after S153 above, the method may further include:

[0187] If the output optical power of the second target is greater than the first optical power threshold, the status of the optical module of the target device is detected;

[0188] If the optical module status of the target device does not meet the third preset condition, the second repair information is determined to be the repair information of the faulty link segment.

[0189] In some embodiments, after the user configures the optical attenuator, if the output optical power of the second target is still greater than the first optical power threshold, the status of the optical module of the target device is detected. If the status of the optical module of the target device does not meet the third preset condition, the second repair information is determined to be repair information for the faulty link segment.

[0190] In some embodiments, the second repair information is a message prompting the user to replace the optical module.

[0191] As an example, the status includes temperature, and the third preset condition includes temperature conditions. If the temperature of the optical module in the target device exceeds a temperature threshold, the second repair information is determined to be repair information for the faulty link segment.

[0192] If the fault persists after prompting the user to perform repairs, the embodiment of this application can also prompt the user to perform manual intervention based on the optical module status, so that the user can promptly repair the faulty link through new repair information.

[0193] Based on this, in some embodiments, such as Figure 5 As shown, the above S150 may specifically include S210.

[0194] S210. If the target detection result includes optical cable attenuation greater than the attenuation threshold, the third repair information is determined to be the repair information of the faulty link segment.

[0195] In some embodiments, the third repair information is a message prompting the user to replace the optical cable.

[0196] This application embodiment can detect optical cables and promptly remind users to repair them if there are any problems with the optical cables.

[0197] Based on this, in some embodiments, the method may further include:

[0198] If the sub-bit error rate of the faulty link segment meets the first preset condition, the output optical power of the optical module of the faulty link segment is adjusted to be less than the first optical power threshold and greater than the second optical power threshold.

[0199] In some embodiments, when the sub-bit error rate of the faulty link segment meets the first preset condition, and the target detection result includes the first target output optical power of the optical module of the target device being greater than the first optical power threshold or less than the second optical power threshold, the output optical power of the optical module of the faulty link segment is adjusted to be less than the first optical power threshold and greater than the second optical power threshold.

[0200] In some embodiments, adjusting the output optical power of the optical module in the faulty link segment to an output optical power that is less than a first optical power threshold and greater than a second optical power threshold includes:

[0201] An optical power adjustment command is sent to the target device on the faulty link segment, and then the third target output optical power of the target device's optical module is detected. If the third target output optical power is greater than a first optical power threshold, the first repair information is determined to be the repair information for the faulty link segment. If the third target output optical power is less than a second optical power threshold, the second repair information is determined to be the repair information for the faulty link segment. If the third target output optical power is greater than the first optical power threshold, the status of the target device's optical module is detected. If the status of the target device's optical module does not meet a third preset condition, the second repair information is determined to be the repair information for the faulty link segment.

[0202] The embodiments of this application can reduce the bit error rate by adjusting the output optical power of the optical module.

[0203] Based on this, in some embodiments, the method may further include:

[0204] If the sub-bit error rate of the faulty link segment meets the first preset condition, and a virtual connection alarm is detected in the optical module of the faulty link segment, the fourth repair information is determined to be the repair information of the faulty link segment.

[0205] In some embodiments, the fourth repair information is a message prompting the user to firmly insert the optical module.

[0206] This application embodiment can use virtual connection alarms to prompt users to repair faults in a timely manner, thereby reducing the bit error rate.

[0207] Based on this, in some embodiments, the method may further include:

[0208] If the sub-bit error rate of the faulty link segment meets the first preset condition, and the temperature of the optical module of the faulty link segment is detected to be greater than the preset temperature threshold, the heat dissipation device is activated.

[0209] This application embodiment monitors the temperature of the optical module and automatically activates a heat dissipation mechanism to ensure the stable operation of the network equipment.

[0210] Based on this, in some embodiments, the method may further include:

[0211] If the sub-delay of the faulty link segment meets the second preset condition, the output optical power of the optical module of the faulty link segment is adjusted to be less than the first optical power threshold and greater than the second optical power threshold.

[0212] In some embodiments, when the sub-delay of the faulty link segment meets the second preset condition, and the target detection result includes the first target output optical power of the optical module of the target device being greater than the first optical power threshold or less than the second optical power threshold, the output optical power of the optical module of the faulty link segment is adjusted to be less than the first optical power threshold and greater than the second optical power threshold.

