Ion implanter parameter generation and adjustment method, apparatus, and electronic device

Abstract

The application provides an ion implanter parameter generation and adjustment method, device and electronic equipment. The method comprises the following steps: obtaining training adjustment data; generating a target state prediction model by using the training adjustment data, the target state prediction model supporting state information prediction under any ion implanter parameter combination; when a target operation response instruction is detected, determining a target operation indicated by the target operation response instruction, and obtaining target operation response data by responding to the target operation through the target state prediction model; wherein the target operation supports forward state prediction function and reverse parameter searching function, the forward state prediction function is used for predicting state information, the reverse parameter searching function is used for searching for a target ion implanter parameter combination meeting a target demand, and the target operation response data is used for guiding ion implanter parameter adjustment. The embodiment of the application can conveniently adjust ion implanter parameters, so that the time consumption of adjustment is effectively reduced.

Description

Technical Field

[0001] This invention relates to the field of semiconductor technology, and in particular to a method, apparatus, and electronic device for generating and adjusting parameters of an ion implanter. Background Technology

[0002] Currently, in semiconductor manufacturing processes, ion implantation is a crucial step in controlling device doping concentration, junction depth, and electrical characteristics. The ion implanter, as the core equipment for this process, must be able to stably generate and control ion beams of specific energy and current to meet the process requirements for dosage, energy, and uniformity. The overall structure of an ion implanter typically includes an ion source, a beamline transport system, an acceleration structure, and a beam implantation region. The ion source region, which generates the ion beam, is the starting point of the equipment, and its beam size, extraction efficiency, and stability significantly impact process quality. However, the ionization efficiency of the ion source region and the generated beam size are influenced by multiple parameters. In practical applications, it is usually necessary to set the initial parameter combination of the ion implanter and then manually adjust the parameters based on actual beam feedback until the desired parameter combination is obtained, resulting in cumbersome operation and long adjustment time. Therefore, there is currently no satisfactory solution for conveniently adjusting ion implanter parameters to effectively reduce adjustment time. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a method, apparatus, and electronic device for generating and adjusting ion implanter parameters to solve the problems of cumbersome operation and long adjustment time caused by related technologies. Specifically, embodiments of the present invention can respond to target operations through a target state prediction model to achieve forward state prediction and reverse parameter seeking functions, thereby guiding ion implanter parameter adjustment through target operation response data. Specifically, when the target operation supports the implementation of the forward state prediction function, the ion implanter parameters can be adjusted based on the state information indicated by the target operation response data; and when the target operation supports the implementation of the reverse parameter seeking function, the ion implanter parameters can be determined based on the target ion implanter parameter combination indicated by the target operation response data. This allows for the efficient generation of target ion implanter parameter combinations that meet the target requirements, thereby efficiently completing ion implanter parameter adjustment. For example, the target ion implanter parameter combination can be directly used as the final adjusted ion implanter parameters, or rapid fine-tuning can be further achieved based on the target ion implanter parameter combination. Therefore, embodiments of the present invention can conveniently adjust ion implanter parameters, thereby effectively reducing adjustment time.

[0004] According to one aspect of the present invention, a method for generating and adjusting ion implanter parameters is provided, the method comprising:

[0005] Acquire training and adjustment data, which includes adjustment and acquisition data of the target ion implanter at multiple historical acquisition times. The adjustment and acquisition data at one historical acquisition time includes the ion implanter parameter combination and tag status information at the corresponding historical acquisition time. A tag information includes at least one of the following: extraction current and mass analyzer Faraday value.

[0006] Using the training and adjustment data, a target state prediction model is generated, which supports the prediction of state information under any combination of ion implanter parameters;

[0007] Upon detecting a target operation response command, the target operation indicated by the target operation response command is determined, and the target operation is responded to through the target state prediction model to obtain target operation response data; wherein, the target operation supports the implementation of a forward state prediction function and a reverse parameter search function, the forward state prediction function is used to predict state information, the reverse parameter search function is used to find a target ion implanter parameter combination that meets the target requirements, and the target operation response data is used to guide the adjustment of ion implanter parameters;

[0008] Wherein, if the target operation includes a positive state prediction operation, and the positive state prediction operation supports the implementation of the positive state prediction function, then the step of responding to the target operation through the target state prediction model to obtain target operation response data includes:

[0009] Determine the combination of ion implanter parameters to be evaluated as indicated by the target operation;

[0010] The target state prediction model is invoked to predict the state information under the parameter combination of the ion implanter to be evaluated.

[0011] The status information of the ion implanter under the parameter combination to be evaluated is added to the target operation response data;

[0012] If the target operation includes a reverse parameter lookup operation, and the reverse parameter lookup operation supports the implementation of the reverse parameter lookup function, then the step of responding to the target operation through the target state prediction model to obtain target operation response data includes:

[0013] Determine the target optimization instruction information indicated by the target operation, and determine the target requirement based on the target optimization instruction information;

[0014] Based on the target requirements, an objective function is determined, and the target ion implanter parameter combination is determined through the objective function, the target state prediction model, and the target intelligent optimization algorithm; wherein, the target state prediction model supports the prediction of state information under any individual parameter.

[0015] The target ion implanter parameters are combined and added to the target operation response data.

[0016] According to another aspect of the present invention, an ion implanter parameter generation and adjustment apparatus is provided, the apparatus comprising:

[0017] The acquisition unit is used to acquire training and adjustment data, which includes adjustment acquisition data of the target ion implanter at multiple historical acquisition times. The adjustment acquisition data at one historical acquisition time includes the ion implanter parameter combination and tag status information at the corresponding historical acquisition time. The tag information includes at least one of the following: extraction current and mass analyzer Faraday value.

[0018] The processing unit is used to generate a target state prediction model using the training and adjustment data, wherein the target state prediction model supports the prediction of state information under any combination of ion implanter parameters;

[0019] The processing unit is further configured to, upon detecting a target operation response command, determine the target operation indicated by the target operation response command, and respond to the target operation through the target state prediction model to obtain target operation response data; wherein, the target operation supports the implementation of a forward state prediction function and a reverse parameter search function, the forward state prediction function is used to predict state information, the reverse parameter search function is used to find a target ion implanter parameter combination that meets the target requirements, and the target operation response data is used to guide the adjustment of ion implanter parameters;

[0020] Wherein, if the target operation includes a positive state prediction operation, and the positive state prediction operation supports the implementation of the positive state prediction function, then when the processing unit responds to the target operation through the target state prediction model and obtains the target operation response data, it is specifically used for:

[0021] Determine the combination of ion implanter parameters to be evaluated as indicated by the target operation;

[0022] The target state prediction model is invoked to predict the state information under the parameter combination of the ion implanter to be evaluated.

[0023] The status information of the ion implanter under the parameter combination to be evaluated is added to the target operation response data;

[0024] If the target operation includes a reverse parameter lookup operation, and the reverse parameter lookup operation supports the implementation of the reverse parameter lookup function, then when the processing unit responds to the target operation through the target state prediction model and obtains the target operation response data, it is specifically used for:

[0025] Determine the target optimization instruction information indicated by the target operation, and determine the target requirement based on the target optimization instruction information;

[0026] Based on the target requirements, an objective function is determined, and the target ion implanter parameter combination is determined through the objective function, the target state prediction model, and the target intelligent optimization algorithm; wherein, the target state prediction model supports the prediction of state information under any individual parameter.

[0027] The target ion implanter parameters are combined and added to the target operation response data.

[0028] According to another aspect of the present invention, an electronic device is provided, the electronic device including a processor and a memory storing a program, wherein the program includes instructions that, when executed by the processor, cause the processor to perform the methods mentioned above.

[0029] According to another aspect of the present invention, a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the methods mentioned above is provided.

[0030] This invention provides embodiments that can acquire training and adjustment data, including adjustment and acquisition data of the target ion implanter at multiple historical acquisition times. The adjustment and acquisition data at one historical acquisition time includes the corresponding ion implanter parameter combination and tag status information. Each tag information includes at least one of the following: extraction current and Faraday value of the mass analyzer. Using the training and adjustment data, a target state prediction model is generated. This model supports predicting state information under any combination of ion implanter parameters. Furthermore, upon detecting a target operation response command, the target operation indicated by the command can be determined, and the target operation is responded to using the target state prediction model to obtain target operation response data. The target operation supports both forward state prediction and reverse parameter seeking functions. The forward state prediction function predicts state information, and the reverse parameter seeking function finds the target ion implanter parameter combination that meets the target requirements. The target operation response data guides the adjustment of ion implanter parameters. As can be seen, embodiments of the present invention can respond to target operations through a target state prediction model to achieve both forward state prediction and reverse parameter seeking functions. This allows for guidance of ion implanter parameter adjustment via target operation response data. Specifically, when the target operation supports the implementation of the forward state prediction function, the ion implanter parameters can be adjusted using the state information indicated by the target operation response data. Furthermore, when the target operation supports the implementation of the reverse parameter seeking function, the ion implanter parameters can be determined using the target ion implanter parameter combination indicated by the target operation response data. This efficiently generates target ion implanter parameter combinations that meet the target requirements, thereby efficiently completing ion implanter parameter adjustment. For example, the target ion implanter parameter combination can be directly used as the final adjusted ion implanter parameters, or rapid fine-tuning can be further achieved based on the target ion implanter parameter combination. Therefore, embodiments of the present invention can conveniently adjust ion implanter parameters, thereby effectively reducing adjustment time. Attached Figure Description

[0031] Further details, features, and advantages of the invention are disclosed in the following description of exemplary embodiments in conjunction with the accompanying drawings, in which:

[0032] Figure 1 A flowchart illustrating a method for generating and adjusting ion implanter parameters according to an exemplary embodiment of the present invention is shown.

