Optical module automatic test method and device, computer equipment and storage medium

Abstract

The embodiment of the invention discloses an optical module automatic testing method and device, computer equipment and a storage medium, and relates to the technical field of optical module testing. The method comprises the steps of collecting a label image of a to-be-tested optical module, and determining model information of the to-be-tested optical module according to the label image based on a pre-trained first neural network model; determining a test item of the to-be-tested optical module from a preset optical module test item knowledge base based on the model information of the to-be-tested optical module; environment parameters of a test environment of the test item are collected, and test parameters of the test item are determined based on a pre-trained second neural network model according to the environment parameters; and executing the test item on the to-be-tested optical module based on the test parameters. Compared with a manual mode, the method has the advantages of high efficiency and high accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of optical module testing, and particularly to an automatic testing method, device, computer equipment and storage medium for optical modules. Background Art

[0002] As a core component of an optical communication system, the performance of an optical module directly determines the reliability and efficiency of data transmission. In the production and quality inspection of optical modules, it is necessary to verify through strict tests whether key indicators such as emission power, receiving sensitivity, and bit error rate meet technical specifications. The traditional testing process mainly relies on manual operations: testers need to manually select test items, configure device parameters according to the optical module model, and execute tests item by item. However, with the increasing variety of optical modules (such as modules with different rates, packages, and transmission distances), and the continuous improvement of the industry's requirements for testing efficiency and accuracy, the following technical defects have gradually emerged in the traditional method:

[0003] Low efficiency of manual identification and configuration. Testers need to visually check the module label or refer to the specification sheet to determine the module type, and then manually match the test items and parameters. This process takes a long time and is prone to test configuration errors due to human negligence (such as misreading the label or confusing the specification sheet version), which in turn affects the validity of the test results. Summary of the Invention

[0004] Embodiments of the present invention provide an automatic testing method, device, computer equipment and storage medium for optical modules, aiming to solve the problems of low efficiency and low accuracy of existing optical module automatic testing methods.

[0005] In a first aspect, embodiments of the present invention provide an automatic testing method for optical modules, which includes:

[0006] Collect a label image of the optical module to be tested, and determine the model information of the optical module to be tested based on the label image by a pre-trained first neural network model;

[0007] Determine the test items of the optical module to be tested from a preset optical module test item knowledge base based on the model information of the optical module to be tested;

[0008] Collect environmental parameters of the test environment of the test item, and determine the test parameters of the test item based on the environmental parameters by a pre-trained second neural network model;

[0009] Execute the test item on the optical module to be tested based on the test parameters.

[0010] A further technical solution thereof is that the determining the model information of the optical module to be tested based on the label image by the pre-trained first neural network model includes:

[0011] Preprocess the label image to obtain an input image;

[0012] Input the input image into a pre-trained first neural network model to predict the category of the input image by the first neural network model;

[0013] Determine the model information of the optical module to be tested based on the category of the input image.

[0014] A further technical solution thereof is that the optical module test item knowledge base includes a standard test item library and a manufacturer extension library. Determining the test items of the optical module to be tested from a preset optical module test item knowledge base based on the model information of the optical module to be tested includes:

[0015] Query and obtain the standard test items of the optical module from the standard test item library, and query the extended test items of the optical module from the manufacturer extension library;

[0016] Use the standard test items and the extended test items as the test items of the optical module to be tested.

[0017] A further technical solution thereof is that the method further includes:

[0018] If the number of the test items is multiple, respectively obtain the historical test data of each test item;

[0019] Determine the failure rate of the test item based on the historical test data of the test item;

[0020] Sort the multiple test items in descending order of the failure rate to obtain the test order of the multiple test items.

[0021] A further technical solution thereof is that determining the failure rate of the test item based on the historical test data of the test item includes:

[0022] Screen out target data matching the model information of the optical module to be tested from the historical test data of the test item;

[0023] Determine the failure rate of the test item based on the target data.

[0024] A further technical solution thereof is that determining the test parameters of the test item based on a pre-trained second neural network model according to the environmental parameters includes:

[0025] Perform data cleaning processing on the environmental parameters to obtain input parameters;

[0026] Input the input parameter into a pre-trained second neural network model to predict the category of the input parameter by the second neural network model;

[0027] Determine the test parameter of the test item based on the category of the input parameter.

