Wavelength division multiplexer chip post-processing management system, device and medium

Abstract

The invention discloses a wavelength division multiplexer chip post-processing management system and device and a medium, and relates to the technical field of processing management, and the method comprises the steps: carrying out the application scene collection of a wavelength division multiplexer chip, and building an application scene set; utilizing the application scene set to configure a performance test scheme, establishing a performance test scheme set, executing a wavelength division multiplexer chip test, and recording test data; after the performance key indexes are configured, the mapping weak recognizer is activated to execute independent key index anomaly recognition of the test data, and a first test result is established; performing feature extraction on the test data, establishing a global feature vector, and inputting the global feature vector as input data into a global evaluation channel to establish a second test result; and after the first test result and the second test result are fused, post-processing quality abnormity is generated. The technical problem that in the prior art, performance abnormity in the post-processing process of the chip cannot be accurately recognized is solved, and the technical effect of improving the accuracy and efficiency of abnormity discovery in the post-processing stage of the chip is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of processing management, and in particular to a wavelength division multiplexer chip post-processing management system, device and medium. Background Art

[0002] After completing front-end manufacturing, wavelength division multiplexer chips undergo post-processing to verify their performance stability under actual application conditions. However, in traditional testing processes, test plans often fail to dynamically adjust to the specific chip application scenarios, resulting in insufficient test coverage and difficulty promptly identifying potential anomalies in key performance indicators. Furthermore, existing test results are often fragmented and lack a unified analysis and identification mechanism, making it difficult to effectively identify and respond to anomalies, thus hindering quality control capabilities during the chip post-processing stage. Summary of the Invention

[0003] The present application provides a wavelength division multiplexer chip post-processing management system, device and medium, which are used to solve the technical problem that the existing technology cannot accurately identify performance anomalies during chip post-processing.

[0004] In view of the above problems, the present application provides a wavelength division multiplexer chip post-processing management system, device and medium.

[0005] In a first aspect of the present application, a wavelength division multiplexer chip post-processing management system is provided, the system comprising: A scenario construction module is used to collect application scenarios for the wavelength division multiplexer chip and establish an application scenario set, wherein the application scenario set is provided with a scenario trust identifier; a test plan establishment module is used to configure a performance test plan using the application scenario set and establish a performance test plan set; a test module is used to perform wavelength division multiplexer chip testing using the performance test plan set and record test data, wherein the test data includes performance data and environmental data; an independent response module is used to activate the mapping weak identifier based on the performance key indicators after configuring the performance key indicators and perform independent key indicator anomaly identification of the test data to establish a first test result; a global response module is used to extract features from the test data, establish a global feature vector, and input the global feature vector as input data into the global evaluation channel to establish a second test result; a reporting module is used to generate a post-processing quality anomaly after fusing the first test result and the second test result.

[0006] According to a second aspect of an embodiment of the present application, an electronic device is provided, comprising: a memory for storing executable instructions; and a processor for implementing the wavelength division multiplexer chip post-processing management system provided by the present application when executing the executable instructions stored in the memory.

[0007] According to a third aspect of the embodiments of the present application, a computer-readable storage medium is provided, which stores a computer program. When the program is executed by a processor, the wavelength division multiplexer chip post-processing management system provided by the present application is implemented.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages: The present application collects application scenarios for wavelength division multiplexer chips and establishes an application scenario set, wherein the application scenario set is provided with a scenario trust identifier; configures a performance test scheme using the application scenario set and establishes a performance test scheme set; uses the performance test scheme set to perform wavelength division multiplexer chip testing and records test data, wherein the test data includes performance data and environmental data; after configuring the key performance indicators, activates the mapping weak identifier based on the key performance indicators to perform independent key indicator anomaly identification of the test data and establishes a first test result; performs feature extraction on the test data and establishes a global feature vector, uses the global feature vector as input data, inputs it into the global evaluation channel, and establishes a second test result; after fusing the first test result and the second test result, generates a post-processing quality anomaly. The present invention solves the technical problem that the prior art cannot accurately identify performance anomalies in the chip post-processing process, and achieves the technical effect of improving the accuracy and efficiency of anomaly detection in the chip post-processing stage by establishing a multi-level testing mechanism and fusing the test results for anomaly identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0010] Figure 1 A schematic diagram of the structure of a wavelength division multiplexer chip post-processing management system provided in an embodiment of the present application; Figure 2 This is a schematic diagram of the structure of an exemplary electronic device of the present application.

