Micro-area bandwidth testing system and method for semiconductor optoelectronic devices

Abstract

The present application relates to the field of intelligent testing, and specifically to a system and method for testing micro-area bandwidth of semiconductor optoelectronic devices. It introduces a signal processing and analysis algorithm based on artificial intelligence and deep learning to perform signal decomposition and feature analysis on the weak electrical signal, thereby extracting the component signal features in the weak electrical signal and the signal component distillation and aggregation semantic representation between these component signal features, so as to decode and generate the photocurrent signal value. In this way, a high degree of consistency can be maintained under different test conditions, thereby improving the accuracy and reliability of bandwidth measurement.

Description

Technical Field

[0001] The present application relates to the field of intelligent testing, and in particular to a system and method for testing micro-area bandwidth of semiconductor optoelectronic devices. Background Art

[0002] Semiconductor optoelectronic devices refer to new semiconductor devices that connect the two physical quantities of light and electricity and convert them into each other. In the research and development and production of semiconductor optoelectronic devices, accurate evaluation of device performance is crucial. Among them, bandwidth is a key parameter to measure the transmission signal frequency range and response speed of semiconductor optoelectronic devices, which directly affects the working efficiency and reliability of the device.

[0003] The current bandwidth measurement methods only test the bandwidth of the entire device. In fact, the bandwidths in different micro-areas of the device are not the same. Due to the influence of the physical mechanism of the semiconductor optoelectronic device itself, the bandwidths of the micro-areas near the electrode and the micro-areas near the junction are very different, which makes the current device bandwidth testing methods not rigorous and accurate enough.

[0004] In response to the above problems, Chinese patent CN117452175A proposes a system and method for testing the micro-area bandwidth of semiconductor optoelectronic devices, which includes main components such as lasers, modulation systems, deterministic optical paths, precision displacement controllers, preamplifiers, phase-locked amplifiers, and PC-side control modules. Its working principle is to generate a light source through a laser, and the modulation system performs frequency control on the light source to obtain light responses at different frequencies. The deterministic optical path ensures that the light source can accurately illuminate the specified micro-area position of the semiconductor optoelectronic device. The precision displacement controller is responsible for controlling the position of the semiconductor optoelectronic device so that it can be scanned during the test. The preamplifier and phase-locked amplifier are used to amplify weak electrical signals to obtain photocurrent signal values. The PC-side control module is responsible for the transmission, storage, and processing of data to calculate the bandwidth values ​​of different micro-area positions.

[0005] However, although the above-mentioned micro-area bandwidth test system for semiconductor optoelectronic devices has made some improvements in improving the accuracy of bandwidth testing, it still has some potential defects. For example, the system relies on preamplifiers and phase-locked amplifiers to process signals, which not only increases the complexity and cost of the system, but also may introduce additional noise, affecting the accuracy of the test results. At the same time, although preamplifiers and phase-locked amplifiers can effectively amplify signals and remove some noise, they may not be able to fully cope with complex signal environments, especially when the signal is weak or the noise is large. In addition, traditional signal processing methods may lack flexibility and find it difficult to adapt to test requirements that may change in the future, reducing the generalization ability of the system.

[0006] Therefore, an optimized micro-area bandwidth testing system for semiconductor optoelectronic devices is desired. Summary of the invention

[0007] This application is made in view of the above problems. One object of this application is to provide a system and method for testing micro-area bandwidth of semiconductor optoelectronic devices.

[0008] The embodiment of the present application provides a system for testing micro-area bandwidth of semiconductor optoelectronic devices, which includes: a laser, a modulation system, a deterministic optical path, a precision displacement controller, a micro-electric signal processor, and a PC-side controller;

[0009] The laser is used to provide a laser light source required for testing semiconductor optoelectronic devices;

[0010] The modulation system is used to adjust the frequency of the laser light source to obtain light responses at different frequencies;

[0011] The deterministic optical path is used to adjust the irradiation position of the laser light source so that the laser light source irradiates a designated micro-region position on the semiconductor optoelectronic device to obtain a weak electrical signal;

[0012] The precision displacement controller is used to control the movement of the semiconductor optoelectronic device by controlling the displacement platform;

[0013] The micro-electric signal processor is used to perform signal feature extraction and component distillation processing on the weak electric signal based on signal decomposition and signal feature energy spectrum analysis to obtain a photocurrent signal value;

[0014] The PC-side controller includes a data transmission module, a data storage module and a data processing module, and the data transmission module is communicatively connected with the precision displacement controller and the micro-electric signal processor respectively to obtain the position of the micro-area to be measured and the value of the photocurrent signal to be measured;

[0015] The data storage module is used to extract the position of the micro-area to be measured and the photocurrent signal value to be measured, then combine the position of the micro-area to be measured with the photocurrent signal value to be measured to obtain the photocurrent signal values ​​of different positions at the same frequency, and then summarize the photocurrent signal values ​​of multiple different positions at the same frequency to obtain a matrix of photocurrent signal values ​​of multiple different positions at the same frequency;

[0016] The data processing module is used to calculate the position-weighted sum of the photocurrent signal value matrices of the multiple photocurrent signal value matrices at different positions at the same frequency to obtain bandwidth values ​​at different micro-region positions.

[0017] For example, according to the micro-area bandwidth testing system for semiconductor optoelectronic devices according to an embodiment of the present application, the micro-electric signal processor includes:

[0018] A weak electric signal decomposition module, used for performing CEEMDAN decomposition on the weak electric signal to obtain a set of IMF components of the weak electric signal;

[0019] A weak electric signal component signal feature extraction module, used for respectively extracting features of each weak electric signal IMF component in the set of weak electric signal IMF components to obtain a set of weak electric signal IMF component signal feature vectors;

[0020] A weak electric signal component signal semantic selection optimization module, used for inputting the set of weak electric signal IMF component signal feature vectors into a sequence screening module based on characteristic energy spectrum analysis to obtain a set of selected weak electric signal IMF component signal feature vectors;

[0021] The optical flow signal generation module is used to generate a weak electric signal component signal component distillation representation vector based on the set of the selected weak electric signal IMF component signal feature vectors, and determine the photocurrent signal decoding value.

[0022] For example, according to the micro-area bandwidth testing system for semiconductor optoelectronic devices according to the embodiment of the present application, the weak electric signal component signal feature extraction module is used to: input each weak electric signal IMF component in the set of weak electric signal IMF components into the component signal feature extractor based on the 1D-CNN model to obtain a set of weak electric signal IMF component signal feature vectors.

