Photon device parameter reverse extraction model construction method and device, terminal, medium and characterization method

Abstract

The application provides a photonic device parameter reverse extraction model construction method and device, a terminal, a medium and a characterization method. The method comprises the following steps: obtaining forward mapping data set of a photonic device in a preset parameter space; the forward mapping data set comprises a plurality of photonic device parameter data in the preset parameter space and corresponding physical parameter data; calculating the parameter sensitivity of different parameter combinations of the physical parameters with respect to the photonic device parameters and the coupling degree matrix; extracting evaluation indexes from the calculated matrices respectively and screening out the optimal parameter combination in the preset parameter space according to the evaluation indexes; and constructing a corresponding photonic device parameter reverse extraction model based on the optimal parameter combination and the forward mapping data set. The application introduces a matrix in mathematics into the photonic device characterization field, pre-selects the optimal parameter combination, constructs a more suitable photonic device parameter reverse extraction model, and greatly avoids ill-posed inversion.

Description

Technical Field

[0001] This application relates to the fields of semiconductor optoelectronic integrated manufacturing and photonics testing and characterization technology, and in particular to a method, apparatus, terminal, medium and characterization method for reverse extraction model construction of photonic device parameters. Background Technology

[0002] In the fabrication of photonic chips, process variations (such as changes in waveguide width and thickness due to etching deviations) can severely impact performance. Existing techniques typically infer the underlying geometric parameters (such as width and height) of the actual fabricated structure by testing the optical response parameters (such as effective refractive index and group refractive index) of the passive structure. However, these techniques suffer from the following drawbacks: First, engineers often rely on experience to select optical parameters. If there is a linear correlation between the selected optical parameters, it can lead to system underdeterminacy; if the system is ill-conditioned, even minute instrument noise (such as 0.1%) can be drastically amplified during inference, resulting in significant errors in the geometric parameters. Second, the actual process variations are large, and using a single linear or low-order model often results in significant fitting errors globally. Third, the sensitivity of the optical field to the geometry differs in different geometric regions (such as narrow and wide waveguide regions). A set of optical parameters that is optimal in region A may be completely ineffective in region B (with extremely low signal-to-noise ratio), a problem that traditional single models cannot solve. Summary of the Invention

[0003] In view of the shortcomings of the prior art described above, the purpose of this application is to provide a method, apparatus, terminal, medium and characterization method for reverse extraction model construction of photonic device parameters, so as to solve at least one of the technical problems in the prior art.

[0004] To achieve the above and other related objectives, a first aspect of this application provides a method for constructing a reverse extraction model for photonic device parameters, comprising: acquiring a forward mapping dataset of photonic devices in a preset parameter space; wherein the forward mapping dataset includes multiple photonic device parameter data and corresponding physical parameter data in the preset parameter space; calculating the parameter sensitivity and coupling metric matrices of different combinations of physical parameters relative to the photonic device parameters; extracting evaluation indicators from each parameter sensitivity and coupling metric matrix and selecting the optimal parameter combination in the preset parameter space accordingly; and constructing a corresponding reverse extraction model for photonic device parameters based on the optimal parameter combination and the forward mapping dataset.

[0005] In some embodiments of the first aspect of this application, obtaining a forward mapping dataset of photonic devices in a preset parameter space includes: obtaining physical parameter data corresponding to multiple photonic device parameter data in the preset parameter space by simulating or actually measuring the photonic devices; the multiple photonic device parameter data in the preset parameter space and their corresponding physical parameter data constitute a forward mapping dataset.

[0006] In some embodiments of the first aspect of this application, the photonic device parameters include one or more types of photonic device sub-parameters; the types of photonic device sub-parameters include waveguide width, waveguide height, grating period, grating duty cycle, doping concentration, sidewall angle, cladding thickness, and material refractive index; the physical parameters include one or more types of physical sub-parameters; the types of physical sub-parameters include effective refractive index, group refractive index, free spectral range of microrings, resonant wavelength, and quality factor.

