Artificial intelligence fitting method and device for device parameters

Abstract

The present invention relates to the field of computer-aided design technology, and discloses an artificial intelligence fitting method, device, electronic device, computer-readable storage medium, and computer program product for device parameters, which are used to solve the technical problems of insufficient fitting accuracy, complex steps, and high time cost when simulating and calculating semiconductor devices in the prior art. It includes: constructing a device simulation case and obtaining a first input parameter and a first output parameter; according to the device type of the semiconductor device, determining the type of influence of the first input parameter on the first output parameter, and generating a mechanism adjustment function of the device simulation case according to the influence type; based on the mechanism adjustment function, correcting the initial artificial intelligence model to obtain a corrected artificial intelligence fitting model and fitting the device simulation case to obtain a first input parameter combination that makes the first output parameter conform to the experimental output parameter; thereby constructing a correlation model between the second input parameter and the second output parameter of the device simulation case.

Description

Technical Field

[0001] The present invention relates to the field of computer-aided design technology, and in particular to an artificial intelligence fitting method, device, electronic equipment, computer storage medium and computer program product for device parameters. Background Art

[0002] In recent years, with the continuous advancement of semiconductor device technology and the rapid expansion of market demand, semiconductor device design is facing increasingly stringent requirements. In the design process of semiconductor devices, the performance of the device is greatly affected by different structural parameters. In order to achieve the expected performance of the device, it is usually necessary to evaluate the performance of the device under different structural parameters through simulation or experimental testing. However, these methods often require a lot of manpower and material resources; and when multiple parameters are involved, it is still necessary to weigh the degree of influence of each parameter on the device performance and determine whether they have a mutually restrictive or mutually influential relationship.

[0003] In semiconductor simulation calculations, an important task is to fit the experimental data. Since the common control parameters in actual production or experiments are generally intuitive parameters such as temperature, humidity and material thickness, while the simulation involves non-intuitive physical variables such as material defect concentration, low-field / high-field electron / hole mobility, doping concentration and electron / hole lifetime; therefore, in order to make the simulation results fit the experimental data, these non-intuitive parameters need to be adjusted.

[0004] However, in the prior art, adjusting these non-intuitive parameters often relies on the experience of engineers, and when faced with complex cases, the parameter adjustment process is often time-consuming and laborious. Therefore, there is an urgent need for an artificial intelligence fitting method for device parameters that can improve fitting accuracy, simplify fitting operations, and reduce the time required for fitting. Summary of the invention

[0005] The main purpose of the present invention is to solve the technical problems in the prior art of insufficient fitting accuracy when adjusting device parameters during simulation calculation of semiconductor devices, and complex fitting steps and high time cost.

[0006] A first aspect of the present invention provides an artificial intelligence fitting method for device parameters, comprising:

[0007] Build device simulation cases for semiconductor devices through simulation tools;

[0008] Obtaining a first input parameter and a first output parameter in a device simulation case;

[0009] Determining, according to the device type of the semiconductor device, the type of influence of the first input parameter on the first output parameter, and generating a mechanism adjustment function of the device simulation case according to the type of influence;

[0010] Based on the mechanism adjustment function, the initial artificial intelligence model is corrected to obtain a corrected artificial intelligence fitting model;

[0011] Calling the artificial intelligence fitting model to fit the device simulation case, adjusting the first input parameter to obtain a first input parameter combination that makes the first output parameter of the device simulation case conform to the experimental output parameter;

[0012] A correlation model between the second input parameter and the second output parameter of the device simulation case is constructed according to the first input parameter combination and the experimental output parameter.

[0013] Optionally, in a first implementation of the first aspect of the present invention, after constructing the association model between the second input parameter and the second output parameter of the device simulation case, the method further includes:

[0014] Based on the design requirements of the semiconductor device, adjusting a second input parameter of the semiconductor device, and based on the association model, acquiring a second output parameter corresponding to the second input parameter;

[0015] The semiconductor device is designed and developed based on the second input parameter and the second output parameter.

[0016] Optionally, in a second implementation of the first aspect of the present invention, constructing a device simulation case of a semiconductor device by using a simulation tool includes:

[0017] Select the material of the semiconductor device in the material library of the simulation tool, and set the material value information according to the design requirements of the semiconductor device;

[0018] Modeling the structure of the semiconductor device according to the design requirements and material numerical information to obtain a device simulation model;

[0019] According to the design requirements, a physical model is added to the simulation model to set boundary conditions, so as to obtain a device simulation case of the semiconductor device.

