Single-molecule conductivity identification method, device, equipment and computer-readable storage medium

Abstract

The present application discloses a single-molecule conductance identification method, apparatus, device, and computer-readable storage medium. The present application relates to the field of single-molecule electrical measurement technology. The method includes: obtaining source domain data, target domain data, and the true conductance label of the source domain data; inputting the source domain data and the target domain data into a to-be-trained model to obtain the conductance characteristics and predicted conductance labels of the source domain data and the target domain data; optimizing the to-be-trained model based on each conductance characteristic, each predicted conductance label, and the true conductance label to obtain a new to-be-trained model; and returning to the step of inputting the source domain data and the target domain data into the to-be-trained model until the to-be-trained model satisfies a preset training termination condition, thereby obtaining a transfer learning model for single-molecule conductance state identification through the transfer learning model. The present application can improve the generalization capability of the model used for single-molecule conductance state identification.

Description

Technical Field

[0001] The present application relates to the field of single-molecule electrical measurement technology, and in particular to a single-molecule conductivity identification method, device, equipment and computer-readable storage medium. Background Art

[0002] With the continuous development of technologies such as scanning tunneling microscopy and mechanically controllable fission junctions, researchers can now achieve electrical measurements at the single-molecule scale, revealing discrete conductivity peaks at the molecule-electrode interface. These phenomena correspond to different molecular conformations and connection states, which are of great significance for a deeper understanding of the basic physical processes in molecular electronics.

[0003] Currently, in the actual preparation of single-molecule junctions, factors such as experimental environment and manipulation techniques lead to significant differences in the single-molecule conductance traces obtained in different scenarios. Some conductance traces are easy to classify and label according to their conductance states. However, models trained on labeled datasets consisting of limited conductance data struggle to learn the global characteristics of the data, resulting in low generalization capabilities.

[0004] Therefore, how to improve the generalization ability of the model used for single-molecule conductance state identification is a problem that needs to be solved urgently. Summary of the Invention

[0005] The main purpose of this application is to provide a single-molecule conductance recognition method, device, equipment and computer-readable storage medium, aiming to improve the generalization ability of the model used for single-molecule conductance state recognition.

[0006] To achieve the above objectives, the present application provides a single-molecule conductance recognition method, which comprises:

[0007] Obtaining source domain data, target domain data, and a real conductance label of the source domain data, wherein the source domain data and the target domain data are single-molecule conductance data in different scenarios, and the real conductance label represents the real conductance state of the single molecule corresponding to the source domain data;

[0008] Inputting the source domain data and the target domain data into a to-be-trained model to obtain conductivity features and predicted conductivity labels of the source domain data and the target domain data;

[0009] The model to be trained is optimized based on each of the conductivity features, each of the predicted conductivity labels, and the true conductivity label to obtain a new model to be trained, and the step of inputting the source domain data and the target domain data into the model to be trained is returned to be executed until the model to be trained meets a preset training termination condition, thereby obtaining a transfer learning model to perform single-molecule conductance state identification through the transfer learning model.

[0010] In one embodiment, the conductance feature includes a global conductance feature and a subdomain conductance feature. The step of inputting the source domain data and the target domain data into the to-be-trained model to obtain the conductance features and predicted conductance labels of the source domain data and the target domain data includes:

[0011] Inputting the source domain data and the target domain data into a to-be-trained model, performing feature extraction on the source domain data and the target domain data through a feature extraction module of the to-be-trained model, and obtaining global conductance features of the source domain data and the target domain data;

[0012] Performing dimensionality reduction processing on each of the global conductance features through the linear module of the to-be-trained model to obtain subdomain conductance features of the source domain data and the target domain data;

[0013] The conductivity state of each of the subdomain conductivity features is classified by the classification module of the model to be trained to obtain predicted conductivity labels of the source domain data and the target domain data.

[0014] In one embodiment, after the step of extracting features from the source domain data and the target domain data using the feature extraction module of the model to be trained to obtain global conductance features of the source domain data and the target domain data, the method further includes:

[0015] The global adaptive module of the model to be trained is used to align the global spatial distribution of the source domain data and the target domain data based on the global conductivity features, so that the model to be trained can learn the global conductivity features of the target domain data.

