Optical module health state detection method and device, storage medium and program product

Abstract

The embodiment of the invention discloses an optical module health state detection method and device, a storage medium and a program product. The method comprises the following steps: extracting time sequence features from time sequence data of an optical module, and extracting key features from system log data of the optical module; fusing the time sequence features and the key features based on the constructed hybrid model, and generating fused features to obtain a current health degree score of the optical module; collecting a historical health degree score of the optical module in a preset time range; detecting at least one environmental parameter of the environment where the optical module is located; obtaining a dynamic threshold value of the optical module based on the historical health degree score and the environmental parameters; and judging the health state of the optical module based on the relationship between the current health degree score and the dynamic threshold. According to the method, the health state of the optical module can be comprehensively, accurately and efficiently evaluated based on multi-dimensional data features, powerful support is provided for operation and maintenance management of the optical module, and the method is of great significance in guaranteeing service continuity and reducing operation and maintenance cost.

Description

Technical Field

[0001] The present disclosure relates to the technical field of equipment safety detection, and in particular to an optical module health status detection method, device, storage medium and program product. Background Art

[0002] In the intelligent computing center, optical modules are key devices for photoelectric conversion and are widely used for high-speed, long-distance data transmission between servers, switches and storage devices. They are the core components for efficient operation of a 10,000-card cluster. A 10,000-card cluster usually contains tens of thousands of optical modules, and their stability and health are directly related to the performance and reliability of the entire system.

[0003] However, existing optical module monitoring methods mostly rely on single-dimensional parameters, such as optical power and temperature, and monitor and manage the status of optical modules through fixed threshold mechanisms and static models. Although this method can ensure the efficient operation and stability of the system to a certain extent, it cannot effectively deal with the sub-healthy state of the optical module. In the training scenario, the abnormality of the optical module may cause the unavailability of the entire Wanka cluster, while the sub-healthy state may reduce the availability of the cluster or cause abnormal performance output. Summary of the invention

[0004] In view of this, the embodiments of the present disclosure provide a method, device, storage medium and program product for detecting the health status of an optical module, which can comprehensively, accurately and efficiently evaluate the health status of the optical module based on multi-dimensional data features, provide strong support for the operation and maintenance management of the optical module, and are of great significance for ensuring business continuity and reducing operation and maintenance costs.

[0005] In a first aspect, an embodiment of the present disclosure provides a method for detecting the health status of an optical module, which adopts the following technical solution: Collect timing data and system log data of optical modules; Extracting time series features from the time series data, and extracting key features from the system log data; Constructing a hybrid model, and fusing the time series feature with the key feature based on the hybrid model to generate a fused feature; Acquire a current health score of the optical module based on the fusion feature; Collecting historical health scores of the optical module within a preset time range; Detecting at least one environmental parameter of the environment in which the optical module is located; Based on the historical health score and the environmental parameter, obtaining a dynamic threshold value of the optical module; Based on the relationship between the current health score and the dynamic threshold, the health status of the optical module is determined.

[0006] Optionally, extracting the time series features from the time series data includes: Obtaining the mean time between failures of the optical module; Determine the time window size based on the mean time between failures and the preset time; A sliding operation is performed on the time series data according to the time window size to extract time series features from the data in the window.

[0007] Optionally, extracting key features from the system log data includes: Traverse each log record in the system log data, and use the log_feature_extraction function to extract key features in each log record; The key features are stored in the feature dictionary in the form of key-value pairs.

[0008] Optionally, the fusing the time series feature with the key feature based on the hybrid model to generate a fused feature includes: Capturing the long-term dependencies in the temporal features through multi-layer dilated convolution operations to generate global features; Performing a pooling operation on the global features to generate an aggregated feature vector; Semantically encoding the key features to generate a coded feature sequence; Performing semantic information mining on the coding feature sequence to generate a comprehensive semantic feature vector; The aggregate feature vector and the comprehensive semantic feature vector are fused using a bidirectional cross attention mechanism to obtain the fused feature.

[0009] Optionally, acquiring the current health score of the optical module based on the fusion feature includes: Mapping the fused features into scalar values ​​through linear transformation; The scalar value is converted into a current health score in percentage through a Sigmoid activation function.

[0010] Optionally, the optical module health status detection method further includes: Deploy the initial hybrid model to the cloud server and each edge device as a global model and a local model respectively; Offline training is performed on the global model based on historical data, the trained global model parameters are synchronized to each edge device, and the local model is updated; When the edge device detects a new abnormality in the optical module, it collects abnormal data, uses the abnormal data to fine-tune the updated local model, and obtains an update gradient of the local model parameters; Upload the updated gradients of each edge device to the cloud server for aggregation to generate aggregated gradients; The global model is updated based on the aggregated gradient, the updated global model parameters are synchronized to each edge device, and the local model is updated again.

[0011] Optionally, the optical module health status detection method further includes: Score the historical health and construct a historical scoring data set in order of size; According to a preset percentile, a corresponding historical health score is selected from the historical score data set as a benchmark threshold, where the benchmark threshold is an initial dynamic threshold; If there is an environmental parameter that deviates from the corresponding reference parameter value, an adjustment coefficient is calculated based on the deviating environmental parameter; A new dynamic threshold is obtained based on the reference threshold and the adjustment coefficient.

[0012] Optionally, the calculation formula of the adjustment coefficient is: ; in, is the adjustment coefficient; Number the categories that deviate from environmental parameters; is the total number of deviations from environmental parameters; For the The weight of the deviation from the environmental parameters; For the An adjustment factor for deviations from environmental parameters; For the a deviation from the current measured value of the environmental parameter; For the Deviation from the baseline parameter value of the environmental parameter; For the A proportional factor that deviates from the environmental parameters.