[0028] A further technical solution thereof is that the test item includes at least one of a transmitted optical power test, a received sensitivity test, a bit error rate test, and an eye diagram test.

[0029] In a second aspect, an embodiment of the present invention further provides an optical module automatic test device, which includes a unit for executing the above method.

[0030] In a third aspect, an embodiment of the present invention further provides a computer device, which includes a memory and a processor, and a computer program is stored on the memory. When the processor executes the computer program, the above method is implemented.

[0031] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, and the storage medium stores a computer program, and when the computer program is executed by a processor, the above method can be implemented.

[0032] An embodiment of the present invention provides an optical module automatic test method, device, computer device, and storage medium. Among them, the method includes: collecting a label image of a to-be-tested optical module, and determining the model information of the to-be-tested optical module based on the label image by a pre-trained first neural network model; determining the test item of the to-be-tested optical module from a preset optical module test item knowledge base based on the model information of the to-be-tested optical module; collecting the environmental parameter of the test environment of the test item, and determining the test parameter of the test item based on the environmental parameter by a pre-trained second neural network model; performing the test item on the to-be-tested optical module based on the test parameter. Compared with the manual method, the present invention has the advantages of high efficiency and high accuracy.

[0033] By integrating image recognition and neural network technologies, the present invention realizes the intelligence and automation of optical module testing. First, by collecting the label image of the optical module to be tested and using a pre-trained first neural network model to analyze the model information, the system can quickly and accurately identify the type of optical module, avoiding problems such as misreading of labels or version confusion that may be caused by traditional manual visual inspection, and significantly improving the recognition efficiency and reliability. Second, based on the model information, test items are dynamically matched from a preset optical module test item knowledge base, solving the problems of incomplete coverage or redundant execution of traditional fixed test lists, and ensuring that the selected test items are strictly adapted to the actual needs of the module. Further, by collecting test environment parameters and using a second neural network model to dynamically generate test parameters, the system can respond to environmental changes in real time (such as temperature and humidity fluctuations), automatically adjust test conditions (such as optical power calibration values, attenuation step sizes), thereby eliminating the influence of environmental interference on test results and improving the accuracy and repeatability of test data. Finally, by executing test items based on optimized test parameters, the performance verification of optical modules can be efficiently completed, reducing the need for manual intervention, especially suitable for multi-model mixed testing scenarios, and providing an automated solution with high precision and high consistency for mass production and quality inspection. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0035] Figure 1 It is a schematic flowchart of the optical module automatic testing method provided by the embodiment of the present invention;

[0036] Figure 2 It is a schematic block diagram of a computer device provided by the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0037] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the scope of protection of the present invention.

[0038] It should be understood that when used in this specification and the appended claims, the terms "comprises" and "comprising" indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0039] It should also be understood that the terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include the plural forms.

[0040] It should be further understood that the term "and / or" used in the specification of the present invention and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0041] As used in this specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when", "once", "in response to determining", or "in response to detecting". Similarly, the phrase "if determined" or "if [the described condition or event] is detected" may be interpreted, depending on the context, as meaning "once determined", "in response to determining", "once [the described condition or event] is detected", or "in response to detecting [the described condition or event]".

[0042] Please refer to Figure 1 , an embodiment of the present invention provides an automatic test method for an optical module. As Figure 1 shown, the method includes the following steps:

[0043] S1, collect a label image of the optical module to be tested, and determine the model information of the optical module to be tested based on the label image according to a pre-trained first neural network model.

[0044] In a specific implementation, the label image of the optical module to be tested is collected based on an industrial camera. Specifically, the industrial camera: uses a global shutter camera (such as Basler ace 2), equipped with a ring-shaped LED light source, to eliminate reflection and ensure a clear label image.

[0045] The first neural network model is pre-trained with a large number of calibrated training data, so that the first neural network model has the ability to identify the model information of the optical module to be tested based on the label image. After the label image of the optical module to be tested is collected, the model information of the optical module to be tested is determined based on the pre-trained first neural network model according to the label image. The first neural network model may be, for example, a convolutional neural network model, which is not specifically limited in the present invention.