[0016] In one embodiment, after the step of performing conductivity state classification on each of the subdomain conductivity features using the classification module of the to-be-trained model to obtain predicted conductivity labels corresponding to the source domain data and the target domain data, the method further comprises:

[0017] The subdomain adaptation module of the model to be trained is used to align the subdomain spatial distribution of the source domain data and the target domain data based on the subdomain conductance features, the predicted conductance labels of the target domain data, and the true conductance labels, so that the model to be trained can learn the subdomain conductance features of the target domain data, wherein each subdomain space is composed of data corresponding to a type of conductance label.

[0018] In one embodiment, the step of optimizing the model to be trained based on each of the conductance features, each of the predicted conductance labels, and the true conductance label to obtain a new model to be trained includes:

[0019] Determining a loss value of the to-be-trained model based on each of the conductance features, each of the predicted conductance labels, and the true conductance label;

[0020] The model to be trained is optimized based on the loss value to obtain a new model to be trained.

[0021] In one embodiment, the step of determining the loss value of the to-be-trained model based on each of the conductance features, each of the predicted conductance labels, and the true conductance label comprises:

[0022] Determining a source domain classification loss value based on a first conductance label and the true conductance label, wherein the first conductance label is a predicted conductance label corresponding to the source domain data;

[0023] Determining a domain adaptation loss value based on each of the conductance features, a second conductance label, and the true conductance label, wherein the second conductance label is a predicted conductance label corresponding to the target domain data;

[0024] The sum of the source domain classification loss value and the domain adaptation loss value is used as the loss value of the model to be trained.

[0025] In one embodiment, the domain adaptation loss value includes a global domain adaptation loss value and a subdomain adaptation loss value, and the step of determining the domain adaptation loss value based on each of the conductance features, the second conductance label, and the true conductance label includes:

[0026] Performing spatial distribution difference measurement on each of the global conductivity features to obtain the global adaptive loss value;

[0027] The spatial distribution difference of each of the sub-domain conductivity features, the second conductivity label and the true conductivity label is measured to obtain the sub-domain adaptive loss value.

[0028] In addition, to achieve the above-mentioned purpose, the present application also provides a single-molecule conductance recognition device, which includes:

[0029] an acquisition module, configured to acquire source domain data, target domain data, and a real conductance label of the source domain data, wherein the source domain data and the target domain data are single-molecule conductance data in different scenarios, and the real conductance label represents the real conductance state of the single molecule corresponding to the source domain data;

[0030] A prediction module, configured to input the source domain data and the target domain data into a to-be-trained model to obtain conductance features and predicted conductance labels for the source domain data and the target domain data, respectively;

[0031] A transfer learning module is used to optimize the model to be trained based on each of the conductivity features, each of the predicted conductivity labels and the true conductivity labels to obtain a new model to be trained, and return to execute the step of inputting the source domain data and the target domain data into the model to be trained until the model to be trained meets the preset training termination condition, thereby obtaining a transfer learning model to perform single-molecule conductivity state identification through the transfer learning model.

[0032] In addition, to achieve the above-mentioned purpose, the present application also provides a storage medium, which is a computer-readable storage medium, and the computer-readable storage medium stores a program for implementing the single-molecule conductivity recognition method. The program for implementing the single-molecule conductivity recognition method is executed by a processor to implement the steps of the single-molecule conductivity recognition method as described above.

[0033] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, including a computer program, which implements the steps of the single-molecule conductance recognition method as described above when executed by a processor.

[0034] The present application provides a single-molecule conductance identification method. The present application first obtains source domain data, target domain data and the real conductance label of the source domain data, wherein the source domain data and the target domain data are single-molecule conductance data in different scenarios, and the real conductance label represents the real conductance state of the single molecule corresponding to the source domain data; the source domain data and the target domain data are input into a model to be trained to obtain the conductance features and predicted conductance labels corresponding to the source domain data and the target domain data respectively; then, the model to be trained is optimized based on each conductance feature, each predicted conductance label and the real conductance label to obtain a new model to be trained, and the step of inputting the source domain data and the target domain data into the model to be trained is returned to execute until the model to be trained meets the preset training termination condition, thereby obtaining a transfer learning model, so as to perform single-molecule conductance state identification through the transfer learning model.