[0023] For example, according to the semiconductor optoelectronic device micro-area bandwidth test system of the embodiment of the present application, the weak electric signal component signal semantic selection optimization module includes:

[0024] A characteristic energy distribution spectrum vector calculation unit is used to calculate the characteristic energy distribution spectrum vector of each weak electric signal IMF component signal feature vector in the set of the weak electric signal IMF component signal feature vectors to obtain a sequence of semantic characteristic energy distribution spectrum vectors of the weak electric signal IMF component signal;

[0025] A position-based mean vector calculation unit is used to calculate the position-based mean vector of the sequence of semantic feature energy distribution spectrum vectors of the weak electric signal IMF component signal as the center vector of the semantic energy spectrum distribution of the weak electric signal IMF component signal;

[0026] An energy distribution spectrum span factor calculation unit is used to calculate the energy distribution spectrum span factor between the weak electric signal IMF component signal semantic energy spectrum distribution center vector and each weak electric signal IMF component signal semantic feature energy distribution spectrum vector in the sequence of the weak electric signal IMF component signal semantic feature energy distribution spectrum vector to obtain a sequence of weak electric signal IMF component signal semantic energy distribution spectrum span factors;

[0027] A preset threshold comparison unit is used to determine the set of selected weak electric signal IMF component signal feature vectors based on the comparison between each weak electric signal IMF component signal semantic energy distribution spectrum span factor in the sequence of the weak electric signal IMF component signal semantic energy distribution spectrum span factor and the preset threshold.

[0028] For example, according to the semiconductor optoelectronic device micro-area bandwidth testing system of the embodiment of the present application, the characteristic energy distribution spectrum vector calculation unit includes:

[0029] A feature distribution energy collaborative representation vector calculation subunit is used to respectively calculate the feature distribution energy collaborative representation vector between each weak electric signal IMF component signal feature vector and other weak electric signal IMF component signal feature vectors in the set of weak electric signal IMF component signal feature vectors to obtain a sequence of multiple weak electric signal IMF component signal semantic feature distribution energy collaborative representation vectors;

[0030] The feature distribution energy synergy factor vector calculation subunit is used to calculate the feature distribution energy synergy factor vector of each sequence of the semantic feature distribution energy synergy representation vectors of the weak electric signal IMF component signals in the sequence of the multiple weak electric signal IMF component signal semantic feature distribution energy synergy representation vectors to obtain the sequence of the semantic feature energy distribution spectrum vectors of the weak electric signal IMF component signals.

[0031] For example, according to the semiconductor optoelectronic device micro-area bandwidth testing system of the embodiment of the present application, the characteristic distribution energy collaborative representation vector calculation subunit is used to:

[0032] Extracting a predetermined weak electric signal IMF component signal feature vector from a sequence of feature energy distribution spectrum vectors of the weak electric signal IMF component signal feature vector;

[0033] The predetermined weak electric signal IMF component signal feature vector and each of the other weak electric signal IMF component signal feature vectors are respectively subjected to element-by-element maximum value extraction to obtain a sequence of weak electric signal IMF component signal semantic feature distribution energy collaborative representation vectors corresponding to the predetermined weak electric signal IMF component signal feature vector.

[0034] For example, according to the semiconductor optoelectronic device micro-area bandwidth testing system of the embodiment of the present application, the characteristic distribution energy synergy factor vector calculation subunit is used to:

[0035] Respectively extracting the maximum value of each weak electric signal IMF component signal semantic feature distribution energy collaborative representation vector in the sequence of the weak electric signal IMF component signal semantic feature distribution energy collaborative representation vector to obtain a sequence of weak electric signal IMF component signal semantic feature maximum values;

[0036] Respectively calculating the mean and variance of the semantic feature distribution energy cooperative representation vector of each weak electric signal IMF component signal to obtain a sequence of the mean values ​​of the semantic features of the weak electric signal IMF component signal and a sequence of the semantic feature variances of the weak electric signal IMF component signal;

[0037] Adding the sequence of semantic feature variances of the weak electric signal IMF component signal and the preset hyperparameters by position to obtain a sequence of first energy distribution coefficients of semantic features of the weak electric signal IMF component signal;

[0038] Calculate the square of the difference between the maximum value of the semantic feature of the weak electric signal IMF component signal and the mean value of the semantic feature of the weak electric signal IMF component signal in each group corresponding to the sequence of the maximum value of the semantic feature of the weak electric signal IMF component signal and the sequence of the mean value of the semantic feature of the weak electric signal IMF component signal to obtain a sequence of semantic difference values ​​of the weak electric signal IMF component signal;

[0039] Multiplying the sequence of semantic feature variances of the weak electric signal IMF component signal by constant 2 by position to obtain a sequence of semantic feature variances of the modulated weak electric signal IMF component signal;

[0040] After adding each group of corresponding weak electric signal IMF component signal semantic difference values ​​and modulated weak electric signal IMF component signal semantic feature variances in the sequence of the weak electric signal IMF component signal semantic difference values ​​and the sequence of the modulated weak electric signal IMF component signal semantic feature variances, the sum is added to the preset hyperparameter to obtain a sequence of weak electric signal IMF component signal semantic feature second energy distribution coefficients;

[0041] The sequence of the first energy distribution coefficients of the semantic features of the weak electric signal IMF component signal is divided by position with the sequence of the second energy distribution coefficients of the semantic features of the weak electric signal IMF component signal to obtain the energy distribution spectrum vector of the semantic features of the weak electric signal IMF component signal composed of multiple feature distribution energy synergy factors.

[0042] For example, according to the semiconductor optoelectronic device micro-area bandwidth testing system of the embodiment of the present application, the energy distribution spectrum span factor calculation unit is used to:

[0043] Calculate the position difference between the semantic feature energy distribution spectrum vector of the weak electric signal IMF component signal and the center vector of the semantic energy spectrum distribution of the weak electric signal IMF component signal to obtain the semantic differential feature vector of the weak electric signal IMF component signal;

[0044] Calculate the covariance matrix between the center vector of the semantic energy spectrum distribution of the weak electric signal IMF component signal and the semantic feature energy distribution spectrum vector of the weak electric signal IMF component signal, and calculate the inverse of the covariance matrix to obtain the semantic inverse covariance matrix of the weak electric signal IMF component signal;

[0045] Calculate the product of the transposed vector of the weak electric signal IMF component signal semantic differential feature vector and the weak electric signal IMF component signal semantic inverse covariance matrix and the weak electric signal IMF component signal semantic differential feature vector to obtain the weak electric signal IMF component signal semantic distribution value;

[0046] The square root of the semantic distribution value of the IMF component signal of the weak electric signal is calculated to obtain the semantic energy distribution spectrum span factor of the IMF component signal of the weak electric signal.

[0047] For example, according to the semiconductor optoelectronic device micro-area bandwidth testing system of the embodiment of the present application, the optical flow signal generating module is used to:

[0048] Calculating the global mean vector of the set of the selected weak electric signal IMF component signal feature vectors to obtain the weak electric signal component signal component distillation representation vector;

[0049] The weak electric signal component signal component distillation representation vector is input into a decoder-based photoelectric signal measurement module to obtain the photocurrent signal decoding value.