[0033] Figure 2 A flowchart illustrating another method for generating and adjusting ion implanter parameters according to an exemplary embodiment of the present invention is shown.

[0034] Figure 3 A flowchart illustrating another method for generating and adjusting ion implanter parameters according to an exemplary embodiment of the present invention is shown;

[0035] Figure 4 A schematic block diagram of an ion implanter parameter generation and adjustment apparatus according to an exemplary embodiment of the present invention is shown;

[0036] Figure 5 A structural block diagram of an exemplary electronic device that can be used to implement embodiments of the present invention is shown. Detailed Implementation

[0037] Embodiments of the present invention will now be described in more detail with reference to the accompanying drawings. While some embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the invention. It should be understood that the accompanying drawings and embodiments are for illustrative purposes only and are not intended to limit the scope of protection of the invention.

[0038] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0039] The term "comprising" and its variations as used herein are open-ended, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the following description. It should be noted that the concepts of "first", "second", etc., mentioned in this invention are used only to distinguish different devices, modules, or units, and are not intended to limit the order of functions performed by these devices, modules, or units or their interdependencies.

[0040] It should be noted that the terms "a" and "a plurality of" used in this invention are illustrative rather than restrictive. Those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0041] The names of the messages or information exchanged between the multiple devices in the embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of these messages or information.

[0042] It should be noted that the execution subject of the ion implanter parameter generation and adjustment method provided in this embodiment of the invention can be one or more electronic devices, and this invention does not limit this; wherein, the electronic device can be a terminal (i.e., a client) or a server. Therefore, when the execution subject includes multiple electronic devices, and among the multiple electronic devices includes at least one terminal and at least one server, the ion implanter parameter generation and adjustment method provided in this embodiment of the invention can be jointly executed by the terminal and the server. Accordingly, the terminal mentioned herein may include, but is not limited to: smartphones, tablets, laptops, desktop computers, smartwatches, smart voice interaction devices, smart home appliances, vehicle terminals, aircraft, etc. The server mentioned herein can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms, etc.

[0043] Based on the above description, this invention proposes a method for generating and adjusting ion implanter parameters. This method can be executed by the aforementioned electronic device (terminal or server); or, it can be executed jointly by the terminal and the server. For ease of explanation, the following description will use the execution of this ion implanter parameter generation and adjustment method by an electronic device as an example. Figure 1 As shown, the method for generating and adjusting the parameters of the ion implanter may include the following steps S101-S103:

[0044] S101, acquire training and adjustment data. The training and adjustment data includes the adjustment and acquisition data of the target ion implanter at multiple historical acquisition times. The adjustment and acquisition data at a historical acquisition time includes the ion implanter parameter combination and tag status information at the corresponding historical acquisition time.

[0045] Optionally, an ion implanter parameter combination (such as an ion implanter parameter combination at a historical acquisition moment, a target ion implanter parameter combination, etc.) may include the parameter values ​​of each parameter among multiple parameters. Optionally, the multiple parameters may include, but are not limited to, at least two of the following: the type of working gas, gas quantity, filament current, bias current, arc voltage, arc current, source magnet current, and the position of the three electrodes, etc.; the embodiments of the present invention do not limit this. It should be understood that these parameters are highly coupled and have a nonlinear relationship. Different parameter combinations (i.e., different combinations of parameter values) will lead to changes in beam generation efficiency, magnitude, and stability. Therefore, finding a suitable parameter configuration is crucial in actual production. Optionally, in addition to the source region (i.e., ion source region) parameters that need to be adjusted, the multiple parameters may also include parameters of the beam optical path, etc., the embodiments of the present invention do not limit this; for example, the multiple parameters may also include, but are not limited to, parameters of the beam optical path such as the mass analysis magnet (MAM) current, filament current (which can also be represented as Fila_I), and extraction voltage (which can also be represented as Ext_V), etc.

[0046] Optionally, a status information (such as tag status information) may include, but is not limited to, at least one of the following: lead-out current, Mass Analyzer Faraday (MAF) value (also known as Mass Analyzer Faraday Cup value or MAF value), etc.; this embodiment of the invention does not limit this. It should be understood that the tag status information at a historical acquisition time may be the status information under the corresponding combination of ion implanter parameters at that historical acquisition time, that is, the status information when running according to the corresponding combination of ion implanter parameters.

[0047] Optionally, the target ion implanter can be any ion implanter, and this embodiment of the invention does not limit this. Optionally, the multiple historical acquisition times can include any historical acquisition times, and this embodiment of the invention does not limit this.

[0048] In this embodiment of the invention, the methods for obtaining training and adjustment data may include, but are not limited to, the following:

[0049] The first method of acquisition: The electronic device can store training and adjustment data in its own storage space. In this case, the electronic device can obtain the training and adjustment data from its own storage space.

[0050] The second method of acquisition: When an electronic device detects a training data upload operation, it can use the training data uploaded in the training data upload operation as training adjustment data to acquire the training adjustment data.

[0051] The third acquisition method: Adjustment data can be acquired through a parameter scanning module in the target ion implanter. This module supports waiting for beam stabilization after parameter adjustment, and then calling the data acquisition interface to record the adjustment data after beam stabilization. In this case, the electronic device can acquire training adjustment data from the target ion implanter. Optionally, the electronic device can acquire training adjustment data from the target ion implanter using a target encryption method. The target encryption method can be any encryption algorithm, and this embodiment of the invention does not limit this. Based on this, this embodiment of the invention can construct a parameter scanning module for automatically generating training adjustment data. It should be understood that although the machine's own operation log can continuously record various operating parameters, the log recording frequency is fixed, the data volume is dense, and it lacks the function of filtering out anomalies. Therefore, if the machine log is used directly as training data, it will inevitably contain a large amount of abnormal data such as transient disturbances of the equipment, unstable discharge stages, and abnormal data generated during the adjustment process. Such abnormal data will significantly reduce the robustness of the subsequent target state prediction model, making the model sensitive to fluctuations and affecting the prediction accuracy. In this regard, the embodiment of the present invention uses a parameter scanning module to generate structured training adjustment data for use as training data, which can effectively improve the stability and accuracy of the training adjustment data, avoid the impact of abnormal data on model training, thereby effectively improving the model performance of the target state prediction model and thus improving the accuracy of state prediction. In other words, the embodiment of the present invention can avoid data during the transient disturbance stage of the equipment and obtain uniformly distributed and quality-controllable training data, thereby significantly improving the model's resistance to fluctuations and generalization performance.

[0052] Optionally, the parameter scanning module also supports preset scanning time range and / or scanning step size; optionally, both the scanning time range and scanning step size can be set based on experience or based on actual needs, and this embodiment of the invention does not limit this. For example, the scanning time range may include a single parameter adjustment scanning time range (also called a single parameter adjustment scanning duration, i.e., a period of time after beam stabilization is determined, such as 10 minutes, in which case data acquisition can be performed according to the single parameter adjustment scanning time range after each parameter adjustment and beam stabilization determination); and / or, the scanning time range may include a total scanning time range (which can be a fixed period of time, such as a certain day, in which case parameters can be adjusted and data acquisition can be performed only within the preset total scanning time range), etc.; this embodiment of the invention does not limit this. Optionally, the parameter scanning module can determine the beam stability after a preset waiting time following parameter adjustment, and then perform data acquisition according to a preset scanning time range and / or scanning step size after the preset waiting time following parameter adjustment; or, the parameter scanning module can determine the fluctuation amplitude of each fluctuation index among at least one fluctuation index after parameter adjustment, and then determine that the beam is stable after parameter adjustment when the fluctuation amplitude of each fluctuation index meets the preset fluctuation range threshold of the corresponding fluctuation index, etc.; the embodiment of the present invention does not limit the method of determining beam stability. Optionally, the preset waiting time, at least one fluctuation index, and the preset fluctuation range threshold of each fluctuation index can all be set according to experience or according to actual needs, and the embodiment of the present invention does not limit this; for example, at least one fluctuation index may include, but is not limited to, beam intensity fluctuation, beam position offset, and vacuum fluctuation, etc.