[0007] In some embodiments of the first aspect of this application, the types of the parameter sensitivity and coupling metric matrix include a Jacobian matrix and a Fisher information matrix; the evaluation index includes a first evaluation index and a second evaluation index; the types of the first evaluation index include: the absolute value of the determinant of the Jacobian matrix, the product of the non-zero singular values ​​of the Jacobian matrix, the Fisher information content, and the trace of the Fisher information matrix; the types of the second evaluation index include: the condition number of the Jacobian matrix and the rank of the Fisher information matrix.

[0008] In some embodiments of the first aspect of this application, the step of selecting the optimal parameter combination under the preset parameter space specifically includes: based on the evaluation indicators extracted from the sensitivity and coupling metric matrices of each parameter, and based on the regional adaptive optimization rule, dividing the preset parameter space into multiple sub-intervals and determining the optimal parameter combination corresponding to each sub-interval; wherein, the regional adaptive optimization rule includes: when the optimal evaluation indicators in a continuous interval of the preset parameter space all correspond to the same parameter combination, dividing the continuous interval into sub-intervals and determining the parameter combination as the optimal parameter combination corresponding to the sub-interval.

[0009] In some embodiments of the first aspect of this application, a corresponding reverse extraction model for photonic device parameters is constructed based on the optimal parameter combination and the forward mapping dataset. This includes: obtaining data related to each sub-interval from the forward mapping dataset based on the optimal parameter combination for each sub-interval; training or fitting the constructed mapping model between the photonic device parameters and the optimal parameter combination for each sub-interval to obtain the reverse extraction model for photonic device parameters corresponding to each sub-interval; wherein the model type includes: high-order polynomial, deep neural network, support vector regression, random forest, and multidimensional interpolation lookup table; the reverse extraction models for photonic device parameters corresponding to each sub-interval constitute the final reverse extraction model for photonic device parameters.

[0010] To achieve the above and other related objectives, a second aspect of this application provides a device for constructing a reverse extraction model of photonic device parameters, comprising: an acquisition module for acquiring a forward mapping dataset of photonic devices in a preset parameter space; wherein the forward mapping dataset includes multiple photonic device parameter data and corresponding physical parameter data in the preset parameter space; a matrix calculation module for calculating the parameter sensitivity and coupling metric matrices of different combinations of physical parameters relative to the photonic device parameters; an optimal parameter combination determination module for extracting evaluation indicators from each parameter sensitivity and coupling metric matrix and thereby selecting the optimal parameter combination in the preset parameter space; and a model construction module for constructing a corresponding reverse extraction model of photonic device parameters based on the optimal parameter combination and the forward mapping dataset.

[0011] To achieve the above and other related objectives, a third aspect of this application provides a method for characterizing photonic device parameters. The method includes: acquiring actual optical test data of the photonic device under test; inputting the actual optical test data into a photonic device parameter inverse extraction model constructed by the photonic device parameter inverse extraction model construction method described above, to obtain the actual photonic device parameters.

[0012] To achieve the above and other related objectives, a fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method for constructing a reverse extraction model of photonic device parameters or the method for characterizing photonic device parameters.

[0013] To achieve the above and other related objectives, a fifth aspect of this application provides an electronic terminal, including a memory, a processor, and a computer program stored in the memory; the processor executes the computer program to implement the method for constructing a reverse extraction model of photonic device parameters or the method for characterizing photonic device parameters.

[0014] As described above, the method, apparatus, terminal, medium, and characterization method for constructing the reverse extraction model of photonic device parameters in this application have the following beneficial effects: This application introduces the matrix from mathematics into the field of photonic device characterization, pre-screens the optimal parameter combination, constructs a more suitable reverse extraction model of photonic device parameters, and greatly avoids ill-conditioned inversion. Attached Figure Description

[0015] Figure 1 The diagram shows a flowchart of a method for constructing a reverse extraction model of photonic device parameters in one embodiment of this application.

[0016] Figure 2 The diagram shown is a schematic block diagram of a photonic device parameter reverse extraction model construction device in one embodiment of this application.

[0017] Figure 3 The diagram shown is a structural schematic of an electronic terminal according to an embodiment of this application. Detailed Implementation

[0018] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.

[0019] In the embodiments of this application, the terms "first" and "second" are used to distinguish identical or similar items with essentially the same function and effect. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and that the terms "first" and "second" do not necessarily imply that they are different.