[0011] Explanation of the accompanying drawings: scenario construction module 11, test plan establishment module 12, test module 13, independent response module 14, global response module 15, reporting module 16, bus 300, receiver 301, processor 302, transmitter 303, memory 304, bus interface 305. DETAILED DESCRIPTION

[0012] This application provides a wavelength division multiplexer chip post-processing management system, device and medium to solve the technical problem that the existing technology cannot accurately identify performance anomalies in the chip post-processing process. By establishing a multi-level testing mechanism and integrating test results for anomaly identification, the accuracy and efficiency of anomaly detection in the chip post-processing stage are improved.

[0013] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only some of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0014] It should be noted that any variations of the terms "include" and "have" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices.

[0015] Example 1, as Figure 1 As shown, the present application provides a wavelength division multiplexer chip post-processing management system, the system comprising: The scenario construction module 11 is used to collect application scenarios of the wavelength division multiplexer chip and establish an application scenario set, wherein the application scenario set is provided with a scenario trust identifier.

[0016] In this embodiment of the present application, scenario construction module 11 collects operational data from the wavelength division multiplexer chip under different operating conditions to construct an application dataset containing multi-dimensional parameters. It then performs similarity cluster analysis on this dataset to identify representative application scenarios. Based on this, the module then identifies each scenario based on its frequency of occurrence and its importance in performance evaluation, ultimately generating a scenario trust identifier for subsequent testing.

[0017] Furthermore, in the system provided by the embodiment of the application, the scene construction module 11 further includes: A data acquisition module is used to read the application scenarios of the wavelength division multiplexer chip and establish an application data set; a clustering module is used to perform scenario similarity clustering on the application data set, perform scenario segmentation based on the scenario similarity clustering results, and establish an application scenario set; a dual-channel trust identification module is used to perform dual-channel identification of frequency trust and importance trust on the application data set in the application scenario set to generate a scenario trust identification.

[0018] In this embodiment of the present application, the data acquisition module uses an embedded sensor acquisition method to acquire real-time environmental parameters and performance indicators of the wavelength division multiplexer chip under different operating conditions. This acquisition includes key information such as temperature, voltage, optical power, bit error rate, and communication load, and is aggregated to the data processing end via a transmission interface. The collected data is standardized and formatted to create a structured application dataset containing a complete operational status record. This step results in an application dataset encompassing multidimensional status information.

[0019] Next, the clustering module classifies the feature vectors extracted from the application dataset using the K-means clustering method. Feature vectors include chip performance parameters and environmental condition indicators, and their similarity is measured by calculating the Euclidean distance between the data. Through multiple rounds of clustering iterations, data points are grouped into the closest cluster centers, ultimately forming multiple data clusters representing typical operating states. Based on the clustering results, scenario semantics are divided to clarify the actual application environment corresponding to each data cluster, and a set of application scenarios is established accordingly.

[0020] Finally, the dual-channel trust identification module uses two methods to identify frequency trust and importance trust, respectively. First, a statistical analysis is performed on the number of times each application scenario appears in historical data. Frequency statistics within a time interval are used to calculate the frequency of each scenario, reflecting its representativeness in real-world applications. Second, an association analysis method based on the Apriori algorithm is used to analyze the regular relationship between the scenario and known anomaly detection results. Scenario-anomaly correspondence rules with high confidence are extracted to assess the impact of the scenario in performance testing and generate the scenario's importance. Finally, the frequency and importance results are combined to form a scenario trust identification.

[0021] The test plan establishing module 12 is used to configure a performance test plan using the application scenario set and establish a performance test plan set.