[0020] Optionally, in a third implementation manner of the first aspect of the present invention, the obtaining of a first input parameter and a first output parameter in a device simulation case includes:

[0021] Extracting alternative input parameters and alternative output parameters that can be modified in the device simulation case;

[0022] Selecting the first input parameter from the candidate input parameters according to the device type of the semiconductor device and the difficulty of modifying the first input parameter;

[0023] According to the device type of the semiconductor device and the design requirements of the output parameters, the first input parameter is selected from the candidate output parameters.

[0024] Optionally, in a fourth implementation of the first aspect of the present invention, the expression of the corrected artificial intelligence fitting model obtained by correcting the initial artificial intelligence model based on the mechanism adjustment function is:

[0025] ;

[0026] in, Represents the input parameter combination, ; represents the mechanism adjustment function, i=[1, n]; F represents the algorithm function of the initial artificial intelligence model before correction and adjustment, Represents the algorithm function of the corrected and adjusted artificial intelligence fitting model.

[0027] Optionally, in a fifth implementation of the first aspect of the present invention, the impact type includes an activation type, a single association type, a multiple association type, and a mixed type.

[0028] A second aspect of the present invention provides an artificial intelligence fitting device for device parameters, comprising:

[0029] A case building module, used to build device simulation cases of semiconductor devices through simulation tools;

[0030] A parameter acquisition module, used to acquire a first input parameter and a first output parameter in a device simulation case;

[0031] An adjustment module, configured to determine the type of influence of the first input parameter on the first output parameter according to the device type of the semiconductor device, and generate a mechanism adjustment function of the device simulation case according to the influence type;

[0032] A correction module, used to correct the initial artificial intelligence model based on the mechanism adjustment function to obtain a corrected artificial intelligence fitting model;

[0033] A parameter fitting module, used for calling the artificial intelligence fitting model to fit the device simulation case, and adjusting the first input parameter to obtain a first input parameter combination that makes the first output parameter of the device simulation case conform to the experimental output parameter;

[0034] A model building module is used to build a correlation model between the second input parameter and the second output parameter of the device simulation case according to the first input parameter combination and the experimental output parameter.

[0035] The third aspect of the present invention provides an artificial intelligence fitting device for device parameters, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory to enable the artificial intelligence fitting device for device parameters to perform the steps of the above-mentioned artificial intelligence fitting method for device parameters.

[0036] A fourth aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the steps of the above-mentioned artificial intelligence fitting method for device parameters.

[0037] A fifth aspect of the present invention provides a computer program product, comprising a computer program / instruction, characterized in that when the computer program / instruction is executed by a processor, the steps of the artificial intelligence fitting method of device parameters as described above are implemented.

[0038] In the technical solution provided by the present invention, a device simulation case of a semiconductor device is constructed by a simulation tool; a first input parameter and a first output parameter in the device simulation case are obtained; according to the device type of the semiconductor device, the type of influence of the first input parameter on the first output parameter is determined, and a mechanism adjustment function of the device simulation case is generated according to the influence type; based on the mechanism adjustment function, the initial artificial intelligence model is corrected to obtain a corrected artificial intelligence fitting model; the artificial intelligence fitting model is called to fit the device simulation case, and the first input parameter is adjusted to obtain a first input parameter combination that makes the first output parameter of the device simulation case conform to the experimental output parameter; according to the first input parameter combination and the experimental output parameter, a correlation model between the second input parameter and the second output parameter of the device simulation case is constructed. This method can improve the fitting accuracy, simplify the fitting operation, and reduce the time required for fitting. In addition, a device, an electronic device, a computer-readable storage medium, and a computer program product provided by the present invention also solve the corresponding technical problems. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0040] Figure 1 It is a schematic flow chart of a first embodiment of an artificial intelligence fitting method for device parameters in an embodiment of the present invention;

[0041] Figure 2 A schematic diagram of a flow chart of a second embodiment of the artificial intelligence fitting method for device parameters in an embodiment of the present invention;