[0213] In some embodiments, adjusting the output optical power of the optical module in the faulty link segment to an output optical power that is less than a first optical power threshold and greater than a second optical power threshold includes:

[0214] An optical power adjustment command is sent to the target device on the faulty link segment, and then the fourth target output optical power of the target device's optical module is detected. If the fourth target output optical power is greater than a first optical power threshold, the first repair information is determined to be the repair information for the faulty link segment. If the fourth target output optical power is less than a second optical power threshold, the second repair information is determined to be the repair information for the faulty link segment. If the fourth target output optical power is greater than the first optical power threshold, the status of the target device's optical module is detected. If the status of the target device's optical module does not meet a third preset condition, the second repair information is determined to be the repair information for the faulty link segment.

[0215] The embodiments of this application can reduce signal attenuation and interference during signal transmission by adjusting the output optical power of the optical module, thereby reducing latency.

[0216] Based on this, in some embodiments, the faulty link segment includes a first device and a second device; such as Figure 6 As shown, the method may further include S310 to S330.

[0217] S310. If the sub-delay of the faulty link segment meets the second preset condition, obtain the network topology information of the service. The network topology information includes the path information from the first device to the second device.

[0218] In some embodiments, network management tools (such as NetBox and Nagios) are used to obtain network topology information for the service, including devices, links, and IP addresses. All possible paths for the service are generated based on graph theory algorithms. The diversity of paths is considered to avoid a single point of failure causing multiple paths to fail simultaneously.

[0219] S320. Based on the path information, determine the bypass link segment between the first device and the second device that meets the fourth preset condition, excluding the faulty link segment.

[0220] In some embodiments, based on multiple factors such as path length, bandwidth utilization, latency, and reliability, a multi-objective optimization algorithm (such as NSGA-II) is used to evaluate all possible paths of the aforementioned services to determine, excluding faulty link segments, the detour link segments between the first device and the second device that satisfy a fourth preset condition. The fourth preset condition may be minimum latency.

[0221] In some embodiments, the detour link segment can also be evaluated based on the service quality index data of the detour link segment to detect whether the detour link segment is a faulty link segment, thereby ensuring the feasibility and optimality of the detour link segment.

[0222] Specifically, monitoring probes are deployed at key network nodes and servers to collect service quality indicator (SMI) data for bypass link segments. Traffic load under real-world business scenarios is simulated to verify the stability and performance of the bypass path. The SMI data for bypass link segments can be collected using tools such as Prometheus and Telegraf, both widely used tools in the monitoring and data collection fields.

[0223] In some embodiments, Grafana can also be used to visualize the service quality index data of bypass link segments.

[0224] In some embodiments, Alertmanager can also be used to set alarm rules to provide timely notifications for faulty link segments. Alertmanager is an important component of the Prometheus ecosystem, primarily used to process and manage alarm information from Prometheus servers or other systems.

[0225] S330. Switch the services on the faulty link segment to the detour link segment.

[0226] In some embodiments, instructions are generated to bypass the faulty link segment, which instruct the services on the faulty link segment to be switched to the bypass link segment and the optical cable route is adjusted.

[0227] In some embodiments, after switching services on the faulty link segment to a detour link segment, the network status and actual service operation after the detour are continuously monitored to ensure that the fault is mitigated in a timely and effective manner.

[0228] In some embodiments, if the latency problem is complex, such as the latency still not meeting the second preset condition after switching links, data such as network congestion and device performance are displayed for users to conduct in-depth analysis.

[0229] The embodiments of this application can reduce latency by switching the link used by the service.

[0230] In the embodiments provided in this application, cleaning prompts for the optical module, optical fiber contact surface, and optical fiber end face are displayed periodically.

[0231] In the embodiments provided in this application, if the fault cannot be resolved, a prompt message is sent to the relevant equipment to remind the relevant personnel that the fault cannot be eliminated.

[0232] In the embodiments provided in this application, data such as detour effects, newly discovered fault information, and network changes can also be fed back to the machine learning model for model retraining and parameter adjustment. Automated operation and maintenance tools (such as Ansible and Terraform) and network management software (such as SolarWinds and Prtg) enable automated management and continuous monitoring of network configurations, ensuring long-term network stability and efficient service operation.