[0022] In an embodiment of the present application, the test solution establishment module 12 is used to configure a corresponding performance test solution for the wavelength division multiplexer chip based on the constructed application scenario set, thereby forming a more targeted performance test solution set. The test solution establishment module 12 first extracts the environmental parameters (such as temperature, voltage, transmission rate) and performance requirements (such as insertion loss, return loss, and channel isolation) contained in each application scenario, and constructs a scenario feature vector. A configuration method based on rule matching is adopted to call a preset test solution template library. By comparing the scenario characteristics with the template conditions, a test task list that meets the scenario is automatically selected or combined, including test content, test conditions, test steps, and evaluation criteria. This process ensures that each application scenario can obtain a test strategy that is highly matched with its characteristics, and realizes the adaptive generation of test solutions driven by the scenario. Ultimately, through this step, a performance test solution set covering various actual application situations is obtained.

[0023] The testing module 13 is configured to execute a wavelength division multiplexer chip test using the performance testing solution set and record test data, wherein the test data includes performance data and environment data.

[0024] In this embodiment of the present application, the testing module 13 is used to perform actual testing of the wavelength division multiplexer chip according to a set of performance test plans and collect key data generated during the testing process. First, the corresponding test equipment, including a tunable laser, optical power meter, spectrum analyzer, and environmental control device, is called up according to the test conditions preset in each performance test plan (such as operating wavelength, input optical power, and temperature control range). Equipment parameter configuration is completed through an automatic control interface. The testing module 13 then performs various functional and performance measurement operations according to the process specified in the test plan. These operations cover multiple key performance indicators, including insertion loss, channel isolation, center wavelength drift, and return loss. The module also monitors and records test environment parameters in real time, such as temperature changes, voltage levels, and humidity conditions during the test. During the test process, all collected data is stored in a standard format and categorized and labeled according to the two dimensions of performance data and environmental data. This process results in structured test data containing complete performance and environmental data.

[0025] The independent response module 14 is configured to, after configuring the performance key indicators, activate the mapped weak identifier based on the performance key indicators to perform independent key indicator anomaly identification of the test data and establish a first test result.

[0026] In an embodiment of the present application, after configuring the key performance indicators, the independent response module 14 activates the corresponding mapped weak identifier based on each indicator, and performs item-by-item abnormality identification on the test data of the wavelength division multiplexer chip. First, by constructing an adaptation evaluation function that includes evaluation features such as recognition accuracy, complexity, adaptability, stability and fault tolerance, the fitness analysis of the weak identifier is performed to establish its evaluation result in the current application scenario. Subsequently, based on the evaluation results, enhanced attention is generated to guide the weak identifier to perform enhanced learning, thereby improving its recognition ability for specific key performance indicators. Finally, the enhanced weak identifier independently identifies each key indicator and obtains a first test result that reflects the abnormality of the local performance of the chip. The first test result identifies a set of performance indicators with abnormalities.

[0027] Furthermore, in the system provided by the embodiment of the application, the independent response module 14 further includes: The evaluation submodule is used to establish an adaptive evaluation function for the weak identifier, and the evaluation characteristics of the adaptive evaluation function include recognition accuracy characteristics, identifier complexity characteristics, adaptability characteristics, stability characteristics, and fault tolerance characteristics; the evaluation submodule is used to use the adaptive evaluation function to evaluate the fitness of the weak identifier and establish a fitness evaluation result; the enhancement submodule is used to use the fitness evaluation result to generate enhanced attention, and after the enhanced attention is used to enhance the learning of the weak identifier, perform abnormal identification of independent key indicators.

[0028] In an embodiment of the present application, the evaluation submodule is used to establish an adaptation evaluation function of a weak identifier, which is used to evaluate the comprehensive adaptability of different weak identifiers under multidimensional performance indicators. A weak identifier refers to a lightweight discriminant model for identifying abnormalities in specific performance key indicators. It is characterized by a simple structure, fast training, and is suitable for processing single or local recognition tasks. A plurality of weak identifiers are pre-configured, and each weak identifier can be constructed by methods such as threshold judgment, logical rule matching, and simple conditional classification, which are derived from historical test data training or empirical rules set by domain experts. In order to perform comprehensive performance evaluation on these weak identifiers, an adaptation evaluation function is constructed. The function is a linear weighted function composed of five evaluation features, namely, recognition accuracy feature, identifier complexity feature, adaptability feature, stability feature, and fault tolerance feature. The recognition accuracy feature is obtained by calculating the correct rate of the recognizer in labeled samples; the recognizer complexity feature is determined by evaluating the number of layers or steps in its internal judgment logic; the adaptability feature uses cross-validation to observe the consistency of the recognizer's output in different application scenarios; the stability feature is characterized by adding small perturbations to the input data, performing multiple recognitions, and comparing the output changes; the fault tolerance feature is tested by constructing samples with missing input fields to test its recognition ability in the presence of incomplete information. These features are normalized and input into a weighting function to form an adaptive scoring function for subsequent evaluation. The weight of each feature is pre-set by technical experts.