[0042] Figure 3A schematic diagram of an embodiment of an artificial intelligence fitting device for device parameters in an embodiment of the present invention;

[0043] Figure 4 A schematic diagram of an embodiment of an artificial intelligence fitting device for device parameters in an embodiment of the present invention;

[0044] Figure 5 The figure is a schematic diagram of a computer-readable medium in an embodiment of the present invention. DETAILED DESCRIPTION

[0045] Exemplary embodiments of the present invention will now be described more fully with reference to the accompanying drawings. However, exemplary embodiments can be implemented in a variety of forms, and should not be construed as limiting the present invention to the embodiments set forth herein. On the contrary, providing these exemplary embodiments enables the present invention to be more comprehensive and complete, and is more convenient for fully conveying the inventive concept to those skilled in the art. The same reference numerals in the figures represent the same or similar elements, components or parts, and thus their repeated description will be omitted.

[0046] Under the premise of being consistent with the technical concept of the present invention, the features, structures, characteristics or other details described in a specific embodiment do not exclude that they can be combined in one or more other embodiments in a suitable manner.

[0047] In the description of specific embodiments, the features, structures, characteristics or other details described in the present invention are intended to enable those skilled in the art to fully understand the embodiments. However, it does not exclude that those skilled in the art can practice the technical solutions of the present invention without one or more of the specific features, structures, characteristics or other details.

[0048] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0049] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0050] The term "and / or" or "and / or" includes all combinations of any one or more of the associated listed items.

[0051] See also Figure 1 The first embodiment of the artificial intelligence fitting method for device parameters in the embodiment of the present invention includes:

[0052] S101. Construct a device simulation case of a semiconductor device by using a simulation tool;

[0053] It is understandable that the execution subject of the present invention may be an artificial intelligence fitting device for device parameters, or a terminal or a server, which is not limited here. The embodiment of the present invention is described by taking a server as the execution subject as an example.

[0054] In this embodiment, a case is first constructed for the semiconductor device to be designed. In a specific implementation, a case can be constructed for the semiconductor device to be designed through TCAD (Technology Computer Aided Design, semiconductor process and device simulation software) simulation software. When performing the specific construction, multiple steps and details are involved, including three main parts: machine material setting, process simulation setting, and device simulation setting.

[0055] Among them, the TCAD is a numerical simulation tool based on semiconductor physics. It can simulate different process conditions and replace or partially replace expensive and time-consuming process experiments; it can also optimize different device structures to obtain ideal characteristics; it can also simulate circuit performance and electrical defects.

[0056] S102, obtaining a first input parameter and a first output parameter in a device simulation case;

[0057] In this embodiment, the semiconductor device has a variety of different input parameters. First, according to the characteristics of the input parameters, they are divided into two categories. The first category can be called non-intuitive parameters. The first input parameter described in this embodiment belongs to the non-intuitive parameter type; the second category can be called intuitive parameters. The second intuitive parameter described in this embodiment belongs to the intuitive parameter. Specifically, the intuitive parameters generally refer to physical quantities that can be directly obtained by conventional measuring equipment and are easy to understand and process. These parameters are usually directly observed or controlled during the design or preparation of semiconductor devices, such as the size, temperature, humidity, material thickness, etc. of the device material, which can be directly measured and can affect the performance of semiconductor materials. Related parameters. Non-intuitive parameters generally refer to parameters that are difficult to measure directly by conventional means, or need to be inferred by complex models or indirect methods, such as parameters corresponding to physical variables such as material defect concentration, low-field / high-field electron / hole mobility, doping concentration, and electron / hole lifetime.

[0058] Therefore, in this embodiment, based on the constructed device simulation case, the input parameters that can be modified and all the output parameters of the device simulation case are extracted, the parameters that are closely related to the experimental production among the modifiable input parameters are screened out, and the non-intuitive parameters are extracted to obtain the first input parameter; the parameters that are closely related to the experimental production among the output parameters are screened out to obtain the first output parameter; wherein the output parameter may be a parameter such as a current value or a current gain value.