[0020] It should be noted that, in the embodiments of this application, the words "exemplary" or "for example" indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0021] In this application embodiment, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0022] To facilitate understanding of the embodiments of this application, firstly, in conjunction with Figure 1 Detailed explanation. Figure 1 This document illustrates a flowchart of a method for constructing a reverse extraction model of photonic device parameters according to an embodiment of the present invention. The method for constructing a reverse extraction model of photonic device parameters in this embodiment mainly includes the following steps:

[0023] Step S101: Obtain the forward mapping dataset of the photonic device in the preset parameter space.

[0024] First, the parameters of the photonic device to be extracted are determined. Then, based on the target process node, a preset parameter space is determined for the parameters of the photonic device to be extracted. The parameter space defines the range of values ​​for the parameters of the photonic device to be extracted. Since there will be process fluctuations in the fabrication of photonic chips, the preset parameter space must completely cover and be slightly larger than the actual process fluctuation range under the target process node to ensure that subsequent fitting can achieve a global nonlinear envelope.

[0025] It should be understood that a process node, also commonly referred to as a manufacturing process, is a key indicator used in semiconductor manufacturing to measure the technological level of integrated circuits (chips). In photonic chips, a process node refers to the minimum linewidth / processing precision of photonic devices such as optical waveguides, gratings, and couplers. Process variation refers to the small, unavoidable deviations between the actual process parameters and the design target values ​​that occur during the manufacturing process of photonic chips.

[0026] Photonic device parameters include one or more types of photonic device sub-parameters. These types of photonic device sub-parameters include, but are not limited to, waveguide width, waveguide height, grating period, grating duty cycle, doping concentration, sidewall angle, cladding thickness, and material refractive index.

[0027] Multiple photonic device parameter data are selected within a preset parameter space. Then, photonic device simulation is performed using physical simulation software under each photonic device parameter data to obtain the corresponding physical parameter data. It should be understood that any existing photonic device physical simulation software can be used for simulation; examples are not listed here. Alternatively, actual physical measurements can be performed on the calibration test structure corresponding to each photonic device parameter data to obtain the corresponding physical parameter data. It should be understood that the calibration test structure refers to a standard optical structure specifically used for calibrating process errors, quantifying device performance, and establishing measurement benchmarks.

[0028] The parameter data of each photonic device in the preset parameter space and their corresponding physical parameter data constitute the forward mapping dataset.

[0029] Physical parameters are generally measurable response parameters of photonic devices. Physical parameters include one or more types of physical sub-parameters; these types include, but are not limited to, effective refractive index, group refractive index, free spectral range of microrings, resonant wavelength, quality factor, etc. The specific parameter types included in the physical parameters can be determined according to requirements. To better illustrate the process of acquiring the forward mapping dataset, a specific example is provided below:

[0030] The photonic device parameters to be extracted include two types of photonic device sub-parameters: waveguide width w and waveguide height h. Physical parameters include effective refractive index. Group refractive index These two types of physical sub-parameters are used. Based on the target process node, the ranges of waveguide width and waveguide height are determined. Within the waveguide width range, N waveguide width data points are selected, and within the waveguide height range, M waveguide height data points are selected, where M and N are positive integers. Then, the selected N waveguide width data points and M waveguide height data points are combined to obtain M×N photonic device parameter data points. Simulations are performed using physical simulation software under each photonic device parameter data point to obtain the corresponding physical parameter data (including effective refractive index and group refractive index). Each photonic device parameter data point and its corresponding physical parameter data constitute a forward mapping dataset.

[0031] Step S102: Calculate the parameter sensitivity and coupling metric matrix of different combinations of physical parameters relative to the photonic device parameters.

[0032] First, we need to determine the different combinations of physical parameters. Specifically, physical parameters include various types of sub-parameters, and these sub-parameters can be combined into various parameter combinations. For example, if the physical parameters include effective refractive index and group refractive index as sub-parameters, then the parameter combinations would be {effective refractive index}, {group refractive index}, and {effective refractive index, group refractive index}, respectively. It should be understood that when the physical parameters change, their parameter combinations will also change accordingly. It is important to emphasize that the number of sub-physical parameters in the selected combination of physical parameters must be greater than or equal to the number of photonic device sub-parameters in the parameters of the photonic device to be characterized.