[0029] The evaluation submodule then uses the adaptation evaluation function to evaluate multiple candidate weak recognizers to form a unified fitness evaluation result. Specifically, the test data is input into each weak recognizer, and its performance in five dimensions, namely recognition accuracy, recognizer complexity, adaptability, stability, and fault tolerance, is extracted step by step. The score of each feature is calculated in turn and input into the adaptation evaluation function to complete the scoring process. The fitness score of each weak recognizer is an evaluation of the comprehensive recognition ability of the recognizer in a specific scenario. The scoring results of all weak recognizers are summarized to establish a structured fitness evaluation result.

[0030] Finally, the enhancement submodule selects weak recognizers with lower fitness scores based on the aforementioned fitness evaluation results and performs enhancement processing to improve their recognition capabilities on the target performance indicators. The enhancement process first extracts samples that the weak recognizer misjudged during the recognition process and samples near the recognition boundary to construct an enhanced focus sample set. This sample set has highly representative and difficult features, which can better highlight the shortcomings of the recognizer in boundary judgment. Subsequently, a sample retraining method is adopted, using this enhanced focus sample set as input to perform local training and update of the weak recognizer, such as adjusting the judgment rules and correcting the threshold settings in the recognition logic, thereby enhancing its recognition ability for key abnormal features. The enhanced weak recognizer is redeployed to the recognition process and performs anomaly recognition tasks in sequence for the configured key performance indicators. Each recognizer independently outputs a recognition result, indicating whether the corresponding indicator has an anomaly. All recognition results are summarized and the first test result is finally established.

[0031] The global response module 15 is configured to extract features from the test data, establish a global feature vector, and use the global feature vector as input data to input into a global evaluation channel to establish a second test result.

[0032] In this embodiment of the present application, the global response module 15 is used to perform a holistic analysis of test data and identify global performance anomalies in the wavelength division multiplexer chip during post-processing. First, a feature extraction operation is performed on the test data, extracting key statistics such as mean, fluctuation amplitude, and anomaly frequency from performance and environmental data to construct a unified global feature vector that comprehensively describes the chip's state characteristics across all test dimensions. This global feature vector is then input into a global evaluation channel for comprehensive evaluation. The global evaluation channel is initially established by aggregating historical test samples and corresponding results. A simple sample comparison and deviation threshold setting method are used to construct initial evaluation rules to determine the degree of deviation between current features and normal samples. To further improve the accuracy and adaptability of the global evaluation channel, the self-evaluation module performs training data backtracking on it to identify recognition biases in historical judgments, thereby identifying training data backtracking defects. Based on these defects, the optimization module generates new data requirements and encrypts them with the current global evaluation channel before sending them to the trusted three parties, completing federated encrypted learning while ensuring data privacy. The trusted three parties return an updated global evaluation channel with enhanced generalization and discrimination accuracy. Finally, the current global feature vector is evaluated based on the returned global evaluation channel to establish a second test result, which clearly identifies the set of performance indicators with abnormalities, namely, abnormal indicators.

[0033] Furthermore, in the system provided by the embodiment of the application, the global response module 15 further includes: The self-evaluation module is used to perform training data backtracking on the global evaluation channel and establish training data backtracking defects. The optimization module is used to generate data requirements based on the training data backtracking defects, encrypt the data requirements and the global evaluation channel, and send them to the trusted three parties, and receive the returned global evaluation channel from the trusted three parties. The returned global evaluation channel is the channel after federated encrypted learning, and the global evaluation channel is returned to perform global evaluation.

