Parameter prediction method and device based on nanomaterial, processor and electronic equipment
By combining multiple primary prediction models and a target model from a multivariate regression model, the problem of low prediction accuracy for nanomaterial parameters was solved, achieving higher prediction accuracy and model optimization.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-12-29
- Publication Date
- 2026-03-24
AI Technical Summary
Existing technologies using single linear regression or multinomial regression models to generate parameters related to nanomaterials have low accuracy.
The target model is composed of multiple first prediction models and multiple regression models, combined with linear regression models or multinomial regression models. Multiple target parameter values are input and output through target activity values, and the model is optimized by calculating the average value and judging the difference to improve accuracy.
It improves the accuracy of nanomaterial parameter prediction, ensures that the prediction results meet the preset requirements, and the optimized model can be continuously adjusted to achieve high accuracy.
Smart Images
Figure CN116343955B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of artificial intelligence technology, and more specifically, to a parameter prediction method and apparatus, processor and electronic device based on nanomaterials. Background Technology
[0002] The rapid development of nanotechnology has led to an increasing variety of functionalized nanomaterials, with continuously expanding production and scale. Research on the parameters of nanomaterials is becoming increasingly important, as improving these parameters can effectively enhance the bioactivity of enzymes prepared based on nanocarriers. Achieving higher enzyme bioactivity is crucial. Current techniques often use single linear regression or multinomial regression models to generate predicted data on nanomaterial parameters, thereby obtaining the desired enzyme bioactivity value. However, the accuracy and reliability of predictive data generated using single linear regression or multinomial regression models heavily rely on effective machine learning methods, model selection, and sufficient training datasets. It is difficult to achieve high precision in both data fitting and accuracy.
[0003] There is currently no effective solution to the problem that the accuracy of predicting parameters of nanomaterials is relatively low when using single linear regression or multinomial regression models to generate relevant parameters in related technologies. Summary of the Invention
[0004] The main objective of this application is to provide a method, device, processor, and electronic device for predicting parameters based on nanomaterials, in order to solve the problem that the accuracy of predicting parameters of nanomaterials is relatively low when using a single linear regression or multinomial regression model to generate relevant parameters of nanomaterials in related technologies.
[0005] To achieve the above objectives, according to one aspect of this application, a parameter prediction method based on nanomaterials is provided. The method includes: determining a target nanomaterial to be predicted; determining a target activity value of an enzyme corresponding to the target nanomaterial; inputting the target activity value into a target model; and outputting predicted multiple target parameter values corresponding to the target nanomaterial. The target model consists of multiple first prediction models and a multiple regression model. The first prediction models are linear regression models or multinomial regression models. The multiple target parameter values include at least: the voltage value of the target nanomaterial, the current value of the target nanomaterial, the temperature value of the target nanomaterial, and the pH value of the target nanomaterial. The multiple first prediction models correspond to the multiple target parameter values.
[0006] Furthermore, inputting the target activity value into the target model and outputting multiple target parameter values corresponding to the target nanomaterial includes: outputting multiple first parameter values based on the target activity value through the multiple first prediction models; outputting multiple second parameter values based on the target activity value through the multiple regression model; and calculating the average value based on the multiple first parameter values and the multiple second parameter values to obtain the multiple target parameter values.
[0007] Furthermore, after predicting multiple target parameter values corresponding to the target nanomaterial through the target model, the method further includes: measuring based on the multiple target parameter values to obtain the predicted activity value of the enzyme corresponding to the target nanomaterial; and determining whether the multiple target parameter values meet preset requirements based on the predicted activity value and the target activity value.
[0008] Further, determining whether the plurality of target parameter values meet the preset requirements based on the predicted activity value and the target activity value includes: calculating the difference between the predicted activity value and the target activity value to obtain a target difference value; determining whether the target difference value is less than a preset threshold; if the target difference value is less than the preset threshold, it indicates that the plurality of target parameter values meet the preset requirements; if the target difference value is greater than or equal to the preset threshold, it indicates that the plurality of target parameter values do not meet the preset requirements.
[0009] Furthermore, if the multiple target parameter values do not meet the preset requirements, the method further includes: optimizing the target model to obtain an optimized target model, and using the optimized target model to predict the parameters of the target nanomaterial again until the multiple target parameter values meet the preset requirements.
[0010] Further, the target model is obtained by the following steps: acquiring a training dataset, wherein the training dataset includes multiple sets of training parameters and the training activity value of the enzyme corresponding to each set of training parameters, wherein each set of training parameters includes multiple training parameters, wherein the multiple training parameters include at least: the voltage value corresponding to the nanomaterial, the current value of the nanomaterial, the temperature value of the nanomaterial, and the pH value of the nanomaterial; determining a first prediction model corresponding to each training parameter and determining a multiple regression model corresponding to the multiple training parameters based on the training activity value of the enzyme corresponding to each set of training parameters; and determining the target model based on the first prediction model and the multiple regression model.