[0053] Optionally, after the beam stabilizes, the parameter scanning module can call the data acquisition interface to record adjustment acquisition data according to the scanning time range and / or scanning step size. Optionally, after each parameter adjustment and waiting for the beam to stabilize, the current adjustment acquisition data (which may include the current ion implanter parameter combination (i.e., the parameter combination after the current parameter adjustment) and tag status information) can be acquired within a preset scanning time range to add the current adjustment acquisition data to the training adjustment data; or, after each parameter adjustment and waiting for the beam to stabilize, the adjustment acquisition data at each of the M acquisition times can be acquired within a preset scanning time range according to the scanning step size, and the adjustment acquisition data at each acquisition time can be added to the training adjustment data; or, candidate tag status information can be selected from the adjustment acquisition data at each acquisition time, and the adjustment acquisition data containing the candidate tag status information can be added to the training adjustment data, etc.; the embodiments of the present invention do not limit this. Optionally, M is a positive integer, and the embodiments of the present invention do not limit the specific value of M. Optionally, the candidate tag status information can be the tag status information with the smallest deviation from the mean of the tag status information at each acquisition time, or it can be the tag status information at the median of the tag status information at each acquisition time (such as the median of the lead-out current), etc.; the embodiments of the present invention do not limit this.

[0054] Optionally, when the parameter scanning module detects a parameter scanning command, it can adjust the ion implanter parameters at preset parameter adjustment intervals (i.e., adjust the parameter values ​​of each parameter among multiple parameters), and wait for the beam to stabilize after each parameter adjustment, so as to perform data acquisition after the beam stabilizes (i.e., call the data acquisition interface to record the adjusted and acquired data); correspondingly, it can stop parameter adjustment and data acquisition after detecting a parameter scanning stop command, and so on. Optionally, the user (such as the manager or engineer of the target ion implanter, etc.) can perform parameter scanning operations on the target ion implanter (e.g., through the parameter scanning module), then the parameter scanning module can detect the parameter scanning command; or, it can determine that the parameter scanning command has been detected when the current time is the start time of the total scanning time range, etc.; the embodiments of the present invention do not limit this. Optionally, the user can perform a parameter scan stop operation on the target ion implanter, in which case the parameter scan module can detect the parameter scan stop command; alternatively, the parameter scan stop command can be determined to have been detected after a preset total scan time has elapsed since the parameter scan command was detected; or, the parameter scan stop command can be determined to have been detected when the current time is the end time of the total scan time range, etc.; this embodiment of the invention does not limit this. Optionally, this embodiment of the invention does not limit the specific execution method of the parameter scan operation and the parameter scan stop operation. Optionally, both the preset parameter adjustment time and the preset total scan time can be set according to experience or actual needs, and this embodiment of the invention does not limit this.

[0055] Optionally, an ion implanter parameter combination may further include the index value of each of the at least one equipment index; that is, the above-mentioned multiple parameters may further include at least one equipment index. The at least one equipment index can be used to indicate the equipment status of the target ion implanter. It should be noted that the embodiments of the present invention do not limit the specific content of the at least one equipment index; for example, the at least one equipment index may include, but is not limited to, the usage time of the ion source. Optionally, the indicator values ​​of each device in the adjustment acquisition data can be added to the corresponding adjustment acquisition data by the parameter scanning module (i.e., added to the ion implanter parameter combination included in the corresponding adjustment acquisition data). Then, the parameter scanning module can add the adjustment acquisition data with the indicator values ​​of each device (such as the current usage time of the ion source) to the training adjustment data. Alternatively, for the adjustment acquisition data at any historical acquisition time in the training adjustment data, the electronic device can obtain the device log of the target ion implanter to obtain the ion source usage time corresponding to any historical acquisition time from the device log, and add the ion source usage time corresponding to any historical acquisition time to the ion implanter parameter combination at any historical acquisition time, so as to update the adjustment acquisition data at any historical acquisition time. Thus, the adjustment acquisition data in the training adjustment data also includes the indicator values ​​of each device (i.e., the indicator values ​​of each device at the corresponding historical acquisition time), etc. The embodiments of the present invention do not limit this. Based on this, embodiments of the present invention can also effectively improve the prediction accuracy of the model through at least one device indicator. This is because different values ​​of indicators such as usage time will lead to different device usage effects. Thus, when the parameters of the ion source are the same but the values ​​of indicators such as usage time are different, the state information may be different. Therefore, embodiments of the present invention can effectively improve the prediction performance of the model through at least one device indicator. That is, the target obtained by the same ion source parameters may be different under different device states, which can effectively improve the prediction accuracy.

[0056] S102 uses training and conditioning data to generate a target state prediction model, which supports the prediction of state information under any combination of ion implanter parameters.

[0057] Optionally, the state information predicted by the target state prediction model can also be called the predicted state information.

[0058] Optionally, a state prediction model (such as a target state prediction model) can be a random forest model (i.e., the random forest algorithm can be used to train the state prediction model), a gradient boosting decision tree model, an artificial neural network model, or a support vector regression model, etc.; this embodiment of the invention does not limit this. For example, the random forest algorithm is used as an example. The execution logic of the random forest algorithm includes firstly, using the bootstrap method to sample the training conditioning data multiple times with replacement to generate multiple subsets of data; secondly, training a regression tree on each subset of data, with the feature selection of tree nodes using a random subset of features; and finally, averaging the outputs of all trees as the final prediction result. Based on this, this embodiment of the invention can use this machine learning mechanism to realize a nonlinear state prediction model from ion implanter parameters (such as ion source region parameters) to state information (such as extraction current and Faraday value of the mass analyzer), providing fast, stable, and repeatable prediction capabilities.

[0059] For example, when the target state prediction model is a random forest model, the electronic device can use training and adjustment data to construct the target state prediction model in order to generate the target state prediction model. That is, the target state prediction model can be constructed by using the combination of ion implanter parameters at each historical acquisition time, so that the state information of any leaf node is the average result of the tag state information under the combination of ion implanter parameters in any leaf node. For example, the extracted current in the state information of any leaf node can be the average of the extracted current in the tag state information under the combination of ion implanter parameters in any leaf node, and so on.

[0060] For example, when the target state prediction model is an artificial neural network or similar model whose training process optimizes model parameters through loss calculation, an initial state prediction model can be invoked to predict the state information under various combinations of ion implanter parameters in the training conditioning data. Based on the predicted state information (i.e., predicted state information) and label state information under various combinations of ion implanter parameters in the training conditioning data, the model loss value is calculated to optimize the model parameters in the initial state prediction model in the direction of reducing the model loss value. Then, the optimized initial state prediction model is trained until the model convergence condition is met (e.g., the model loss value is less than a preset loss threshold, or the number of iterations reaches a preset iteration threshold, etc.), thereby obtaining the target state prediction model, thus achieving the generation of the target state prediction model, and so on. Optionally, the preset loss threshold and the preset iteration threshold can be set according to experience or actual needs, and this embodiment of the invention does not limit this. Based on this, this embodiment of the invention does not limit the specific generation method of the target state prediction model.

[0061] Optionally, the electronic device may include a data training module, in which case the electronic device can use the data training module to generate a target state prediction model by using training and conditioning data.

[0062] S103, when a target operation response command is detected, the target operation indicated by the target operation response command is determined, and the target operation is responded to through the target state prediction model to obtain target operation response data; wherein, the target operation supports the implementation of forward state prediction function and reverse parameter search function, the forward state prediction function is used to predict state information, the reverse parameter search function is used to find the target ion implanter parameter combination that meets the target requirements, and the target operation response data is used to guide the adjustment of ion implanter parameters.

[0063] Optionally, the electronic device may also include a prediction and optimization parameter module. In this case, the electronic device can load the target state prediction model into the prediction and optimization parameter module, thereby executing the target operation indicated by the aforementioned target operation response instruction through the prediction and optimization parameter module, and responding to the target operation through the target state prediction model to obtain target operation response data, etc. Optionally, the prediction and optimization parameter module may also include a model prediction module and a parameter optimization module. In this case, the electronic device can realize the forward state prediction function through the model prediction module and the reverse parameter optimization function through the parameter optimization module.