[0034] In an embodiment of the present application, the self-evaluation module is used to perform training data backtracking on the global evaluation channel to identify its recognition defects in historical tests. Specifically, first, the historical test data and the corresponding true annotation results are called, and they are compared one by one with the historical recognition results output by the global evaluation channel. The self-evaluation module adopts the error matrix statistical method to identify misjudgments, missed judgments and uncertainty judgments by constructing a confusion matrix with true values ​​and channel output results as dimensions. After the statistics are completed, the recognition error types that occur more frequently are marked and associated with their corresponding input features, and finally a group of representative recognition weak areas are obtained to form training data backtracking defects, which are used to describe the problem of insufficient judgment ability of the current global evaluation channel under specific conditions.

[0035] After identifying a backtracking defect in the training data, the optimization module generates new data requirements based on this defect to compensate for the channel's insufficient training data coverage. To achieve this, the optimization module employs a feature distribution difference analysis method. This method extracts key feature values ​​(such as temperature range, bit error rate peak, and frequency change rate) from the backtracking defect samples and compares them with the statistical distribution of the corresponding features in the training dataset of the original global evaluation channel. The analysis focuses on the overlap and deviation of feature distributions. If a feature interval is significantly insufficient or missing in the original training set, the feature and its value range are marked as a data type requiring supplementation, ultimately forming a data requirement. This data requirement is used to guide the selection of samples required for subsequent model training.

[0036] After generating the data requirements, the optimization module processes the data requirements and the current global evaluation channel and sends both to the trusted third party to complete the model update. During this process, symmetric encryption methods, such as the AES algorithm, are used to uniformly encrypt the data requirements and the global evaluation channel. This method generates a single key to encrypt and decrypt information, ensuring that data is not leaked during network transmission. After encryption, the ciphertext data is sent to the trusted third party platform via a secure channel to trigger the subsequent privacy-preserving model optimization process.

[0037] After receiving the encrypted data, the three trusted parties use federated learning to optimize and update the global evaluation channel. This method allows multiple data participants to train their models using their own local data without sharing the original data, and only upload the updated local models to a central server for aggregation. In this scenario, based on the existing global evaluation channel structure and supplementary data requirements, the three trusted parties perform a distributed model training process, making appropriate adjustments to the channel's judgment rules or parameters to form a new, more generalizable, return global evaluation channel.

[0038] The reporting module 16 is configured to generate a post-processing quality abnormality after fusing the first test result and the second test result.

[0039] In this embodiment of the present application, reporting module 16 employs a result fusion method to jointly analyze the first and second test results in terms of anomaly indicators, judgment intervals, and result consistency, extracting common or complementary anomaly features to form a unified basis for anomaly judgment. After fusion is complete, the degree of anomaly is graded according to pre-set multi-level warning indicators, and a warning trigger analysis is performed to determine whether the anomaly reporting conditions have been met. If the triggering requirements are met, a post-processing quality anomaly is generated, which indicates the overall quality anomaly status of the wavelength division multiplexer chip during the post-processing stage.

[0040] Furthermore, in the system provided in the embodiment of the application, the reporting module 16 further includes: A joint test anomaly is established based on the first test result and the second test result; after configuring multi-level warning indicators, a warning trigger analysis is performed based on the joint test anomaly and the multi-level warning indicators, and an anomaly is reported based on the warning trigger analysis result.

[0041] In an embodiment of the present application, first, a joint test anomaly is established based on the first test result and the second test result using an abnormal label cross-comparison method. The specific steps are to extract the set of abnormal indicators identified in the first test result and the second test result, and standardize and align the abnormal results according to the test indicators, timestamps and test channels; then, by comparing the abnormal status of the same indicators in the two results, if both are marked as abnormal, they are marked as "high confidence anomaly", and if only one is marked as abnormal, it is marked as "unconfirmed anomaly". Through this method, the joint test anomaly covering key performance indicators and global feature indicators is finally output, and the result is used to comprehensively reflect the abnormal performance of the chip at the multi-dimensional detection level.