[0011] Further, determining the first prediction model corresponding to each training parameter based on the training activity value of the enzyme corresponding to each set of training parameters includes: establishing a linear regression model corresponding to each training parameter based on the training activity value of the enzyme corresponding to each set of training parameters; establishing a polynomial regression model corresponding to each training parameter based on the training activity value of the enzyme corresponding to each set of training parameters; calculating the goodness of fit of each linear regression model to obtain multiple first goodness of fits; calculating the goodness of fit of each polynomial regression model to obtain multiple second goodness of fits; and determining the first prediction model corresponding to each training parameter from the linear regression model and the polynomial regression model corresponding to each training parameter based on the multiple first goodness of fits and the multiple second goodness of fits.
[0012] To achieve the above objectives, according to another aspect of this application, a parameter prediction device based on nanomaterials is provided. The device includes: a first determining unit for determining a target nanomaterial to be predicted; a second determining unit for determining a target activity value of an enzyme corresponding to the target nanomaterial; and a prediction unit for inputting the target activity value into a target model and outputting predicted target parameter values corresponding to the target nanomaterial. The target model consists of multiple first prediction models and a multiple regression model, wherein the first prediction models are linear regression models or multinomial regression models, and the multiple target parameter values include at least: the voltage value of the target nanomaterial, the current value of the target nanomaterial, the temperature value of the target nanomaterial, and the pH value of the target nanomaterial. The multiple first prediction models correspond to the multiple target parameter values.
[0013] Furthermore, the prediction unit includes: a first output module, configured to output multiple first parameter values based on the target activity value using the multiple first prediction models; a second output module, configured to output multiple second parameter values based on the target activity value using the multiple regression model; and a first calculation module, configured to calculate the average value of the multiple first parameter values and the multiple second parameter values to obtain the multiple target parameter values.
[0014] Furthermore, the device further includes: a measurement unit, used to measure based on the multiple target parameter values corresponding to the target nanomaterial after the multiple target parameter values are predicted by the target model, to obtain the predicted activity value of the enzyme corresponding to the target nanomaterial; and a third determination unit, used to determine whether the multiple target parameter values meet preset requirements based on the predicted activity value and the target activity value.
[0015] Further, the third determining unit includes: a second calculation module, used to calculate the difference between the predicted activity value and the target activity value to obtain a target difference; a judging module, used to judge whether the target difference is less than a preset threshold; a first determining module, used to indicate that the plurality of target parameter values meet the preset requirements if the target difference is less than the preset threshold; and a second determining module, used to indicate that the plurality of target parameter values do not meet the preset requirements if the target difference is greater than or equal to the preset threshold.
[0016] Furthermore, the device further includes an optimization unit, configured to optimize the target model if the multiple target parameter values do not meet preset requirements, to obtain an optimized target model, and to predict the parameters of the target nanomaterial again using the optimized target model until the multiple target parameter values meet preset requirements.
[0017] Further, the target model is obtained by the following steps: an acquisition unit, used to acquire a training dataset, wherein the training dataset includes multiple sets of training parameters and the training activity value of the enzyme corresponding to each set of training parameters, each set of training parameters includes multiple training parameters, the multiple training parameters including at least: the voltage value corresponding to the nanomaterial, the current value of the nanomaterial, the temperature value of the nanomaterial, and the pH value of the nanomaterial; a fourth determination unit, used to determine the first prediction model corresponding to each training parameter and the multiple regression model corresponding to the multiple training parameters based on the training activity value of the enzyme corresponding to each set of training parameters; and a fifth determination unit, used to determine the target model based on the first prediction model and the multiple regression model.
[0018] Further, the fourth determining unit includes: a first establishing module, used to establish a linear regression model corresponding to each training parameter based on the training activity value of the enzyme corresponding to each set of training parameters; a second establishing module, used to establish a polynomial regression model corresponding to each training parameter based on the training activity value of the enzyme corresponding to each set of training parameters; a third calculation module, used to calculate the goodness of fit of each linear regression model to obtain multiple first goodness of fits; a fourth calculation module, used to calculate the goodness of fit of each polynomial regression model to obtain multiple second goodness of fits; and a third determining module, used to determine a first prediction model corresponding to each training parameter from the linear regression model and the polynomial regression model corresponding to each training parameter based on the multiple first goodness of fits and the multiple second goodness of fits.
[0019] To achieve the above objectives, according to one aspect of this application, a processor is provided for running a program, wherein the program executes the parameter prediction method based on nanomaterials as described above.
[0020] To achieve the above objectives, according to one aspect of this application, an electronic device is provided, comprising one or more processors and a memory, the memory being used to store the parameter prediction method based on nanomaterials implemented by the one or more processors as described above.