[0046] S2, determine the test items of the optical module to be tested from a preset optical module test item knowledge base based on the model information of the optical module to be tested.

[0047] In specific implementation, a knowledge base for optical module test items is established in advance. The knowledge base for optical module test items records the test items required for optical modules of various types and models. The knowledge base for optical module test items is updated in real time, synchronizes with the industry standard database (such as the IEC official website) regularly (for example, weekly). If a change in the detection standard is detected, a reminder for revising the test items is triggered, and the knowledge base for optical module test items is updated.

[0048] After determining the model information of the optical module to be tested, determine the test items of the optical module to be tested from the preset knowledge base for optical module test items.

[0049] S3. Collect the environmental parameters of the test environment of the test item, and determine the test parameters of the test item based on the pre-trained second neural network model according to the environmental parameters.

[0050] In specific implementation, the environmental parameters can be collected by sensors. The environmental parameters include temperature, humidity, light intensity, electromagnetic intensity, etc., which are not specifically limited in the present invention.

[0051] In the traditional solution, the test parameters are usually fixed or adjusted manually by the user, with low efficiency and unable to match the actual test environment.

[0052] In this solution, the second neural network model is pre-trained with a large amount of test data, so that the second neural network model is capable of determining the test parameters of the test item according to the environmental parameters. The second neural network model can be, for example, a convolutional neural network model, which is not specifically limited in the present invention.

[0053] After collecting the environmental parameters of the test environment of the test item, further determine the test parameters of the test item based on the pre-trained second neural network model according to the environmental parameters, thereby ensuring that the test parameters of the test item match the test environment. For example, realize automatic correction of the optical power calibration value according to the environmental temperature and humidity.

[0054] S4. Execute the test item on the optical module to be tested based on the test parameters.

[0055] In specific implementation, execute each test item on the optical module to be tested based on the test parameters of each test item in sequence.

[0056] By integrating image recognition and neural network technologies, the present invention realizes the intelligence and automation of optical module testing. First, by collecting the label image of the optical module to be tested and using a pre-trained first neural network model to analyze the model information, the system can quickly and accurately identify the type of optical module, avoiding problems such as misreading of labels or version confusion that may be caused by traditional manual visual inspection, and significantly improving the recognition efficiency and reliability. Secondly, based on the model information, test items are dynamically matched from a pre-set optical module test item knowledge base, solving the problems of incomplete coverage or redundant execution of traditional fixed test lists, and ensuring that the selected test items are strictly adapted to the actual needs of the module. Further, by collecting test environment parameters and using a second neural network model to dynamically generate test parameters, the system can respond to environmental changes in real time (such as temperature and humidity fluctuations), automatically adjust test conditions (such as optical power calibration value, attenuation step size), thereby eliminating the influence of environmental interference on test results and improving the accuracy and repeatability of test data. Finally, by executing test items based on optimized test parameters, the performance verification of optical modules can be efficiently completed, reducing the need for manual intervention, especially suitable for scenarios of mixed testing of multiple models, and providing an automated solution with high precision and high consistency for mass production and quality inspection.

[0057] In some preferred embodiments, the above step of "determining the model information of the optical module to be tested based on the label image according to the pre-trained first neural network model" specifically includes: preprocessing the label image to obtain an input image; inputting the input image into the pre-trained first neural network model so that the first neural network model predicts the category of the input image; and determining the model information of the optical module to be tested based on the category of the input image.

[0058] In specific implementation, through the collaborative optimization of image preprocessing and neural network classification, the robustness and accuracy of optical module recognition are enhanced.

[0059] Specifically, preprocessing the label image (such as denoising, contrast enhancement, perspective correction) can eliminate interference factors in the shooting environment (such as reflection, stains or tilt angle), generate a standardized input image, and provide a high-quality data basis for subsequent model inference.

[0060] Inputting the preprocessed image into the pre-trained first neural network model for classification prediction, and using the ability of deep learning to extract complex features (such as tiny characters, two-dimensional codes or special symbols), the features of the optical module can be accurately identified. Even in the case of label wear or blurred printing, a high recognition accuracy can still be maintained.