[0033] For each parameter combination, calculate the parameter sensitivity and coupling metric matrix of that parameter combination relative to the photonic device parameters. The types of parameter sensitivity and coupling metric matrices include, but are not limited to, the Jacobian matrix (also known as the partial derivative matrix or sensitivity matrix), the Fisher information matrix, etc.

[0034] Assume the photonic device parameters to be extracted include device parameter A and device parameter B, and the corresponding physical parameters include physical parameter A, physical parameter B, physical parameter C, and physical parameter D. Parameter combinations can be {physical parameter A, physical parameter B}, {physical parameter B, physical parameter C}, {physical parameter C, physical parameter D}, {physical parameter A, physical parameter D}, etc., and will not be listed here. Taking the parameter combination {physical parameter A, physical parameter B} as an example, the photonic device parameters to be extracted and this parameter combination can be expressed as a functional relationship as follows:

[0035] (Physical parameter A, Physical parameter B) = f (Device parameter A, Device parameter B);

[0036] Based on this, when the parameter sensitivity and coupling metric matrix are Jacobian matrices, the specific calculation process is as follows:

[0037] Since any combination of the photonic device parameters and physical parameters to be extracted can construct the above functional relationship, for each parameter combination, the corresponding Jacobian matrix can be calculated based on the photonic device parameters in the forward mapping dataset and the physical parameters related to that parameter combination.

[0038] In one implementation, the Jacobian matrix can be calculated using finite difference. Specifically, for a photonic device parameter and its corresponding physical parameter in the forward mapping dataset, finite difference is performed using several nearby photonic device parameters and their corresponding physical parameters to obtain the corresponding Jacobian matrix. In another implementation, an approximate function can be fitted using all the data in the forward mapping dataset, and then the Jacobian matrix can be calculated. Substituting the values ​​of each photonic device parameter and its corresponding physical parameter into the function yields the corresponding Jacobian matrix. It should be noted that this is only an example and does not imply that the calculation method of the Jacobian matrix is ​​limited to this. The specific calculation methods of the above two methods can refer to existing calculation methods, and will not be elaborated further here.

[0039] When the parameter sensitivity and coupling metric matrix are Fisher information matrices, the specific calculation process is as follows:

[0040] Since the aforementioned functional relationship can be constructed between the photonic device parameters to be extracted and any combination of parameters, a functional relationship can be assumed first (e.g., a polynomial function), and the parameter vector can be determined based on it. Then, the Jacobian vector of each photonic device parameter and its corresponding physical parameter is calculated, and the corresponding outer product is calculated based on the Jacobian vectors of each photonic device parameter and its corresponding physical parameter. Finally, the outer product is divided by a preset noise variance to obtain the corresponding Fisher information matrix. It should be noted that the specific calculation method can refer to existing calculation methods, which will not be elaborated here.

[0041] Step S103: Extract evaluation indicators from the sensitivity and coupling metric matrices of each parameter and select the optimal parameter combination in the preset parameter space accordingly.

[0042] The evaluation metrics include a first evaluation metric that reflects the mapping sensitivity or linear correlation, and a second evaluation metric that reflects the ill-conditioning of the system or the error amplification rate.

[0043] The types of the first evaluation metric include, but are not limited to, the absolute value of the determinant of the Jacobian matrix, the product of the non-zero singular values ​​of the Jacobian matrix, Fisher information, the trace of the Fisher information matrix, etc. The types of the second evaluation metric include, but are not limited to, the condition number of the Jacobian matrix, the rank of the Fisher information matrix, etc.

[0044] It should be understood that the absolute value of the determinant measures the area change of the mapping; a larger value indicates stronger resistance to test noise. The condition number measures the shape change of the mapping; a value closer to 1 indicates a more benign system and lower error amplification. The higher the product of the non-zero singular values ​​of the Jacobian matrix, the stronger the local transformation at that point, the greater the volume amplification, the better the numerical stability, and the better the observation / control performance. Fisher information measures how much information about unknown parameters is contained in the data. A larger value indicates that the parameters are easier to estimate and the estimation accuracy is higher. If the rank of the Fisher information matrix is ​​insufficient, it indicates a high error amplification; if it is full rank, it indicates a low error amplification. A larger trace of the Fisher information matrix indicates higher mapping sensitivity; a smaller trace indicates lower mapping sensitivity.