[0021] This application employs the following steps: determining the target nanomaterial to be predicted; determining the target activity value of the enzyme corresponding to the target nanomaterial; inputting the target activity value into a target model, and outputting multiple target parameter values corresponding to the target nanomaterial. The target model consists of multiple first prediction models and a multiple regression model. The first prediction models are linear regression or polynomial regression models. The multiple target parameter values include at least: the voltage value, current value, temperature value, and pH value of the target nanomaterial. The multiple first prediction models correspond to the multiple target parameter values, solving the problem in related technologies where using a single linear or polynomial regression model to generate relevant parameters for nanomaterials leads to low accuracy in predicting nanomaterial parameters. In this scheme, the expected target activity value of the corresponding enzyme for the target nanomaterial is determined, and then the target activity value is input into the target model, which includes multiple first prediction models and a multiple regression model. By combining the first prediction models and the multiple regression model, the optimal parameter values for the target nanomaterial are output, thereby improving the accuracy of predicting nanomaterial parameters. Attached Figure Description
[0022] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:
[0023] Figure 1 This is a flowchart of a parameter prediction method based on nanomaterials provided in the embodiments of this application;
[0024] Figure 2 This is a flowchart of an optional parameter prediction method based on nanomaterials provided according to an embodiment of this application;
[0025] Figure 3 This is a schematic diagram of a parameter prediction device based on nanomaterials provided in the embodiments of this application;
[0026] Figure 4 This is a schematic diagram of an electronic device provided according to an embodiment of this application. Detailed Implementation
[0027] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.
[0028] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.
[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0030] For ease of description, the following explains some of the nouns or terms used in the embodiments of this application:
[0031] Linear regression: A statistical analysis method that uses regression analysis in mathematical statistics to determine the quantitative relationship of interdependence between two or more variables.
[0032] Multinomial regression: The regression function is a multinomial of the regression variables. It is a special type of linear regression, where the regression function is linear with respect to the regression coefficients.
[0033] Multiple regression: It is a statistical method for studying the regression of a dependent variable with multiple independent variables, and for establishing linear or nonlinear mathematical models of quantitative relationships between multiple variables.
[0034] r-squared: The goodness of fit of a simple model, measured by a value called r-squared. The r-squared value ranges from 0 to 1, where 0 indicates no correlation and 1 indicates 100% correlation.
[0035] It should be noted that all information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) involved in this disclosure are information and data authorized by the user or fully authorized by all parties. For example, this system has an interface with relevant users or organizations. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or organization through the interface, and obtain the relevant information after receiving consent information from the aforementioned user or organization.
[0036] The present invention will now be described in conjunction with preferred implementation steps. Figure 1 This is a flowchart of a parameter prediction method based on nanomaterials provided in the embodiments of this application, such as... Figure 1 As shown, the method includes the following steps:
[0037] Step S101: Determine the target nanomaterial to be predicted;
[0038] Step S102: Determine the target activity value of the enzyme corresponding to the target nanomaterial;
[0039] Step S103: Input the target activity value into the target model and output the predicted target parameter values corresponding to the target nanomaterial. The target model consists of multiple first prediction models and a multiple regression model. The first prediction model is a linear regression model or a multinomial regression model. The multiple target parameter values include at least the voltage value, current value, temperature value, and pH value of the target nanomaterial. The multiple first prediction models and the multiple target parameter values have a corresponding relationship.
[0040] Specifically, the target nanomaterial to be predicted and the target activity value of the enzyme corresponding to the desired target nanomaterial are obtained. Then, the target activity value of the enzyme is input into the target model, which processes the target activity value of the enzyme and outputs multiple target parameter values corresponding to the target nanomaterial.
[0041] It should be noted that the target parameter values include at least the voltage, current, temperature, and pH of the target nanomaterial. These parameters all affect the target activity of the enzyme.
[0042] It should be noted that the target model consists of multiple primary prediction models and multiple regression models. The primary prediction models may be linear regression models or multinomial regression models, and there is a correspondence between the primary prediction models and the target parameter values. Simply put, one primary prediction model corresponds to one parameter of a nanomaterial. By fusing multiple primary prediction models and multiple regression models, the parameter values of nanomaterials can be predicted more accurately.
[0043] In summary, by combining the first prediction model and the multiple regression model, the optimal parameter values of the target nanomaterial are output, thereby improving the accuracy of the predicted parameters of the nanomaterial.
[0044] Obtaining the target parameter values corresponding to the target nanomaterial through the target model is crucial. Therefore, in the parameter prediction method based on nanomaterials provided in this application embodiment, inputting the target activity value into the target model and outputting multiple target parameter values corresponding to the target nanomaterial includes: outputting multiple first parameter values based on the target activity value through multiple first prediction models; outputting multiple second parameter values based on the target activity value through a multiple regression model; and calculating the average value based on the multiple first parameter values and the multiple second parameter values to obtain multiple target parameter values.
[0045] Specifically, after the target activity value is input into the target model, each first prediction model outputs its corresponding first parameter value based on its own parameter values, thus obtaining multiple first parameter values. The multiple regression model will directly output multiple second parameter values based on the target activity value. The average value of the first and second parameter values is calculated, and the resulting multiple average values are used as multiple target parameter values.
[0046] In an optional embodiment, weight values can be set for the first parameter value and the second parameter value, a weighted average value can be calculated, and the weighted average value can be used as the target parameter value.