[0061] In addition, directly mapping the category of the input image to the model information avoids the dependence on fixed templates in traditional rule matching, supports the rapid adaptation to new model optical modules, and significantly improves the scalability and generalization ability of the system.

[0062] In some preferred embodiments, the optical module test item knowledge base includes a standard test item library and a manufacturer extension library. The above step of "determining the test items of the optical module to be tested from a preset optical module test item knowledge base based on the model information of the optical module to be tested" specifically includes: querying and obtaining the standard test items of the optical module from the standard test item library, and querying the extended test items of the optical module from the manufacturer extension library; and taking the standard test items and the extended test items as the test items of the optical module to be tested.

[0063] In specific implementation, by constructing a composite knowledge base including a standard test item library and a manufacturer extension library, the comprehensiveness and flexibility of test item selection are realized. The standard test item library defines basic test items based on industry general specifications (such as IEEE 802.3, MSA protocol) to ensure that the core performance indicators of the optical module (such as transmit power, bit error rate) meet the industry benchmark requirements; while the manufacturer extension library includes additional test items (such as non-linear distortion, temperature adaptability test) for specific manufacturers or customized modules, which can meet the differentiated requirements.

[0064] By querying the standard test items and the extended test items from the two types of libraries respectively, the system can dynamically combine and generate a complete test list, which not only avoids missing key test items but also prevents waste of resources caused by redundant tests. For example, for a high-speed module of a certain manufacturer, the system can automatically add customized items such as eye diagram jitter test, so as to ensure the test coverage and accurately adapt to diverse application scenarios.

[0065] In some preferred embodiments, the optical module automatic test method further includes: if the number of the test items is multiple, respectively obtaining the historical test data of each of the test items; determining the failure rate of each of the test items based on the historical test data of the test items; and sorting the multiple test items in descending order of the failure rate to obtain the test order of the multiple test items.

[0066] In specific implementation, by introducing a failure rate sorting mechanism driven by historical test data, the execution order of multiple test items is optimized, significantly improving the test efficiency and problem detection rate.

[0067] Specifically, the system calculates the failure rate of each test item according to the historical test data of each test item, and dynamically adjusts the test order in descending order of the failure rate. For example, if the historical data of a certain model of optical module shows that the failure rate of the receive sensitivity test is as high as 60%, the system will give priority to executing this test item, so as to quickly identify potential defects in the early stage and avoid resource consumption of subsequent non-critical tests.

[0068] In addition, when a fatal fault (such as a serious over - standard emission power) is detected during the testing process, the system can terminate the subsequent testing in advance, further shortening the overall testing cycle. This data - driven priority strategy not only improves the intelligent level of the testing process but also provides a scientific basis for resource allocation in batch testing scenarios.

[0069] In some preferred embodiments, the above step of "determining the failure rate of the test item based on the historical test data of the test item" specifically includes: screening out target data that matches the model information of the optical module under test from the historical test data of the test item; and determining the failure rate of the test item based on the target data.

[0070] In specific implementation, by only extracting the historical test data that matches the model of the optical module under test, the pertinence and accuracy of the failure rate analysis are ensured.

[0071] Specifically, historical data may contain mixed information of different models or batches of modules. Directly counting the global failure rate is likely to introduce biases. However, in this solution, by screening target data through model matching, for example, only selecting the historical records of optical modules with the same model and the same rate, the typical failure modes of this model can be accurately reflected (such as the concentrated high incidence of eye diagram jitter in a certain batch of modules). Based on this, the failure rate index generated by the system is more representative, thus ensuring the scientific nature and reliability of the optimization of the test sequence.

[0072] Meanwhile, this screening mechanism supports dynamic update. When enough test data of new - model modules has been accumulated, the system can automatically include them in the analysis scope to achieve the adaptive expansion of the knowledge base.

[0073] In some preferred embodiments, the above step of "determining the test parameters of the test item according to the environmental parameters based on the pre - trained second neural network model" specifically includes: performing data cleaning processing on the environmental parameters to obtain input parameters; inputting the input parameters into the pre - trained second neural network model so that the second neural network model predicts the category of the input parameters; and determining the test parameters of the test item based on the category of the input parameters.