[0050] The embodiment of the present application also provides a method for testing micro-area bandwidth of a semiconductor optoelectronic device, which comprises:

[0051] Provide the laser light source required for testing semiconductor optoelectronic devices;

[0052] Adjusting the frequency of the laser light source to obtain light responses at different frequencies;

[0053] Adjusting the irradiation position of the laser light source so that the laser light source irradiates a designated micro-region position on the semiconductor optoelectronic device to obtain a weak electrical signal;

[0054] Performing signal feature extraction and component distillation processing on the weak electrical signal based on signal decomposition and signal feature energy spectrum analysis to obtain a photocurrent signal value;

[0055] Obtaining the position of the micro-area to be measured and the value of the photocurrent signal to be measured;

[0056] Combining the micro-area position to be measured with the photocurrent signal value to be measured to obtain photocurrent signal values ​​at different positions at the same frequency, and then summarizing a plurality of photocurrent signal values ​​at different positions at the same frequency to obtain a matrix of photocurrent signal values ​​at different positions at the same frequency;

[0057] The position-weighted sum of the photocurrent signal value matrices at different positions under the same frequency is calculated to obtain bandwidth values ​​at different micro-region positions.

[0058] According to the semiconductor optoelectronic device micro-area bandwidth test system and method of the embodiment of the present application, it introduces a signal processing and analysis algorithm based on artificial intelligence and deep learning to perform signal decomposition and feature analysis on the weak electrical signal, so as to extract the component signal features in the weak electrical signal and the signal component distillation and aggregation semantic representation between these component signal features, so as to decode and generate the photocurrent signal value. In this way, it is possible to maintain a high degree of consistency under different test conditions and improve the accuracy and reliability of bandwidth measurement. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings of the embodiments of the present application are briefly introduced below. Obviously, the drawings described below only relate to some embodiments of the present application, and are not intended to limit the present application.

[0060] Figure 1 A schematic diagram of the structure of a semiconductor optoelectronic device micro-area bandwidth testing system in an embodiment of the present application is shown;

[0061] Figure 2 A schematic diagram of the structure of a micro-electric signal processor for a semiconductor optoelectronic device micro-area bandwidth test system in an embodiment of the present application is shown; and

[0062] Figure 3 A flow chart of a method for testing micro-area bandwidth of a semiconductor optoelectronic device in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0063] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work also fall within the scope of protection of the present application.

[0064] The terms used in this specification are those common terms currently widely used in the art in consideration of the functions of the present application, but these terms may vary according to the intentions of those skilled in the art, precedents, or new technologies in the art. In addition, specific terms may be selected, and in this case, their detailed meanings will be described in the detailed description of the present application. Therefore, the terms used in the specification should not be understood as simple names, but rather as a general description based on the meaning of the terms and the present application.

[0065] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules can be used and run on the user terminal and / or server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0066] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. At the same time, other operations may also be added to these processes, or a certain step or several steps of operations may be removed from these processes.

[0067] In addition, the application architecture diagram in the embodiment of the present application is intended to more clearly illustrate the technical solution in the embodiment of the present application, and does not constitute a limitation on the technical solution provided in the embodiment of the present application. Of course, for other application architectures and business applications, the technical solution provided in the embodiment of the present application is also applicable to similar problems.

[0068] The following is a non-restrictive description of a micro-area bandwidth testing system for semiconductor optoelectronic devices provided according to at least one embodiment of the present application through several examples or embodiments. As described below, different features in these specific examples or embodiments can be combined with each other without conflicting with each other to obtain new examples or embodiments, and these new examples or embodiments also fall within the scope of protection of the present application.

[0069] In view of the above technical problems, in the technical solution of the present application, a system for testing micro-area bandwidth of semiconductor optoelectronic devices is proposed, such as Figure 1As shown, it includes: a laser 810, a modulation system 820, a deterministic optical path 830, a precision displacement controller 840, a micro-electric signal processor 850 and a PC-side controller 860; the laser 810 is used to provide a laser light source required for testing semiconductor optoelectronic devices; the modulation system 820 is used to adjust the frequency of the laser light source to obtain light responses at different frequencies; the deterministic optical path 830 is used to adjust the irradiation position of the laser light source so that the laser light source irradiates a specified micro-region position on the semiconductor optoelectronic device to obtain a weak electric signal; the precision displacement controller 840 is used to control the movement of the semiconductor optoelectronic device by controlling the displacement platform; the micro-electric signal processor 850 is used to perform signal feature extraction and component distillation processing on the weak electric signal based on signal decomposition and signal feature energy spectrum analysis to obtain a photocurrent signal value; The C-end controller 860 includes a data transmission module 861, a data storage module 862 and a data processing module 863. The data transmission module 861 is communicatively connected to the precision displacement controller 840 and the micro-electric signal processor 850 respectively to obtain the position of the micro-area to be measured and the photocurrent signal value to be measured; the data storage module 862 is used to extract the position of the micro-area to be measured and the photocurrent signal value to be measured, and then combine the position of the micro-area to be measured with the photocurrent signal value to be measured to obtain the photocurrent signal value of different positions at the same frequency, and then summarize the photocurrent signal values ​​of multiple different positions at the same frequency to obtain a photocurrent signal value matrix of multiple different positions at the same frequency; the data processing module 863 is used to calculate the position-weighted sum of the photocurrent signal value matrix of the multiple different positions at the same frequency to obtain the bandwidth value of different micro-area positions.

[0070] In the above-mentioned semiconductor optoelectronic device micro-area bandwidth test system, the preamplifier and the phase-locked amplifier in the existing solution are replaced by a micro-electric signal processor to perform signal feature extraction and component distillation processing on the weak electric signal based on signal decomposition and signal feature energy spectrum analysis, thereby realizing signal decoding measurement of the photocurrent signal value. It is worth mentioning that the micro-electric signal processor can introduce a signal processing and analysis algorithm based on artificial intelligence and deep learning to perform signal decomposition and feature analysis on the weak electric signal, so as to extract the component signal features in the weak electric signal and the signal component distillation aggregation semantic representation between these component signal features, so as to decode and generate the photocurrent signal value. In this way, by introducing artificial intelligence and deep learning technology, it is possible to learn the complex pattern of the signal in an intelligent way, automatically identify and separate useful signal features, remove the influence of noise, and have good measurement and generalization capabilities in the case of weak signals or large noise, which helps to adapt to the test requirements that may change in the future. In this way, it is possible to maintain a high degree of consistency under different test conditions, thereby further improving the accuracy and reliability of bandwidth measurement.