[0047] By using the first prediction model and the multiple regression model described above, more accurate and reliable prediction values can be obtained than those of a single model, which can effectively improve the accuracy of predicting nanomaterial parameters.
[0048] To further improve the accuracy of the predicted parameters, the parameter prediction method based on nanomaterials provided in this application embodiment, after predicting multiple target parameter values corresponding to the target nanomaterial through the target model, further includes: measuring based on the multiple target parameter values to obtain the predicted activity value of the enzyme corresponding to the target nanomaterial; and determining whether the multiple target parameter values meet the preset requirements based on the predicted activity value and the target activity value.
[0049] Determining whether multiple target parameter values meet preset requirements based on predicted activity values and target activity values includes: calculating the difference between predicted activity values and target activity values to obtain target difference values; determining whether the target difference value is less than a preset threshold; if the target difference value is less than the preset threshold, it indicates that multiple target parameter values meet preset requirements; if the target difference value is greater than or equal to the preset threshold, it indicates that multiple target parameter values do not meet preset requirements.
[0050] Specifically, after obtaining multiple target parameter values output by the target model, the target nanomaterial is measured based on these target parameter values to obtain the predicted activity value of the enzyme corresponding to the target nanomaterial. Then, the difference between the predicted activity value and the target activity value is compared to determine whether the multiple target parameter values meet the preset requirements.
[0051] Specifically, the difference between the predicted activity value and the target activity value is calculated to obtain the target difference value. If the target difference value is greater than a preset threshold (for example, the preset threshold can be set between 1 and 20), it indicates that the gap between the predicted activity value and the target activity value is large, thus indicating that multiple target parameter values do not meet the preset requirements. If the target difference value is less than the preset threshold, it indicates that multiple target parameter values meet the requirements.
[0052] The accuracy of the prediction parameters can be further improved by determining whether the difference between the predicted activity value and the target activity value is greater than a threshold.
[0053] Optionally, in the parameter prediction method based on nanomaterials provided in the embodiments of this application, if multiple target parameter values do not meet the preset requirements, the method further includes: optimizing the target model to obtain an optimized target model, and predicting the parameters of the target nanomaterials again using the optimized target model until multiple target parameter values meet the preset requirements.
[0054] Specifically, if multiple target parameter values do not meet the preset requirements, the target model is optimized to obtain an optimized target model. Then, the parameters of the target nanomaterial are predicted again using the optimized target model until multiple target parameter values meet the preset requirements.
[0055] Obtaining the target model is crucial. Therefore, in the parameter prediction method based on nanomaterials provided in this application embodiment, the target model is obtained by the following steps: acquiring a training dataset, wherein the training dataset includes multiple sets of training parameters and the training activity values of enzymes corresponding to each set of training parameters. Each set of training parameters includes multiple training parameters, which at least include: the voltage value corresponding to the nanomaterial, the current value of the nanomaterial, the temperature value of the nanomaterial, and the pH value of the nanomaterial; determining a first prediction model corresponding to each training parameter and a multiple regression model corresponding to multiple training parameters based on the training activity values of enzymes corresponding to each set of training parameters; and determining the target model based on the first prediction model and the multiple regression model.
[0056] Specifically, multiple sets of training parameters and the corresponding enzyme training activity values are obtained for each set of training parameters, forming a training dataset. Each set of training parameters includes multiple training parameters, at least: the voltage value, current value, temperature value, and pH value corresponding to the nanomaterial. The training activity values of the enzymes corresponding to each set of training parameters are used to fit the data to obtain a first prediction model for each training parameter and a multiple regression model corresponding to multiple training parameters. The target model is then determined using the first prediction model and the multiple regression model. The first prediction model and the multiple regression model can be accurately fitted using the aforementioned training dataset.
[0057] Optionally, in the parameter prediction method based on nanomaterials provided in this application embodiment, determining the first prediction model corresponding to each training parameter based on the training activity value of the enzyme corresponding to each set of training parameters includes: establishing a linear regression model corresponding to each training parameter based on the training activity value of the enzyme corresponding to each set of training parameters; establishing a polynomial regression model corresponding to each training parameter based on the training activity value of the enzyme corresponding to each set of training parameters; calculating the goodness of fit of each linear regression model to obtain multiple first goodness of fits; calculating the goodness of fit of each polynomial regression model to obtain multiple second goodness of fits; and determining the first prediction model corresponding to each training parameter from the linear regression model and the polynomial regression model corresponding to each training parameter based on the multiple first goodness of fits and the multiple second goodness of fits.
[0058] Specifically, data fitting analysis is performed based on the training activity values of the enzymes corresponding to each set of training parameters to establish a linear regression model for each training parameter. Similarly, a multinomial regression model is established based on the same data fitting analysis. Then, the goodness of fit (r-squared value) for each linear regression model and each multinomial regression model is calculated. Finally, the first prediction model for each training parameter is determined from both the linear and multinomial regression models based on the goodness of fit. Generally, a higher goodness of fit indicates higher model accuracy; therefore, the choice between a linear regression model and a multinomial regression model as the first prediction model is based on the goodness of fit.