[0035] In summary, this application inputs source domain data labeled with real conductance labels and target domain data not labeled with conductance labels into a model to be trained. The model to be trained analyzes the source and target domain data to obtain the data's conductance characteristics, and predicts the conductance labels of single molecules corresponding to the source and target domain data (i.e., predicted conductance labels). The model is then optimized based on the conductance characteristics and prediction results until the model meets the preset training termination conditions, resulting in a transfer learning model for identifying the conductance state of single molecules. Thus, compared to the traditional approach of training models based solely on labeled conductance data, which results in weak model generalization capabilities, this application, through the application of transfer learning, enables the model to utilize knowledge learned from the source domain data to identify and classify target domain data, thereby improving the generalization capabilities of the model for identifying single-molecule conductance states. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0037] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0038] Figure 1 This is a schematic diagram of the process of the first embodiment of the single-molecule conductance recognition method of the present application;

[0039] Figure 2 A schematic diagram showing a comparison of conductance traces involved in an embodiment of the single-molecule conductance recognition method of the present application;

[0040] Figure 3 Schematic diagram of the attention mechanism involved in one embodiment of the single-molecule conductance recognition method of the present application;

[0041] Figure 4 This is a schematic diagram of target domain data classification and recognition results involved in one embodiment of the single-molecule conductance recognition method of the present application;

[0042] Figure 5 Schematic diagram of the model loss calculation process involved in one embodiment of the single-molecule conductance recognition method of the present application;

[0043] Figure 6 A schematic diagram of global adaptation involved in an embodiment of the single-molecule conductance recognition method of the present application;

[0044] Figure 7 A schematic diagram of subdomain adaptation involved in an embodiment of the single-molecule conductance recognition method of the present application;

[0045] Figure 8 Schematic diagram of the single molecule conductance recognition process involved in one embodiment of the single molecule conductance recognition method of the present application;

[0046] Figure 9 This is a schematic diagram of the module structure of the single-molecule conductance recognition device of this application;

[0047] Figure 10 Schematic diagram of the device structure of the hardware operating environment involved in the single-molecule conductance recognition method in the embodiment of the present application.

[0048] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0049] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0050] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0051] The main solution of this application is: obtaining source domain data, target domain data and the real conductance label of the source domain data, wherein the source domain data and the target domain data are single-molecule conductance data in different scenarios, and the real conductance label represents the real conductance state of the single molecule corresponding to the source domain data; inputting the source domain data and the target domain data into the model to be trained to obtain the conductance characteristics and predicted conductance labels of the source domain data and the target domain data respectively; optimizing the model to be trained based on each of the conductance characteristics, each of the predicted conductance labels and the real conductance label to obtain a new model to be trained, and returning to execute the step of inputting the source domain data and the target domain data into the model to be trained until the model to be trained meets the preset training termination condition, thereby obtaining a transfer learning model to perform single-molecule conductance state identification through the transfer learning model.

[0052] Currently, in the actual preparation of single-molecule junctions, factors such as experimental environment and manipulation techniques lead to significant differences in the single-molecule conductance traces obtained in different scenarios. Some conductance traces are easy to classify and label according to their conductance states. However, models trained on labeled datasets consisting of limited conductance data struggle to learn the global characteristics of the data, resulting in low generalization capabilities.

[0053] Therefore, how to improve the generalization ability of the model used for single-molecule conductance state identification is a problem that needs to be solved urgently.

[0054] This application inputs source domain data labeled with real conductance labels and target domain data not labeled with conductance labels into a model to be trained. The model to be trained analyzes the source and target domain data to obtain the data's conductance characteristics and predicts the conductance labels of single molecules corresponding to the source and target domain data (i.e., predicted conductance labels). The model is then optimized based on the conductance characteristics and prediction results until the model meets a preset training termination condition, resulting in a transfer learning model for identifying the conductance state of single molecules. Thus, compared to traditional methods that train models based solely on labeled conductance data, resulting in weak model generalization capabilities, this application, through the application of transfer learning, enables the model to utilize knowledge learned from the source domain data to identify and classify target domain data, thereby improving the generalization capabilities of the model for identifying single-molecule conductance states.