[0064] Optionally, the electronic device may also display a function setting interface, which allows users (such as engineers) to select forward state prediction and / or reverse parameter seeking functions. Correspondingly, when the electronic device detects a target operation in the function setting interface, it can determine that a target operation response command has been detected. Specifically, when the target operation is used to implement the forward state prediction function, the target operation is set with the parameter combination of the ion implanter to be evaluated; when the target operation is used to implement the reverse parameter seeking function, the target operation is set with target optimization indication information. In other words, the user can execute the target operation in the function setting interface, thereby enabling the electronic device to detect the target operation in the function setting interface. Optionally, the target operation may include a forward state prediction operation, in which case the target operation can be used to implement the forward state prediction function, i.e., the forward state prediction operation supports the implementation of the forward state prediction function; and / or, the target operation may include a reverse parameter seeking operation, in which case the target operation can be used to implement the reverse parameter seeking function, i.e., the reverse parameter seeking operation supports the implementation of the reverse parameter seeking function, and so on. It should be noted that the embodiments of the present invention do not limit the specific execution methods of the forward state prediction operation and the reverse parameter search operation, that is, they do not limit the specific execution method of the target operation. For example, assuming that the function setting interface can include a forward state prediction function setting area and a reverse parameter search function setting area, then the user can input the parameter combination of the ion implanter to be evaluated in the forward state prediction function setting area and the target optimization instruction information in the reverse parameter search function setting area, and after inputting the information, click the submit button to realize the target operation. At this time, the target operation can include the forward state prediction operation and the reverse parameter search operation. Alternatively, the user can select the forward state prediction function or the reverse parameter search function and input the corresponding data (e.g., if the forward state prediction function is selected, the parameter combination of the ion implanter to be evaluated is input; if the reverse parameter search function is selected, the target optimization instruction information is input; at this time, the input area for the two types of data can be the same area), thereby realizing the execution of the forward state prediction operation or the reverse parameter search operation. At this time, the target operation can be the forward state prediction operation (i.e., only the forward state prediction operation is included) or the reverse parameter search operation (i.e., only the reverse parameter search operation is included), and so on. Optionally, the parameter combination of the ion implanter to be evaluated may include the parameter values ​​of each parameter among multiple parameters; optionally, both the parameter combination of the ion implanter to be evaluated and the target optimization indication information can be input according to experience or actual needs, and the embodiments of the present invention do not limit this.

[0065] Optionally, the electronic device may also include a user interaction module. In this case, the electronic device can display a function setting interface through the user interaction module. Based on this, the user can select the positive state prediction function and input the parameter combination of the ion implanter to be evaluated in the user interaction module (i.e., the positive state prediction operation can be performed in the function setting interface at this time). Correspondingly, after the electronic device calls the target state prediction model to predict the state information under the parameter combination of the ion implanter to be evaluated, it can return the state information under the parameter combination of the ion implanter to be evaluated through the user interaction module, and output the state information under the parameter combination of the ion implanter to be evaluated through the user interaction module, and so on. It can be seen that the state prediction process of this embodiment can be performed locally without additional data collection, is short in time, and can provide real-time feedback, enabling users to quickly evaluate parameter combinations without actually operating the equipment, that is, to quickly determine the state information under the parameter combination of the ion implanter to be evaluated.

[0066] Specifically, if the target operation includes a positive state prediction operation, then when responding to the target operation through the target state prediction model and obtaining the target operation response data, the electronic device can determine the parameter combination of the ion implanter to be evaluated indicated by the target operation, that is, determine the parameter combination of the ion implanter to be evaluated indicated by the positive state prediction operation (i.e., the parameter combination of the ion implanter to be evaluated input by the user); and can call the target state prediction model to predict the state information under the parameter combination of the ion implanter to be evaluated; based on this, the state information under the parameter combination of the ion implanter to be evaluated can be added to the target operation response data, that is, the state information under the parameter combination of the ion implanter to be evaluated can be used as the target operation response data, thereby obtaining the target operation response data. At this time, the target operation response data may include the state information under the parameter combination of the ion implanter to be evaluated. Optionally, the number of parameter combinations of the ion implanter to be evaluated can be one or more, that is, the user can input one or more parameter combinations of the ion implanter to be evaluated at one time. This embodiment of the invention does not limit this; for ease of explanation, this embodiment of the invention uses one parameter combination of the ion implanter to be evaluated as an example for illustration.

[0067] It should be noted that the specific implementation process of the target operation, including the reverse parameter search operation, is shown below, and will not be repeated here in the embodiments of the present invention. Optionally, the electronic device may also output target operation response data, such as displaying target operation response data, so that the user can quickly adjust the ion implanter parameters according to the target operation response data; for example, it may output the prediction result (i.e., the state information under the parameter combination of the ion implanter to be evaluated), and / or output the optimal parameter combination (i.e., the target ion implanter parameter combination).

[0068] Optionally, modules can be connected via function calls, separating user interface operations from computational logic for easier use and maintenance. Figure 2 As shown. Based on this, embodiments of the present invention can realize a modular system structure in which automatic parameter scanning, model training, and parameter optimization are decoupled.

[0069] In summary, the embodiments of the present invention can improve the quality of training data by constructing a parameter scanning module and introducing a waiting beam stabilization mechanism into the algorithm, thereby avoiding the interference of transient disturbances and anomalies commonly found in machine logs. Furthermore, by utilizing algorithms such as random forests, a nonlinear mapping relationship can be established between multiple parameters (such as ion source region parameters) and state information (such as extraction current and MAF value), thus enabling reliable prediction results to be given quickly without relying heavily on human experience and trial and error. This reduces the uncertainty caused by differences in engineer experience.

[0070] This invention provides embodiments that can acquire training and adjustment data, including adjustment and acquisition data of the target ion implanter at multiple historical acquisition times. The adjustment and acquisition data at one historical acquisition time includes the corresponding ion implanter parameter combination and tag status information. Each tag information includes at least one of the following: extraction current and Faraday value of the mass analyzer. Using the training and adjustment data, a target state prediction model is generated. This model supports predicting state information under any combination of ion implanter parameters. Furthermore, upon detecting a target operation response command, the target operation indicated by the command can be determined, and the target operation is responded to using the target state prediction model to obtain target operation response data. The target operation supports both forward state prediction and reverse parameter seeking functions. The forward state prediction function predicts state information, and the reverse parameter seeking function finds the target ion implanter parameter combination that meets the target requirements. The target operation response data guides the adjustment of ion implanter parameters. As can be seen, embodiments of the present invention can respond to target operations through a target state prediction model to achieve both forward state prediction and reverse parameter seeking functions. This allows for guidance of ion implanter parameter adjustment via target operation response data. Specifically, when the target operation supports the implementation of the forward state prediction function, the ion implanter parameters can be adjusted using the state information indicated by the target operation response data. Furthermore, when the target operation supports the implementation of the reverse parameter seeking function, the ion implanter parameters can be determined using the target ion implanter parameter combination indicated by the target operation response data. This efficiently generates target ion implanter parameter combinations that meet the target requirements, thereby efficiently completing ion implanter parameter adjustment. For example, the target ion implanter parameter combination can be directly used as the final adjusted ion implanter parameters, or rapid fine-tuning can be further achieved based on the target ion implanter parameter combination. Therefore, embodiments of the present invention can conveniently adjust ion implanter parameters, thereby effectively reducing adjustment time.

[0071] Based on the above description, this embodiment of the invention also proposes a more specific method for generating and adjusting ion implanter parameters. Accordingly, this method for generating and adjusting ion implanter parameters can be executed by the aforementioned electronic device (terminal or server); or, this method can be executed jointly by the terminal and the server. For ease of explanation, the following description will use the execution of this method by an electronic device as an example; please refer to [link to relevant documentation]. Figure 3 The method for generating and adjusting the parameters of the ion implanter may include the following steps S301-S306:

[0072] S301, acquire training and adjustment data. The training and adjustment data includes the adjustment and acquisition data of the target ion implanter at multiple historical acquisition times. The adjustment and acquisition data at a historical acquisition time includes the ion implanter parameter combination and tag status information at the corresponding historical acquisition time.

[0073] S302 uses training and conditioning data to generate a target state prediction model, which supports the prediction of state information under any combination of ion implanter parameters.

[0074] S303, when a target operation response command is detected, the target operation indicated by the target operation response command is determined.

[0075] In this embodiment of the invention, the target operation includes a reverse parameter lookup operation, which supports the implementation of the reverse parameter lookup function; that is, if the target operation includes a reverse parameter lookup operation, then steps S304-S306 can be executed when the target operation response data is obtained by responding to the target operation through the target state prediction model.

[0076] S304, determine the target optimization instruction information indicated by the target operation, and determine the target requirements based on the target optimization instruction information.

[0077] Optionally, a status information may include, but is not limited to, at least one of the following: lead current, quality analyzer Faraday value, etc., which are not limited in this embodiment of the invention; based on this, the target optimization indication information may be the target lead current or the target quality analyzer Faraday value, etc.

[0078] In one implementation, when the target optimization indication information is the target extraction current, the electronic device can determine the current deviation minimization requirement based on the target extraction current and use the current deviation minimization requirement as the target requirement, thereby realizing the determination of the target requirement according to the target optimization indication information; wherein, the current deviation minimization requirement may include, but is not limited to: the requirement to minimize the deviation between the predicted extraction current and the target extraction current and / or the requirement to maximize the Faraday value of the mass analyzer, so that the deviation between the predicted extraction current and the target extraction current is minimized, and the target ion implanter parameter combination that maximizes the Faraday value of the mass analyzer is found.