[0059] S103, determining the influence type of the first input parameter on the first output parameter according to the device type of the semiconductor device, and generating a mechanism adjustment function of the device simulation case according to the influence type;

[0060] S104, correcting the initial artificial intelligence model based on the mechanism adjustment function to obtain a corrected artificial intelligence fitting model;

[0061] In combination with the design requirements of the device, the corresponding physical mechanism and production experience, the influence of the input parameters on the output parameters is first classified to obtain the influence type of the first input parameter on the first output parameter in the device type of the current device simulation case; wherein the influence type may include activation type, single association type, and complex association type, and a mechanism adjustment function of the device simulation case is generated according to different influence types.

[0062] An initial artificial intelligence model is obtained in advance, wherein the initial artificial intelligence model can be constructed based on an artificial neural network algorithm and obtained after initial training; after obtaining the mechanism adjustment function under various types of influence, the initial artificial intelligence model is corrected based on the mechanism adjustment function to obtain a corrected artificial intelligence fitting model.

[0063] S105, calling the artificial intelligence fitting model to fit the device simulation case, adjusting the first input parameter to obtain a first input parameter combination that makes the first output parameter of the device simulation case conform to the experimental output parameter;

[0064] The fitting process described in this embodiment is a method of continuously iteratively adjusting an initial input parameter combination through an artificial intelligence algorithm to ultimately approximate the required input parameter combination.

[0065] Specifically, the purpose of this embodiment is to make the simulation results fit the experimental output parameters, that is, it is necessary to adjust the non-intuitive parameters. Therefore, when calling the fitting model to fit the device simulation case, it is necessary to adjust the first input parameter to obtain the first input parameter combination that makes the first output parameter of the device simulation case match the experimental output parameter.

[0066] S106 . Construct a correlation model between the second input parameter and the second output parameter of the device simulation case according to the first input parameter combination and the experimental output parameter.

[0067] After the first input parameter combination is adjusted based on the experimental output parameter, a correlation model between the second input parameter and the second output parameter of the device simulation case can be constructed based on the first input parameter combination. Based on the correlation model, the correlation information between the intuitive parameters and the output parameters of the semiconductor device can be obtained, and the subsequent design parameter adjustment can be guided based on this correlation information.

[0068] The method provided in the embodiment of the present invention can intelligently fit the device simulation case constructed by the simulation tool, so that the simulation results can be fitted to the experimental data, and the fitting method provided in this embodiment can improve the fitting accuracy, simplify the fitting operation, and reduce the time required for fitting.

[0069] Please see Figure 2 , the second embodiment of the artificial intelligence fitting method for device parameters in the embodiment of the present invention includes:

[0070] S201, constructing a device simulation case of a semiconductor device by using a simulation tool;

[0071] First, build a case for the semiconductor device that needs to be designed, such as TFT (Thin Film Transistor), MOSFET (Metal-Oxide-Semiconductor Field-Effect Transistor), etc.

[0072] In a specific implementation, a case may be constructed for a semiconductor device to be designed by TCAD (Technology Computer Aided Design, semiconductor process and device simulation software) simulation software. In this step, the case construction for the semiconductor device to be designed is a process involving multiple steps and details, mainly including three main parts: material setting, process simulation setting, and device simulation setting, specifically including:

[0073] (1) Material setting: Select the materials required for device design from the material library, and perform numerical calculations on the material's temperature, refractive index, electron low-field mobility, hole low-field mobility, electron high-field mobility, hole high-field mobility and other properties according to the case requirements, as well as make appropriate adjustments to the expressions;

[0074] (2) Process simulation settings: Based on the design of the case device, combined with the material and the type of process adopted, such as deposition, etching, oxidation, etc., the device geometry and topology are modeled;

[0075] (3) Device simulation settings: Based on the model obtained from process simulation, combined with device design, the required physical models, such as tunneling model, interface charge model, etc., are added to set boundary conditions.

[0076] Furthermore, the simulation calculation can be set to adjust the simulation accuracy of the simulation algorithm.

[0077] S202, obtaining a first input parameter and a first output parameter in a device simulation case;

[0078] In this embodiment, based on the constructed device simulation case, the input parameters that can be modified and all the output parameters of the device simulation case are extracted, the parameters that are closely related to the experimental production among the modifiable input parameters are screened out, and the non-intuitive parameters are extracted to obtain the first input parameter; the parameters that are closely related to the experimental production among the output parameters are screened out to obtain the first output parameter; wherein the output parameter may be a parameter such as a current value or a current gain value.