[0055] It should be noted that the execution entity of the methods in each embodiment of the single-molecule conductance recognition method of this application can be a single-molecule conductance recognition system, or a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, mobile phone, etc., or a single-molecule conductance recognition device capable of performing the above functions, etc., and this embodiment is not specifically limited to this. The following describes this embodiment and the following embodiments using a single-molecule conductance recognition system as the execution entity.

[0056] Based on this, this application proposes a single molecule conductance recognition method of the first embodiment, please refer to Figure 1 The single-molecule conductivity recognition method includes steps S10 to S30:

[0057] Step S10, obtaining source domain data, target domain data, and a real conductance label of the source domain data, wherein the source domain data and the target domain data are single-molecule conductance data in different scenarios, and the real conductance label represents the real conductance state of the single molecule corresponding to the source domain data;

[0058] It should be noted that domain adaptation technology is a branch of transfer learning. In domain adaptation, there are two fundamental concepts: domain and task. The domain is the subject of transfer learning and includes the source domain (source domain) and the target domain (target domain). The source domain is the domain with knowledge and data labels, while the target domain is the domain where data labels are required. The task is the goal of transfer learning. By training a classifier on the task, the knowledge learned in the source domain is transferred to the target domain to correctly label sample data in the target domain. Source domain data refers to the knowledge in the source domain, and the true conductance labels of the source domain data refer to the data labels in the source domain. Target domain data refers to sample data in the target domain. The source and target domain data are single-molecule conductance data from different scenarios. The true conductance labels represent the true conductance states of the single molecules corresponding to the source domain data. True conductance labels can be either conductive or non-conductive.

[0059] In this embodiment, data preparation is first performed, that is, obtaining multiple source domain data and the true conductance label of each source domain data , and obtain multiple target domain data The number of source domain data is recorded as , the number of target domain data is recorded as .

[0060] For example, there are many different scenarios where source domain data and target domain data exist, as shown in the following table:

[0061] Domain Adaptation Scenario Table

[0062]

[0063] In a first feasible embodiment, the source domain data and the target domain data correspond to different experimental environments, that is, the source domain data is the conductance data of molecule X in experimental environment A, and the target domain data is the conductance data of molecule X in experimental environment B. In a second feasible embodiment, the source domain data and the target domain data correspond to different calculation methods, that is, the source domain data is the conductance data obtained by simulating molecule X in computational simulation software, and the target domain data is the conductance data obtained by actually measuring the conductance of molecule X in a laboratory. In a third feasible embodiment, the source domain data and the target domain data correspond to different molecules, that is, the source domain data is the conductance data of molecule X in an experimental environment, and the target domain data is the conductance data of molecule Y in an experimental environment.

[0064] For example, the conductivity traces (i.e., conductivity data) of a molecule are collected in experimental environment A and experimental environment B (there are differences in vibration noise and electrical equipment between the experiments). The conductivity data collected in experimental environment A is called source domain data. Source domain data is usually conductivity data with clear and obvious conductivity traces, low noise, and easy to classify and label. The conductivity data collected in experimental environment B is called target domain data. Target domain data is usually conductivity data with large fluctuations in the conductivity traces. Figure 2 The following is a comparison diagram of the conductivity traces, where: Figure 2 (a) shows the non-conductance step trace of a single molecule in the source domain (labeled as non-conductance). Figure 2 (b) shows the conductance step trace of a single molecule in the source domain (labeled as conductance), and Figure 2 (c) shows the conductance trace of a single molecule in the target domain. In the data preparation stage, the source domain data is represented as , the total sample size of source domain data is ,Label It is divided into non-conductance steps (ie, no conduction) and conduction steps (ie, conduction). The target domain data is represented as , the total sample size of the target domain data is Since the number of points of each conductivity trace collected during the experiment is different, the fixed-length sampling method is used to process the conductivity traces so that the conductivity data has a unified dimension, which is convenient for subsequent model processing. The source domain data specifications after processing are , the target domain data specifications are .