[0079] In another implementation, when the target optimization indication information is the target mass analyzer Faraday value, the electronic device can determine the requirement to minimize the deviation of the mass analyzer Faraday value based on the target mass analyzer Faraday value, and take the requirement to minimize the deviation of the mass analyzer Faraday value as the target requirement; wherein, the requirement to minimize the deviation of the mass analyzer Faraday value may include, but is not limited to: the requirement to minimize the deviation between the predicted mass analyzer Faraday value and the target mass analyzer Faraday value and / or the requirement to minimize the extraction current. At this time, the deviation between the predicted mass analyzer Faraday value and the target mass analyzer Faraday value can be minimized, and the target ion implanter parameter combination that minimizes the extraction current will be sought.

[0080] S305 determines the objective function based on the target requirements, and determines the target ion implanter parameter combination through the objective function, the target state prediction model, and the target intelligent optimization algorithm; wherein, the target state prediction model supports the prediction of state information under any individual parameter.

[0081] Optionally, a requirement (such as minimizing current deviation or minimizing the Faraday value deviation of the quality analyzer) can correspond to an optimization function. Therefore, the optimization function corresponding to the target requirement can be used as the objective function. It should be noted that the optimization objective of the objective function can be either minimizing or maximizing the objective function; this embodiment of the invention does not limit this. For ease of explanation, the following description will use minimizing the objective function as an example.

[0082] Optionally, when the target requirement is to minimize current deviation, the electronic device can use the current deviation minimization function as the objective function (the current deviation minimization function can be the optimization function corresponding to the current deviation minimization requirement). The current deviation minimization function may include, but is not limited to, the current deviation term and / or the quality analyzer Faraday value term. When the target requirement is to minimize the quality analyzer Faraday value deviation, the quality analyzer Faraday value deviation minimization function can be used as the objective function (the quality analyzer Faraday value deviation minimization function can be the optimization function corresponding to the quality analyzer Faraday value deviation minimization requirement). The quality analyzer Faraday value deviation minimization function may include, but is not limited to, the quality analyzer Faraday value deviation term and / or the lead-in current term. The objective function may also include at least one penalty term and a penalty factor (also called a weight) corresponding to each penalty term in the at least one penalty term. The at least one penalty term is constructed based on at least one constraint condition. Optionally, a penalty term can correspond to a penalty factor, and a penalty factor can be used to scale the corresponding penalty term so that a penalty term can be represented in a function as the corresponding penalty factor × the corresponding penalty term; Optionally, the penalty factor corresponding to each penalty term can be set according to experience or according to actual needs, and the embodiments of the present invention do not limit this; Optionally, the penalty factors corresponding to different penalty terms can be the same or different, and the embodiments of the present invention do not limit this.

[0083] Optionally, in the current deviation minimization function, the current deviation term can be the deviation between the predicted lead-in current and the target lead-in current (e.g., the absolute value of the difference between the predicted and target lead-in currents), and the mass analyzer Faraday value term can be a negative mass analyzer Faraday value (i.e., a negative number of the predicted mass analyzer Faraday value). Correspondingly, in the mass analyzer Faraday value deviation minimization function, the mass analyzer Faraday value deviation term can be the deviation between the predicted and target mass analyzer Faraday values ​​(e.g., the absolute value of the difference between the predicted and target mass analyzer Faraday values), and the lead-in current term can be the predicted lead-in current (i.e., a positive lead-in current). Based on this, an optimization function can be expressed as the sum of the corresponding function terms (i.e., the included function terms, such as the current deviation term, the quality analyzer Faraday value term, etc.), which can be expressed as the sum of the corresponding function terms; optionally, when a function term is a penalty term, the weight of the function term can be the corresponding penalty factor.

[0084] Optionally, at least one penalty term in different optimization functions may be the same or different, and this embodiment of the invention does not limit this. Optionally, at least one constraint condition may include, but is not limited to, at least one of the following: at least one physical constraint condition, at least one safety threshold constraint condition, at least one process window constraint condition, at least one hardware limitation constraint condition, and at least one parameter physical relationship constraint condition, etc.; this embodiment of the invention does not limit this. Based on this, this embodiment of the invention does not limit the specific content of at least one constraint condition.

[0085] Optionally, a constraint can be a parameter boundary condition (i.e., a constraint condition indicating the range of parameter values, such as a physical constraint condition which can be a parameter boundary condition), or a parameter relationship constraint condition (i.e., a constraint condition indicating the parameter relationship, such as a parameter physical relationship constraint condition which can be a parameter relationship constraint condition), etc. This embodiment of the invention does not limit this. In other words, at least one constraint condition may include at least one parameter boundary condition to set a boundary condition for each of at least one parameter among a plurality of parameters. The at least one parameter may include at least one parameter to be sought (such as ion source region parameters, etc.); and / or, at least one constraint condition may also include at least one parameter relationship constraint condition, a parameter relationship constraint condition that can be used to constrain the parameter relationship between any number of parameters, etc.; this embodiment of the invention does not limit this. Based on this, at least one penalty term may include boundary condition penalty terms for the parameters constrained by each of the at least one parameter boundary conditions. A boundary condition penalty term is used to penalize cases where the value of the corresponding parameter is outside the parameter range indicated by the corresponding parameter boundary condition. For example, for any parameter among multiple parameters, when at least one constraint condition includes a parameter boundary condition for any parameter, and the parameter boundary condition for any parameter can be used to indicate that the parameter value of any parameter is greater than or equal to a first parameter value, and the parameter value of any parameter is less than or equal to a second parameter value, at least one penalty term may include a first parameter boundary condition penalty term and a second parameter boundary condition penalty term for any parameter. The first parameter boundary condition penalty term may be max(first parameter value - parameter value of any parameter, 0). n The second parameter, the boundary condition penalty term, can be max(the value of any parameter - the value of the second parameter, 0). n Wherein, n can be a positive integer. In this embodiment of the invention, the specific value of n is not limited, such as n can be 1 or 2, etc.

[0086] Optionally, at least one penalty term may further include parameter relationship penalty terms constrained by each parameter relationship constraint in at least one parameter relationship constraint condition. A parameter penalty term is used to penalize cases where the corresponding parameter relationship group does not satisfy the corresponding parameter relationship. Optionally, a parameter relationship constraint condition may be a value range constraint condition for a parameter relationship group (which may include any number of parameters from multiple parameters) under a constraint calculation method, or a parameter relationship constraint condition may be a value range constraint condition for a relative parameter relative to another reference parameter (a relative parameter may correspond to a reference parameter), and so on. Based on this, at least one parameter relationship constraint condition may include parameter relationship constraint conditions corresponding to each parameter relationship group in at least one parameter relationship group (a parameter relationship group may correspond to a constraint calculation method) and / or parameter relationship constraint conditions corresponding to each relative parameter in at least one relative parameter. A relative parameter may refer to a parameter whose value range constraint condition changes with the value of another parameter, and so on. Accordingly, at least one penalty term may further include parameter relationship penalty terms corresponding to each parameter relationship group in at least one parameter relationship group and / or parameter relationship penalty terms corresponding to each relative parameter in at least one relative parameter, and so on.

[0087] For example, for any parameter relationship group in at least one parameter relationship group, when the parameter relationship constraint condition corresponding to any parameter relationship group is used to indicate that the calculation result obtained by the parameter in any parameter relationship group according to the corresponding constraint calculation method is greater than or equal to the first parameter relationship constraint threshold, at least one penalty term may include the first parameter relationship penalty term corresponding to any parameter relationship group. The first parameter relationship penalty term may be max(first parameter relationship constraint threshold - calculation result of any parameter relationship group under the corresponding constraint calculation method, 0). p ; and / or, when the parameter relationship constraint condition corresponding to any parameter relationship group is also used to indicate that the calculation result obtained by the parameter in any parameter relationship group according to the corresponding constraint calculation method is less than or equal to the second parameter relationship constraint threshold, at least one penalty term may also include the second parameter relationship penalty term corresponding to any parameter relationship group, which may be max(calculation result of any parameter relationship group under the corresponding constraint calculation method - second parameter relationship constraint threshold, 0) pAnd so on; where p is a positive integer, and the specific value of p is not limited in the embodiments of the present invention. For example, for any one of the at least one relative parameters, the electronic device can determine the value of the reference parameter corresponding to that relative parameter, and determine the current value range constraint condition corresponding to that relative parameter based on the value of the reference parameter corresponding to that relative parameter, and determine the parameter relationship penalty term corresponding to that relative parameter according to the current value range constraint condition. That is, the parameter relationship penalty term corresponding to that relative parameter can be determined based on the value of the reference parameter corresponding to that relative parameter. The embodiments of the present invention can more fully consider the correlation between different parameters, thereby constructing a more accurate objective function to improve the accuracy of parameter finding.