[0013] In a second aspect, the embodiment of the present disclosure further provides an optical module health status detection system, which adopts the following technical solution: A data collection module, used to collect the timing data and system log data of the optical module; A feature extraction module, used to extract time series features from the time series data and to extract key features from the system log data; A feature fusion module, used for constructing a hybrid model, fusing the time series feature with the key feature based on the hybrid model to generate a fusion feature; A score acquisition module, used to acquire a current health score of the optical module based on the fusion feature; A score collection module, used to collect the historical health scores of the optical module within a preset time range; An environment detection module, used to detect at least one environmental parameter of the environment in which the optical module is located; A threshold acquisition module, used to acquire a dynamic threshold of the optical module based on the historical health score and the environmental parameter; The health judgment module is used to judge the health status of the optical module based on the relationship between the current health score and the dynamic threshold.

[0014] In a third aspect, the embodiments of the present disclosure further provide a computer device, which adopts the following technical solution: The computer device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any of the above-mentioned methods for detecting the health status of an optical module.

[0015] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to execute any of the above-mentioned optical module health status detection methods.

[0016] In a fifth aspect, an embodiment of the present disclosure further provides a computer program product, including a computer program / instruction, which implements the steps of any of the above methods when executed by a processor.

[0017] The optical module health status detection method provided by the embodiment of the present disclosure collects the time series data and system log data of the optical module at the same time, and can obtain the operation information of the optical module from multiple dimensions. This multi-source data collection method ensures comprehensive monitoring of the operation status of the optical module and avoids misjudgment caused by insufficient information from a single data source. Extracting time series features from time series data and extracting key features from system log data can deeply mine useful information in the data. This feature extraction process is actually to perform dimensionality reduction and statistical processing on the original data, remove a large amount of redundant information, and give statistical features in combination with partial information, so that subsequent analysis and processing are more efficient, which not only reduces the consumption of computing resources, but also speeds up the detection speed and improves the real-time performance of the system. Constructing a hybrid model to fuse the time series features and key features can give full play to the advantages of different types of features. Based on the fusion features, the current health score of the optical module is obtained, and the health status of the optical module is quantitatively represented. At the same time, a dynamic threshold judgment mechanism is adopted. The dynamic threshold is set for each optical module in combination with the historical health score of the optical module and the environmental parameters. The dynamic threshold is used to determine the health status of the optical module, which can be flexibly adjusted according to the actual operation of the optical module and environmental changes. This method can accurately determine the health status of the optical module and detect the sub-health status of the optical module in advance. Before the optical module fails seriously, preventive maintenance measures can be taken in time, thereby ensuring business continuity while reducing operation and maintenance costs.

[0018] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the following preferred embodiments are specifically cited and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 A flowchart of a method for detecting the health status of an optical module provided in an embodiment of the present disclosure; Figure 2 A flow chart of a method for acquiring time series features provided in an embodiment of the present disclosure; Figure 3 A flow chart of a method for fusing timing features and key features provided in an embodiment of the present disclosure; Figure 4A flowchart of a method for obtaining a current health score provided in an embodiment of the present disclosure; Figure 5 A flow chart of a hybrid model updating method provided in an embodiment of the present disclosure; Figure 6 A schematic diagram of a flow chart of a method for obtaining a dynamic threshold value provided in an embodiment of the present disclosure; Figure 7 A principle block diagram of an optical module health status detection system provided in an embodiment of the present disclosure; Figure 8 A schematic diagram of the structure of a computer device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0021] The embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0022] It should be clear that the following embodiments of the present disclosure are described by specific specific examples, and those skilled in the art can easily understand other advantages and effects of the present disclosure from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all of the embodiments. The present disclosure can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that the following embodiments and features in the embodiments can be combined with each other in the absence of conflict. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present disclosure.

[0023] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein may be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present disclosure, it should be understood by those skilled in the art that an aspect described herein may be implemented independently of any other aspect, and two or more of these aspects may be combined in various ways. For example, any number of aspects described herein may be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein may be used to implement this device and / or practice this method.

[0024] It should also be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present disclosure. The drawings only show components related to the present disclosure rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0025] Additionally, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, it will be understood by those skilled in the art that the aspects described may be practiced without these specific details.

[0026] Reference Figure 1 The present disclosure provides a method for detecting the health status of an optical module, comprising the following steps: S1: collects the timing data and system log data of the optical module; S2: Extract time series features from time series data and extract key features from system log data; S3: Build a hybrid model, fuse the time series features and key features based on the hybrid model, and generate fused features; S4: Obtain the current health score of the optical module based on the fusion feature; S5: collect historical health scores of optical modules within a preset time range; S6: Detect at least one environmental parameter of the environment in which the optical module is located; S7: Obtain the dynamic threshold of the optical module based on the historical health score and environmental parameters; S8: Based on the relationship between the current health score and the dynamic threshold, determine the health status of the optical module.

[0027] The optical module health status detection method provided by the present disclosure collects the timing data and system log data of the optical module at the same time, and can obtain the operation information of the optical module from multiple dimensions. The timing data reflects the dynamic changes of the optical module over a period of time, such as the fluctuation of optical power over time, the real-time change of temperature, etc.; the system log data records various events and abnormal information during the operation of the optical module, including error information, configuration changes, etc. This multi-source data collection method ensures comprehensive monitoring of the operating status of the optical module and avoids misjudgment caused by insufficient information from a single data source. Compared with the traditional method based on experience or simple parameter judgment, this method based on actual operation data can more accurately reflect the actual status of the optical module and reduce the interference of human factors and subjective judgment.

[0028] Extracting time series features from time series data and key features from system log data can deeply mine useful information in the data. Time series features can capture the dynamic characteristics of the operation of optical modules, such as periodicity and trend, while key features focus on important information in the system log, such as specific error codes, abnormal events, etc. This information plays a key role in judging the health status of optical modules. The process of extracting features is actually to reduce the dimension and perform statistical processing on the original data, remove a large amount of redundant information, and combine some information to give statistical features, making subsequent analysis and processing more efficient, which not only reduces the consumption of computing resources, but also speeds up the detection speed and improves the real-time performance of the system.