[0071] Accordingly, if Figure 2 As shown, the micro-electric signal processor 850 includes: a weak electric signal decomposition module 851, which is used to perform CEEMDAN decomposition on the weak electric signal to obtain a set of weak electric signal IMF components; a weak electric signal component signal feature extraction module 852, which is used to perform feature extraction on each weak electric signal IMF component in the set of weak electric signal IMF components to obtain a set of weak electric signal IMF component signal feature vectors; a weak electric signal component signal semantic selection optimization module 853, which is used to input the set of weak electric signal IMF component signal feature vectors into a sequence screening module based on characteristic energy spectrum analysis to obtain a set of selected weak electric signal IMF component signal feature vectors; an optical flow signal generation module 854, which is used to generate a weak electric signal component signal component distillation representation vector based on the set of selected weak electric signal IMF component signal feature vectors, and determine the photocurrent signal decoding value.

[0072] Specifically, in the micro-electric signal processor, first, the acquired weak electric signal is decomposed by CEEMDAN to obtain a set of IMF components of the weak electric signal. It should be understood that in the semiconductor optoelectronic device micro-area bandwidth test system, the processing of weak electric signals is a challenge because the signal usually contains a lot of noise and other interference factors, which will affect the final measurement results. Therefore, in order to extract useful information from the weak electric signal, thereby generating a more accurate photocurrent signal value, and providing an accurate data basis for subsequent bandwidth testing, in the technical solution of the present application, the CEEMDAN decomposition technology is used to obtain the IMF component set of the weak electric signal. The main advantage of the CEEMDAN decomposition technology is that it can decompose complex nonlinear signals into a set of relatively simple, physically meaningful IMF components. Each IMF component represents the fluctuation characteristics of the weak electric signal at different scales, and such a decomposition helps to distinguish different features in the weak electric signal, such as periodic components, trend components, and random noise. In this way, useful information in the weak electric signal can be more easily identified while suppressing the influence of noise.

[0073] Next, in order to extract meaningful signal features from each weak electric signal IMF component, so as to better understand and analyze the content of the weak electric signal, based on this, in the technical solution of the present application, each weak electric signal IMF component in the set of weak electric signal IMF components is further input into a component signal feature extractor based on the 1D-CNN model for feature mining, so as to extract the signal semantic features in each weak electric signal IMF component, thereby obtaining a set of weak electric signal IMF component signal feature vectors.

[0074] Correspondingly, the weak electric signal component signal feature extraction module 852 is used to: input each weak electric signal IMF component in the set of weak electric signal IMF components into a component signal feature extractor based on the 1D-CNN model to obtain a set of weak electric signal IMF component signal feature vectors.

[0075] Furthermore, since each weak electric signal IMF component signal feature vector in the set of weak electric signal IMF component signal feature vectors contains different IMF component signal semantic feature information, which respectively reflect different component features in the weak electric signal, some of these component features play an important role and contribution to the analysis and understanding of weak electric signals and the subsequent measurement tasks of photocurrent signal values, while some are redundant information and noise interference information. Therefore, in order to further optimize the expression of weak electric signal IMF component signal features, it is necessary to select these component signal features to remove those irrelevant or noisy feature vectors, retain the most representative and informative feature vectors, and provide a basis for subsequent photoelectric signal flow signal measurement tasks. Based on this, in the technical solution of the present application, the set of weak electric signal IMF component signal feature vectors is further input into a sequence screening module based on characteristic energy spectrum analysis to obtain a set of selected weak electric signal IMF component signal feature vectors.

[0076] Specifically, the sequence screening module based on characteristic energy spectrum analysis first calculates the characteristic energy distribution spectrum vector for each weak electric signal IMF component signal feature vector. This step can map each weak electric signal IMF component signal feature vector to an energy distribution spectrum space, in which the distribution of the feature vector at different frequencies or energy levels can be better understood. In this way, the periodic patterns or trends that may exist in the feature vectors of each weak electric signal IMF component signal can be captured, and these patterns may not be obvious in the original feature space. Next, the position mean vector of the semantic feature energy distribution spectrum vector of all weak electric signal IMF component signals is calculated, that is, the so-called weak electric signal IMF component signal semantic energy spectrum distribution center vector. This center vector represents the average position or center position of all weak electric signal IMF component signal semantic features in the energy distribution spectrum space, which can be used to evaluate the closeness of other IMF component signal semantic features to the overall distribution in the energy distribution spectrum space. Then, the difference between the semantic feature energy distribution spectrum vector of each weak electric signal IMF component signal and the center vector is calculated, namely, the "semantic energy distribution spectrum span factor of the weak electric signal IMF component signal". These span factors quantify the distance between the semantic feature energy distribution spectrum vector of each weak electric signal IMF component signal and the center vector, reflecting the discrete degree of the feature vector. Finally, based on the comparison between the semantic energy distribution spectrum span factor of each weak electric signal IMF component signal and the preset threshold, the weak electric signal IMF component signal feature vectors that meet the conditions are selected to form a new sequence. By selecting feature vectors within a certain range of distance from the center vector, the selection optimization of feature vectors is achieved. In this way, feature vectors that deviate far from the center and may contain noise or outliers can be removed, and the most representative and informative feature vectors of weak electric signal IMF component signals can be retained.

[0077] Correspondingly, the weak electric signal component signal semantic selection optimization module 853 includes: a characteristic energy distribution spectrum vector calculation unit, which is used to calculate the characteristic energy distribution spectrum vector of each weak electric signal IMF component signal feature vector in the set of the weak electric signal IMF component signal feature vector to obtain a sequence of weak electric signal IMF component signal semantic feature energy distribution spectrum vectors; a position mean vector calculation unit, which is used to calculate the position mean vector of the sequence of the weak electric signal IMF component signal semantic feature energy distribution spectrum vectors as the weak electric signal IMF component signal semantic energy spectrum distribution center vector; an energy distribution spectrum span factor calculation unit, which is used to calculate the The energy distribution spectrum span factor between the center vector of the semantic energy spectrum distribution of the weak electric signal IMF component signal and each semantic feature energy distribution spectrum vector of the weak electric signal IMF component signal in the sequence of the semantic feature energy distribution spectrum vector of the weak electric signal IMF component signal is used to obtain a sequence of semantic energy distribution spectrum span factors of the weak electric signal IMF component signal; a preset threshold comparison unit is used to determine the set of the selected weak electric signal IMF component signal feature vectors based on the comparison between each semantic energy distribution spectrum span factor of the weak electric signal IMF component signal in the sequence of semantic energy distribution spectrum span factors of the weak electric signal IMF component signal and a preset threshold.

[0078] Among them, the characteristic energy distribution spectrum vector calculation unit includes: a characteristic distribution energy synergistic representation vector calculation subunit, which is used to respectively calculate the characteristic distribution energy synergistic representation vector between each weak electric signal IMF component signal feature vector and other each weak electric signal IMF component signal feature vector in the set of the weak electric signal IMF component signal feature vector to obtain a sequence of multiple weak electric signal IMF component signal semantic feature distribution energy synergistic representation vectors; a characteristic distribution energy synergistic factor vector calculation subunit, which is used to calculate the characteristic distribution energy synergistic factor vector of the sequence of each weak electric signal IMF component signal semantic feature distribution energy synergistic representation vector in the sequence of the multiple weak electric signal IMF component signal semantic feature distribution energy synergistic representation vectors to obtain the sequence of the weak electric signal IMF component signal semantic feature energy distribution spectrum vectors.