[0079] Specifically, the description of the intuitive parameters and the non-intuitive parameters can refer to the content of step S102 in the aforementioned embodiment, so they will not be repeated here.

[0080] In a specific embodiment, the first input parameter includes defect concentration (Gaussian, exponential, composite, etc. according to defect type), electron / hole mobility at low field / high field, doping concentration, leakage current value, interface effect parameters, etc. When screening parameters closely related to experimental production, it is necessary to screen according to specific device cases, such as: for general TFT devices, closely related parameters can be defect concentration, electron / hole mobility at low field / high field; for MOSFET devices, closely related parameters can be interface effect parameters.

[0081] S203, determining the influence type of the first input parameter on the first output parameter according to the device type of the semiconductor device, and generating a mechanism adjustment function of the device simulation case according to the influence type;

[0082] In combination with the design requirements of the device, the corresponding physical mechanism and production experience, the influence of the input parameters on the output parameters is first classified to obtain the influence type of the first input parameter on the first output parameter in the device type of the current device simulation case; wherein the influence type may include activation type, single association type, and complex association type, and a mechanism adjustment function of the device simulation case is generated according to different influence types.

[0083] In a specific implementation, the functions of each impact type may be specifically described as follows:

[0084] (1) When the influence type is active, such as the influence type of the base doping concentration on the current gain value of the HBT (Heterojunction Bipolar Transistor) device, the Sigmoid function can be used to describe the nonlinear relationship between input and output. The specific expression can be:

[0085] ;

[0086] (2) When the influence type is a single correlation type, for example, the influence type of low-field electron mobility on the current value of a TFT device, the following expression can be used to describe the nonlinear relationship between input and output:

[0087]

[0088] (3) When the influence type is complex correlation type, such as the influence type of Gaussian defect concentration on the current value of MOSFET device, the following expression can be used to describe the nonlinear relationship between input and output:

[0089]

[0090] (4) When the influence type is a mixed type, such as the influence type of exponential defect concentration on the current value of the TFT device, the following expression can be used to describe the nonlinear relationship between input and output:

[0091]

[0092] In the above formulas, x is the first input parameter, i.e., the defect concentration, low field / high field electron / hole mobility, doping concentration, electron / hole lifetime and other parameters mentioned above; other parameters such as k, It is the exponent value of the mathematical power operation, which is related to the specific relationship between the input and the output; the details are not repeated here.

[0093] S204, correcting the initial artificial intelligence model based on the mechanism adjustment function to obtain a corrected artificial intelligence fitting model;

[0094] S205, calling the artificial intelligence fitting model to fit the device simulation case, adjusting the first input parameter to obtain a first input parameter combination that makes the first output parameter of the device simulation case conform to the experimental output parameter;

[0095] This embodiment also includes pre-acquisition of an initial artificial intelligence model, wherein the initial artificial intelligence model can be constructed based on an artificial neural network algorithm and obtained after initial training; after obtaining the mechanism adjustment function under various different types of influence, the initial artificial intelligence model is corrected based on the mechanism adjustment function to obtain a corrected artificial intelligence fitting model.

[0096] Specifically, for a general initial artificial intelligence model, the fitting process is to continuously iteratively adjust the built-in artificial intelligence algorithm based on an initial input parameter combination, and finally approach the required input parameter combination. In one implementation, the current input parameter combination is recorded as:

[0097] ;

[0098] The new input parameter combination obtained after iterative adjustment is:

[0099] ;

[0100] Combined with each first input parameter determined in the previous steps Corresponding mechanism adjustment function , adjust the algorithm corresponding to the artificial intelligence fitting model as follows:

[0101] ;

[0102] Among them, the Represents the input parameter combination, ; represents the mechanism adjustment function, i=[1, n]; F represents the algorithm function of the initial artificial intelligence model before correction and adjustment, Represents the algorithm function of the corrected and adjusted artificial intelligence fitting model.

[0103] Specifically, based on the fitting process of the initial artificial intelligence model, combined with the initial input parameter combination and optimization algorithms such as the simplex algorithm, simulated annealing algorithm, genetic algorithm, etc., the initial input is continuously iterated, and ultimately the first output parameter is made close to the experimental output parameter, thereby obtaining the required first input parameter combination.