[0045] In step S102, for each parameter combination, based on the parameter data of multiple photonic devices in the forward mapping data and the physical parameter data corresponding to that parameter combination, the parameter sensitivity and coupling metric matrix relative to the photonic device parameters is calculated. The parameter sensitivity and coupling metric matrix of each parameter combination relative to the photonic device parameters changes with the changes in the photonic device parameter data and the physical parameter data; therefore, the evaluation index also changes with the changes in the photonic device parameter data and the physical parameter data. Therefore, in step S103, the evaluation index of the parameter sensitivity and coupling metric matrix of each parameter combination relative to the photonic device parameters under different combinations of photonic device parameter data and physical parameter data is calculated. It should be understood that the specific calculation method of the evaluation index can refer to existing methods, and will not be elaborated here.

[0046] When accuracy requirements are low, the optimal parameter combination can be found based on all the evaluation indicators calculated above. This parameter combination is the optimal parameter combination under the preset parameter space.

[0047] For applications requiring high precision, the preset parameter space can be divided into multiple sub-intervals based on all the calculated evaluation indicators and a regional adaptive optimization rule. The optimal parameter combination for each sub-interval can then be determined. The regional adaptive optimization rule includes: when the optimal evaluation indicators within a continuous interval of the preset parameter space all correspond to the same parameter combination, this continuous interval is divided into sub-intervals, and this parameter combination is determined as the optimal parameter combination for that sub-interval. This method dynamically switches the optimal parameter combination based on the optical field physical characteristics of different parameter sub-intervals (e.g., group refractive index for narrow waveguides, effective refractive index for wide waveguides), ensuring the highest signal-to-noise ratio is maintained even in the most challenging technological environments.

[0048] For example, suppose the physical parameters include physical parameter A, physical parameter B, and physical parameter C. Based on all the calculated evaluation indicators, it is found that the evaluation indicators for the parameter combination {physical parameter A, physical parameter B} are optimal within a continuous interval of the preset parameter space. This continuous interval is then defined as a sub-interval, and the optimal parameter combination for this sub-interval is {physical parameter A, physical parameter B}. There is also a continuous interval within the preset parameter space, hereinafter referred to as interval 2. In interval 2, the evaluation indicators for the parameter combination {physical parameter B, physical parameter C} are optimal. Therefore, interval 2 is defined as a sub-interval, and the optimal parameter combination for this sub-interval is {physical parameter B, physical parameter C}. The determination of the remaining sub-intervals is the same as described above and will not be repeated here.

[0049] In one embodiment, the evaluation rule for the optimal evaluation index depends on the specific type of the evaluation index. The optimal evaluation index can be determined according to actual needs, and no limitation is made here. For example, if the first evaluation index is the absolute value of the determinant and the second evaluation index is the condition number, then the optimal evaluation index can be a combination of the first evaluation index with the highest absolute value of the determinant and the second evaluation index with the condition number closest to 1.

[0050] Step S104: Based on the optimal parameter combination and the forward mapping dataset, construct the corresponding reverse extraction model of photonic device parameters.

[0051] For cases where there is only one optimal parameter combination, a model is constructed that combines the photonic device parameters with that optimal parameter combination. Model types include, but are not limited to, higher-order polynomials, deep neural networks (DNNs), support vector regression (SVR), random forests, multidimensional interpolation lookup tables (LUTs), etc. The model is trained or fitted using the photonic device parameter data from the forward mapping dataset and the physical parameter data related to the optimal parameter combination, thus obtaining the inverse extraction model of the photonic device parameters.