[0233] In the core domain of network management, end-to-end (E2E) data transmission quality is considered a key factor in service smoothness and user experience. However, when a link in the network fails or experiences performance degradation, this data transmission quality can be severely impacted, leading to poor quality. To address this phenomenon quickly and effectively, the embodiments provided in this application propose an automatically triggered end-to-end poor quality diagnostic process that can immediately identify the problematic link upon detecting poor quality. Once poor quality is detected, the AI ​​system immediately initiates its diagnostic program, deeply analyzing relevant network data and subdividing the faulty link into different fault types. This not only deepens the understanding of the problem's essence but also provides solid support for subsequent solutions. After identifying the problem, the AI ​​system determines precise repair information based on the real-time network status, device performance status, and user needs. This is not only feasible and efficient but also allows the AI ​​system to continuously optimize and improve the repair information based on historical data and rich experience, ensuring that the problem can be resolved quickly and accurately. Throughout the process, it fully demonstrated its superior data processing, in-depth analysis, and accurate decision-making capabilities, while also highlighting its remarkable efficiency, intelligence, and automation in network management. It can respond to various network issues more quickly, thereby ensuring network stability and business continuity.

[0234] The embodiments provided in this application are based on the operation and maintenance requirements of 5G bearer networks. Combining the advantages and disadvantages of existing performance detection technologies, they directly measure service packets. Combined with telemetry's second-level data acquisition and a unified management, calculation, and visualization platform, they enable the detection of latency, packet loss rate, and packet rate of IP traffic in the network. They support various traffic models such as point-to-point (P2P), point-to-multipoint (P2MP), and multi-point-to-multipoint (MP2MP), and support end-to-end, point-by-point detection, providing powerful performance monitoring and fault location tools for network operation and maintenance. The service flow detection technology, based on RFC 8321 (alternating labeling method for passive and hybrid performance monitoring), is a path-based detection technology that marks (colors) the actual service flow with features and measures packet loss and latency on the feature fields. The workbench collects real-time data on the entire network's service performance and calculates packet loss, latency, and other metrics for each E2E flow at different periodic granularities. This data is presented in real-time through reports and trend charts, and threshold settings are used to color-code out-of-limit indicators for E2E flows. 24 / 7 proactive monitoring makes risks readily apparent, enabling proactive detection and handling of faults before they occur. This transforms network operations from passively handling fault complaints to proactive monitoring and prevention, reducing user failure rates and improving user experience.

[0235] Telemetry typically refers to telemetry technology, which is a technical means used to collect, transmit, and analyze data from remote devices or systems.

[0236] In the embodiments provided in this application, second-level E2E perception of service quality enables high-precision, real-time visibility of the actual service-level service level agreement (SLA), supporting proactive operation and maintenance. Poor quality flow hop-by-hop delimitation and localization is an efficient and accurate network management solution focused on resolving data transmission quality issues. It rapidly determines the approximate scope of the problem at the network element level, narrowing down the investigation area; then, through precise port-level localization, it accurately locates the problematic port, deeply analyzes the port status and configuration, and reveals the root cause of the problem. Furthermore, this technology also has the function of replaying historical data at any time, allowing administrators to reproduce the network state at the time of the problem, aiding in problem diagnosis and serving as a means of proving innocence. When problems cannot be directly attributed, this technology can clearly demonstrate the process and cause of the problem, supporting relevant parties in proving their innocence and eliminating misunderstandings and disputes. Poor quality flow hop-by-hop delimitation and localization, with its superior performance, greatly improves the efficiency and quality of network management. By using AI algorithms, base stations that exceed traffic limits are clustered into different fault types, common problem points are discovered, and the handling of abnormal base stations is transformed into a limited number of fault handling tasks with clear impact and scope, thereby improving the efficiency of network operation and maintenance. Based on AI big data alarm aggregation and root cause analysis, invalid dispatching is eliminated.

[0237] The core of the embodiments provided in this application lies in the calculation of multi-level network availability. This calculation foundation not only provides strong data support for the entire process of determining repair information, but also ensures the high degree of targeting and effectiveness of repair strategies. By comprehensively considering all aspects from basic network infrastructure to upper-layer application services, multi-level network availability calculation can accurately reflect the overall health status of services. For different degradation scenarios, AI technology, combined with deep learning and pattern recognition methods, is used to formulate specific repair process solutions. These solutions are not only forward-looking and targeted, but can also dynamically adjust repair strategies based on real-time data, thereby ensuring the continuous stability and high quality of services. Therefore, multi-level network availability calculation is not only a data foundation, but also a key link connecting business status analysis and repair strategies, providing users with accurate and efficient service quality assurance and contributing to the continuous optimization and improvement of business performance.