[0029] Constructing a hybrid model to fuse timing features and key features can give full play to the advantages of different types of features. Timing features reflect the dynamic changes of optical modules, while key features reflect abnormal conditions during system operation. Fusion of the two can more comprehensively and accurately describe the health status of optical modules. For example, combining the timing features of optical power and the key features of optical signal loss in the system log can more accurately determine whether the optical module has potential faults. Compared with single timing features or key features, fused features have stronger expressive power. They can capture the associations and interactions between different features, thereby providing richer and more valuable information for subsequent acquisition of the current health score, making the scoring results more accurate and reliable.

[0030] Based on the fusion features, the current health score of the optical module is obtained, and the health status of the optical module is quantified. This quantitative evaluation method makes the health status of the optical module more intuitive and clear, which is convenient for operation and maintenance personnel to manage and make decisions. At the same time, a dynamic threshold judgment mechanism is adopted. The dynamic threshold is set for each optical module in combination with the historical health score of the optical module and environmental parameters. The dynamic threshold is used to determine the health status of the optical module, which can be flexibly adjusted according to the actual operation of the optical module and environmental changes. Different optical modules may have different normal operation standards in different application scenarios. The dynamic threshold can better adapt to such differences, avoid the misjudgment that may be caused by the traditional fixed threshold method, and improve the accuracy and reliability of status judgment.

[0031] In summary, by accurately determining the health status of the optical module, the sub-health status of the optical module can be discovered in advance. Before a serious failure of the optical module occurs, preventive maintenance measures can be taken in a timely manner, such as replacing parts and debugging, to avoid the impact of the optical module failure on the business and ensure business continuity. At the same time, preventive maintenance can reduce operation and maintenance costs, reduce downtime and maintenance costs caused by optical module failures.

[0032] In S1, the timing data (also known as time series data) of the optical module is collected in real time through the digital optical monitoring (DOM) interface. The timing data refers to the operating parameters of the optical module recorded in time sequence. It is usually sampled and recorded at fixed time intervals (such as 1 second), reflecting the real-time status of the optical module at different time points. These data mainly include the digital diagnostic monitoring (DDM) parameters of the optical module, such as optical power, operating temperature and power supply voltage. Among them, the optical power includes the transmit power (Tx Power) and receive power (Rx Power) of the optical module, with an accuracy of ±0.1dBm, that is, the error range between the measured value and the true value does not exceed ±0.1 decibel milliwatt (dBm); the operating temperature refers to the internal temperature of the optical module, with an accuracy of ±0.5℃, that is, the error range between the measured value and the true temperature does not exceed ±0.5 degrees Celsius; the power supply voltage refers to the power supply voltage of the optical module, with an accuracy of ±1 millivolt (mV), that is, the error range between the measured value and the true voltage does not exceed ±1mV.

[0033] At the same time, use log collection tools such as Flume or Rsyslog or tail_logs function to collect system log data. System log data refers to the event records and related content generated by the optical module or its affiliated equipment during operation, which are usually generated by the equipment management system or monitoring software. These data not only record the operating status, fault alarm, configuration change and operation log of the optical module and its related equipment, but also cover multi-dimensional information such as performance indicators, resource utilization, user behavior, and security events.

[0034] Time series data is mainly used for performance monitoring and fault prediction, and potential problems can be discovered in advance by analyzing the trend of parameter changes. System log data is mainly used for troubleshooting and operation and maintenance management. By recording events and performance monitoring information, it provides detailed clues and operation history of the problem, helping to quickly locate the root cause of the problem. By combining time series data and system log data, key parameters such as voltage fluctuations and bit error rate gradient changes can be integrated, and events such as link oscillations and CRC error surges in the system log can be quantitatively modeled, thereby achieving comprehensive monitoring from the underlying hardware to the upper-layer application. It can not only monitor the operating status of the optical module in real time, but also supplement other key information of the optical module through the event information and performance indicators recorded in the log, thereby avoiding the difficulty of troubleshooting and fault response delays caused by a single monitoring dimension.

[0035] In S2, refer to Figure 2 The flowchart of the method for obtaining time series features is shown in the figure. "Extracting time series features from time series data" includes the following steps: S21: Obtain the mean time between failures of the optical module; S22: Determine the time window size based on the mean time between failures and the preset time; S23: Perform a sliding window operation on the time series data according to the time window size, and extract time series features from the data in the window.

[0036] In S21, the mean time between failures (MTBF) of the optical module can be obtained through the following methods: For common types of optical modules, the average data in the industry or the MTBF value of similar products can be directly referred to; the optical module manufacturer usually indicates the MTBF value of the optical module of this model in the product's technical manual or specification sheet, which can be directly referenced and obtained; if there are a large number of actual usage records of the optical module, the MTBF can be calculated by counting the number of failures of the optical module within a certain period of time. The specific method is to divide the total operating time by the number of failures to obtain the mean time between failures.

[0037] In S22, the MTBF of the optical module is compared with the preset time, and the maximum value of the two is selected as the time window size. This method comprehensively considers the needs of long-term reliability and short-term anomaly detection. When the MTBF is large, it means that the optical module itself is highly reliable, and using a larger time window can more comprehensively capture its long-term stable operation characteristics; when the MTBF is small, the preset time can prevent the time window from being too small and losing key trend information, thereby ensuring that the performance of the optical module can be effectively analyzed in different situations.