[0104] S206, constructing a correlation model between a second input parameter and a second output parameter of a device simulation case according to the first input parameter combination and the experimental output parameter;

[0105] After the first input parameter combination is adjusted based on the experimental output parameter, a correlation model between the second input parameter and the second output parameter of the device simulation case can be constructed based on the first input parameter combination.

[0106] S207, adjusting a second input parameter of the semiconductor device based on the design requirements of the semiconductor device, and acquiring a second output parameter corresponding to the second input parameter based on the association model;

[0107] S208 , design and develop a semiconductor device based on the second input parameter and the second output parameter.

[0108] After the association model is obtained, the association information between the intuitive parameters and output parameters of the semiconductor device can be constructed based on the association model. Based on this association information, the second input parameter of the semiconductor device can be adjusted based on the design requirements of the semiconductor device, thereby guiding the adjustment of the design parameters and accelerating the device development.

[0109] The method in the embodiment of the present invention can intelligently fit the device simulation case constructed by the simulation tool, so that the simulation result can be fitted to the experimental data, and the fitting method provided in the embodiment can improve the fitting accuracy, simplify the fitting operation, and reduce the time required for fitting; and the fitting method in the embodiment is an artificial intelligence fitting model generated by an artificial neural network instead of the simulation software to perform specific iterative fitting, which can further speed up the fitting speed and reduce the errors that are easy to generate during fitting. Then generate a parameter association model of the semiconductor device to guide the adjustment of the design parameters and accelerate the development of the device.

[0110] The artificial intelligence fitting method for device parameters in the embodiment of the present invention is described above. The artificial intelligence fitting device for device parameters in the embodiment of the present invention is described below. Figure 3 , an embodiment of the artificial intelligence fitting device for device parameters in the embodiment of the present invention includes:

[0111] A case construction module 301 is used to construct a device simulation case of a semiconductor device by using a simulation tool;

[0112] A parameter acquisition module 302 is used to acquire a first input parameter and a first output parameter in a device simulation case;

[0113] An adjustment module 303, configured to determine the type of influence of the first input parameter on the first output parameter according to the device type of the semiconductor device, and generate a mechanism adjustment function of the device simulation case according to the influence type;

[0114] A correction module 304, used to correct the initial artificial intelligence model based on the mechanism adjustment function to obtain a corrected artificial intelligence fitting model;

[0115] A parameter fitting module 305 is used to call the artificial intelligence fitting model to fit the device simulation case, and adjust the first input parameter to obtain a first input parameter combination that makes the first output parameter of the device simulation case conform to the experimental output parameter;

[0116] The model building module 306 is used to build a correlation model between the second input parameter and the second output parameter of the device simulation case according to the first input parameter combination and the experimental output parameter.

[0117] The artificial intelligence fitting device for device parameters provided in the embodiment of the present invention can intelligently fit the device simulation case constructed by the simulation tool, so that it can fit the simulation results to the experimental data, and the fitting method provided in this embodiment can improve the fitting accuracy, simplify the fitting operation, and reduce the time required for fitting.

[0118] In another embodiment of the present application, the artificial intelligence fitting device for device parameters further includes a development simulation module, and the development simulation module is specifically used for:

[0119] Based on the design requirements of the semiconductor device, adjusting a second input parameter of the semiconductor device, and based on the association model, acquiring a second output parameter corresponding to the second input parameter;

[0120] The semiconductor device is designed and developed based on the second input parameter and the second output parameter.

[0121] In another embodiment of the present application, the case construction module 301 includes:

[0122] A material design unit, used to select materials for semiconductor devices from a material library of a simulation tool and set material numerical information according to design requirements of the semiconductor device;

[0123] A structural design unit, used to model the structure of the semiconductor device according to the design requirements and material numerical information to obtain a device simulation model;

[0124] The physical design unit is used to add a physical model to the simulation model to set boundary conditions according to the design requirements, so as to obtain a device simulation case of the semiconductor device.

[0125] In another embodiment of the present application, the parameter acquisition module 302 is specifically used for:

[0126] Extracting alternative input parameters and alternative output parameters that can be modified in the device simulation case;

[0127] Selecting the first input parameter from the candidate input parameters according to the device type of the semiconductor device and the difficulty of modifying the first input parameter;

[0128] According to the device type of the semiconductor device and the design requirements of the output parameters, the first input parameter is selected from the candidate output parameters.