[0059] In an alternative embodiment, the following can be employed: Figure 2The flowchart shown illustrates the parameter prediction for nanomaterials. Specifically, a training dataset is acquired, and a linear regression model and a multinomial regression model are obtained by fitting the training dataset. Then, a first prediction model is determined from the linear regression model and the multinomial regression model based on the goodness of fit. A multivariate regression model is obtained by fitting the training dataset, and a target model is determined by combining the multivariate regression model and the first prediction model. Finally, the enzyme activity value is input into the target model to obtain multiple predicted parameter values.
[0060] The parameter prediction method based on nanomaterials provided in this application determines the target nanomaterial to be predicted; determines the target activity value of the enzyme corresponding to the target nanomaterial; inputs the target activity value into a target model, and outputs multiple predicted target parameter values corresponding to the target nanomaterial. The target model consists of multiple first prediction models and a multiple regression model. The first prediction models are linear regression models or polynomial regression models. The multiple target parameter values include at least: the voltage value, current value, temperature value, and pH value of the target nanomaterial. The multiple first prediction models correspond to the multiple target parameter values, solving the problem in related technologies where the use of a single linear or polynomial regression model to generate relevant parameters for nanomaterials leads to low accuracy in predicting nanomaterial parameters. In this solution, the expected target activity value of the corresponding enzyme for the target nanomaterial is determined, and then the target activity value is input into the target model, which includes multiple first prediction models and a multiple regression model. By combining the first prediction models and the multiple regression model, the optimal parameter values for the target nanomaterial are output, thereby improving the accuracy of predicting nanomaterial parameters.
[0061] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.
[0062] This application also provides a parameter prediction device based on nanomaterials. It should be noted that this nanomaterial-based parameter prediction device can be used to execute the parameter prediction method based on nanomaterials provided in this application. The following describes the nanomaterial-based parameter prediction device provided in this application.
[0063] Figure 3 This is a schematic diagram of a parameter prediction device based on nanomaterials according to an embodiment of this application. Figure 3 As shown, the device includes: a first determining unit 301, a second determining unit 302, and a prediction unit 303.
[0064] The first determining unit 301 is used to determine the target nanomaterial to be predicted;
[0065] The second determining unit 302 is used to determine the target activity value of the enzyme corresponding to the target nanomaterial;
[0066] The prediction unit 303 is used to input the target activity value into the target model and output the predicted target parameter values corresponding to the target nanomaterial. The target model consists of multiple first prediction models and a multiple regression model. The first prediction model is a linear regression model or a multinomial regression model. The multiple target parameter values include at least the voltage value, current value, temperature value, and pH value of the target nanomaterial. The multiple first prediction models have a corresponding relationship with the multiple target parameter values.
[0067] The parameter prediction device based on nanomaterials provided in this application embodiment determines the target nanomaterial to be predicted through a first determining unit 301; a second determining unit 302 determines the target activity value of the enzyme corresponding to the target nanomaterial; and a prediction unit 303 inputs the target activity value into a target model and outputs multiple target parameter values corresponding to the target nanomaterial. The target model consists of multiple first prediction models and a multiple regression model. The first prediction models are linear regression models or polynomial regression models. The multiple target parameter values include at least: the voltage value, current value, temperature value, and pH value of the target nanomaterial. The multiple first prediction models correspond to the multiple target parameter values, solving the problem in related technologies where the use of a single linear regression or polynomial regression model to generate relevant parameters for nanomaterials leads to low accuracy in predicting nanomaterial parameters. In this solution, the expected target activity value of the corresponding enzyme for the target nanomaterial is determined, and then the target activity value is input into the target model, which includes multiple first prediction models and a multiple regression model. By combining the first prediction models and the multiple regression model, the optimal parameter value of the target nanomaterial is output, thereby improving the accuracy of predicting nanomaterial parameters.
[0068] Optionally, in the parameter prediction device based on nanomaterials provided in the embodiments of this application, the prediction unit includes: a first output module, used to output multiple first parameter values based on the target activity value through multiple first prediction models; a second output module, used to output multiple second parameter values based on the target activity value through a multiple regression model; and a first calculation module, used to calculate the average value based on the multiple first parameter values and the multiple second parameter values to obtain multiple target parameter values.
[0069] Optionally, in the parameter prediction device based on nanomaterials provided in the embodiments of this application, the device further includes: a measurement unit, used to measure based on the multiple target parameter values corresponding to the target nanomaterial after the multiple target parameter values are predicted by the target model, to obtain the predicted activity value of the enzyme corresponding to the target nanomaterial; and a third determination unit, used to determine whether the multiple target parameter values meet the preset requirements based on the predicted activity value and the target activity value.
[0070] Optionally, in the parameter prediction device based on nanomaterials provided in this application embodiment, the third determining unit includes: a second calculation module, used to calculate the difference between the predicted activity value and the target activity value to obtain a target difference value; a judging module, used to judge whether the target difference value is less than a preset threshold; a first determining module, used to characterize multiple target parameter values as meeting preset requirements if the target difference value is less than the preset threshold; and a second determining module, used to characterize multiple target parameter values as not meeting preset requirements if the target difference value is greater than or equal to the preset threshold.