[0038] In S23, the sliding step size is set according to actual needs, and then the sliding operation is performed on the timing data of the optical module according to the determined time window size and sliding step size. The data in the window is extracted each time for feature extraction to obtain timing features. Timing features include statistical features and frequency domain features. Statistical features include the average, standard deviation (or variance), slope, skewness and kurtosis of various types of data in the window. Among them, the average value is used to measure the absolute level of the data in the time period; the standard deviation or variance is used to measure the fluctuation range of the data in the time period; the slope is calculated by fitting the linear trend of the data in the window, and the positive and negative slopes reflect the upward or downward trend of the data, respectively, reflecting the change trend of the recent data; skewness and kurtosis are used to reflect the distribution form of the data. The skewness measures the asymmetry of the data distribution, and the kurtosis measures the sharpness or flatness of the data distribution.

[0039] Frequency domain characteristics refer to the frequency domain representation of the key performance data of the optical module, covering the frequency domain characteristics of parameters such as the optical power, operating temperature, bias current and voltage fluctuation of the optical module, including the main frequency component and its amplitude, the proportion of signal energy in different frequency bands and the frequency peak characteristics. By performing a fast Fourier transform (FFT) on the data in the window, the main frequency component of the signal and its corresponding amplitude are obtained to capture the periodic changes in the data; the distribution of signal energy in different frequency bands after the FFT transformation is analyzed to understand the frequency component distribution of the data, that is, the proportion of signal energy in different frequency bands; focus on the significant peaks in the spectrum to identify the periodic oscillation of the optical module parameters. For example, if the optical power of the optical module has a significant peak in the spectrum, it may mean that there is a stable oscillation source.

[0040] The extracted timing features can capture different change patterns of optical module parameters, including short-term anomalies (such as sudden spikes), medium-term drifts (such as gradual attenuation), and long-term cycles (such as day and night environmental cycles), providing a basis for performance analysis and fault prediction of optical modules.

[0041] The system log data includes multiple log records. The key features are extracted from each log record using the log_feature_extraction function (a key feature extraction function). The key features include CRC (Cyclic Redundancy Check) error rate, LOS (Loss of Signal) duration, and reset trend. Among them, the CRC error rate refers to the frequency of errors caused by verification failure during data transmission; the LOS duration refers to the length of time the signal loss state lasts; and the reset trend refers to the frequency and pattern of device reset operations. The extracted key features are stored in the feature dictionary in the form of key-value pairs, where the key is the feature name (such as 'crc_error_rate', 'los_duration', 'reset_trend'), and the value is the corresponding feature value.

[0042] In S3, the hybrid model includes the TCN temporal network module, the Transformer encoding module, the cross-modal attention fusion module and the health score module. Through the effective combination of these modules, not only can the effective fusion of temporal features and key features be achieved, but also the health of the optical module can be evaluated and the corresponding health score can be generated. In the inference process, TensorRT can also be used to accelerate the optimization of the hybrid model, reduce the inference time, and improve the inference efficiency, so that the current health score can be obtained more quickly.

[0043] Reference Figure 3The flowchart of the method for fusing time series features and key features is shown. “Fusing time series features and key features based on a hybrid model to generate fused features” includes the following steps: S31: Capture long-term dependencies in temporal features through multi-layer dilated convolution operations to generate global features; S32: Performing pooling operation on the global features to generate an aggregated feature vector; S33: semantically encode the key features and generate a coded feature sequence; S34: perform semantic information mining on the coding feature sequence to generate a comprehensive semantic feature vector; S35: Use the bidirectional cross attention mechanism to fuse the aggregated feature vector and the comprehensive semantic feature vector to obtain the fused feature.

[0044] In S31 and S32, the TCN time series network module is used to process time series features. The module includes a first output layer, at least three layers of dilated convolutions with different dilation rates, and a global pooling layer. The first output layer is used to receive time series features as input and transmit them to the first layer of dilated convolutions. When processing time series data, the dilated convolution adopts the form of one-dimensional convolution (Conv1D). By introducing the dilation rate, the receptive field of the convolution kernel is expanded without increasing the number of parameters and the amount of calculation, thereby effectively capturing the dependencies in the time series data. Among them, the dilated convolution with a low dilation rate is used to capture short-term fluctuations in time series features (such as changes in seconds), extract local time series features, and reflect the rapid changes of data in a short time (such as within a few seconds); the dilated convolution with a medium dilation rate is used to extract medium-term trends in time series features (such as changes in minutes), and can capture the dynamic changes of data on a medium time scale; the dilated convolution with a high dilation rate is used to capture long-term dependencies in time series features (such as hour-level periodicity), and can identify the periodicity and long-term trends of data over a longer time span. For example, 4 layers of dilated convolution are set. The first layer of dilated convolution uses a convolution kernel with a dilation rate of 1 (i.e., dilation=1), which extracts local temporal features and outputs preliminary local feature representations; the second layer of dilated convolution uses a convolution kernel with a dilation rate of 2 (i.e., dilation=2), which expands the receptive field, captures features of longer time scales, and outputs feature representations of medium time scales; the third layer of dilated convolution uses a convolution kernel with a dilation rate of 4 (i.e., dilation=1), which further expands the receptive field, extracts a wider range of temporal dependencies, and outputs long-time feature representations; the fourth layer of dilated convolution uses a convolution kernel with a dilation rate of 8 (i.e., dilation=1), captures global temporal features through a larger dilation rate, and outputs global temporal feature representations, referred to as global features. The global pooling layer performs global pooling operations on global features, compresses feature dimensions, and generates compact aggregated feature vectors.

[0045] Through multi-layer dilated convolution operations, the TCN time series network module can not only effectively capture the multi-scale dependencies in time series data and enhance the model's perception of complex time series patterns, but also significantly expand the receptive field by increasing the dilation rate layer by layer (for example, exponential growth of 2). This structure enables TCN to capture long-term dependencies without significantly increasing the computational cost, thereby better handling long-distance time dependencies. In addition, the layer-by-layer increase of dilated convolutions also allows the model to achieve a larger receptive field in a shallower network structure, thereby maintaining efficient computing while avoiding the gradient vanishing problem caused by too many layers in traditional convolutional networks.