[0079] Specifically, the feature distribution energy collaborative representation vector calculation subunit is used to: extract a predetermined weak electric signal IMF component signal feature vector from a sequence of feature energy distribution spectrum vectors of the weak electric signal IMF component signal feature vector; perform element-by-element maximum value extraction on the predetermined weak electric signal IMF component signal feature vector and each of the other weak electric signal IMF component signal feature vectors, so as to obtain a sequence of weak electric signal IMF component signal semantic feature distribution energy collaborative representation vectors corresponding to the predetermined weak electric signal IMF component signal feature vector.

[0080] Specifically, the feature distribution energy synergy factor vector calculation subunit is used to: respectively extract the maximum value of each weak electric signal IMF component signal semantic feature distribution energy synergy representation vector in the sequence of the weak electric signal IMF component signal semantic feature distribution energy synergy representation vector to obtain a sequence of weak electric signal IMF component signal semantic feature maximum values; respectively calculate the mean and variance of each weak electric signal IMF component signal semantic feature distribution energy synergy representation vector to obtain a sequence of weak electric signal IMF component signal semantic feature mean values ​​and a sequence of weak electric signal IMF component signal semantic feature variances; add the sequence of weak electric signal IMF component signal semantic feature variances and preset hyperparameters by position to obtain a sequence of weak electric signal IMF component signal semantic feature first energy distribution coefficients; calculate the sequence of weak electric signal IMF component signal semantic feature maximum values ​​and weak electric signal IMF component signal semantic feature mean values ​​in each group of the weak electric signal IMF component signal semantic feature maximum values ​​and weak electric signal IMF component signal semantic feature variances. The square of the difference between the means of the semantic features of the F component signals is calculated to obtain a sequence of semantic difference values ​​of the weak electric signal IMF component signals; the sequence of semantic feature variances of the weak electric signal IMF component signals is multiplied by constant two by position to obtain a sequence of semantic feature variances of the modulated weak electric signal IMF component signals; after adding each group of corresponding weak electric signal IMF component signal semantic difference values ​​and modulated weak electric signal IMF component signal semantic feature variances in the sequence of semantic feature difference values ​​of the weak electric signal IMF component signals and the sequence of semantic feature variances of the modulated weak electric signal IMF component signals, the sum is added to the preset hyperparameter to obtain a sequence of second energy distribution coefficients of semantic features of the weak electric signal IMF component signals; the sequence of first energy distribution coefficients of semantic features of the weak electric signal IMF component signals is divided by the sequence of second energy distribution coefficients of semantic features of the weak electric signal IMF component signals by position to obtain an energy distribution spectrum vector of the semantic feature of the weak electric signal IMF component signals composed of multiple feature distribution energy synergy factors.

[0081] Among them, the energy distribution spectrum span factor calculation unit is used to: calculate the positional difference between the weak electric signal IMF component signal semantic feature energy distribution spectrum vector and the weak electric signal IMF component signal semantic energy spectrum distribution center vector to obtain the weak electric signal IMF component signal semantic differential feature vector; calculate the covariance matrix between the weak electric signal IMF component signal semantic energy spectrum distribution center vector and the weak electric signal IMF component signal semantic feature energy distribution spectrum vector, and calculate the inverse of the covariance matrix to obtain the weak electric signal IMF component signal semantic inverse covariance matrix; calculate the transposed vector of the weak electric signal IMF component signal semantic differential feature vector and the product of the weak electric signal IMF component signal semantic inverse covariance matrix and the weak electric signal IMF component signal semantic differential feature vector to obtain the weak electric signal IMF component signal semantic distribution value; calculate the square root of the weak electric signal IMF component signal semantic distribution value to obtain the weak electric signal IMF component signal semantic energy distribution spectrum span factor.

[0082] In a specific example, the weak electric signal component signal semantic selection optimization module 853 is used to: input the set of weak electric signal IMF component signal feature vectors into the sequence screening module based on characteristic energy spectrum analysis to process with the following feature selection optimization formula to obtain the set of selected weak electric signal IMF component signal feature vectors; wherein the feature selection optimization formula is:

[0083]

[0084]

[0085]

[0086]

[0087]

[0088]

[0089]

[0090] in, and Respectively represent the first and The signal eigenvectors of the weak electric signal IMF components, It means taking the maximum value between two vectors element by element. For the and The weak electric signal IMF component signal semantic feature distribution energy collaborative representation vector between the weak electric signal IMF component signal feature vectors, To extract the maximum value of a vector, and They are The mean and variance of To preset hyperparameters, is the first in the sequence of semantic feature energy distribution spectrum vectors of the IMF component signal of the weak electric signal The semantic feature energy distribution spectrum vector of the IMF component signal of the weak electric signal The characteristic distribution energy synergy factor, For the The semantic feature energy distribution spectrum vector of the IMF component signal of the weak electric signal The characteristic distribution energy synergy factor, A sequence representing the energy distribution spectrum vector of the semantic feature of the IMF component signal of the weak electric signal, is the first in the sequence of semantic feature energy distribution spectrum vectors of the IMF component signal of the weak electric signal The semantic feature energy distribution spectrum vector of the weak electric signal IMF component signal, is the number of vectors in the sequence of the semantic feature energy distribution spectrum vector of the IMF component signal of the weak electric signal, is the center vector of the semantic energy spectrum distribution of the IMF component signal of the weak electric signal, is the transpose of a vector, It is The covariance matrix between the semantic feature energy distribution spectrum vector of the weak electric signal IMF component signal and the center vector of the semantic energy spectrum distribution of the weak electric signal IMF component signal, For the The semantic energy distribution spectrum span factor of the weak electric signal IMF component signal corresponding to the semantic feature energy distribution spectrum vector of the weak electric signal IMF component signal, is the preset threshold, is the first in the set of the selected weak electric signal IMF component signal feature vectors The selected weak electric signal IMF component signal feature vector, is the set of the selected weak electric signal IMF component signal feature vectors.

[0091] Then, since each selected weak electric signal IMF component signal feature vector in the set of the selected weak electric signal IMF component signal feature vectors respectively contains the semantic features of the weak electric signal IMF component signal after feature selection optimization, these selected and optimized weak electric signal IMF component signal semantic features have filtered the noise component semantics in the weak electric signal and the redundant information irrelevant to the subsequent task, so as to better reflect the true attributes of the signal. Therefore, in the technical solution of the present application, the global mean vector of the set of the selected weak electric signal IMF component signal feature vectors is further calculated to obtain the weak electric signal component signal component distillation representation vector. By calculating the global mean vector between multiple selected weak electric signal IMF component signal feature vectors, a vector representing the average level of these feature vectors can be found in a statistical sense. This mean vector can be regarded as a distillation representation, which integrates all the filtered weak electric signal IMF component signal feature information, removes unnecessary details and noise, highlights the essential semantics and characteristics of the signal, and helps to more accurately perform the photocurrent signal measurement task, thereby obtaining a more accurate bandwidth value.