[0238] The embodiments provided in this application comprehensively consider the user's usage and operating status of the service, extract data of unqualified services, conduct service situation analysis, more accurately locate potential problems, and intelligently repair potential problems, providing strong and reliable service technical support for the user's service quality needs.

[0239] The embodiments provided in this application calculate the network availability of different instances based on data information such as the required bandwidth and traffic, related alarms, and current network status in the user's request, for service degradation analysis, to support AI repair of different degradation tasks, so as to avoid the situation where the service cannot be used due to link interruption and improve user satisfaction.

[0240] Based on the method for determining repair information provided in the above embodiments, this application also provides specific implementations of the apparatus for determining repair information. Please refer to the following embodiments.

[0241] First see Figure 7 The repair information determination device 400 provided in this application embodiment includes:

[0242] The acquisition module 410 is used to acquire the network availability rate of the service within a preset time period;

[0243] The acquisition module 410 is also used to acquire service quality indicator data of the service within a preset time period when the network availability is less than a preset value. The service quality indicator data includes at least one of optical power, bit error rate and latency.

[0244] The identification module 420 is used to identify faulty link segments based on business quality indicator data;

[0245] The detection module 430 is used to detect the output optical power of the optical module in the faulty link segment and the optical cable attenuation in the faulty link segment to obtain the target detection result.

[0246] The determination module 440 is used to determine the target repair information corresponding to the target detection result as the repair information of the faulty link segment based on the relationship information between the preset detection results and the preset repair information.

[0247] Based on this, in some embodiments, the acquisition module 410 can be specifically used for:

[0248] Obtain the actual bandwidth traffic and alarm information of the service within a preset time period;

[0249] Determine the first time period during which the ratio of actual bandwidth traffic to the service's required bandwidth traffic is less than the traffic threshold.

[0250] Determine the alarm time period corresponding to the alarm information;

[0251] Cyclic Redundancy Check (CRC) is used to determine the error time period;

[0252] The second time period is obtained by combining the first time period, the alarm time period, and the error time period.

[0253] The second ratio between the duration of the second time period and the duration of the preset time period is determined as the network availability rate for the preset time period.

[0254] Based on this, in some embodiments, optical power includes the optical power of the service across multiple link segments; the identification module 420 can specifically be used for:

[0255] If the optical power of the first target link segment is greater than a first optical power threshold or less than a second optical power threshold, the first target link segment is determined to be a faulty link segment. The first optical power threshold is less than a first preset optical power when the optical power is highly degraded, and the second optical power threshold is greater than a second preset optical power when the optical power is low.

[0256] And / or, if the duration during which the bit error rate is greater than the bit error rate threshold exceeds a first preset duration, obtain the sub-bit error rate of the service in multiple link segments;

[0257] If the sub-bit error rate of the second target link segment meets the first preset condition, the second target link segment is determined to be a faulty link segment.

[0258] And / or, if the duration of the delay being greater than the delay threshold exceeds the second preset duration, obtain the sub-delay of the service in multiple link segments;

[0259] If the sub-delay of the third target link segment meets the second preset condition, the third target link segment is determined to be a faulty link segment.

[0260] Based on this, in some embodiments, the device 400 may further include:

[0261] The determination module 440 is also used to determine the fourth target link segment as a faulty link segment if the duration of continuous decrease in the optical power of the fourth target link segment exceeds a third preset duration.

[0262] Based on this, in some embodiments, the device 400 may further include:

[0263] The display module is used to display the business quality indicator data after obtaining the business quality indicator data for a preset time period.

[0264] Based on this, in some embodiments, the device 400 may further include:

[0265] The acquisition module 410 is also used to acquire network log data of the service within a preset time period;

[0266] The identification module 420 is also used to input network log data into the fault link identification model, and use the relationship information between the preset network log data and the preset fault link segment in the fault link identification model to identify the fault link segment;

[0267] The fault link identification model is trained using historical network log data of historical problematic link segments.