[0046] The global pooling operation further compresses the global features into aggregated feature vectors, reducing the feature dimension and improving the computational efficiency of the model. This compact feature representation not only provides high-quality timing features for subsequent feature fusion, but also enhances the model's ability to analyze the timing data of optical modules, which helps to more accurately evaluate the health status of optical modules. In addition, this TCN design also has the advantage of parallel computing, which can make full use of modern hardware acceleration capabilities and is suitable for large-scale data processing.

[0047] In S33 and S34, the Transformer encoding module is used to process key features. The module includes the second input layer, the token embedding layer, the position encoding layer, the multi-head attention layer, the feedforward network layer, and the feature vector layer. The second input layer receives the key features as input and transmits them to the token embedding layer. The token embedding layer uses the pre-trained BERT model to map each token (unit) in the key features to a feature vector of a preset dimension (e.g., 768 dimensions). The position encoding layer adds position information to the token embedding, retains the order of the sequence, and generates a feature vector with position information, i.e., the encoding feature sequence. The multi-head attention layer captures the dynamic association between tokens in the encoding feature sequence and extracts the complex relationship between features. The feedforward network layer introduces nonlinear transformation to further extract the abstract representation of features and increase the nonlinear representation ability of the model. The feature vector layer integrates the feature sequence processed by the multi-head attention and feedforward network to generate a comprehensive semantic feature vector.

[0048] In S35, the cross-modal attention fusion module is used to fuse the aggregated feature vector with the comprehensive semantic feature vector, and its structure includes an attention calculation layer, a residual connection layer, and a layer normalization layer. The attention calculation layer contains at least one set of bidirectional cross-attention sub-layers, each of which uses the aggregated feature vector and the comprehensive semantic feature vector as the query vector and the key-value vector. Specifically, on the one hand, the aggregated feature vector is used as the query vector and the comprehensive semantic feature vector is used as the key-value vector to calculate the "log features of temporal attention"; on the other hand, the comprehensive semantic feature vector is used as the query vector and the aggregated feature vector is used as the key-value vector to calculate the "temporal features of log attention". This two-way interaction mechanism is implemented through a multi-head attention mechanism, which can dynamically align and fuse the information of the two modalities from two directions, and finally splice or weighted sum the results of multiple sets of two-way interactions to generate spliced ​​features.

[0049] The concatenated features are further residually connected with the original input (aggregate feature vector and comprehensive semantic feature vector) through the residual connection layer to ensure direct information transmission. Subsequently, the result after the residual connection processing enters the layer normalization layer for normalization operation to stabilize the training process. The final fusion feature representation is a comprehensive vector containing time series and log information, which is used for subsequent health assessment.

[0050] This fusion method uses a bidirectional cross-attention mechanism to dynamically align the information of the two modalities to achieve information complementarity. At the same time, it combines a multi-head attention mechanism to enhance the richness and flexibility of feature representation. Residual connections and layer normalization improve the training stability of the model. These designs enable the fused feature vector to provide more comprehensive and accurate input for health assessment, thereby improving the model's ability to assess the health status of the optical module.

[0051] In S4, refer to Figure 4 The flowchart of the method for obtaining the current health score is shown in the figure. "Obtaining the current health score of the optical module based on the fusion feature" includes the following steps: S41: Mapping the fused features to scalar values ​​through linear transformation; S42: The scalar value is converted into a current health score in percentage through the Sigmoid activation function.

[0052] Specifically, the health score module is used to process the fusion features and generate the current health score (Health Index) of the optical module. The module includes a regression calculation layer and an activation mapping layer. Among them, the regression calculation layer can use a fully connected layer (such as nn.Linear) to map the input fusion features to a scalar value through a series of linear transformations. This scalar value reflects the "degree of deviation" of the optical module from the ideal health state. It is a continuous value. The higher the score, the more likely the optical module may have performance degradation or potential failures, and the lower the score, the normal operation of the module. In order to make the score more intuitive, the activation mapping layer uses the Sigmoid activation function to map the output of the regression calculation layer to the range of 0-1, and then multiply the mapped result by 100 to obtain the current health score in percentage.

[0053] Considering that the operating environment and data distribution of optical modules may evolve over time, and static models are difficult to adapt to the parameter differences of modules from multiple vendors, in order to keep the hybrid model valid for a long time, it is necessary to dynamically update the hybrid model. Figure 5 A flow chart of the hybrid model updating method is shown, wherein the method for training and dynamically updating the hybrid model comprises the following steps: S43: deploying the initial hybrid model to the cloud server and each edge device as a global model and a local model respectively; S44: Perform offline training on the global model based on historical data, synchronize the trained global model parameters to each edge device, and update the local model; S45: When the edge device detects a new abnormality in the optical module, it collects abnormal data, uses the abnormal data to fine-tune the updated local model, and obtains the update gradient of the local model parameters; S46: Upload the updated gradient of each edge device to the cloud server for aggregation to generate an aggregated gradient; S47: Update the global model based on the aggregated gradient, synchronize the updated global model parameters to each edge device, and update the local model again.

[0054] In S43, the initial hybrid model code and its parameters are transmitted to the cloud server and each edge device through the network, and the corresponding operating environment is configured on the cloud server and the edge device. A global model is built on the cloud server for centralized optimization and management; a local model is built on each edge device for real-time inference and local fine-tuning to ensure that the model can run normally in its respective environment.

[0055] In S44, the cloud server collects historical data (e.g., massive historical data of 50,000 optical modules from 10 data centers) and uses this data to perform offline training on the global model and optimize the model parameters. After the training is completed, the cloud server synchronizes the parameters of the global model to each edge device in the form of a binary file or through network transmission. After the edge device receives and loads these parameters, it updates the local model.