[0129] In another embodiment of the present application, the expression for obtaining the corrected artificial intelligence fitting model by correcting the initial artificial intelligence model based on the mechanism adjustment function in the correction module 304 is:

[0130] ;

[0131] in, Represents the input parameter combination, ; represents the mechanism adjustment function, i=[1, n]; F represents the algorithm function of the initial artificial intelligence model before correction and adjustment, Represents the algorithm function of the corrected and adjusted artificial intelligence fitting model.

[0132] In another embodiment of the present application, in the adjustment module 303, the impact type includes an activation type, a single association type, a multiple association type, and a mixed type.

[0133] The device provided by the embodiment of the present invention can intelligently fit the device simulation case constructed by the simulation tool, so that it can fit the simulation result to the experimental data, and the fitting method provided in this embodiment can improve the fitting accuracy, simplify the fitting operation, and reduce the time required for fitting; and the fitting method in this embodiment is an artificial intelligence fitting model generated by an artificial neural network instead of the simulation software to perform specific iterative fitting, which can further speed up the fitting speed and reduce the errors that are easy to generate during fitting. Then generate a parameter association model of the semiconductor device to guide the adjustment of the design parameters and accelerate the development of the device.

[0134] Based on the same inventive concept, an embodiment of this specification also provides an electronic device for artificial intelligence fitting of device parameters. The electronic device for artificial intelligence fitting of device parameters in an embodiment of the present invention is described in detail below from the perspective of hardware processing.

[0135] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this specification. Figure 4 The electronic device 400 according to this embodiment of the present invention is described. Figure 4 The electronic device 400 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0136] like Figure 4 As shown, the electronic device 400 is in the form of a general computing device. The components of the electronic device 400 may include, but are not limited to: at least one processing unit 410, at least one storage unit 420, a bus 430 connecting different system components (including the storage unit 420 and the processing unit 410), a display unit 440, etc.

[0137] The storage unit stores program codes, which can be executed by the processing unit 410, so that the processing unit 410 performs the steps according to various exemplary embodiments of the present invention described in the above processing method section of this specification. For example, the processing unit 410 can perform the following steps: Figure 1 or Figure 2 Steps shown.

[0138] The storage unit 420 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 4201 and / or a cache memory unit 4202 , and may further include a read-only memory unit (ROM) 4203 .

[0139] The storage unit 420 may also include a program / utility 4204 having a set (at least one) of program modules 4205, such program modules 4205 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include the implementation of a network environment.

[0140] Bus 430 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0141] The electronic device 400 may also communicate with one or more external devices 100 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device 400, and / or any device that enables the electronic device 400 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 450. Furthermore, the electronic device 400 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 460. The network adapter 460 may communicate with other modules of the electronic device 400 via the bus 430. It should be understood that although Figure 4 Not shown, other hardware and / or software modules may be used in conjunction with electronic device 400, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0142] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the exemplary embodiments described in the present invention can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation method of the present invention can be embodied in the form of a software product, which can be stored in a computer-readable storage medium (which can be a CD-ROM, USB flash drive, mobile hard disk, etc.) or on a network, including a number of instructions to enable a computing device (which can be a personal computer, server, or network device, etc.) to execute the above method according to the present invention. When the computer program is executed by a data processing device, the computer-readable medium can implement the above method of the present invention, that is: Figure 1 or Figure 2 The method shown.

[0143] Figure 5 A schematic diagram of a computer-readable medium provided for an embodiment of this specification.

[0144] accomplish Figure 1 or Figure 2 The computer program of the method shown can be stored on one or more computer readable media. The computer readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, a system, device or component of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0145] The computer readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by an instruction execution system, an apparatus, or a device or used in combination with it. The program code contained on the readable storage medium may be transmitted with any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0146] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0147] In summary, the present invention can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that general data processing devices such as microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all functions of some or all components in the embodiments of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., a computer program and a computer program product) for executing part or all of the methods described herein. Such a program for implementing the present invention can be stored on a computer-readable medium, or can be in the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0148] In addition, the present invention also provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the artificial intelligence fitting method for device parameters as described in any of the above embodiments.