[0042] Next, configure multi-level warning indicators and analyze the triggering of joint test anomalies against these indicators. These indicators use an interval-based classification method to set numerical threshold ranges corresponding to different anomaly levels. For example, a mild anomaly corresponds to a slight deviation from the normal range for one key indicator (e.g., a deviation of no more than 10%); a moderate anomaly corresponds to deviations from the normal range for two or more indicators, but within the normal range; and a severe anomaly corresponds to the simultaneous violation of the normal range for three or more indicators. Using a rule-matching method, the actual characteristic value of each anomaly item in the joint test anomaly is compared against the threshold of the corresponding level of the multi-level warning indicator. The number of anomalies that meet the triggering conditions at each level is counted.

[0043] Finally, based on the comparison results, a warning trigger analysis is performed to determine whether the conditions for an anomaly report are met. If any of the combined test anomalies meet a certain level of warning conditions (for example, if the number of items exceeding the critical threshold is met), the anomaly level is determined to be established and an anomaly report is issued. The resulting report information is the post-processing quality anomaly, including the anomaly level, anomaly indicator, and its corresponding test value.

[0044] Furthermore, the system provided in the application embodiment also includes: The storage management module is used to establish a cloud storage space and set an identification code on the wavelength division multiplexer chip. The identification code corresponds one-to-one with the cloud storage space. The first test result, the second test result, and the quality abnormality identifier are stored in the mapped cloud space, and storage management is performed according to the identification code and the cloud storage space.

[0045] In an embodiment of the present application, the storage management module is used to implement structured storage and one-to-one identification management of WDM chip test results. Specifically, by first invoking a cloud service interface, an independent cloud storage space is established for each WDM chip. This space has object-oriented storage capabilities, supports the writing and management of multiple data formats, and ensures data isolation and scalability. Subsequently, an identification code is set on the chip. This identification code can be generated by combining parameters such as the chip number, production batch, and test time, ensuring that each chip has a unique identification.

[0046] The identification code is mapped to the corresponding cloud storage space, forming a unique association between the chip and its test data. Once the first test results (reflecting the individual anomalies of each key performance indicator), the second test results (comprehensive performance anomalies derived from global feature analysis), and the final quality anomaly indicator (indicating whether the chip has quality anomalies) are generated, the storage management module stores these data in the cloud storage space that matches the identification code.

[0047] Furthermore, the system provided in the application embodiment also includes: The verification management module is used to activate the permission authentication unit when the cloud storage space is triggered to start, use the permission authentication unit to perform editing permission authentication, establish a first authentication result, obtain the user's editing information, and perform joint authentication based on the editing information and the trust code of the wavelength division multiplexer chip. If the joint authentication passes, the data in the cloud storage space is updated based on the editing information.

[0048] In this embodiment of the present application, when the cloud storage space receives an external access request (such as a user attempting to modify a test result or quality anomaly indicator), the verification management module immediately activates the permission authentication unit. This permission authentication unit performs permission verification using a role-based access control (RBAC) approach. The RBAC approach verifies whether the current accessing user's role has editing permissions by mapping pre-set user roles (such as administrator, quality inspector, and auditor) to operational permissions. If the permission authentication passes, a first authentication result is generated, indicating that the user has basic editing qualifications.

[0049] The verification management module then retrieves the user's edit information from the front-end interactive interface. This information includes the fields the user wishes to modify (such as updating anomaly indicator descriptions or replacing test result entries). To further verify the authenticity of the edit operation, the module retrieves the unique trust code written into the WDM chip during storage. This trust code is generated using hardware-bound encryption based on the TPM module, ensuring uniqueness and tamper-resistance.

[0050] The Verification Management Module then performs joint authentication, verifying the consistency between the user's edited information and the chip's trusted code. This is done using a hash comparison method: a hash is calculated for the chip number field declared in the edited information and compared with the hash value of the corresponding trusted code to verify their consistency. If the hash values ​​match, the edit operation is indeed targeted at the current chip and is within the trusted execution environment.

[0051] Once the joint authentication is successful, the verification management module invokes the data update method to modify the data in the cloud storage space. This update method uses a key-value overwrite strategy. After identifying a valid edit field, the original value is directly replaced with the new data provided by the user. An edit log record is also appended, containing the operator ID, edit time, and a copy of the original value, ensuring data version traceability.

[0052] Furthermore, the system provided in the application embodiment also includes: The self-update management module is used to record post-processing quality anomalies, record real identification feedback, establish feedback mapping, and perform system self-update optimization management based on the feedback mapping.