[0071] Optionally, in the parameter prediction device based on nanomaterials provided in the embodiments of this application, the device further includes: an optimization unit, used to optimize the target model if multiple target parameter values do not meet the preset requirements, to obtain an optimized target model, and to predict the parameters of the target nanomaterials again through the optimized target model until multiple target parameter values meet the preset requirements.
[0072] Optionally, in the parameter prediction device based on nanomaterials provided in this application embodiment, the target model is obtained by the following steps: an acquisition unit, used to acquire a training dataset, wherein the training dataset includes multiple sets of training parameters and the training activity value of the enzyme corresponding to each set of training parameters, each set of training parameters includes multiple training parameters, and the multiple training parameters include at least: the voltage value corresponding to the nanomaterial, the current value of the nanomaterial, the temperature value of the nanomaterial, and the pH value of the nanomaterial; a fourth determination unit, used to determine the first prediction model corresponding to each training parameter and determine the multiple regression model corresponding to multiple training parameters based on the training activity value of the enzyme corresponding to each set of training parameters; and a fifth determination unit, used to determine the target model based on the first prediction model and the multiple regression model.
[0073] Optionally, in the parameter prediction device based on nanomaterials provided in this application embodiment, the fourth determining unit includes: a first establishing module, used to establish a linear regression model corresponding to each training parameter based on the training activity value of the enzyme corresponding to each set of training parameters; a second establishing module, used to establish a polynomial regression model corresponding to each training parameter based on the training activity value of the enzyme corresponding to each set of training parameters; a third calculation module, used to calculate the goodness of fit of each linear regression model to obtain multiple first goodness of fits; a fourth calculation module, used to calculate the goodness of fit of each polynomial regression model to obtain multiple second goodness of fits; and a third determining module, used to determine a first prediction model corresponding to each training parameter from the linear regression model and the polynomial regression model corresponding to each training parameter based on the multiple first goodness of fits and the multiple second goodness of fits.
[0074] It should be noted that the first determining unit 301 in this embodiment can be used to execute step S101 in this application embodiment, the second determining unit 302 in this embodiment can be used to execute step S102 in this application embodiment, and the prediction unit 303 in this embodiment can be used to execute step S103 in this application embodiment. The examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the content disclosed in the above embodiments.
[0075] The parameter prediction device based on nanomaterials includes a processor and a memory. The first determining unit 301, the second determining unit 302, and the prediction unit 303 mentioned above are all stored in the memory as program units. The processor executes the program units stored in the memory to realize the corresponding functions.
[0076] The processor contains a kernel, which retrieves the corresponding program unit from memory. One or more kernels can be configured, and the parameters of the kernels can be adjusted to predict the parameters of nanomaterials.
[0077] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.
[0078] This invention provides a computer-readable storage medium storing a program that, when executed by a processor, implements a parameter prediction method based on nanomaterials.
[0079] This invention provides a processor for running a program, wherein the program executes a parameter prediction method based on nanomaterials.
[0080] like Figure 4As shown, this embodiment of the invention provides an electronic device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs the following steps: determining the target nanomaterial to be predicted; determining the target activity value of the enzyme corresponding to the target nanomaterial; inputting the target activity value into a target model, and outputting multiple target parameter values corresponding to the target nanomaterial. The target model consists of multiple first prediction models and a multiple regression model. The first prediction models are linear regression models or multinomial regression models. The multiple target parameter values include at least: the voltage value of the target nanomaterial, the current value of the target nanomaterial, the temperature value of the target nanomaterial, and the pH value of the target nanomaterial. The multiple first prediction models have a corresponding relationship with the multiple target parameter values.
[0081] Optionally, inputting the target activity value into the target model and outputting multiple target parameter values corresponding to the target nanomaterial by predicting them includes: outputting multiple first parameter values based on the target activity value through multiple first prediction models; outputting multiple second parameter values based on the target activity value through a multiple regression model; and calculating multiple target parameter values by averaging the multiple first parameter values and the multiple second parameter values.
[0082] Optionally, after predicting multiple target parameter values corresponding to the target nanomaterial through the target model, the method further includes: measuring based on the multiple target parameter values to obtain the predicted activity value of the enzyme corresponding to the target nanomaterial; and determining whether the multiple target parameter values meet the preset requirements based on the predicted activity value and the target activity value.
[0083] Optionally, determining whether multiple target parameter values meet preset requirements based on predicted activity values and target activity values includes: calculating the difference between predicted activity values and target activity values to obtain a target difference value; determining whether the target difference value is less than a preset threshold; if the target difference value is less than the preset threshold, it indicates that multiple target parameter values meet preset requirements; if the target difference value is greater than or equal to the preset threshold, it indicates that multiple target parameter values do not meet preset requirements.