[0074] In specific implementation, through the combination of data cleaning and neural network prediction, a high - precision mapping from environmental parameters to test parameters is achieved.

[0075] First, cleaning the original environmental parameters (such as temperature, humidity, light intensity) (such as removing outliers, normalizing, and imputing missing values) can eliminate noise interference and generate a standardized set of input parameters, providing a reliable data basis for model inference.

[0076] Subsequently, the cleaned parameters are input into the pre-trained second neural network model, and its non-linear fitting ability is utilized to dynamically predict the optimal test parameters (such as automatically adjusting the receiving sensitivity threshold according to the current temperature). For example, when the ambient temperature rises, the model can output a lower optical power calibration value to compensate for the impact of thermal noise, thereby ensuring the stability of the test results. This closed-loop parameter optimization mechanism breaks through the limitations of traditional manual experience configuration and significantly improves the adaptability of the test system to complex environments.

[0077] Furthermore, in the embodiments of the present invention, the test items include at least one of transmitted optical power test, receiving sensitivity test, bit error rate test, and eye diagram test.

[0078] In specific implementation, the transmitted optical power test directly verifies the output intensity of the module, avoiding communication interruption caused by insufficient power or overload; the receiving sensitivity test locates the critical power point through dynamic attenuation to ensure the reliability of the module in a weak light environment; the bit error rate test quantifies the stability of data transmission to prevent signal distortion; and the eye diagram test analyzes the signal integrity (such as jitter, noise level) from the time domain and frequency domain to identify potential defects of high-speed rate modules.

[0079] By integrating the above key test items, the system can comprehensively evaluate the performance of the optical module from multiple dimensions, meet diverse requirements from basic verification to high-precision diagnosis, and is particularly suitable for the strict quality inspection scenarios of high-speed (such as 400G / 800G) optical modules.

[0080] To further elaborate on the technical solution of the present invention, the test procedures for the transmitted optical power test, receiving sensitivity test, bit error rate test, and eye diagram test will be described in detail below.

[0081] Transmitted optical power test:

[0082] 1. Use an optical power meter to test the transmitted optical power of the optical module.

[0083] 2. Set the wavelength of the optical power meter to be the same as the central wavelength of the optical module.

[0084] 3. Insert the optical module to be tested into the test board, and connect the transmitting port of the optical module to the adapter interface of the optical power meter through a jumper wire.

[0085] 4. Read the data on the display screen of the optical power meter, which is the transmitted optical power of the optical module.

[0086] 5. Compare the test result with the technical specifications of the optical module to determine whether it meets the requirements.

[0087] Receiving sensitivity test:

[0088] 1. Use an optical power meter and a variable optical attenuator to test the receiving sensitivity of the optical module.

[0089] 2. Connect the dimmable optical power meter between the optical power meter and the optical module, and gradually increase the attenuation.

[0090] 3. Observe the minimum optical power value at which the optical module can correctly decode at the receiving end, which is the receiving sensitivity of the optical module.

[0091] 4. Compare the test results with the technical specifications of the optical module to determine whether they meet the requirements.

[0092] Bit error rate test:

[0093] 1. Connect the transmitting end of the bit error tester to the test board and the receiving end to the receiving port of the optical module.

[0094] 2. Set the test parameters of the bit error tester, such as test time, data rate, etc.

[0095] 3. Start the bit error tester for testing and record the number of bit errors during the test.

[0096] 4. Calculate the bit error rate and compare it with the technical specifications of the optical module to determine whether they meet the requirements.

[0097] Eye diagram test:

[0098] 1. Use an eye diagram tester to test the eye diagram of the optical module.

[0099] 2. Connect the test board between the eye diagram tester and the optical module.

[0100] 3. Start the eye diagram tester for testing and observe the eye diagram of the optical module.

[0101] 4. Analyze parameters such as the opening, jitter, and noise of the eye diagram to evaluate the signal quality of the optical module.

[0102] 5. Compare the test results with the technical specifications of the optical module to determine whether they meet the requirements.