[0053] In an embodiment of the present application, the self-update management module is used to provide closed-loop feedback management for quality anomalies that occur during the post-processing phase of the wavelength division multiplexer chip, and to dynamically optimize and adjust the system's identification logic by establishing a feedback mapping mechanism. First, by calling the quality anomaly collection interface and employing an anomaly label extraction method, anomaly information is extracted from the quality anomaly identifier generated by the reporting module. This includes key fields such as the chip identification code, anomaly performance indicators, and the time of anomaly occurrence. Standardized anomaly record entries are then generated and stored in the quality anomaly log database, forming a structured anomaly dataset.

[0054] The system then receives real identification feedback from on-site maintenance terminals or quality inspection systems. It uses static field matching to standardize the format of the feedback content, removes redundant or ambiguous data, and stores it in the feedback buffer. The feedback typically includes the chip number, confirmed abnormal status, confirmer identity, and time, ensuring traceability and comparability.

[0055] The self-update management module then uses a primary key index matching method, using the chip identification code and the time of the exception as the matching key, to match each quality exception record with the feedback record, establishing a feedback mapping relationship. Each feedback mapping relationship clearly records whether the exception is valid, whether there is a false alarm, the corresponding performance indicator, and the processing result, thus forming a feedback mapping table.

[0056] Based on the feedback mapping table, a policy weight adjustment method is used to locally optimize key identification parameters in the anomaly identification process. This optimization involves adjusting the anomaly threshold, response sensitivity, and priority ranking within the identifier to improve the accuracy of identifying true anomalies and reduce the false positive rate. For example, for indicators whose feedback confirms false positives, their judgment thresholds are appropriately raised; for indicators that consistently identify true anomalies, their identification response weights are increased. Finally, after the updated identification parameters are deployed within the anomaly identification process, a closed-loop evolution of the system's identification strategy is achieved, completing the self-updating and optimized management of the system.

[0057] In the embodiments of the present application, in summary, the embodiments of the present application have at least the following technical effects: The present application collects application scenarios for wavelength division multiplexer chips and establishes an application scenario set, wherein the application scenario set is provided with a scenario trust identifier; configures a performance test scheme using the application scenario set and establishes a performance test scheme set; uses the performance test scheme set to perform wavelength division multiplexer chip testing and records test data, wherein the test data includes performance data and environmental data; after configuring the key performance indicators, activates the mapping weak identifier based on the key performance indicators to perform independent key indicator anomaly identification of the test data and establishes a first test result; performs feature extraction on the test data and establishes a global feature vector, uses the global feature vector as input data, inputs it into the global evaluation channel, and establishes a second test result; after fusing the first test result and the second test result, generates a post-processing quality anomaly. The present invention solves the technical problem that the prior art cannot accurately identify performance anomalies in the chip post-processing process, and achieves the technical effect of improving the accuracy and efficiency of anomaly detection in the chip post-processing stage by establishing a multi-level testing mechanism and fusing the test results for anomaly identification.

[0058] In the second embodiment, based on the inventive concept of the wavelength division multiplexer chip post-processing management system in the aforementioned embodiment, the present application also provides an electronic device, comprising: at least one processor; 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 the steps of the system described in any one of the above-mentioned embodiments.

[0059] Figure 2 This is a schematic diagram of the structure of an exemplary electronic device of this application. Figure 2 In the figure, the bus architecture is represented by bus 300, which can include any number of interconnected buses and bridges. Bus 300 connects various circuits including one or more processors represented by processor 302 and memory represented by memory 304. Bus 300 can also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are all well known in the art and therefore will not be described further herein. Bus interface 305 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 can be the same component, namely a transceiver, which provides a unit for communicating with various other devices over a transmission medium. Processor 302 is responsible for managing bus 300 and general processing, while memory 304 can be used to store data used by processor 302 when performing operations.

[0060] In the third embodiment, based on the same inventive concept as the wavelength division multiplexer chip post-processing management system in the aforementioned embodiment, the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed, the steps of the system described in any one of the aforementioned embodiments are implemented.

[0061] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0062] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

[0063] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.