[0065] Step S20: inputting the source domain data and the target domain data into a to-be-trained model to obtain conductivity features and predicted conductivity labels of the source domain data and the target domain data, respectively;

[0066] It should be noted that the embodiment of the present application does not limit the specific type of the model to be trained. In this embodiment, the model to be trained can be a convolutional neural network model or a recurrent network model.

[0067] The source domain data and target domain data are input into the model to be trained. The model extracts features from the source and target domain data to obtain conductivity features, and then performs classification prediction on the source and target domain data to obtain predicted conductivity labels. The predicted conductivity labels include conductivity and non-conductivity.

[0068] It should be understood that when there are multiple source domain data input and multiple target domain data input, the model to be trained will obtain the conductivity features and predicted conductivity labels of each input data.

[0069] Step S30, optimizing the model to be trained based on each of the conductivity features, each of the predicted conductivity labels and the true conductivity labels to obtain a new model to be trained, and returning to execute the step of inputting the source domain data and the target domain data into the model to be trained until the model to be trained meets the preset training termination condition, thereby obtaining a transfer learning model to perform single-molecule conductance state identification through the transfer learning model.

[0070] It should be noted that the pre-set model training termination condition is that the number of training steps reaches a preset number of steps, or the model loss function converges.

[0071] Based on the conductance features, predicted conductance labels and true conductance labels output by the model to be trained, the model parameters of the model to be trained are optimized to obtain a new model to be trained. The source domain data and the target domain data are re-input into the new model to be trained until the optimized model to be trained meets the preset training termination conditions. The model to be trained at this time is used as a transfer learning model for single-molecule conductance state recognition.

[0072] It's important to note that in traditional machine learning approaches, thresholding relies on prior baseline information and is sensitive to Gaussian white noise. Clustering algorithms have limited dimensionality reduction capabilities for high-dimensional features, making it difficult to distinguish similar conductance states (such as the difference between upright and tilted conformations). The accuracy of SVM (Support Vector Machine) classifiers is highly dependent on handcrafted features (such as peak-to-valley ratios and autocorrelation coefficients), requiring feature redesign when the molecular architecture changes. Conventional deep learning models are prone to overfitting when trained on small datasets due to the scarcity of labeled samples. The models are unable to adapt to variations in conductance trace data (such as current noise, conductance length, and height) for the same molecule due to changes in the experimental environment. For example, in single-molecule device stability testing, the models over-remember the noise patterns in the training data, resulting in reduced recognition accuracy for new data.

[0073] The embodiment of the present application uses domain adaptation technology to solve the cross-domain generalization problem of the classification model in the analysis of single-molecule conductance data, targeting different scenarios in fields such as experimental conditions, molecular systems, and noise patterns. Through feature alignment, sample weighting, and model optimization, the robustness of the model in different experimental conditions and molecular systems is significantly improved. Compared with traditional methods (traditional machine learning models, early deep learning models), the use of domain adaptation technology can improve the generalization ability of the classification model across experimental conditions while reducing the degree of dependence on labeled data, significantly improving the robustness, efficiency, and interpretability of single-molecule conductance data recognition, helping researchers to more easily obtain valuable electrical feature information from the data, and providing guidance for further theoretical research and experimental design.

[0074] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction and will not be repeated hereafter. On this basis, the conductivity characteristics include global conductivity characteristics and sub-domain conductivity characteristics, and the step S20 may include:

[0075] Step S201: inputting the source domain data and the target domain data into a to-be-trained model, performing feature extraction on the source domain data and the target domain data through a feature extraction module of the to-be-trained model, and obtaining global conductance features of the source domain data and the target domain data;

[0076] It should be noted that conductivity features include global conductivity features. The model to be trained includes a feature extraction module for extracting conductivity features from the source and target domain data. Conductivity features include, but are not limited to, conductivity height, conductivity length, and conductivity distribution.