[0103] Corresponding to the above optical module automatic test method, the present invention also provides an optical module automatic test device. The optical module automatic test device includes units for performing the above optical module automatic test method, and the optical module automatic test device can be configured in terminals such as desktop computers, tablet computers, laptop computers, etc. Specifically, the optical module automatic test device includes:

[0104] A first determination unit for collecting a label image of the optical module to be tested and determining the model information of the optical module to be tested based on the label image according to a pre-trained first neural network model;

[0105] A second determination unit, configured to determine a test item of the optical module to be tested from a pre-set knowledge base of optical module test items based on the model information of the optical module to be tested;

[0106] A third determination unit, configured to collect environmental parameters of a test environment of the test item, and determine test parameters of the test item based on the environmental parameters according to a pre-trained second neural network model;

[0107] A test unit, configured to execute the test item on the optical module to be tested based on the test parameters.

[0108] In some preferred embodiments, the determining the model information of the optical module to be tested according to the labeled image based on the pre-trained first neural network model includes:

[0109] Performing preprocessing on the labeled image to obtain an input image;

[0110] Inputting the input image into the pre-trained first neural network model, so that the first neural network model predicts the category of the input image;

[0111] Determining the model information of the optical module to be tested based on the category of the input image.

[0112] In some preferred embodiments, the knowledge base of optical module test items includes a standard test item library and a manufacturer extension library. The determining the test item of the optical module to be tested from the pre-set knowledge base of optical module test items based on the model information of the optical module to be tested includes:

[0113] Querying and obtaining the standard test items of the optical module from the standard test item library, and querying the extended test items of the optical module from the manufacturer extension library;

[0114] Taking the standard test items and the extended test items as the test items of the optical module to be tested.

[0115] In some preferred embodiments, the optical module automatic test device further includes:

[0116] If the number of the test items is multiple, respectively obtaining historical test data of each of the test items;

[0117] Determining the failure rate of the test item based on the historical test data of the test item;

[0118] Sorting the multiple test items in descending order of the failure rate to obtain a test order of the multiple test items.

[0119] In some preferred embodiments, determining the failure rate of the test item based on the historical test data of the test item includes:

[0120] Screening out target data that matches the model information of the optical module under test from the historical test data of the test item;

[0121] Determining the failure rate of the test item based on the target data.

[0122] In some preferred embodiments, determining the test parameters of the test item according to the environmental parameters based on a pre-trained second neural network model includes:

[0123] Performing data cleaning processing on the environmental parameters to obtain input parameters;

[0124] Inputting the input parameters into a pre-trained second neural network model to predict the category of the input parameters by the second neural network model;

[0125] Determining the test parameters of the test item based on the category of the input parameters.

[0126] In some preferred embodiments, the test item includes at least one of transmit optical power test, receive sensitivity test, bit error rate test, and eye diagram test.

[0127] It should be noted that those skilled in the art can clearly understand that the specific implementation processes of the above optical module automatic test device and each unit can refer to the corresponding descriptions in the foregoing method embodiments. For the sake of convenience and brevity of description, they will not be elaborated here.

[0128] The above optical module automatic test device can be implemented in the form of a computer program, and the computer program can run on a computer device as shown in Figure 2 shown.

[0129] Please refer to Figure 2 , Figure 2 which is a schematic block diagram of a computer device provided by an embodiment of the present application. The computer device 500 can be a terminal or a server. Among them, the terminal can be an electronic device with a communication function such as a smart phone, a tablet computer, a notebook computer, a desktop computer, a personal digital assistant, and a wearable device. The server can be an independent server or a server cluster composed of multiple servers.

[0130] The computer device 500 includes a processor 502, a memory, and a network interface 505 connected through a system bus 501. Among them, the memory can include a non-volatile storage medium 503 and an internal memory 504.

[0131] The non-volatile storage medium 503 can store an operating system 5031 and a computer program 5032. When the computer program 5032 is executed, it can cause the processor 502 to execute an optical module automatic testing method.

[0132] The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500.

[0133] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, it can cause the processor 502 to execute an optical module automatic testing method.