[0056] In S45-S47, online incremental update technology is used. When the edge device detects a new abnormal situation, relevant data is collected for the new abnormal situation, and the local model is fine-tuned with this data to improve the sensitivity of the local model to similar situations. Through this continuous learning, the local model can "keep pace with the times" and continuously improve the generalization performance and accuracy.

[0057] At the same time, during the fine-tuning process, the update gradient is calculated and uploaded to the cloud through a secure network channel. After the cloud server receives the update gradient uploaded by each edge device, it uses the aggregation algorithm of federated learning (such as the FedAvg algorithm) to aggregate the gradient and generate an aggregated gradient. The cloud server uses the aggregated gradient to update the global model and adjust the parameters of the global model to improve performance. Subsequently, the updated global model parameters are synchronized to each edge device. After receiving the parameters, the edge device updates the local model, completing a round of model update process.

[0058] By combining federated learning and incremental learning, the model can continuously learn new data and abnormal patterns, gradually adapt to new module batches, new environmental conditions, and potential new failure modes, thereby significantly improving the model's generalization performance and adaptability to different scenarios. This dynamic update mechanism not only improves the real-time and accuracy of the model, but also optimizes the performance of the global model through the Federated Average Algorithm (FedAvg), ensuring the stability and reliability of the system in the face of new challenges.

[0059] Furthermore, when a new module model or cross-manufacturer equipment is introduced, the existing hybrid model can be fine-tuned with a small amount of new data to quickly derive a new hybrid model that adapts to the new scenario. This transfer learning method does not require training from scratch, significantly reduces training time and computing resource requirements, and not only ensures that the solution can support device heterogeneity, but also enhances flexibility in practical applications.

[0060] At the same time, the model update process is automatically carried out in the background and will not interfere with the real-time monitoring of the foreground. Through version management and sufficient testing, it can be ensured that the performance of the updated model does not deteriorate, and it can be rolled back to the previous version if necessary. As time goes by, the system accumulates more and more knowledge, and the hybrid model's ability to distinguish the sub-health status of optical modules will gradually improve.

[0061] In S5-S8, when the current health score is greater than the dynamic threshold, the optical module is determined to be sub-healthy; when the current health score is not greater than the dynamic threshold, the optical module is determined to be healthy.

[0062] The traditional fixed threshold mechanism is not sensitive to the detection of progressive degradation and lacks timely and effective detection means. Therefore, the optical module health status detection method disclosed in the present invention introduces an adaptive threshold mechanism to adjust the alarm threshold of the current health score according to historical statistics and environmental changes. Figure 6 The flowchart of the dynamic threshold acquisition method shown in the figure, "Acquiring the dynamic threshold of the optical module based on the historical health score and environmental parameters" includes the following steps: S71: Score the historical health and construct a historical score data set in order of size; S72: According to a preset percentile, a corresponding historical health score is selected from the historical score data set as a benchmark threshold, where the benchmark threshold is an initial dynamic threshold; S73: If there is an environmental parameter that deviates from the corresponding reference parameter value, calculating an adjustment coefficient based on the deviated environmental parameter; S74: Obtain a new dynamic threshold based on the reference threshold and the adjustment coefficient.

[0063] In S71, the system continuously maintains the historical distribution of health scores within a preset time range (e.g., 7 days), that is, the collected historical health scores are sorted in order from small to large or from large to small, and the sorted historical health scores are combined into a historical score data set.

[0064] In S72, if the collected historical health scores are sorted in order from small to large, the percentile is the N% percentile, and if the collected historical health scores are sorted in order from large to small, the percentile is the (100-N)% percentile. In this way, it means that under normal circumstances, only N% of the time, the historical health score will exceed this value, N can be 90, and through the method, the baseline threshold obtained for the first time is the initial dynamic threshold (Threshold).

[0065] In S73 and S74, at least one environmental parameter is collected in real time through a sensor network deployed in the environment where the optical module is located. These parameters include at least one of the equipment load rate, power supply voltage stability value, computer room temperature, computer room humidity, fan speed, and power supply status value. Among them, the power supply voltage stability value is the result of a quantitative evaluation of the power supply voltage stability, and the power supply status value is the result of a quantitative evaluation of the power supply status. The benchmark parameter value of each environmental parameter is pre-set. For example, for the rack temperature, its benchmark parameter value is set to 25°C, and for the computer room humidity, its benchmark parameter value is set to 50%. After the environmental parameters are collected, they are compared with the corresponding benchmark parameter values. If the two are inconsistent, it indicates that the environmental parameters have deviated; if they are consistent, it indicates that the environmental parameters have not deviated.

[0066] When it is detected that the environmental parameters deviate from their baseline values, the dynamic threshold update task is triggered. At this time, the adjustment coefficient is calculated based on the deviated environmental parameters, and the adjustment coefficient is multiplied by the baseline threshold. The product is the new dynamic threshold. In the next round of environmental detection, if new environmental parameter deviations are found and the historical scoring data set has been updated, a new baseline threshold is selected from the new historical scoring data set, and the dynamic threshold is recalculated accordingly. The calculation formula for the adjustment coefficient is: ; In the formula, is the adjustment factor; Number the categories of deviations from environmental parameters; is the total number of deviations from environmental parameters; For the The weight of the deviating environmental parameter. The sum of the weights of all environmental parameters (regardless of whether deviation occurs) should be equal to 1. When a certain environmental parameter does not deviate, it is 0 after deducting the corresponding baseline parameter value, and it does not need to participate in the calculation of the adjustment coefficient. For the An adjustment factor for deviation from environmental parameters, which is used to control the sensitivity of the deviation from environmental parameters to the dynamic threshold, such as 0.05 for rack temperature and 0.03 for room humidity; For the a deviation from the current measured value of the environmental parameter; For the Deviation from the baseline parameter value of the environmental parameter; For the A scaling factor for deviations from environmental parameters is used to normalize the deviation, such as 10°C for rack temperature and 20% for room humidity.