[0084] Optionally, if multiple target parameter values do not meet the preset requirements, the method further includes: optimizing the target model to obtain an optimized target model, and using the optimized target model to predict the parameters of the target nanomaterial again until multiple target parameter values meet the preset requirements.
[0085] Optionally, the target model is obtained by the following steps: acquiring a training dataset, wherein the training dataset includes multiple sets of training parameters and the training activity values of enzymes corresponding to each set of training parameters, each set of training parameters includes multiple training parameters, and the multiple training parameters include at least: the voltage value corresponding to the nanomaterial, the current value of the nanomaterial, the temperature value of the nanomaterial, and the pH value of the nanomaterial; determining a first prediction model corresponding to each training parameter and determining a multiple regression model corresponding to multiple training parameters based on the training activity values of enzymes corresponding to each set of training parameters; and determining the target model based on the first prediction model and the multiple regression model.
[0086] Optionally, determining the first prediction model corresponding to each training parameter based on the training activity value of the enzyme corresponding to each set of training parameters includes: establishing a linear regression model corresponding to each training parameter based on the training activity value of the enzyme corresponding to each set of training parameters; establishing a multinomial regression model corresponding to each training parameter based on the training activity value of the enzyme corresponding to each set of training parameters; calculating the goodness of fit of each linear regression model to obtain multiple first goodness of fits; calculating the goodness of fit of each multinomial regression model to obtain multiple second goodness of fits; and determining the first prediction model corresponding to each training parameter from the linear regression model and the multinomial regression model corresponding to each training parameter based on the multiple first goodness of fits and the multiple second goodness of fits.
[0087] The devices mentioned in this article can be servers, PCs, tablets, mobile phones, etc.
[0088] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program having the following method steps: determining the target nanomaterial to be predicted; determining the target activity value of the enzyme corresponding to the target nanomaterial; inputting the target activity value into a target model; and outputting multiple target parameter values corresponding to the target nanomaterial obtained from the prediction. The target model consists of multiple first prediction models and a multiple regression model. The first prediction models are linear regression models or multinomial regression models. The multiple target parameter values include at least: the voltage value of the target nanomaterial, the current value of the target nanomaterial, the temperature value of the target nanomaterial, and the pH value of the target nanomaterial. The multiple first prediction models have a corresponding relationship with the multiple target parameter values.
[0089] Optionally, inputting the target activity value into the target model and outputting multiple target parameter values corresponding to the target nanomaterial by predicting them includes: outputting multiple first parameter values based on the target activity value through multiple first prediction models; outputting multiple second parameter values based on the target activity value through a multiple regression model; and calculating multiple target parameter values by averaging the multiple first parameter values and the multiple second parameter values.
[0090] Optionally, after predicting multiple target parameter values corresponding to the target nanomaterial through the target model, the method further includes: measuring based on the multiple target parameter values to obtain the predicted activity value of the enzyme corresponding to the target nanomaterial; and determining whether the multiple target parameter values meet the preset requirements based on the predicted activity value and the target activity value.
[0091] Optionally, determining whether multiple target parameter values meet preset requirements based on predicted activity values and target activity values includes: calculating the difference between predicted activity values and target activity values to obtain a target difference value; determining whether the target difference value is less than a preset threshold; if the target difference value is less than the preset threshold, it indicates that multiple target parameter values meet preset requirements; if the target difference value is greater than or equal to the preset threshold, it indicates that multiple target parameter values do not meet preset requirements.
[0092] Optionally, if multiple target parameter values do not meet the preset requirements, the method further includes: optimizing the target model to obtain an optimized target model, and using the optimized target model to predict the parameters of the target nanomaterial again until multiple target parameter values meet the preset requirements.
[0093] Optionally, the target model is obtained by the following steps: acquiring a training dataset, wherein the training dataset includes multiple sets of training parameters and the training activity values of enzymes corresponding to each set of training parameters, each set of training parameters includes multiple training parameters, and the multiple training parameters include at least: the voltage value corresponding to the nanomaterial, the current value of the nanomaterial, the temperature value of the nanomaterial, and the pH value of the nanomaterial; determining a first prediction model corresponding to each training parameter and determining a multiple regression model corresponding to multiple training parameters based on the training activity values of enzymes corresponding to each set of training parameters; and determining the target model based on the first prediction model and the multiple regression model.
[0094] Optionally, determining the first prediction model corresponding to each training parameter based on the training activity value of the enzyme corresponding to each set of training parameters includes: establishing a linear regression model corresponding to each training parameter based on the training activity value of the enzyme corresponding to each set of training parameters; establishing a multinomial regression model corresponding to each training parameter based on the training activity value of the enzyme corresponding to each set of training parameters; calculating the goodness of fit of each linear regression model to obtain multiple first goodness of fits; calculating the goodness of fit of each multinomial regression model to obtain multiple second goodness of fits; and determining the first prediction model corresponding to each training parameter from the linear regression model and the multinomial regression model corresponding to each training parameter based on the multiple first goodness of fits and the multiple second goodness of fits.
[0095] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0096] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0097] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0098] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0099] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0100] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.
[0101] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.