[0092] Then, the weak electric signal component signal component distillation representation vector is input into the decoder-based photoelectric signal measurement module to obtain the photocurrent signal decoding value. That is to say, the decoding regression is performed by selecting and optimizing the component distillation representation information between the semantic features of the IMF component signal of the weak electric signal to generate the photocurrent signal value. In this way, by introducing artificial intelligence and deep learning technology, it is possible to learn the complex pattern of the signal in an intelligent way, and automatically identify and separate useful signal features, remove the influence of noise, and have good measurement and generalization capabilities even when the signal is weak or the noise is large, which helps to adapt to the test requirements that may change in the future. In this way, it is possible to maintain a high degree of consistency under different test conditions, thereby further improving the accuracy and reliability of bandwidth measurement.

[0093] Correspondingly, the optical flow signal generation module 854 is used to: calculate the global mean vector of the set of selected weak electric signal IMF component signal feature vectors to obtain the weak electric signal component signal component distillation representation vector; input the weak electric signal component signal component distillation representation vector into the decoder-based photoelectric signal measurement module to obtain the photocurrent signal decoding value.

[0094] In a preferred example, the weak electric signal component signal component distillation representation vector is input into a decoder-based photoelectric signal measurement module to obtain the photocurrent signal decoding value, including: determining the weak electric signal component signal component distillation maximum eigenvalue and the weak electric signal component signal component distillation minimum eigenvalue of the weak electric signal component signal component distillation representation vector, and calculating the weak electric signal component signal component distillation mean and the weak electric signal component signal component distillation standard deviation of the feature set of the weak electric signal component signal component distillation representation vector; calculating the quotient of the weak electric signal component signal component distillation mean and the weak electric signal component signal component distillation standard deviation to obtain the weak electric signal component signal component distillation statistical normalization value; calculating the inverse of each eigenvalue of the weak electric signal component signal component distillation representation vector, and comparing it with the weak electric signal component signal component distillation maximum eigenvalue. After multiplying the difference between the eigenvalue and the minimum eigenvalue of the weak electric signal component signal component distillation, subtract the eigenvalue from the weak electric signal component signal component distillation statistical normalized value to obtain the weak electric signal component signal component distillation distribution approximation vector; calculate an exponential function with a natural constant as the base, with each eigenvalue of the weak electric signal component signal component distillation distribution approximation vector as an exponent, and add the eigenvalue to the weak electric signal component signal component distillation statistical normalized value to obtain the weak electric signal component signal component distillation probability approximation vector; calculate the base-two logarithm of the absolute value of each eigenvalue of the weak electric signal component signal component distillation probability approximation vector to obtain an optimized weak electric signal component signal component distillation representation vector; and pass the optimized weak electric signal component signal component distillation representation vector through the decoder-based photoelectric signal measurement module to obtain the optical flow signal decoding value.

[0095] Among them, the signal component distillation representation vector of the weak electric signal component is recorded as The optimization process is expressed as follows:

[0096]

[0097] in, is the distilled representation vector of the weak electric signal component signal, , , and They are the feature sets of the distillation representation vectors of the weak electric signal components. The mean, standard deviation, minimum and maximum values ​​of Indicates point reduction, represents dot product, Indicates point addition, To calculate the inverse of each eigenvalue of the distillation representation vector of the weak electric signal component signal component, is an exponential operation of a value, wherein the exponential operation of the value represents the calculation of the value of a natural exponential function with the value as a power, and is the logarithmic function value with base 2, is the optimized signal component distillation representation vector of the weak electric signal component.

[0098] Here, in the preferred example, considering that each weak electric signal IMF component signal feature vector in the set of the weak electric signal IMF component signal feature vectors respectively represents the signal waveform semantic features of each weak electric signal IMF component determined by the weak electric signal through CEEMDAN decomposition, after performing sequence screening based on characteristic energy spectrum analysis, unimportant components in the set of weak electric signal IMF component signal feature vectors will be filtered and important components will be given more attention, which can improve the significance of the selected set of weak electric signal IMF component signal feature vectors as a whole feature distribution, but will also make the selected set of weak electric signal IMF component signal feature vectors as a whole feature distribution have a relatively stronger diversified set expression distribution. Therefore, it is expected to improve the balance between the regression mapping accuracy and completeness of the weak electric signal component signal component distillation representation vector when decoding regression is performed through the decoder-based photoelectric signal measurement module, thereby improving the accuracy of the obtained optical flow signal decoding value.

[0099] Therefore, by performing random statistical normalization on the diversified feature set of the weak electric signal component signal component distillation representation vector, the confidence space constructed based on the overall eigenvalue of the weak electric signal component signal component distillation representation vector is approximated by the standardized continuous probability density distribution relative to the response hypothesis test of each eigenvalue of the weak electric signal component signal component distillation representation vector, thereby establishing the target reachability of the discrete feature distribution of the weak electric signal component signal component distillation representation vector to the unified regression target, so as to achieve the balanced executableness between mapping accuracy and mapping completeness in the decoding regression process based on the discrete feature distribution of the weak electric signal component signal component distillation representation vector, and improve the accuracy of the optical flow signal decoding value obtained by the weak electric signal component signal component distillation representation vector through the decoder-based photoelectric signal measurement module. In this way, the photocurrent signal value can be generated more accurately, and in this way, a high degree of consistency can be maintained under different test conditions, thereby further improving the accuracy and reliability of bandwidth measurement.

[0100] Based on the above embodiments, see Figure 3 As shown in FIG. 1 , it is a flow chart of a method for testing micro-area bandwidth of a semiconductor optoelectronic device in an embodiment of the present application. Figure 3As shown, according to the embodiment of the present application, the method for testing the micro-area bandwidth of a semiconductor optoelectronic device includes the following steps: S510, providing a laser light source required for testing a semiconductor optoelectronic device; S520, regulating the frequency of the laser light source to obtain light responses at different frequencies; S530, adjusting the irradiation position of the laser light source so that the laser light source irradiates a designated micro-area position on the semiconductor optoelectronic device to obtain a weak electrical signal; S540, performing signal feature extraction and component distillation processing on the weak electrical signal based on signal decomposition and signal feature energy spectrum analysis to obtain a photocurrent signal value; S550, obtaining a micro-area position to be tested and a photocurrent signal value to be tested; S560, combining the micro-area position to be tested with the photocurrent signal value to be tested to obtain photocurrent signal values ​​at different positions at the same frequency, and then summing up a plurality of photocurrent signal values ​​at different positions at the same frequency to obtain a plurality of photocurrent signal value matrices at different positions at the same frequency; S570, calculating the position-weighted sum of the photocurrent signal value matrices at different positions at the same frequency to obtain bandwidth values ​​at different micro-area positions.