[0088] Based on this, the electronic device can determine at least one penalty term based on at least one constraint condition. Correspondingly, the electronic device can determine a current deviation minimization function based on at least one penalty term. For example, the current deviation minimization function can be constructed using at least one penalty term, a current deviation term, and a quality analyzer Faraday value term. In this case, the current deviation minimization function can be the sum of at least one penalty term, a current deviation term, and a quality analyzer Faraday value term, which is a weighted summation of at least one penalty term, a current deviation term, and a quality analyzer Faraday value term. Similarly, the electronic device can determine a quality analyzer Faraday value deviation minimization function based on at least one penalty term. For example, the quality analyzer Faraday value deviation minimization function can be constructed using at least one penalty term, a quality analyzer Faraday value deviation term, and a lead-in current term. In this case, the quality analyzer Faraday value deviation minimization function can be the sum of at least one penalty term, a quality analyzer Faraday value deviation term, and a lead-in current term. Optionally, the weights of the current deviation term, the quality analyzer Faraday value term, the quality analyzer Faraday value deviation term, and the lead-in current term can all be set according to experience or actual needs, and the embodiments of the present invention do not limit this; for example, the weights of these function terms can all be 1, etc.

[0089] Optionally, the objective function may also include at least one parameter optimization term corresponding to each objective parameter group in the objective parameter group. The parameter optimization term corresponding to an objective parameter group can be used to maximize or minimize the optimization objective of the corresponding objective parameter group under a target calculation method. Optionally, the target calculation method corresponding to an objective parameter group can be set according to experience or according to actual needs, and the embodiments of the present invention do not limit this. For example, when searching for parameters, when the user has a tendency to adjust parameters based on process and equipment lifespan, in order to maximize the efficiency of the extraction current at the extraction electrode to the MAF beam current, the target parameter combination with the largest MAF / I_ext (extraction current) can be found. That is, the parameter optimization term corresponding to the target parameter combination (MAF, I_ext) can be a function term that maximizes MAF / I_ext, such as -MAF / I_ext; and / or, in order to achieve the same process requirements, the smaller the arc chamber power and the longer the ion source life, the target parameter combination that minimizes power, i.e., arc voltage × arc current, is sought, and so on.

[0090] In one implementation, the current deviation minimization function and / or the quality analyzer Faraday value deviation minimization function may, during construction, include parameter optimization terms corresponding to each target parameter group in at least one target parameter group. In another implementation, the electronic device may, upon detecting a parameter optimization term setting instruction, add the parameter optimization terms indicated by the parameter optimization term setting instruction to the current deviation minimization function and / or the quality analyzer Faraday value deviation minimization function, so that the current deviation minimization function and / or the quality analyzer Faraday value deviation minimization function includes the parameter optimization terms indicated by the parameter optimization term setting instruction, i.e., it includes parameter optimization terms corresponding to each target parameter group in at least one target parameter group. In yet another implementation, after determining the target function, the parameter optimization terms indicated by the parameter optimization term setting instruction may be added to the target function; in this case, the currently set parameter optimization terms may only apply to the current target function, and so on. Based on this, the objective function may include at least one parameter optimization term corresponding to each objective parameter group in the objective parameter group. The parameter optimization term in the objective function may be preset by the current deviation minimization function and / or the quality analyzer Faraday value deviation minimization function, or it may be set according to the parameter optimization term setting instruction. This embodiment of the invention does not limit this.

[0091] Optionally, the electronic device can determine that a parameter optimization item setting instruction has been detected when it detects a parameter optimization item setting operation performed by the user. The parameter optimization item indicated by the parameter optimization item setting instruction may include the parameter optimization item set by the parameter optimization item setting operation. It should be noted that the specific implementation of the parameter optimization item setting operation is not limited in the embodiments of the present invention; for example, the parameter optimization item setting operation may set a function to add parameter optimization items, or it may add corresponding parameter optimization items to both the current deviation minimization function and the quality analyzer Faraday value deviation minimization function without specifying a function, etc. Optionally, the parameter optimization item set by the parameter optimization item setting operation can be empty, in which case the previously set parameter optimization item can be deleted; or, the user may also perform a parameter optimization item initialization operation, then the electronic device may respond to the parameter optimization item initialization operation, thereby deleting the parameter optimization items in the current deviation minimization function and / or the quality analyzer Faraday value deviation minimization function, etc.

[0092] Optionally, the above-mentioned target intelligent optimization algorithm can be any intelligent optimization algorithm, and the embodiments of the present invention do not limit it; for example, the target intelligent optimization algorithm can be any of the following: differential evolution algorithm, genetic algorithm, particle swarm optimization algorithm, simulated annealing algorithm, and ant colony algorithm, etc.

[0093] Optionally, when determining the target ion implanter parameter combination through the objective function, target state prediction model, and target intelligent optimization algorithm, the electronic device can generate an initial parameter population, which may include W parameter individuals. Each parameter individual may include the parameter values ​​of each parameter among multiple parameters, i.e., one parameter individual can represent one ion implanter parameter combination, where W is a positive integer. Correspondingly, the target state prediction model can be invoked to predict the state information of each parameter individual in the initial parameter population, and the objective function value of each parameter individual can be calculated based on the state information and objective function of each parameter individual. Furthermore, the target intelligent optimization algorithm can be invoked to generate a candidate parameter population, and the target state prediction model can be invoked to predict the state information of each parameter individual in the candidate parameter population. Thus, the objective function value of each parameter individual in the candidate parameter population can be determined through the objective function and the state information of each parameter individual in the candidate parameter population. Based on this, the electronic device can determine the next generation of parameter populations based on the objective function values ​​of each parameter individual in the initial parameter population and the objective function values ​​of each parameter individual in the candidate parameter populations, and continue iterating until convergence conditions are met (such as the number of iterations reaching a preset population iteration threshold). The parameter individual with the highest fitness value (such as the lowest objective function value) in the final parameter population is then used as the target ion implanter parameter combination, thereby determining the target ion implanter parameter combination. Optionally, the preset population iteration threshold can be set based on experience or actual needs; this embodiment of the invention does not limit this.

[0094] For example, taking the differential evolution algorithm as the target intelligent optimization algorithm, the electronic device can perform differential mutation and crossover operations in each iteration to generate new candidate solutions (i.e., candidate parameter individuals). Then, it calls the target state prediction model to evaluate the performance of all candidate solutions (i.e., predict the corresponding state information). Then, it can select the optimal solution to enter the next generation according to the objective function (i.e., calculate the objective function value through the objective function, and then obtain the corresponding fitness value to select the parameter individual with a larger fitness value (such as a smaller objective function value) to enter the next generation). Iterates until the convergence condition is met, and finally obtains the target ion implanter parameter combination.

[0095] Optionally, to ensure the practicality of the results, parameter boundary conditions (i.e., setting the parameter range of each parameter) can be added during the search process such as differential evolution. This ensures that the output parameters are all within a reasonable range allowed by the ion source, ensuring that the parameter value of each individual parameter is within the corresponding parameter range. Correspondingly, embodiments of the present invention can add penalty terms indicated by constraints such as physical constraints to the objective function, making the given target ion implanter parameter combination reasonable when applied to the device.

[0096] S306, Add the target ion implanter parameter combination to the target operation response data.

[0097] Based on this, the electronic device can obtain target operation response data. This target operation response data can be used to guide the adjustment of ion implanter parameters. In this embodiment of the invention, the target operation response data may include a target ion implanter parameter combination; it should be understood that when the target operation also includes a positive state prediction operation, the target operation response data may further include state information under the ion implanter parameter combination to be evaluated.

[0098] Optionally, this invention also proposes an intelligent system for predicting and automatically setting source region parameters of an ion implanter (also known as an ion implanter parameter generation and adjustment system). This system may include a target ion implanter and electronic equipment (i.e., electronic equipment for executing the ion implanter parameter generation and adjustment method proposed in this invention). It constructs a technical solution that can automatically provide the optimal parameter combination through parameter scanning data acquisition, machine learning model training, a forward state prediction module (i.e., a model prediction module), and a reverse parameter search module (i.e., a reverse optimization module). Furthermore, this invention can further introduce intelligent optimization algorithms such as differential evolution algorithms to perform a global search on multiple parameters (such as ion source region parameters) and incorporate physical constraints and boundary conditions between parameters. This achieves the reverse solution of executable parameter combinations from the process objective, avoiding the problem of easily getting trapped in local optima during traditional parameter adjustment. Based on this, this invention, through the synergistic effect of the above-mentioned technical means, can shorten the machine setup time and improve equipment utilization. Optionally, the ion implanter parameter generation and adjustment system proposed in this embodiment of the invention can be implemented using software running on a local computer, or it can be deployed in a server, industrial control computer, or edge computing device. The user interaction module can be implemented through a local interface, a remote terminal, or a network interface. Correspondingly, the calling method between the model prediction module and the parameter optimization module can also be implemented through function calls, process communication, etc. This embodiment of the invention does not limit this.