[0052] For cases where there are multiple optimal parameter combinations (i.e., the preset parameter space is divided into multiple sub-intervals and the optimal parameter combinations corresponding to each sub-interval are determined), a mapping model is constructed between the photonic device parameters and the optimal parameter combinations of each sub-interval. The types of mapping models include, but are not limited to, higher-order polynomials, deep neural networks (DNNs), support vector regression (SVR), random forests, multidimensional interpolation lookup tables (LUTs), etc. Based on the optimal parameter combinations of each sub-interval, data related to each sub-interval is obtained from the forward mapping dataset to obtain the inverse extraction model of photonic device parameters corresponding to each sub-interval. The data related to each sub-interval in the forward mapping dataset includes the photonic device parameter data within each sub-interval and the physical parameter data related to the optimal parameter combinations of each sub-interval. The inverse extraction models of photonic device parameters corresponding to each sub-interval constitute the final inverse extraction model of photonic device parameters, which is a segmented mapping model library.

[0053] Figure 2 This is a schematic block diagram of the photonic device parameter reverse extraction model construction device provided in the embodiments of this application. For example... Figure 2 As shown, the reverse extraction model construction device 200 for photonic device parameters includes:

[0054] The acquisition module 201 is used to acquire a forward mapping dataset of photonic devices in a preset parameter space; wherein, the forward mapping dataset includes parameter data of multiple photonic devices in the preset parameter space and their corresponding physical parameter data;

[0055] The matrix calculation module 202 is used to calculate the parameter sensitivity and coupling metric matrix of different combinations of physical parameters relative to the parameters of the photonic device.

[0056] The optimal parameter combination determination module 203 is used to extract evaluation indicators from the sensitivity and coupling metric matrices of each parameter and thereby select the optimal parameter combination in the preset parameter space.

[0057] The model building module 204 is used to construct a corresponding reverse extraction model of photonic device parameters based on the optimal parameter combination and the forward mapping dataset.

[0058] It should be understood that the specific process of each module performing the above-mentioned steps has been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0059] It should also be understood that the module division in the embodiments of this application is illustrative and only represents a logical functional division; in actual implementation, there may be other division methods. Furthermore, the functional modules in the various embodiments of this application can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0060] The present invention also provides a method for characterizing photonic device parameters, the method comprising: acquiring actual optical test data of the photonic device under test; inputting the actual optical test data into a photonic device parameter inverse extraction model constructed by the photonic device parameter inverse extraction model construction method described above, to obtain the actual photonic device parameters.

[0061] It should be understood that the construction method of the reverse extraction model of photonic device parameters has been described in the above embodiments and will not be repeated here.

[0062] In one embodiment, the actual optical test data includes one or more physical sub-parameters, the types of which include, but are not limited to, effective refractive index, group refractive index, free spectral range of the microring, resonant wavelength, quality factor, etc. The types of parameters included in the actual photonic device parameters obtained are related to the inverse extraction model of photonic device parameters.

[0063] Figure 3 This is a schematic block diagram of the electronic terminal provided in an embodiment of this application. Figure 3 As shown, the electronic terminal 300 includes at least one processor 301, a memory 302, at least one network interface 303, and a user interface 305. The various components in the electronic terminal 300 are coupled together via a bus system 304. It is understood that the bus system 304 is used to implement communication between these components. In addition to a data bus, the bus system 304 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in… Figure 3 The general will label all buses as bus systems.

[0064] The user interface 305 may include a monitor, keyboard, mouse, trackball, clicker, button, touchpad, or touch screen.

[0065] It is understood that memory 302 can be volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM) or programmable read-only memory (PROM), which serves as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM) and synchronous static random access memory (SSRAM). The memories described in the embodiments of this invention are intended to include, but are not limited to, these and any other suitable categories of memory.

[0066] In this embodiment of the invention, the memory 302 is used to store various types of data to support the operation of the electronic terminal 300. Examples of this data include: any executable program for operation on the electronic terminal 300, such as the operating system 3021 and application programs 3022; the operating system 3021 contains various system programs, such as the framework layer, core library layer, driver layer, etc., for implementing various basic services and handling hardware-based tasks. The application program 3022 may contain various applications, such as a media player, browser, etc., for implementing various application services. The method for constructing a reverse extraction model of photonic device parameters or the method for characterizing photonic device parameters provided in this embodiment of the invention may be included in the application program 3022.

[0067] The methods disclosed in the above embodiments of the present invention can be applied to processor 301, or implemented by processor 301. Processor 301 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in processor 301 or by instructions in the form of software. The processor 301 may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 301 can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. General-purpose processor 301 may be a microprocessor or any conventional processor, etc. The steps of the accessory optimization method provided in the embodiments of the present invention can be directly reflected as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in the decoding processor. The software module may be located in a storage medium, which is located in memory. The processor reads the information in the memory and combines it with its hardware to complete the steps of the aforementioned method.