[0077] After the source domain data and target domain data are input into the model to be trained, the feature extraction module of the model to be trained is used to extract features from the source domain data and target domain data to obtain the low-dimensional features of the source domain data and target domain data (i.e., global conductivity features).

[0078] Step S202: performing dimensionality reduction processing on each of the global conductance features using a linear module of the model to be trained to obtain subdomain conductance features of the source domain data and the target domain data;

[0079] It should be noted that the conductance features also include subdomain conductance features, which have a lower dimensionality than the global conductance features. For example, the global conductance features have a 64-dimensional dimension, while the subdomain conductance features have a 32-dimensional dimension. The model to be trained also includes a linear module for performing dimensionality reduction on the global conductance features to obtain lower-dimensional features (i.e., subdomain conductance features).

[0080] Step S203 , classifying the conductivity state of each of the sub-domain conductivity features by the classification module of the model to be trained, and obtaining predicted conductivity labels of the source domain data and the target domain data.

[0081] It should be noted that the model to be trained also includes a classification module for outputting sample labels (i.e., predicted conductance labels).

[0082] In one feasible implementation, after the data preparation step, a convolutional neural network or a recurrent network is used to build the model, and an attention mechanism module is introduced into the model to improve the model's weight distribution of the conductivity feature, that is, a one-dimensional convolutional neural network with an attention mechanism is used to build a feature extraction module, which is recorded as Module_1; a linear module is connected after the feature extraction module to further reduce the dimension of the feature, which is recorded as Module_2; a classification module is connected after the linear module to output the sample label, which is recorded as Module_3. The total model Model = Module_1 + Module_2 + Module_3. The source domain data and the target domain data are respectively obtained through Module_1. Feature vector and , that is, the global conductivity characteristics; and Then pass through Module_2 to get the eigenvector and , that is, the subdomain conductivity characteristics; and Get the predicted label through Module_3 and , i.e. predicting the conductance label.

[0083] For example, Figure 3 The figure shows a schematic diagram of the attention mechanism. Source and target domain data are input into a model with an attention mechanism. The model extracts the conductivity features from the data as input features F. It then performs maximum pooling and average pooling on the input features F. The processed data is input into the shared perception layer. Finally, a weight is assigned to each channel, that is, a weight is assigned to each conductivity feature. In this way, the embodiment of the present application introduces the attention mechanism into the domain adaptation technology, making it easier for the model to focus on the key features of the data, thereby enhancing the interpretability of the model through visualization operations.

[0084] In this embodiment, step S30 may include:

[0085] Step S301, determining a loss value of the to-be-trained model based on each of the conductance features, each of the predicted conductance labels, and the true conductance label;

[0086] Step S302: Optimize the model to be trained based on the loss value to obtain a new model to be trained.

[0087] Based on the conductance features, predicted conductance labels, and true conductance labels of each source domain data and each target domain data output by the to-be-trained model, the loss value of the to-be-trained model for the current training round is calculated. Based on the loss value, the parameters in the to-be-trained model are optimized to obtain the optimized to-be-trained model.

[0088] For example, after calculating the loss value of this round of model training, the optimizer can be used to reversely optimize the weight parameters of each module in the model to be trained until the preset step threshold is reached or the loss value is less than the preset threshold (that is, the loss function converges), and the model training is confirmed to be complete. Among them, the optimizer can be SGD (Stochastic Gradient Descent) or adaptive gradient methods. Then, the trained classification model (that is, the transfer learning model) is set as a gradient-free optimization model, and the target domain data is input into the classification model again to obtain the predicted conductivity label to complete the classification recognition task. In addition, according to actual needs, the embodiment of the present application can also use Python language to build a model for user terminal recognition analysis, or use C++ language to build a model in an embedded device to complete specific automated recognition tasks.

[0089] In this embodiment, step S301 may include:

[0090] Step A10: determining a source domain classification loss value based on a first conductance label and the true conductance label, wherein the first conductance label is a predicted conductance label corresponding to the source domain data;

[0091] It should be noted that the predicted conductance label corresponding to the source domain data is called the first conductance label for distinction.