[0149] The specific embodiments described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the present invention is not inherently related to any specific computer, virtual device or electronic device, and various general devices can also implement the present invention. The above description is only a specific embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0150] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0151] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. An artificial intelligence fitting method for device parameters, characterized in that: include: Build device simulation cases for semiconductor devices through simulation tools; Obtaining a first input parameter and a first output parameter in a device simulation case; Determining, according to the device type of the semiconductor device, the type of influence of the first input parameter on the first output parameter, and generating a mechanism adjustment function of the device simulation case according to the type of influence; Based on the mechanism adjustment function, the initial artificial intelligence model is corrected to obtain a corrected artificial intelligence fitting model; Calling the artificial intelligence fitting model to fit the device simulation case, adjusting the first input parameter to obtain a first input parameter combination that makes the first output parameter of the device simulation case conform to the experimental output parameter; A correlation model between the second input parameter and the second output parameter of the device simulation case is constructed according to the first input parameter combination and the experimental output parameter.

2. The artificial intelligence fitting method for device parameters according to claim 1, characterized in that: After constructing the correlation model between the second input parameter and the second output parameter of the device simulation case, the method further includes: Based on the design requirements of the semiconductor device, adjusting a second input parameter of the semiconductor device, and based on the association model, acquiring a second output parameter corresponding to the second input parameter; The semiconductor device is designed and developed based on the second input parameter and the second output parameter.

3. The artificial intelligence fitting method for device parameters according to claim 2, characterized in that: The device simulation cases of building semiconductor devices by simulation tools include: Select the material of the semiconductor device in the material library of the simulation tool, and set the material value information according to the design requirements of the semiconductor device; Modeling the structure of the semiconductor device according to the design requirements and material numerical information to obtain a device simulation model; According to the design requirements, a physical model is added to the simulation model to set boundary conditions, so as to obtain a device simulation case of the semiconductor device.

4. The artificial intelligence fitting method for device parameters according to claim 2, characterized in that: The obtaining of the first input parameter and the first output parameter in the device simulation case includes: Extracting alternative input parameters and alternative output parameters that can be modified in the device simulation case; Selecting the first input parameter from the candidate input parameters according to the device type of the semiconductor device and the difficulty of modifying the first input parameter; According to the device type of the semiconductor device and the design requirements of the output parameters, the first input parameter is selected from the candidate output parameters.

5. The artificial intelligence fitting method for device parameters according to any one of claims 2 to 4, characterized in that: The expression of the modified artificial intelligence fitting model obtained by modifying the initial artificial intelligence model based on the mechanism adjustment function is: ； in, Represents the input parameter combination, ; represents the mechanism adjustment function, i=[1, n]; F represents the algorithm function of the initial artificial intelligence model before correction and adjustment, Represents the algorithm function of the corrected and adjusted artificial intelligence fitting model.

6. The artificial intelligence fitting method for device parameters according to claim 5, characterized in that: The impact types include activation type, single association type, multiple association type and mixed type.

7. An artificial intelligence fitting device for device parameters, characterized in that: include: A case building module, used to build device simulation cases of semiconductor devices through simulation tools; A parameter acquisition module, used to acquire a first input parameter and a first output parameter in a device simulation case; An adjustment module, configured to determine the type of influence of the first input parameter on the first output parameter according to the device type of the semiconductor device, and generate a mechanism adjustment function of the device simulation case according to the influence type; A correction module, used to correct the initial artificial intelligence model based on the mechanism adjustment function to obtain a corrected artificial intelligence fitting model; A parameter fitting module, used for calling the artificial intelligence fitting model to fit the device simulation case, and adjusting the first input parameter to obtain a first input parameter combination that makes the first output parameter of the device simulation case conform to the experimental output parameter; A model building module is used to build a correlation model between the second input parameter and the second output parameter of the device simulation case according to the first input parameter combination and the experimental output parameter.

8. An artificial intelligence fitting device for device parameters, characterized in that: The artificial intelligence fitting device for device parameters comprises: a memory and at least one processor, wherein instructions are stored in the memory; The at least one processor calls the instructions in the memory to enable the artificial intelligence fitting device for device parameters to perform the steps of the artificial intelligence fitting method for device parameters as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the program / instructions are executed by a processor, the steps of the artificial intelligence fitting method for device parameters as described in any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the artificial intelligence fitting method for device parameters according to any one of claims 1 to 6 are implemented.

Images