[0134] The network interface 505 is used for network communication with other devices. Those skilled in the art can understand that the above structure is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device 500 to which the solution of this application is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0135] Among them, the processor 502 is used to run the computer program 5032 stored in the memory to implement the steps of an optical module automatic testing method provided in any embodiment of the present invention.

[0136] It should be understood that in the embodiments of this application, the processor 502 may be a central processing unit (CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0137] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a storage medium, and the storage medium is a computer-readable storage medium. The computer program is executed by at least one processor in the computer system to implement the process steps of the embodiments of the above method.

[0138] Therefore, the present invention also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program. When the computer program is executed by a processor, the processor is caused to execute the steps of an optical module automatic testing method provided in any embodiment of the present invention.

[0139] The storage medium is a physical, non-transitory storage medium, for example, it may be various physical storage media such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a magnetic disk, or an optical disc, etc., that can store program codes. The computer-readable storage medium may be non-volatile or volatile.

[0140] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been generally described according to their functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0141] In several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of each unit is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0142] The steps in the method embodiments of the present invention can be adjusted, combined, and deleted according to actual needs. The units in the device embodiments of the present invention can be combined, divided, and deleted according to actual needs. In addition, the functional units in each embodiment of the present invention can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0143] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a terminal, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0144] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0145] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, provided that these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these changes and modifications.

[0146] As described above, the above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. An automatic test method for an optical module, characterized in that, Including: Collect the label image of the optical module to be tested, and determine the model information of the optical module to be tested based on the pre-trained first neural network model according to the label image; Determine the test items of the optical module to be tested from a preset optical module test item knowledge base based on the model information of the optical module to be tested; Collect the environmental parameters of the test environment of the test item, and determine the test parameters of the test item based on the pre-trained second neural network model according to the environmental parameters; Execute the test item on the optical module to be tested based on the test parameters.

2. The optical module automatic test method according to claim 1, wherein The determining the model information of the optical module to be tested based on the pre-trained first neural network model according to the label image includes: Preprocess the label image to obtain an input image; Input the input image into the pre-trained first neural network model, so that the first neural network model predicts the category of the input image; Determine the model information of the optical module to be tested based on the category of the input image.

3. The optical module automatic test method according to claim 1, characterized in that The optical module test item knowledge base includes a standard test item library and a manufacturer extension library. The determining the test items of the optical module to be tested from a preset optical module test item knowledge base based on the model information of the optical module to be tested includes: Query and obtain the standard test items of the optical module from the standard test item library, and query the extended test items of the optical module from the manufacturer extension library; Use the standard test items and the extended test items as the test items of the optical module to be tested.

4. The optical module automatic test method according to claim 1, wherein The method further includes: If the number of the test items is multiple, respectively obtain the historical test data of each test item; Determine the failure rate of the test item based on the historical test data of the test item; Sort the multiple test items in descending order of the failure rate to obtain the test order of the multiple test items.

5. The optical module automatic test method according to claim 4, characterized in that The determining the failure rate of the test item based on the historical test data of the test item includes: Screen out the target data matching the model information of the optical module to be tested from the historical test data of the test item; Determine the failure rate of the test item based on the target data.

6. The optical module automatic test method according to claim 1, characterized in that, The determining the test parameters of the test item based on the pre-trained second neural network model according to the environmental parameters includes: Perform data cleaning on the environmental parameters to obtain input parameters; Input the input parameters into the pre-trained second neural network model, so that the second neural network model predicts the category of the input parameters; Determine the test parameters of the test item based on the category of the input parameters.

7. The optical module automatic test method according to claim 1, characterized in that The test item includes at least one of transmit optical power test, receive sensitivity test, bit error rate test, and eye diagram test.

8. An optical module automatic test device, characterized in that, Including a unit for executing the method according to any one of claims 1-7.

9. A computer device, characterized in that, The computer device includes a memory and a processor. A computer program is stored on the memory. When the processor executes the computer program, the method according to any one of claims 1-7 is implemented.

10. A computer-readable storage medium, characterized in that, The storage medium stores a computer program. When the computer program is executed by a processor, the method according to any one of claims 1-7 can be implemented.

Images