[0268] Based on this, in some embodiments, the identification module 420 can specifically be used for:

[0269] Obtain the shared link segment for the service within a preset time period;

[0270] Based on service quality index data, identify faulty link segments from the shared link segments.

[0271] Based on this, in some embodiments, the determining module 440 can specifically be used for:

[0272] If the target detection result includes the first target output optical power of the optical module of the target device being greater than the first optical power threshold or less than the second optical power threshold, an optical power adjustment command is sent to the target device. The optical power adjustment command is used to instruct the target device to adjust the first target output optical power to an output optical power that is less than the first optical power threshold and greater than the second optical power threshold.

[0273] The second target output optical power of the optical module of the target device is detected;

[0274] If the output optical power of the second target is greater than the first optical power threshold, the first repair information is determined to be the repair information of the faulty link segment.

[0275] Based on this, in some embodiments, the device 400 may further include:

[0276] The determination module 440 is also used to determine the second repair information as the repair information of the faulty link segment when the output optical power of the second target is less than the second optical power threshold.

[0277] Based on this, in some embodiments, the device 400 may further include:

[0278] The detection module 430 is also used to detect the status of the optical module of the target device when the output optical power of the second target is greater than the first optical power threshold after determining that the first repair information is the repair information of the faulty link segment.

[0279] The determination module 440 is also used to determine the second repair information as the repair information of the faulty link segment when the state of the optical module of the target device does not meet the third preset condition.

[0280] Based on this, in some embodiments, the determining module 440 can specifically be used for:

[0281] If the target detection results include optical cable attenuation greater than the attenuation threshold, the third repair information is determined to be the repair information for the faulty link segment.

[0282] Based on this, in some embodiments, the device 400 may further include:

[0283] The adjustment module is used to adjust the output optical power of the optical module of the faulty link segment to an output optical power that is less than a first optical power threshold and greater than a second optical power threshold, provided that the sub-bit error rate of the faulty link segment meets a first preset condition.

[0284] Based on this, in some embodiments, the device 400 may further include:

[0285] The determination module 440 is further configured to determine the fourth repair information as the repair information of the faulty link segment when the sub-bit error rate of the faulty link segment meets the first preset condition and a virtual connection alarm is detected in the optical module of the faulty link segment.

[0286] Based on this, in some embodiments, the device 400 may further include:

[0287] The startup module is used to activate the heat dissipation device when the sub-bit error rate of the faulty link segment meets the first preset condition and the optical module temperature of the faulty link segment is detected to be greater than the preset temperature threshold.

[0288] Based on this, in some embodiments, the device 400 may further include:

[0289] The adjustment module is used to adjust the output optical power of the optical module of the faulty link segment to an output optical power that is less than a first optical power threshold and greater than a second optical power threshold when the sub-delay of the faulty link segment meets the second preset condition.

[0290] Based on this, in some embodiments, the faulty link segment includes a first device and a second device; the apparatus 400 may further include:

[0291] The acquisition module 410 is also used to acquire network topology information of the service when the sub-delay of the faulty link segment meets the second preset condition. The network topology information includes path information from the first device to the second device.

[0292] The determination module 440 is also used to determine, based on the path information, the detour link segments between the first device and the second device that meet the fourth preset condition, excluding the faulty link segments.

[0293] The switching module is used to switch services on a faulty link segment to a detour link segment.

[0294] Each module of the repair information determination device provided in this application embodiment can realize the functions of each step of the repair information determination method provided above, and can achieve its corresponding technical effects. For the sake of brevity, it will not be described in detail here.

[0295] Based on the same inventive concept, embodiments of this application also provide an electronic device.

[0296] Figure 8 A schematic diagram of the hardware structure of the electronic device provided in an embodiment of this application is shown.

[0297] An electronic device may include a processor 501 and a memory 502 storing computer program instructions.

[0298] Specifically, the processor 501 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0299] Memory 502 may include mass storage for data or instructions. For example, and not limitingly, memory 502 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 502 may include removable or non-removable (or fixed) media. Where appropriate, memory 502 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 502 is non-volatile solid-state memory.

[0300] Memory may include read-only memory (ROM), random access memory (RAM), disk storage media devices, optical storage media devices, flash memory devices, and electrical, optical, or other physical / tangible memory storage devices. Therefore, typically, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to one aspect of this disclosure.

[0301] The processor 501 reads and executes computer program instructions stored in the memory 502 to implement any of the methods for determining repair information in the above embodiments.