Claims

1. Wavelength division multiplexer chip post-processing management system, characterized in that: The system comprises: A scenario construction module is used to collect application scenarios for the wavelength division multiplexer chip and establish an application scenario set, wherein the application scenario set is provided with a scenario trust identifier; A test plan establishment module, configured to configure a performance test plan using the application scenario set and establish a performance test plan set; A testing module, configured to perform a wavelength division multiplexer chip test using the performance test solution set and record test data, wherein the test data includes performance data and environmental data; An independent response module is configured to, after configuring the performance key indicators, activate the mapped weak identifier based on the performance key indicators to perform independent key indicator anomaly identification on the test data and establish a first test result; A global response module is used to extract features from the test data, establish a global feature vector, and input the global feature vector as input data into a global evaluation channel to establish a second test result; The reporting module is used to generate a post-processing quality abnormality after fusing the first test result and the second test result.

2. The wavelength division multiplexer chip post-processing management system according to claim 1, characterized in that: The scene construction module includes: A data acquisition module, configured to read application scenarios of the wavelength division multiplexer chip and establish an application data set; A clustering module, configured to perform scene similarity clustering on the application data set, perform scene segmentation based on the scene similarity clustering results, and establish an application scene set; The dual-channel trust identification module is used to perform dual-channel identification of frequency trust and importance trust on the application data set in the application scenario set to generate a scenario trust identification.

3. The wavelength division multiplexer chip post-processing management system according to claim 1, characterized in that: The independent response module includes: An evaluation submodule is used to establish an adaptive evaluation function for a weak identifier, wherein the evaluation characteristics of the adaptive evaluation function include recognition accuracy characteristics, identifier complexity characteristics, adaptability characteristics, stability characteristics, and fault tolerance characteristics; An evaluation submodule, configured to perform fitness evaluation on the weak identifier using the adaptation evaluation function and establish a fitness evaluation result; The enhancer module is used to generate enhanced attention using the fitness evaluation result, and perform abnormal identification of independent key indicators after enhancing the learning of the weak identifier with the enhanced attention.

4. The wavelength division multiplexer chip post-processing management system according to claim 1, characterized in that: The reporting module is used to: Establishing a joint test exception according to the first test result and the second test result; After configuring the multi-level warning indicators, the combined test anomaly and the multi-level warning indicators are used to perform warning trigger analysis, and the anomaly is reported based on the warning trigger analysis results.

5. The wavelength division multiplexer chip post-processing management system according to claim 1, characterized in that: The system comprises: The storage management module is used to establish a cloud storage space and set an identification code on the wavelength division multiplexer chip. The identification code corresponds one-to-one with the cloud storage space. The first test result, the second test result, and the quality abnormality identifier are stored in the mapped cloud space, and storage management is performed according to the identification code and the cloud storage space.

6. The wavelength division multiplexer chip post-processing management system according to claim 5, characterized in that: The system further comprises: The verification management module is used to activate the permission authentication unit when the cloud storage space is triggered to start, use the permission authentication unit to perform editing permission authentication, establish a first authentication result, obtain the user's editing information, and perform joint authentication based on the editing information and the trust code of the wavelength division multiplexer chip. If the joint authentication passes, the data in the cloud storage space is updated based on the editing information.

7. The wavelength division multiplexer chip post-processing management system according to claim 1, characterized in that: The global response module includes: A self-evaluation module, configured to perform training data backtracking on the global evaluation channel and establish training data backtracking defects; The optimization module is used to generate data requirements based on the backtracking defects of the training data, encrypt the data requirements and the global evaluation channel and send them to the trusted three parties, receive the returned global evaluation channel from the trusted three parties, and perform global evaluation on the returned global evaluation channel, which is the channel after federated encrypted learning.

8. The wavelength division multiplexer chip post-processing management system according to claim 1, characterized in that: The system further comprises: The self-update management module is used to record post-processing quality anomalies, record real identification feedback, establish feedback mapping, and perform system self-update optimization management based on the feedback mapping.

9. An electronic device, characterized in that: The electronic device comprises: a memory for storing executable instructions; The processor is configured to implement the wavelength division multiplexer chip post-processing management system according to any one of claims 1 to 8 when executing the executable instructions stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the wavelength division multiplexer chip post-processing management system according to any one of claims 1 to 8 is implemented.

Images