[0068] In an exemplary embodiment, the electronic terminal 300 may be used by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), or complex programmable logic devices (CPLDs) to execute the aforementioned method.

[0069] According to the method provided in the embodiments of this application, this application also provides a computer program product, which includes: computer program code, which, when run on a computer, causes the computer to execute the above-described method for constructing a reverse extraction model of photonic device parameters or a method for characterizing photonic device parameters.

[0070] According to the method provided in the embodiments of this application, this application also provides a computer-readable storage medium storing program code. When the program code is run on a computer, it causes the computer to execute the above-described method for constructing a reverse extraction model of photonic device parameters or a method for characterizing photonic device parameters.

[0071] As used in this specification, the terms "component," "module," "system," etc., are used to refer to computer-related entities, hardware, firmware, combinations of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program, and / or a computer. As illustrated, applications running on computing devices and computing devices can both be components. One or more components may reside in a process and / or an execution thread, and components may be located on a single computer and / or distributed among two or more computers. Furthermore, these components can be executed from various computer-readable media on which various data structures are stored. Components can communicate, for example, via local and / or remote processes based on signals having one or more data packets (e.g., data from two components interacting with another component between a local system, a distributed system, and / or a network, such as the Internet interacting with other systems via signals).

[0072] Those skilled in the art will recognize that the various illustrative logical blocks and steps described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0073] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0074] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0075] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0076] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0077] In the above embodiments, the functions of each functional unit can be implemented entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. A computer program product includes one or more computer instructions (programs). When the computer program instructions (programs) are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., high-density digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0078] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0079] In summary, this application provides a method, apparatus, terminal, medium, and characterization method for constructing a reverse extraction model of photonic device parameters. The method includes: acquiring a forward mapping dataset of photonic devices within a preset parameter space; the forward mapping dataset includes multiple photonic device parameter data and their corresponding physical parameter data within the preset parameter space; calculating the parameter sensitivity and coupling metric matrices of different combinations of physical parameters relative to the photonic device parameters; extracting evaluation indicators from each matrix and selecting the optimal parameter combination within the preset parameter space accordingly; and constructing a corresponding reverse extraction model of photonic device parameters based on the optimal parameter combination and the forward mapping dataset. This application introduces matrices from mathematics into the field of photonic device characterization, pre-selects the optimal parameter combination, and constructs a more suitable reverse extraction model of photonic device parameters, greatly avoiding ill-conditioned inversion. Therefore, this application effectively overcomes various shortcomings of the prior art and has high industrial application value.

[0080] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. A method for constructing a reverse extraction model of photonic device parameters, characterized in that, include: Obtain a forward mapping dataset of photonic devices in a preset parameter space; wherein, the forward mapping dataset includes parameter data of multiple photonic devices in the preset parameter space and their corresponding physical parameter data; The parameter sensitivity and coupling metric matrix of different combinations of physical parameters are calculated relative to the parameters of the photonic device. Evaluation indices are extracted from the sensitivity and coupling metric matrices of each parameter, and the optimal parameter combination in the preset parameter space is selected accordingly. The parameter sensitivity and coupling metric matrices include Jacobian matrices and Fisher information matrices. The evaluation indices include a first evaluation index and a second evaluation index. The first evaluation index includes the absolute value of the determinant of the Jacobian matrix, the product of the non-zero singular values ​​of the Jacobian matrix, Fisher information, and the trace of the Fisher information matrix. The second evaluation index includes the condition number of the Jacobian matrix and the rank of the Fisher information matrix. The step of selecting the optimal parameter combination under the preset parameter space specifically includes: based on the evaluation indicators extracted from the sensitivity and coupling metric matrices of each parameter, and based on the regional adaptive optimization rule, dividing the preset parameter space into multiple sub-intervals and determining the optimal parameter combination corresponding to each sub-interval; wherein, the regional adaptive optimization rule includes: when the optimal evaluation indicators in a continuous interval of the preset parameter space all correspond to the same parameter combination, dividing the continuous interval into sub-intervals and determining the parameter combination as the optimal parameter combination corresponding to the sub-interval; Based on the optimal parameter combination and the forward mapping dataset, a corresponding reverse extraction model for photonic device parameters is constructed.