[0102] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.
[0103] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0104] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.
Claims
1. A parameter prediction method based on nanomaterials, characterized in that, include: Identify the target nanomaterial to be predicted; Determine the target activity value of the enzyme corresponding to the target nanomaterial; The target activity value is input into the target model, and multiple target parameter values corresponding to the target nanomaterial are predicted and output. The target model consists of multiple first prediction models and a multiple regression model. The first prediction model is a linear regression model or a multinomial regression model. The multiple target parameter values include at least: the voltage value of the target nanomaterial, the current value of the target nanomaterial, the temperature value of the target nanomaterial, and the pH value of the target nanomaterial. The multiple first prediction models have a corresponding relationship with the multiple target parameter values. In this context, each first prediction model corresponds to a parameter of a nanomaterial; The target activity value is input into the target model, and the predicted target parameter values corresponding to the target nanomaterial are output, including: Based on the target activity value, the multiple first prediction models output multiple first parameter values; Based on the target activity value, the multivariate regression model outputs multiple second parameter values. The multiple target parameter values are obtained by averaging the multiple first parameter values and the multiple second parameter values.
2. The method according to claim 1, characterized in that, After predicting multiple target parameter values corresponding to the target nanomaterial using the target model, the method further includes: Based on the values of the multiple target parameters, the predicted activity value of the enzyme corresponding to the target nanomaterial is obtained. Based on the predicted activity value and the target activity value, determine whether the multiple target parameter values meet the preset requirements.
3. The method according to claim 2, characterized in that, Determining whether the plurality of target parameter values meet preset requirements based on the predicted activity value and the target activity value includes: The difference between the predicted activity value and the target activity value is calculated to obtain the target difference value; Determine whether the target difference is less than a preset threshold; If the target difference is less than the preset threshold, it indicates that the multiple target parameter values meet the preset requirements; If the target difference is greater than or equal to the preset threshold, it indicates that the multiple target parameter values do not meet the preset requirements.
4. The method according to claim 3, characterized in that, If the multiple target parameter values do not meet the preset requirements, the method further includes: The target model is optimized to obtain an optimized target model, and the parameters of the target nanomaterial are predicted again using the optimized target model until the values of the multiple target parameters meet the preset requirements.
5. The method according to claim 1, characterized in that, The target model is obtained through the following steps: Obtain a training dataset, wherein the training dataset includes multiple sets of training parameters and the training activity value of the enzyme corresponding to each set of training parameters. Each set of training parameters includes multiple training parameters, and the multiple training parameters include at least: the voltage value corresponding to the nanomaterial, the current value of the nanomaterial, the temperature value of the nanomaterial, and the pH value of the nanomaterial. Based on the training activity value of the enzyme corresponding to each set of training parameters, determine the first prediction model corresponding to each training parameter and the multiple regression model corresponding to the multiple training parameters; The target model is determined based on the first prediction model and the multiple regression model.
6. The method according to claim 5, characterized in that, Based on the training activity values of the enzyme corresponding to each set of training parameters, the first prediction model corresponding to each training parameter is determined as follows: Based on the training activity values of the enzyme corresponding to each set of training parameters, a linear regression model is established for each training parameter. Based on the training activity values of the enzyme corresponding to each set of training parameters, a multinomial regression model is established for each training parameter. Calculate the goodness of fit for each linear regression model to obtain multiple first goodness of fits; Calculate the goodness of fit for each polynomial regression model to obtain multiple second goodness of fits; Based on the plurality of first fit degrees and the plurality of second fit degrees, a first prediction model corresponding to each training parameter is determined from the linear regression model corresponding to each training parameter and the multinomial regression model corresponding to each training parameter.
7. A parameter prediction device based on nanomaterials, characterized in that, include: The first determining unit is used to determine the target nanomaterial to be predicted; The second determining unit is used to determine the target activity value of the enzyme corresponding to the target nanomaterial; The prediction unit is used to input the target activity value into the target model and output multiple target parameter values corresponding to the target nanomaterial. The target model consists of multiple first prediction models and a multiple regression model. The first prediction models are linear regression models or multinomial regression models. The multiple target parameter values include at least: the voltage value of the target nanomaterial, the current value of the target nanomaterial, the temperature value of the target nanomaterial, and the pH value of the target nanomaterial. The multiple first prediction models have a corresponding relationship with the multiple target parameter values. Wherein, each of the first prediction models corresponds to a parameter of a nanomaterial; The prediction unit includes: a first output module, configured to output multiple first parameter values based on the target activity value using the multiple first prediction models; a second output module, configured to output multiple second parameter values based on the target activity value using the multiple regression model; and a first calculation module, configured to calculate the average value of the multiple first parameter values and the multiple second parameter values to obtain the multiple target parameter values.
8. A processor, characterized in that, The processor is used to run a program, wherein the program executes the parameter prediction method based on nanomaterials according to any one of claims 1 to 6.
9. An electronic device, characterized in that, It includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the parameter prediction method based on nanomaterials as described in any one of claims 1 to 6.