[0067] By introducing a dynamic threshold update mechanism, the system can flexibly adjust the threshold according to different operating conditions. For example, in a high temperature and high load environment, the health of the optical module may deviate slightly from the normal range. At this time, the threshold is increased to avoid false alarms. Under good cooling and idle business conditions, even minor anomalies are worthy of attention. At this time, the threshold is lowered to increase sensitivity. The dynamic threshold is regularly recalculated and updated based on new data to ensure that the alarm criteria are always consistent with the latest historical distribution of health scores and environmental conditions. This mechanism overcomes the defect that fixed thresholds are insensitive to progressive degradation, and can detect signs of health decline earlier, while reducing the false alarm rate caused by environmental fluctuations.

[0068] Binary alarms can be realized through dynamic thresholds and current health scores. When the optical module is determined to be in a sub-healthy state, a maintenance work order is generated based on the detection results to arrange professional technicians to conduct targeted inspections on the optical module, troubleshoot potential faults, and assess whether maintenance operations such as component replacement, cleaning, or performance optimization are needed to ensure that the optical module can be restored to a healthy and stable working state as soon as possible, reducing the risk of failure of the entire system due to degradation of optical module performance.

[0069] When the optical module is judged to be in a healthy state, new time series data and system log data are collected for a new round of detection. At the same time, the dynamic threshold is maintained to keep the timeliness, accuracy and adaptability of the dynamic threshold. That is, the dynamic threshold is continuously updated and adjusted according to the newly collected data, so that it can accurately reflect the normal performance range of the optical module under different operating conditions and working stages, so as to more sensitively and accurately identify the state changes of the optical module and improve the reliability and effectiveness of the alarm.

[0070] Optionally, the health scores of all monitored optical modules are sorted and displayed from high to low, so that operation and maintenance personnel can give priority to high-risk modules. This is a horizontal display. At the same time, for each optical module, the change trend of its health score is displayed in chronological order, so as to observe the speed of health deterioration of a single module. This is a vertical display. The horizontal display method and the vertical display method can be organically combined and presented in the same chart, so that operation and maintenance personnel can comprehensively and intuitively compare the differences and connections between the horizontal and vertical dimensions of the data.

[0071] In summary, this solution maximizes the value of data by monitoring the multi-dimensional data of optical modules and using corresponding methods to mine features for different types of data. At the same time, this also facilitates the hybrid model to process and analyze data more efficiently. The hybrid model can be dynamically updated to accurately identify potential problems and failure trends of optical modules, allowing operation and maintenance personnel to take preventive maintenance measures in advance, greatly reducing operation and maintenance costs. Preventive maintenance measures can effectively ensure business continuity and avoid economic losses caused by optical module failures. From data monitoring to visual display, the entire process forms a complete and efficient closed loop, providing a solid guarantee for the stable operation of optical modules and the continued development of business.

[0072] Reference Figure 7 The present disclosure provides an optical module health status detection system, comprising: The data collection module 101 is used to collect the timing data and system log data of the optical module; A feature extraction module 102 is used to extract time series features from time series data and key features from system log data; The feature fusion module 103 is used to build a hybrid model, fuse the time series features with the key features based on the hybrid model, and generate fusion features; A score acquisition module 104, used to acquire a current health score of the optical module based on the fusion feature; The score collection module 105 is used to collect the historical health scores of the optical modules within a preset time range; An environment detection module 106, used to detect at least one environmental parameter of the environment in which the optical module is located; A threshold acquisition module 107, used to acquire a dynamic threshold of the optical module based on the historical health score and environmental parameters; The health determination module 108 is used to determine the health status of the optical module based on the relationship between the current health score and the dynamic threshold.

[0073] The various variations and specific examples of the optical module health status detection method provided above are also applicable to the optical module health status detection system provided in the present disclosure. Through the above detailed description of the optical module health status detection method, those skilled in the art can clearly know the implementation method of the optical module health status detection system. For the sake of brevity of the specification, it will not be described in detail here.

[0074] The computer device according to the embodiment of the present disclosure includes a memory and a processor. The memory is used to store non-temporary computer-readable instructions. Specifically, the memory may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The non-volatile memory may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc.

[0075] The processor may be a central processing unit (CPU) or other forms of processing units with data processing capabilities and / or instruction execution capabilities, and may control other components in the computer device to perform desired functions. In one embodiment of the present disclosure, the processor is used to run the computer-readable instructions stored in the memory, so that the computer device performs all or part of the steps of the optical module health status detection method of each embodiment of the present disclosure.

[0076] Those skilled in the art should be able to understand that in order to solve the technical problem of how to obtain a good user experience, the present embodiment may also include well-known structures such as a communication bus and an interface, and these well-known structures should also be included in the protection scope of the present disclosure.

[0077] like Figure 8 A schematic diagram of the structure of a computer device provided in an embodiment of the present disclosure is shown, which is a schematic diagram of the structure of a computer device suitable for implementing the embodiment of the present disclosure. Figure 8 The computer device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0078] like Figure 8 As shown, the computer device may include a processor (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) or a program loaded from a storage device into a random access memory (RAM). In the RAM, various programs and data required for the operation of the computer device are also stored. The processor, ROM, and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.

[0079] Typically, the following devices can be connected to the I / O interface: input devices such as sensors or visual information acquisition devices; output devices such as display screens; storage devices such as tapes, hard disks, etc.; and communication devices. The communication device can allow the computer device to communicate with other devices (such as edge computing devices) wirelessly or by wire to exchange data. Figure 8A computer device having various devices is shown, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead.

[0080] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device, or installed from a ROM. When the computer program is executed by a processor, all or part of the steps of the optical module health status detection method of the embodiment of the present disclosure are executed.

[0081] For detailed description of this embodiment, reference may be made to the corresponding descriptions in the aforementioned embodiments, which will not be repeated here.