[0302] In one example, the electronic device may also include a communication interface 503 and a bus 510. Wherein, as... Figure 8As shown, the processor 501, memory 502, and communication interface 503 are connected through bus 510 and complete communication with each other.

[0303] The communication interface 503 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0304] Bus 510 includes hardware, software, or both, that couples components of an electronic device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Linear Predictive Coding (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (Peripheral Component Interconnect-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VESA Local Bus, VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, bus 510 may include one or more buses. Although specific buses are described and illustrated in the embodiments of this application, this application contemplates any suitable bus or interconnection. The electronic device can perform the method for determining repair information in the embodiments of the present invention, thereby implementing the aforementioned method for determining repair information.

[0305] Furthermore, in conjunction with the methods for determining repair information in the above embodiments, this application embodiment can provide a computer storage medium for implementation. This computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the methods for determining repair information in the above embodiments.

[0306] This application also provides a computer program product, wherein the instructions in the computer program product, when executed by a processor of an electronic device, cause the electronic device to perform various processes implementing any of the above-described embodiments of the method for determining repair information.

[0307] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0308] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, read-only memory (ROM), flash memory, erasable read-only memory (EROM), floppy disks, compact disc read-only memory (CD-ROM), optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0309] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0310] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0311] The above are merely specific embodiments of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A method for determining repair information, characterized in that, include: Obtain the network availability rate of the service within a preset time period; When the network availability is less than a preset value, the service quality index data of the service is obtained during the preset time period. The service quality index data includes at least one of optical power, bit error rate and latency. Based on the aforementioned service quality indicator data, identify faulty link segments; The output optical power of the optical module in the faulty link segment and the optical cable attenuation in the optical cable in the faulty link segment are detected to obtain the target detection result; Based on the relationship between the preset detection results and the preset repair information, the target repair information corresponding to the target detection results is determined as the repair information for the faulty link segment.

2. The method for determining repair information according to claim 1, characterized in that, The acquisition of network availability for the service within a preset time period includes: Obtain the actual bandwidth traffic and alarm information of the service within a preset time period; Determine a first time period in which the first ratio of the actual bandwidth traffic to the required bandwidth traffic of the service is less than a traffic threshold. Determine the alarm time period corresponding to the alarm information; Cyclic Redundancy Check (CRC) is used to determine the error time period; The second time period is obtained by combining the first time period, the alarm time period, and the error time period; A second ratio is determined between the duration of the second time period and the duration of the preset time period, which is the network availability rate of the preset time period.

3. The method for determining repair information according to claim 1, characterized in that, The optical power includes the optical power of the service across multiple link segments; identifying faulty link segments based on the service quality index data includes: If the optical power of the first target link segment is greater than a first optical power threshold or less than a second optical power threshold, the first target link segment is determined to be a faulty link segment, wherein the first optical power threshold is less than a first preset optical power when the optical power is highly degraded, and the second optical power threshold is greater than a second preset optical power when the optical power is low. And / or, if the duration during which the bit error rate is greater than the bit error rate threshold exceeds a first preset duration, the sub-bit error rate of the service in the multiple link segments is obtained; If the sub-bit error rate of the second target link segment meets the first preset condition, the second target link segment is determined to be a faulty link segment; And / or, if the duration for which the delay is greater than the delay threshold exceeds a second preset duration, obtain the sub-delay of the service in the multiple link segments; If the sub-delay of the third target link segment meets the second preset condition, the third target link segment is determined to be a faulty link segment.

4. The method for determining repair information according to claim 3, characterized in that, The method further includes: If the duration of continuous decrease in optical power of the fourth target link segment exceeds a third preset duration, the fourth target link segment is determined to be a faulty link segment.

5. The method for determining repair information according to claim 1, characterized in that, After acquiring the service quality indicator data of the service within the preset time period, the method further includes: Display the business quality indicator data.

6. The method for determining repair information according to claim 1, characterized in that, The method further includes: Obtain network log data of the service within the preset time period; The network log data is input into the fault link identification model, and the fault link segment is identified by using the relationship information between the preset network log data and the preset fault link segment in the fault link identification model. The fault link identification model is trained using historical network log data of historical problematic link segments.