[0099] In summary, this invention proposes a model-based parameter prediction and automatic optimization technology for ion implanters. By modeling the relationship between equipment operating parameters and beam performance, it enables state prediction analysis of parameters and automatically provides optimized parameters. Based on this, this invention can achieve parameter mapping prediction and optimization in ion implanters using machine learning, and can combine parameter physical constraints and boundary conditions to realize a global parameter optimization mechanism.

[0100] This invention, after acquiring training and adjustment data, generates a target state prediction model using that data. This model can predict state information for any combination of ion implanter parameters. Then, upon detecting a target operation response command, the target operation indicated by the command can be determined. This target operation may include a reverse parameter search operation. Based on this, target optimization indication information indicated by the target operation can be determined, and target requirements can be determined accordingly. Further, a target function can be determined based on the target requirements, and the target ion implanter parameter combination can be determined using the target function, the target state prediction model, and the target intelligent optimization algorithm. This target ion implanter parameter combination can then be added to the target operation response data, which can be used to guide ion implanter parameter adjustment. As can be seen, the embodiments of the present invention can realize intelligent prediction and automatic optimization of state information. It can perform machine learning modeling on the relationship between multi-dimensional parameters of ion implanter and state information (such as beam performance indicators such as extraction current and MAF value), and on this basis, realize the reverse solution of executable source region parameter combination from target process indicators (i.e. target optimization indication information). It breaks through the traditional technical mode of relying on manual experience to set parameters for trial and error, and realizes a dual-mode parameter tuning structure that combines forward state prediction and target-driven reverse parameter tuning, thereby facilitating parameter adjustment and effectively reducing adjustment time.

[0101] Based on the description of the relevant embodiments of the ion implanter parameter generation and adjustment method above, this invention also proposes an ion implanter parameter generation and adjustment device, which can be a computer program (including program code) running in an electronic device; such as Figure 4 As shown, the ion implanter parameter generation and adjustment device may include an acquisition unit 401 and a processing unit 402. This ion implanter parameter generation and adjustment device can perform... Figure 1 or Figure 3 The method for generating and adjusting ion implanter parameters shown, i.e., the ion implanter parameter generation and adjustment device, can operate the above-mentioned unit:

[0102] The acquisition unit 401 is used to acquire training and adjustment data, which includes adjustment acquisition data of the target ion implanter at multiple historical acquisition times. The adjustment acquisition data at one historical acquisition time includes the ion implanter parameter combination and tag status information at the corresponding historical acquisition time. The tag information includes at least one of the following: extraction current and mass analyzer Faraday value.

[0103] Processing unit 402 is used to generate a target state prediction model using the training and adjustment data, wherein the target state prediction model supports the prediction of state information under any combination of ion implanter parameters;

[0104] The processing unit 402 is further configured to, upon detecting a target operation response command, determine the target operation indicated by the target operation response command, and respond to the target operation through the target state prediction model to obtain target operation response data; wherein, the target operation supports the implementation of a forward state prediction function and a reverse parameter search function, the forward state prediction function is used to predict state information, the reverse parameter search function is used to find a target ion implanter parameter combination that meets the target requirements, and the target operation response data is used to guide the adjustment of ion implanter parameters;

[0105] Wherein, if the target operation includes a positive state prediction operation, and the positive state prediction operation supports the implementation of the positive state prediction function, then when the processing unit 402 responds to the target operation through the target state prediction model and obtains the target operation response data, it may specifically be used for:

[0106] Determine the combination of ion implanter parameters to be evaluated as indicated by the target operation;

[0107] The target state prediction model is invoked to predict the state information under the parameter combination of the ion implanter to be evaluated.

[0108] The status information of the ion implanter under the parameter combination to be evaluated is added to the target operation response data;

[0109] If the target operation includes a reverse parameter lookup operation, and the reverse parameter lookup operation supports the implementation of the reverse parameter lookup function, then when the processing unit 402 responds to the target operation through the target state prediction model and obtains the target operation response data, it can specifically be used for:

[0110] Determine the target optimization instruction information indicated by the target operation, and determine the target requirement based on the target optimization instruction information;

[0111] Based on the target requirements, an objective function is determined, and the target ion implanter parameter combination is determined through the objective function, the target state prediction model, and the target intelligent optimization algorithm; wherein, the target state prediction model supports the prediction of state information under any individual parameter.

[0112] The target ion implanter parameters are combined and added to the target operation response data.

[0113] In one embodiment, when the processing unit 402 determines the target requirement based on the target optimization instruction information, it may specifically be used to:

[0114] When the target optimization indication information is the target lead-out current, the current deviation minimization requirement is determined based on the target lead-out current, and the current deviation minimization requirement is taken as the target requirement; wherein, the current deviation minimization requirement includes: the requirement to minimize the deviation between the predicted lead-out current and the target lead-out current and / or the requirement to maximize the Faraday value of the quality analyzer;

[0115] When the target optimization indication information is the target quality analyzer Faraday value, the requirement to minimize the Faraday value deviation of the quality analyzer is determined based on the target quality analyzer Faraday value, and the requirement to minimize the Faraday value deviation of the quality analyzer is taken as the target requirement; wherein, the requirement to minimize the Faraday value deviation of the quality analyzer includes: the requirement to minimize the deviation between the predicted quality analyzer Faraday value and the target quality analyzer Faraday value and / or the requirement to minimize the lead-in current.

[0116] In another implementation, when determining the objective function based on the target requirement, the processing unit 402 may specifically be used to:

[0117] When the target requirement is the current deviation minimization requirement, the current deviation minimization function is used as the target function, and the current deviation minimization function includes a current deviation term and / or a quality analyzer Faraday value term;

[0118] When the target requirement is the requirement to minimize the Faraday value deviation of the quality analyzer, the function for minimizing the Faraday value deviation of the quality analyzer is used as the target function. The function for minimizing the Faraday value deviation of the quality analyzer includes a Faraday value deviation term and / or a lead-out current term.

[0119] The objective function further includes at least one penalty term and a penalty factor corresponding to each penalty term, wherein the at least one penalty term is constructed based on at least one constraint condition.

[0120] In another embodiment, the processing unit 402 may also be used for:

[0121] The display function settings interface allows users to select the forward state prediction function and / or the reverse parameter search function.

[0122] When the target operation is detected in the function setting interface, it is determined that the target operation response instruction has been detected; wherein, when the target operation is used to implement the forward state prediction function, the target operation is set with the ion implanter parameter combination to be evaluated; when the target operation is used to implement the reverse parameter search function, the target operation is set with target optimization indication information.

[0123] In another embodiment, adjustment data is acquired through a parameter scanning module in the target ion implanter. This parameter scanning module supports waiting for beam stabilization after parameter adjustment, and then calling the data acquisition interface to record the adjustment data after beam stabilization. When acquiring training adjustment data, the acquisition unit 401 can specifically be used for:

[0124] Training and conditioning data are obtained from the target ion implanter.

[0125] According to one embodiment of the present invention, Figure 4 Each unit in the ion implanter parameter generation and adjustment device shown can be individually or entirely combined into one or more other units, or one or more of the units can be further divided into multiple functionally smaller units. This achieves the same operation without affecting the technical effect of the embodiments of the present invention. The above units are based on logical function division. In practical applications, the function of one unit can be implemented by multiple units, or the function of multiple units can be implemented by one unit. In other embodiments of the present invention, any ion implanter parameter generation and adjustment device may also include other units. In practical applications, these functions can also be implemented with the assistance of other units, and can be implemented collaboratively by multiple units.

[0126] According to another embodiment of the present invention, it is possible to perform operations such as those described above by running on a general-purpose electronic device, such as a computer, which includes processing elements and storage elements such as a central processing unit (CPU), random access memory (RAM), and read-only memory (ROM). Figure 1 or Figure 3 The computer program (including program code) involved in each step of the corresponding method shown, to construct such... Figure 4 The diagram illustrates an ion implanter parameter generation and adjustment apparatus, as well as a method for generating and adjusting ion implanter parameters to implement embodiments of the present invention. The computer program can be stored on, for example, a computer storage medium, loaded onto the aforementioned electronic device via the computer storage medium, and run therein.

[0127] Based on the description of the method and apparatus embodiments above, an exemplary embodiment of the present invention also provides an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor. The memory stores a computer program executable by the at least one processor, which, when executed by the at least one processor, causes the electronic device to perform the method according to an embodiment of the present invention.

[0128] An exemplary embodiment of the present invention also provides a non-transitory computer-readable storage medium storing a computer program, wherein the computer program, when executed by a computer's processor, is used to cause the computer to perform a method according to an embodiment of the present invention.