[0101] Here, those skilled in the art will appreciate that the specific operations of each step in the above-mentioned method for testing the micro-area bandwidth of a semiconductor optoelectronic device have been described in the above reference. Figure 1 to Figure 2 The micro-area bandwidth testing system 800 for semiconductor optoelectronic devices has been described in detail, and therefore, its repeated description will be omitted.

[0102] Based on the above embodiments, another exemplary embodiment of an electronic device is also provided in the embodiments of the present application. In some possible implementations, the electronic device in the embodiments of the present application may include a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor can implement the steps of the semiconductor optoelectronic device micro-area bandwidth test method in the above embodiments when executing the program.

[0103] The embodiment of the present application also provides a computer-readable storage medium, on which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, the method for testing the micro-area bandwidth of a semiconductor optoelectronic device according to the embodiment of the present application described with reference to the above figures can be executed. The computer-readable storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. The volatile memory may, for example, include a random access memory (RAM) and / or a cache memory (cache), etc. The non-volatile memory may, for example, include a read-only memory (ROM), a hard disk, a flash memory, etc.

[0104] The embodiment of the present application also provides a computer program product or a computer program, which includes computer executable instructions, and the computer executable instructions are stored in a computer readable storage medium. The processor of the computer device reads the computer executable instructions from the computer readable storage medium, and the processor executes the computer executable instructions, so that the computer device executes the semiconductor optoelectronic device micro-area bandwidth test method according to the embodiment of the present application.

[0105] Those skilled in the art will appreciate that the contents disclosed in this application may be subject to various variations and improvements. For example, the various devices or components described above may be implemented by hardware, or by software, firmware, or a combination of some or all of the three.

[0106] In addition, although the present application makes various references to certain units in the system according to embodiments of the present application, any number of different units can be used and run on the client and / or server. The units are only illustrative, and different aspects of the system and method can use different units.

[0107] Those skilled in the art will appreciate that all or part of the steps in the above method can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, such as a read-only memory, a disk or an optical disk. Optionally, all or part of the steps in the above embodiment can also be implemented using one or more integrated circuits. Accordingly, each module / unit in the above embodiment can be implemented in the form of hardware or in the form of software function modules. The present application is not limited to any particular form of combination of hardware and software.

[0108] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art to which this application belongs. It should also be understood that terms such as those defined in common dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an idealized or extremely formal sense, unless explicitly defined as such herein.

[0109] The above is an explanation of the present application and should not be considered as limiting thereof. Although several exemplary embodiments of the present application have been described, those skilled in the art will readily appreciate that many modifications may be made to the exemplary embodiments without departing from the novel teachings and advantages of the present application.

Claims

1. A micro-area bandwidth testing system for semiconductor optoelectronic devices, characterized in that: include: Laser, modulation system, deterministic optical path, precision displacement controller, micro-electric signal processor and PC-side controller; The laser is used to provide a laser light source required for testing semiconductor optoelectronic devices; The modulation system is used to adjust the frequency of the laser light source to obtain light responses at different frequencies; The deterministic optical path is used to adjust the irradiation position of the laser light source so that the laser light source irradiates a designated micro-region position on the semiconductor optoelectronic device to obtain a weak electrical signal; The precision displacement controller is used to control the movement of the semiconductor optoelectronic device by controlling the displacement platform; The micro-electric signal processor is used to perform signal feature extraction and component distillation processing on the weak electric signal based on signal decomposition and signal feature energy spectrum analysis to obtain a photocurrent signal value; The PC-side controller includes a data transmission module, a data storage module and a data processing module, and the data transmission module is communicatively connected with the precision displacement controller and the micro-electric signal processor respectively to obtain the position of the micro-area to be measured and the value of the photocurrent signal to be measured; The data storage module is used to extract the position of the micro-area to be measured and the photocurrent signal value to be measured, then combine the position of the micro-area to be measured with the photocurrent signal value to be measured to obtain the photocurrent signal values ​​of different positions at the same frequency, and then summarize the photocurrent signal values ​​of multiple different positions at the same frequency to obtain a matrix of photocurrent signal values ​​of multiple different positions at the same frequency; The data processing module is used to calculate the position-weighted sum of the photocurrent signal value matrices at different positions under the same frequency to obtain bandwidth values ​​at different micro-region positions; The micro-electric signal processor comprises: A weak electric signal decomposition module, used for performing CEEMDAN decomposition on the weak electric signal to obtain a set of IMF components of the weak electric signal; A weak electric signal component signal feature extraction module, used for respectively extracting features of each weak electric signal IMF component in the set of weak electric signal IMF components to obtain a set of weak electric signal IMF component signal feature vectors; A weak electric signal component signal semantic selection optimization module, used for inputting the set of weak electric signal IMF component signal feature vectors into a sequence screening module based on characteristic energy spectrum analysis to obtain a set of selected weak electric signal IMF component signal feature vectors; An optical flow signal generation module is used to generate a weak electric signal component signal component distillation representation vector based on the set of weak electric signal IMF component signal feature vectors selected, and determine a photocurrent signal decoding value; The optical flow signal generating module is used for: Calculating the global mean vector of the set of the selected weak electric signal IMF component signal feature vectors to obtain the weak electric signal component signal component distillation representation vector; The weak electric signal component signal component distillation representation vector is input into a decoder-based photoelectric signal measurement module to obtain the photocurrent signal decoding value.

2. The micro-area bandwidth testing system for semiconductor optoelectronic devices according to claim 1, characterized in that: The weak electric signal component signal feature extraction module is used to: input each weak electric signal IMF component in the set of weak electric signal IMF components into a component signal feature extractor based on a 1D-CNN model to obtain a set of weak electric signal IMF component signal feature vectors.

3. The micro-area bandwidth testing system for semiconductor optoelectronic devices according to claim 2, characterized in that: The weak electric signal component signal semantic selection optimization module comprises: A characteristic energy distribution spectrum vector calculation unit is used to calculate the characteristic energy distribution spectrum vector of each weak electric signal IMF component signal feature vector in the set of the weak electric signal IMF component signal feature vectors to obtain a sequence of semantic characteristic energy distribution spectrum vectors of the weak electric signal IMF component signal; A position-based mean vector calculation unit is used to calculate the position-based mean vector of the sequence of semantic feature energy distribution spectrum vectors of the weak electric signal IMF component signal as the center vector of the semantic energy spectrum distribution of the weak electric signal IMF component signal; An energy distribution spectrum span factor calculation unit is used to calculate the energy distribution spectrum span factor between the weak electric signal IMF component signal semantic energy spectrum distribution center vector and each weak electric signal IMF component signal semantic feature energy distribution spectrum vector in the sequence of the weak electric signal IMF component signal semantic feature energy distribution spectrum vector to obtain a sequence of weak electric signal IMF component signal semantic energy distribution spectrum span factors; A preset threshold comparison unit is used to determine the set of selected weak electric signal IMF component signal feature vectors based on the comparison between each weak electric signal IMF component signal semantic energy distribution spectrum span factor in the sequence of the weak electric signal IMF component signal semantic energy distribution spectrum span factor and the preset threshold.