[0082] The computer-readable storage medium according to the embodiment of the present disclosure stores non-transitory computer-readable instructions, and when the non-transitory computer-readable instructions are executed by a processor, all or part of the steps of the optical module health status detection method of each embodiment of the present disclosure are executed.

[0083] The above-mentioned computer-readable storage media include, but are not limited to: optical storage media (e.g., CD-ROM and DVD), magneto-optical storage media (e.g., MO), magnetic storage media (e.g., magnetic tape or mobile hard disk), media with built-in rewritable non-volatile memory (e.g., memory card) and media with built-in ROM (e.g., ROM box).

[0084] For detailed description of this embodiment, reference may be made to the corresponding descriptions in the aforementioned embodiments, which will not be repeated here.

[0085] The basic principles of the present disclosure are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present disclosure are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present disclosure. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, and are not limitations. The above details do not limit the present disclosure to the necessity of adopting the above specific details to be implemented.

[0086] In the present disclosure, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. The block diagrams of the devices, devices, equipment, and systems involved in the present disclosure are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, devices, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The words "such as" used here refer to the phrase "such as but not limited to", and can be used interchangeably with them.

[0087] Additionally, as used herein, "or" used in a list of items beginning with "at least one" indicates a separate list, so that, for example, a list of "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word "exemplary" does not mean that the example described is preferred or better than other examples.

[0088] It should also be noted that in the system and method of the present disclosure, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present disclosure.

[0089] Various changes, substitutions, and modifications of the techniques described herein may be made without departing from the teachings defined by the appended claims. Furthermore, the scope of the claims of the present disclosure is not limited to the specific aspects of the processes, machines, manufactures, compositions of events, means, methods, and actions described above. Currently existing or later to be developed processes, machines, manufactures, compositions of events, means, methods, or actions that perform substantially the same functions or achieve substantially the same results as the corresponding aspects described herein may be utilized. Thus, the appended claims include such processes, machines, manufactures, compositions of events, means, methods, or actions within their scope.

[0090] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0091] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A method for detecting the health status of an optical module, characterized in that: include: Collect timing data and system log data of optical modules; Extracting time series features from the time series data, and extracting key features from the system log data; Constructing a hybrid model, and fusing the time series feature with the key feature based on the hybrid model to generate a fused feature; Acquire a current health score of the optical module based on the fusion feature; Collecting historical health scores of the optical module within a preset time range; Detecting at least one environmental parameter of the environment in which the optical module is located; Based on the historical health score and the environmental parameter, obtaining a dynamic threshold value of the optical module; Based on the relationship between the current health score and the dynamic threshold, the health status of the optical module is determined.

2. The optical module health status detection method according to claim 1, characterized in that: The extracting the time series features from the time series data includes: Obtaining the mean time between failures of the optical module; Determine the time window size based on the mean time between failures and the preset time; A sliding operation is performed on the time series data according to the time window size to extract time series features from the data in the window.

3. The optical module health status detection method according to claim 1, characterized in that: The extracting key features from the system log data includes: Traverse each log record in the system log data, and use the log_feature_extraction function to extract key features in each log record; The key features are stored in the feature dictionary in the form of key-value pairs.

4. According to any one of claims 1 to 3, the step of fusing the timing feature with the key feature based on the hybrid model to generate a fusion feature comprises: Capturing the long-term dependencies in the temporal features through multi-layer dilated convolution operations to generate global features; Performing a pooling operation on the global features to generate an aggregated feature vector; Semantically encoding the key features to generate a coded feature sequence; Performing semantic information mining on the coding feature sequence to generate a comprehensive semantic feature vector; The aggregate feature vector and the comprehensive semantic feature vector are fused using a bidirectional cross attention mechanism to obtain the fused feature.

5. According to the optical module health status detection method of claim 4, the step of obtaining the current health score of the optical module based on the fusion feature comprises: Mapping the fused features into scalar values ​​through linear transformation; The scalar value is converted into a current health score in percentage through a Sigmoid activation function.

6. The optical module health status detection method according to claim 1, further comprising: Deploy the initial hybrid model to the cloud server and each edge device as a global model and a local model respectively; Offline training is performed on the global model based on historical data, the trained global model parameters are synchronized to each edge device, and the local model is updated; When the edge device detects a new abnormality in the optical module, it collects abnormal data, uses the abnormal data to fine-tune the updated local model, and obtains an update gradient of the local model parameters; Upload the updated gradients of each edge device to the cloud server for aggregation to generate aggregated gradients; The global model is updated based on the aggregated gradient, the updated global model parameters are synchronized to each edge device, and the local model is updated again.

7. The optical module health status detection method according to claim 1, wherein the obtaining the dynamic threshold of the optical module based on the historical health score and the environmental parameter comprises: Score the historical health and construct a historical scoring data set in order of size; According to a preset percentile, a corresponding historical health score is selected from the historical score data set as a benchmark threshold, where the benchmark threshold is an initial dynamic threshold; If there is an environmental parameter that deviates from the corresponding reference parameter value, an adjustment coefficient is calculated based on the deviating environmental parameter; A new dynamic threshold is obtained based on the reference threshold and the adjustment coefficient.

8. According to the optical module health status detection method of claim 7, the calculation formula of the adjustment coefficient is: ； in, is the adjustment coefficient; Number the categories that deviate from environmental parameters; is the total number of deviations from environmental parameters; For the The weight of the deviation from the environmental parameters; For the An adjustment factor for deviations from environmental parameters; For the a deviation from the current measured value of the environmental parameter; For the Deviation from the baseline parameter value of the environmental parameter; For the A proportional factor that deviates from the environmental parameters.

9. A computer device, characterized in that: The computer device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the optical module health status detection method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the optical module health status detection method according to any one of claims 1 to 8.

11. A computer program product comprising computer instructions, characterized in that: When the computer instruction is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images