[0129] An exemplary embodiment of the present invention also provides a computer program product, including a computer program, wherein, when executed by a computer's processor, the computer program is used to cause the computer to perform a method according to an embodiment of the present invention.

[0130] refer to Figure 5 The present invention will now be described in the form of a structural block diagram of an electronic device 500 that can serve as a server or client of the present invention, which is an example of a hardware device that can be applied to various aspects of the present invention. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0131] like Figure 5 As shown, the electronic device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. The RAM 503 may also store various programs and data required for the operation of the electronic device 500. The computing unit 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0132] Multiple components in electronic device 500 are connected to I / O interface 505, including: input unit 506, output unit 507, storage unit 508, and communication unit 509. Input unit 506 can be any type of device capable of inputting information to electronic device 500. Input unit 506 can receive input digital or character information and generate key signal inputs related to user settings and / or function control of electronic device. Output unit 507 can be any type of device capable of presenting information and may include, but is not limited to, a display, speaker, video / audio output terminal, vibrator, and / or printer. Storage unit 508 may include, but is not limited to, disk and optical disk. Communication unit 509 allows electronic device 500 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers, and / or chipsets, such as Bluetooth™ devices, WiFi devices, WiMax devices, cellular communication devices, and / or the like.

[0133] The computing unit 501 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 501 performs the various methods and processes described above. For example, in some embodiments, the ion implanter parameter generation and adjustment method can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 508. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 500 via ROM 502 and / or communication unit 509. In some embodiments, the computing unit 501 can be configured to perform the ion implanter parameter generation and adjustment method by any other suitable means (e.g., by means of firmware).

[0134] The program code used to implement the methods of the present invention can be written in any combination of one or more programming languages. This program code can be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable ion implanter parameter generation and adjustment apparatus, such that when executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program code can be executed entirely on the machine, partially on the machine, as a standalone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0135] In the context of this invention, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0136] As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, device, and / or apparatus (e.g., disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including machine-readable media that receive machine instructions as machine-readable signals. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0137] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0138] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0139] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other.

[0140] Furthermore, it should be understood that the above-disclosed embodiments are merely preferred embodiments of the present invention and should not be construed as limiting the scope of the present invention. Therefore, any equivalent variations made in accordance with the claims of the present invention are still within the scope of the present invention.

Claims

1. A method for generating and adjusting parameters of an ion implanter, characterized in that, include: Acquire training and adjustment data, which includes adjustment and acquisition data of the target ion implanter at multiple historical acquisition times. The adjustment and acquisition data at one historical acquisition time includes the ion implanter parameter combination and tag status information at the corresponding historical acquisition time. A tag information includes at least one of the following: extraction current and mass analyzer Faraday value. Using the training and adjustment data, a target state prediction model is generated, which supports the prediction of state information under any combination of ion implanter parameters; Upon detecting a target operation response command, the target operation indicated by the target operation response command is determined, and the target operation is responded to through the target state prediction model to obtain target operation response data; wherein, the target operation supports the implementation of a forward state prediction function and a reverse parameter search function, the forward state prediction function is used to predict state information, the reverse parameter search function is used to find a target ion implanter parameter combination that meets the target requirements, and the target operation response data is used to guide the adjustment of ion implanter parameters; Wherein, if the target operation includes a positive state prediction operation, and the positive state prediction operation supports the implementation of the positive state prediction function, then the step of responding to the target operation through the target state prediction model to obtain target operation response data includes: Determine the combination of ion implanter parameters to be evaluated as indicated by the target operation; The target state prediction model is invoked to predict the state information under the parameter combination of the ion implanter to be evaluated. The status information of the ion implanter under the parameter combination to be evaluated is added to the target operation response data; If the target operation includes a reverse parameter lookup operation, and the reverse parameter lookup operation supports the implementation of the reverse parameter lookup function, then the step of responding to the target operation through the target state prediction model to obtain target operation response data includes: Determine the target optimization instruction information indicated by the target operation, and determine the target requirement based on the target optimization instruction information; Based on the target requirements, an objective function is determined, and the target ion implanter parameter combination is determined through the objective function, the target state prediction model, and the target intelligent optimization algorithm; wherein, the target state prediction model supports the prediction of state information under any individual parameter. The target ion implanter parameters are combined and added to the target operation response data.

2. The method according to claim 1, characterized in that, Determining the target requirement based on the target optimization indication information includes: When the target optimization indication information is the target lead-out current, the current deviation minimization requirement is determined based on the target lead-out current, and the current deviation minimization requirement is taken as the target requirement; wherein, the current deviation minimization requirement includes: the requirement to minimize the deviation between the predicted lead-out current and the target lead-out current and / or the requirement to maximize the Faraday value of the quality analyzer; When the target optimization indication information is the target quality analyzer Faraday value, the requirement to minimize the Faraday value deviation of the quality analyzer is determined based on the target quality analyzer Faraday value, and the requirement to minimize the Faraday value deviation of the quality analyzer is taken as the target requirement; wherein, the requirement to minimize the Faraday value deviation of the quality analyzer includes: the requirement to minimize the deviation between the predicted quality analyzer Faraday value and the target quality analyzer Faraday value and / or the requirement to minimize the lead-in current.

3. The method according to claim 2, characterized in that, The determination of the objective function based on the target requirement includes: When the target requirement is the current deviation minimization requirement, the current deviation minimization function is used as the target function, and the current deviation minimization function includes a current deviation term and / or a quality analyzer Faraday value term; When the target requirement is the requirement to minimize the Faraday value deviation of the quality analyzer, the function for minimizing the Faraday value deviation of the quality analyzer is used as the target function. The function for minimizing the Faraday value deviation of the quality analyzer includes a Faraday value deviation term and / or a lead-out current term. The objective function further includes at least one penalty term and a penalty factor corresponding to each penalty term, wherein the at least one penalty term is constructed based on at least one constraint condition.

4. The method according to any one of claims 1-3, characterized in that, The method further includes: The display function settings interface allows users to select the forward state prediction function and / or the reverse parameter search function. When the target operation is detected in the function setting interface, it is determined that the target operation response instruction has been detected; wherein, when the target operation is used to implement the forward state prediction function, the target operation is set with the ion implanter parameter combination to be evaluated; when the target operation is used to implement the reverse parameter search function, the target operation is set with target optimization indication information.

5. The method according to any one of claims 1-3, characterized in that, One type of adjustment data acquisition is performed through a parameter scanning module in the target ion implanter. This parameter scanning module supports waiting for beam stabilization after parameter adjustment, and then calling the data acquisition interface to record the adjustment data after beam stabilization. The acquisition of training adjustment data includes: Training and conditioning data are obtained from the target ion implanter.

6. A parameter generation and adjustment device for an ion implanter, characterized in that, The device includes: The acquisition unit is used to acquire training and adjustment data, which includes adjustment acquisition data of the target ion implanter at multiple historical acquisition times. The adjustment acquisition data at one historical acquisition time includes the ion implanter parameter combination and tag status information at the corresponding historical acquisition time. The tag information includes at least one of the following: extraction current and mass analyzer Faraday value. The processing unit is used to generate a target state prediction model using the training and adjustment data, wherein the target state prediction model supports the prediction of state information under any combination of ion implanter parameters; The processing unit is further configured to, upon detecting a target operation response command, determine the target operation indicated by the target operation response command, and respond to the target operation through the target state prediction model to obtain target operation response data; wherein, the target operation supports the implementation of a forward state prediction function and a reverse parameter search function, the forward state prediction function is used to predict state information, the reverse parameter search function is used to find a target ion implanter parameter combination that meets the target requirements, and the target operation response data is used to guide the adjustment of ion implanter parameters; Wherein, if the target operation includes a positive state prediction operation, and the positive state prediction operation supports the implementation of the positive state prediction function, then when the processing unit responds to the target operation through the target state prediction model and obtains the target operation response data, it is specifically used for: Determine the combination of ion implanter parameters to be evaluated as indicated by the target operation; The target state prediction model is invoked to predict the state information under the parameter combination of the ion implanter to be evaluated. The status information of the ion implanter under the parameter combination to be evaluated is added to the target operation response data; If the target operation includes a reverse parameter lookup operation, and the reverse parameter lookup operation supports the implementation of the reverse parameter lookup function, then when the processing unit responds to the target operation through the target state prediction model and obtains the target operation response data, it is specifically used for: Determine the target optimization instruction information indicated by the target operation, and determine the target requirement based on the target optimization instruction information; Based on the target requirements, an objective function is determined, and the target ion implanter parameter combination is determined through the objective function, the target state prediction model, and the target intelligent optimization algorithm; wherein, the target state prediction model supports the prediction of state information under any individual parameter. The target ion implanter parameters are combined and added to the target operation response data.

7. An electronic device, characterized in that, include: processor; as well as Stored program memory, The program includes instructions that, when executed by the processor, cause the processor to perform the method according to any one of claims 1-5.

8. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-5.

Images