2. The method for constructing a reverse extraction model of photonic device parameters according to claim 1, characterized in that, Obtain the forward mapping dataset of photonic devices in a preset parameter space, including: By simulating or actually measuring photonic devices, physical parameter data corresponding to multiple photonic device parameter data within a preset parameter space can be obtained. The parameter data of multiple photonic devices in the preset parameter space and their corresponding physical parameter data constitute the forward mapping dataset.

3. The method for constructing a reverse extraction model of photonic device parameters according to claim 1, characterized in that, Photonic device parameters include one or more types of photonic device sub-parameters; the types of photonic device sub-parameters include waveguide width, waveguide height, grating period, grating duty cycle, doping concentration, sidewall angle, cladding thickness, and material refractive index; physical parameters include one or more types of physical sub-parameters; the types of physical sub-parameters include effective refractive index, group refractive index, free spectral range of microrings, resonant wavelength, and quality factor.

4. The method for constructing a reverse extraction model of photonic device parameters according to claim 1, characterized in that, Based on the optimal parameter combination and the forward mapping dataset, a corresponding reverse extraction model for photonic device parameters is constructed, including: Based on the optimal parameter combination of each sub-interval, data related to each sub-interval is obtained from the forward mapping dataset, and the mapping model between the constructed photonic device parameters and the optimal parameter combination of each sub-interval is trained or fitted to obtain the inverse extraction model of photonic device parameters corresponding to each sub-interval; wherein, the types of the model include: high-order polynomial, deep neural network, support vector regression, random forest and multidimensional interpolation lookup table. The reverse extraction models of photonic device parameters corresponding to each sub-interval constitute the final reverse extraction model of photonic device parameters.

5. A device for reverse extraction and model construction of photonic device parameters, characterized in that, include: The acquisition module is used to acquire a forward mapping dataset of photonic devices in a preset parameter space; wherein, the forward mapping dataset includes parameter data of multiple photonic devices in the preset parameter space and their corresponding physical parameter data; The matrix calculation module is used to calculate the parameter sensitivity and coupling metric matrix of different combinations of physical parameters relative to the parameters of the photonic device. The optimal parameter combination determination module is used to extract evaluation indicators from the sensitivity and coupling metric matrices of each parameter and thereby select the optimal parameter combination in the preset parameter space. The parameter sensitivity and coupling metric matrices include Jacobian matrices and Fisher information matrices. The evaluation indicators include a first evaluation indicator and a second evaluation indicator. The first evaluation indicator includes the absolute value of the determinant of the Jacobian matrix, the product of the non-zero singular values ​​of the Jacobian matrix, Fisher information, and the trace of the Fisher information matrix. The second evaluation indicator includes the condition number of the Jacobian matrix and the rank of the Fisher information matrix. The step of selecting the optimal parameter combination under the preset parameter space specifically includes: based on the evaluation indicators extracted from the sensitivity and coupling metric matrices of each parameter, and based on the regional adaptive optimization rule, dividing the preset parameter space into multiple sub-intervals and determining the optimal parameter combination corresponding to each sub-interval; wherein, the regional adaptive optimization rule includes: when the optimal evaluation indicators in a continuous interval of the preset parameter space all correspond to the same parameter combination, dividing the continuous interval into sub-intervals and determining the parameter combination as the optimal parameter combination corresponding to the sub-interval; The model building module is used to construct the corresponding reverse extraction model of photonic device parameters based on the optimal parameter combination and the forward mapping dataset.

6. A method for characterizing parameters of a photonic device, characterized in that, The method includes: Obtain actual optical test data of the photonic device under test; The actual optical test data is input into the photonic device parameter reverse extraction model constructed by the photonic device parameter reverse extraction model construction method according to any one of claims 1 to 4 to obtain the actual photonic device parameters.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 4, or the method as described in claim 6.

8. An electronic terminal, comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the method as described in any one of claims 1 to 4, or the method as described in claim 6.

Images