[0092] In one possible implementation, the cross entropy loss is used to calculate the true conductance label of the source domain data. and predicted conductance labels The classification loss between (i.e., the source domain classification loss value) can be expressed as:

[0093]

[0094] in, is the source domain classification loss value, Represents the cross entropy loss calculation. It can be understood that when the number of source domain data is When , the source domain classification loss is calculated based on the true conductance label and the predicted conductance label of each source domain data.

[0095] Step A20: determining a domain adaptation loss value based on each of the conductance features, a second conductance label, and the true conductance label, wherein the second conductance label is a predicted conductance label corresponding to the target domain data;

[0096] It should be noted that the predicted conductance label corresponding to the target domain data is called the second conductance label for distinction.

[0097] The domain adaptation loss value is calculated based on the conductance features, the second conductance label, and the true conductance label output by the training model.

[0098] In this embodiment, the domain adaptation loss value includes a global domain adaptation loss value and a subdomain adaptation loss value. Step A20 may include:

[0099] Step A201, measuring the spatial distribution difference of each of the global conductivity features to obtain the global adaptive loss;

[0100] It should be noted that the conductivity feature includes the global conductivity feature, and the domain adaptive loss value includes the global adaptive loss value.

[0101] In one embodiment, the MMD (Maximum Mean Discrepancy) method based on RKHS (Reproducing Kernel Hilbert Space) is used to calculate the feature vectors of the source domain data and the target domain data. and The global adaptive loss between , the calculation formula is:

[0102]

[0103] Step A202: performing spatial distribution difference measurement on each of the sub-domain conductivity features, the second conductivity label, and the true conductivity label to obtain the sub-domain adaptive loss value.

[0104] It should be noted that the conductivity feature includes the subdomain conductivity feature, and the domain adaptive loss value includes the subdomain adaptive loss value.

[0105] In one possible implementation, the MMD method based on the reproducing kernel Hilbert space is used to calculate the eigenvector of the source domain data. and real conductance labels , the feature vector of the target domain data and the subdomain adaptation loss between the predicted conductance labels , the calculation formula is:

[0106]

[0107] Wherein, c represents the type of the conductivity tag. In this embodiment, the value of c is 2.

[0108] Step A30: Taking the sum of the source domain classification loss value and the domain adaptation loss value as the loss value of the model to be trained.

[0109] It should be noted that the loss value of the model to be trained includes the source domain classification loss ( ) and domain adaptation loss ( ), where domain adaptation loss has two categories: global domain adaptation loss ( ) and subdomain adaptation loss ( The maximum mean difference method (MMD) is used to measure the spatial distribution difference. The specific calculation method is as follows:

[0110]

[0111]

[0112] The total loss function of the model to be trained is , Based on the total loss value, the model is trained in reverse until the model meets the preset training termination conditions, resulting in a classification model. The classification model is then tested based on the target domain data, completing the classification and recognition task of the target domain data.

[0113] For example, Figure 4 The following is a schematic diagram of the target domain data classification and recognition results. Figure 4 (a) is the target domain data to be classified and identified, including multiple conductance traces. The target domain data is input into the classification model, and the classification model can classify each conductance trace into a trace without conductance step and a trace with conductance step, that is, Figure 4 (b) is the conductance-free step trace of a single molecule in the target domain. Figure 4 (c) shows the conductance step trace of a single molecule in the target domain.

[0114] In one possible implementation, Figure 5 The figure shows the model loss calculation process. First, the source domain data and target domain data are input into the convolutional neural network with attention mechanism (i.e., feature extraction module) to obtain low-dimensional features. , that is, the global conductivity feature; then the low-dimensional feature is processed by the model linear layer (i.e., linear module) Perform dimensionality reduction to obtain low-dimensional features , that is, the subdomain conductivity feature; then the model classification layer (i.e., classification module) is used to classify the subdomain conductivity feature based on the low-dimensional feature. The predicted labels of the source and target domain data (i.e., predicted conductance labels) are obtained. The global loss (i.e., global adaptive loss) is calculated based on the global conductance features, the subdomain loss (i.e., subdomain adaptive loss) is calculated based on the conductance features of each subdomain, the true labels of the source domain data, and the predicted labels of the target domain data, and the classification loss (i.e., source domain classification loss) is calculated based on the predicted labels of the source domain data and the true labels of the source domain data. The total loss of the model is obtained by adding these three losses.