4. The micro-area bandwidth testing system for semiconductor optoelectronic devices according to claim 3, characterized in that: The characteristic energy distribution spectrum vector calculation unit comprises: A feature distribution energy collaborative representation vector calculation subunit is used to respectively calculate the feature distribution energy collaborative representation vector between each weak electric signal IMF component signal feature vector and other weak electric signal IMF component signal feature vectors in the set of weak electric signal IMF component signal feature vectors to obtain a sequence of multiple weak electric signal IMF component signal semantic feature distribution energy collaborative representation vectors; The feature distribution energy synergy factor vector calculation subunit is used to calculate the feature distribution energy synergy factor vector of each sequence of the semantic feature distribution energy synergy representation vectors of the weak electric signal IMF component signals in the sequence of the multiple weak electric signal IMF component signal semantic feature distribution energy synergy representation vectors to obtain the sequence of the semantic feature energy distribution spectrum vectors of the weak electric signal IMF component signals.

5. The micro-area bandwidth testing system for semiconductor optoelectronic devices according to claim 4, characterized in that: The feature distribution energy collaborative representation vector calculation subunit is used to: Extracting a predetermined weak electric signal IMF component signal feature vector from a sequence of feature energy distribution spectrum vectors of the weak electric signal IMF component signal feature vector; The predetermined weak electric signal IMF component signal feature vector and each of the other weak electric signal IMF component signal feature vectors are respectively subjected to element-by-element maximum value extraction to obtain a sequence of weak electric signal IMF component signal semantic feature distribution energy collaborative representation vectors corresponding to the predetermined weak electric signal IMF component signal feature vector.

6. The micro-area bandwidth testing system for semiconductor optoelectronic devices according to claim 5, characterized in that: The characteristic distribution energy synergy factor vector calculation subunit is used to: Respectively extracting the maximum value of each weak electric signal IMF component signal semantic feature distribution energy collaborative representation vector in the sequence of the weak electric signal IMF component signal semantic feature distribution energy collaborative representation vector to obtain a sequence of weak electric signal IMF component signal semantic feature maximum values; Respectively calculating the mean and variance of the semantic feature distribution energy cooperative representation vector of each weak electric signal IMF component signal to obtain a sequence of the mean values ​​of the semantic features of the weak electric signal IMF component signal and a sequence of the semantic feature variances of the weak electric signal IMF component signal; Adding the sequence of semantic feature variances of the weak electric signal IMF component signal and the preset hyperparameters by position to obtain a sequence of first energy distribution coefficients of semantic features of the weak electric signal IMF component signal; Calculate the square of the difference between the maximum value of the semantic feature of the weak electric signal IMF component signal and the mean value of the semantic feature of the weak electric signal IMF component signal in each group corresponding to the sequence of the maximum value of the semantic feature of the weak electric signal IMF component signal and the sequence of the mean value of the semantic feature of the weak electric signal IMF component signal to obtain a sequence of semantic difference values ​​of the weak electric signal IMF component signal; Multiplying the sequence of semantic feature variances of the weak electric signal IMF component signal by constant 2 by position to obtain a sequence of semantic feature variances of the modulated weak electric signal IMF component signal; After adding each group of corresponding weak electric signal IMF component signal semantic difference values ​​and modulated weak electric signal IMF component signal semantic feature variances in the sequence of the weak electric signal IMF component signal semantic difference values ​​and the sequence of the modulated weak electric signal IMF component signal semantic feature variances, the sum is added to the preset hyperparameter to obtain a sequence of weak electric signal IMF component signal semantic feature second energy distribution coefficients; The sequence of the first energy distribution coefficients of the semantic features of the weak electric signal IMF component signal is divided by position with the sequence of the second energy distribution coefficients of the semantic features of the weak electric signal IMF component signal to obtain the energy distribution spectrum vector of the semantic features of the weak electric signal IMF component signal composed of multiple feature distribution energy synergy factors.

7. The micro-area bandwidth testing system for semiconductor optoelectronic devices according to claim 6, characterized in that: The energy distribution spectrum span factor calculation unit is used to: Calculate the position difference between the semantic feature energy distribution spectrum vector of the weak electric signal IMF component signal and the center vector of the semantic energy spectrum distribution of the weak electric signal IMF component signal to obtain the semantic differential feature vector of the weak electric signal IMF component signal; Calculate the covariance matrix between the center vector of the semantic energy spectrum distribution of the weak electric signal IMF component signal and the semantic feature energy distribution spectrum vector of the weak electric signal IMF component signal, and calculate the inverse of the covariance matrix to obtain the semantic inverse covariance matrix of the weak electric signal IMF component signal; Calculate the product of the transposed vector of the weak electric signal IMF component signal semantic differential feature vector and the weak electric signal IMF component signal semantic inverse covariance matrix and the weak electric signal IMF component signal semantic differential feature vector to obtain the weak electric signal IMF component signal semantic distribution value; The square root of the semantic distribution value of the IMF component signal of the weak electric signal is calculated to obtain the semantic energy distribution spectrum span factor of the IMF component signal of the weak electric signal.

8. A method for testing micro-area bandwidth of semiconductor optoelectronic devices, performed by the micro-area bandwidth testing system for semiconductor optoelectronic devices as claimed in claim 1, characterized in that: The method comprises: Provide the laser light source required for testing semiconductor optoelectronic devices; Adjusting the frequency of the laser light source to obtain light responses at different frequencies; Adjusting the irradiation position of the laser light source so that the laser light source irradiates a designated micro-region position on the semiconductor optoelectronic device to obtain a weak electrical signal; Performing signal feature extraction and component distillation processing on the weak electrical signal based on signal decomposition and signal feature energy spectrum analysis to obtain a photocurrent signal value; Obtaining the position of the micro-area to be measured and the value of the photocurrent signal to be measured; Combining the micro-area position to be measured with the photocurrent signal value to be measured to obtain photocurrent signal values ​​at different positions at the same frequency, and then summarizing a plurality of photocurrent signal values ​​at different positions at the same frequency to obtain a matrix of photocurrent signal values ​​at different positions at the same frequency; The position-weighted sum of the photocurrent signal value matrices at different positions under the same frequency is calculated to obtain bandwidth values ​​at different micro-region positions.

Images