7. The method for determining repair information according to claim 1, characterized in that, The step of identifying faulty link segments based on the service quality indicator data includes: Obtain the shared link segment of the service during the preset time period; Based on the service quality index data, faulty link segments are identified from the shared link segments.

8. The method for determining repair information according to claim 1, characterized in that, The step of determining the target repair information corresponding to the target detection result as the repair information for the faulty link segment based on the relationship information between the preset detection result and the preset repair information includes: If the target detection result includes the first target output optical power of the optical module of the target device being greater than a first optical power threshold or less than a second optical power threshold, an optical power adjustment command is sent to the target device. The optical power adjustment command is used to instruct the target device to adjust the first target output optical power to an output optical power that is less than the first optical power threshold and greater than the second optical power threshold. Detect the second target output optical power of the optical module of the target device; If the output optical power of the second target is greater than the first optical power threshold, the first repair information is determined to be the repair information of the faulty link segment.

9. The method for determining repair information according to claim 8, characterized in that, The method further includes: If the output optical power of the second target is less than the second optical power threshold, the second repair information is determined to be the repair information of the faulty link segment.

10. The method for determining repair information according to claim 8, characterized in that, When the output optical power of the second target is greater than the first optical power threshold, after determining that the first repair information is the repair information of the faulty link segment, the method further includes: If the output optical power of the second target is greater than the first optical power threshold, the state of the optical module of the target device is detected; If the state of the optical module of the target device does not meet the third preset condition, the second repair information is determined to be the repair information of the faulty link segment.

11. The method for determining repair information according to any one of claims 1 or 8-10, characterized in that, The step of determining the target repair information corresponding to the target detection result as the repair information for the faulty link segment based on the relationship information between the preset detection result and the preset repair information includes: If the target detection result includes the optical cable attenuation being greater than the attenuation threshold, the third repair information is determined to be the repair information for the faulty link segment.

12. The method for determining repair information according to claim 1, characterized in that, The method further includes: If the sub-bit error rate of the faulty link segment meets the first preset condition, the output optical power of the optical module of the faulty link segment is adjusted to be less than the first optical power threshold and greater than the second optical power threshold.

13. The method for determining repair information according to claim 1, characterized in that, The method further includes: If the sub-bit error rate of the faulty link segment meets the first preset condition, and a virtual connection alarm is detected in the optical module of the faulty link segment, the fourth repair information is determined to be the repair information of the faulty link segment.

14. The method for determining repair information according to claim 1, characterized in that, The method further includes: If the sub-bit error rate of the faulty link segment meets the first preset condition, and the temperature of the optical module of the faulty link segment is detected to be greater than the preset temperature threshold, the heat dissipation device is activated.

15. The method for determining repair information according to claim 1, characterized in that, The method further includes: If the sub-delay of the faulty link segment meets the second preset condition, the output optical power of the optical module of the faulty link segment is adjusted to be less than the first optical power threshold and greater than the second optical power threshold.

16. The method for determining repair information according to claim 1, characterized in that, The faulty link segment includes a first device and a second device; the method further includes: If the sub-delay of the faulty link segment meets the second preset condition, the network topology information of the service is obtained, and the network topology information includes the path information from the first device to the second device; Based on the path information, detour link segments that meet the fourth preset condition are identified, excluding the faulty link segments. Switch the service on the faulty link segment to the detour link segment.

17. A device for determining repair information, characterized in that, include: The acquisition module is used to acquire the network availability of services within a preset time period; The acquisition module is further configured to acquire service quality index data of the service during the preset time period when the network availability is less than a preset value, wherein the service quality index data includes at least one of optical power, bit error rate and latency. The identification module is used to identify faulty link segments based on the service quality indicator data; The detection module is used to detect the output optical power of the optical module in the faulty link segment and the optical cable attenuation in the optical cable in the faulty link segment, and to obtain the target detection result. The determination module is used to determine the target repair information corresponding to the target detection result as the repair information of the faulty link segment based on the relationship information between the preset detection result and the preset repair information.

18. An electronic device, characterized in that, The device includes: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, it implements the method for determining repair information as described in any one of claims 1-16.

19. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions, which, when executed by a processor, implement the method for determining repair information as described in any one of claims 1-16.

20. A computer program product, characterized in that, When the instructions in the computer program product are executed by the processor of the electronic device, the electronic device is able to perform the method for determining repair information as described in any one of claims 1-16.

Images