[0115] In this way, the embodiment of the present application measures the difference between the source domain and the target domain by designing two types of loss functions (source domain classification loss and domain adaptation loss), and minimizes this difference during the model training process, so that the source domain data and the target domain data are closer in the feature space, thereby improving the effect of model adaptation.

[0116] In this embodiment, after step S201, the single-molecule conductance recognition method of the present application further includes:

[0117] In step B10, the global adaptive module of the model to be trained performs global spatial distribution alignment on the source domain data and the target domain data based on the global conductance features, so that the model to be trained can learn the global conductance features of the target domain data.

[0118] It should be noted that the model to be trained also includes a global adaptation module for performing global adaptation operations on source domain data and target domain data.

[0119] After extracting features from the source and target domain data through the feature extraction module of the model to be trained and obtaining the global conductivity features of each data, the global adaptation module aligns the overall numerical spatial distribution of the source and target domain data based on the global conductivity features, so that the model to be trained can learn the global conductivity features of the target domain.

[0120] For example, Figure 6 The figure shows a schematic diagram of global adaptation, fusing source and target domain data into a single numerical distribution space, thus achieving numerical spatial distribution alignment. As you can see, the blue graph represents source domain data, and the yellow graph represents target domain data.

[0121] In this embodiment, after step S203, the single-molecule conductance recognition method of the present application further includes:

[0122] Step B20, through the subdomain adaptation module of the model to be trained, based on each of the subdomain conductance features, the predicted conductance label of the target domain data and the true conductance label, the source domain data and the target domain data are aligned in subdomain space distribution, so that the model to be trained can learn the subdomain conductance features of the target domain data, wherein each subdomain space is composed of data corresponding to a type of conductance label.

[0123] It should be noted that the model to be trained also includes a subdomain adaptation module for performing subdomain adaptation operations on the source domain data and the target domain data.

[0124] After the model to be trained outputs the conductivity features of each subdomain and the predicted conductivity labels of the target domain data, the subdomain adaptation module aligns the subdomain numerical space distribution of the space after global adaptive alignment according to different conductivity label categories.

[0125] For example, Figure 7 The figure below shows a schematic diagram of subdomain adaptation. It can be understood that the triangles and squares represent different types of conductance labels. The source and target domain data are divided into two subdomains according to these categories, and the numerical spatial distribution of the subdomains is aligned. That is, each subdomain space contains data corresponding to the same type of conductance label.

[0126] In one possible implementation, Figure 8 The figure shows a schematic diagram of the single-molecule conductance recognition process. First, data preparation is performed to obtain source domain conductance data (i.e., source domain data) and target domain conductance data (i.e., target domain data); the source domain conductance data and target domain conductance data are input into the model to obtain the model output; the source domain classification loss and domain adaptation loss are calculated based on the model output; the model parameters are reversely optimized based on the sum of the two types of losses until the optimized model meets the training termination conditions to obtain a classification model; the target domain conductance samples (i.e., target domain data) are predicted through the classification model to obtain the conductance labels of the target domain conductance samples.

[0127] In this way, the embodiment of the present application uses domain adaptation technology to transfer the knowledge learned in the source domain to the target domain to achieve correct labeling of target domain samples, effectively bridging the differences between conductivity data in different scenarios, so that the model trained in one domain can be better applied to other domains, improving the generalization ability and applicability of the model. At the same time, due to the high cost of obtaining a large amount of high-quality annotated data in single-molecule conductivity research, the embodiment of the present application uses a small amount of annotated data in the source domain to learn the unknown label data in the target domain. Through transfer learning, the dependence on the annotated data in the target domain is reduced, thereby achieving more efficient use of existing data resources for accurate identification and classification, and improving the model's ability to process complex distributed data.

[0128] The present application also provides a single molecule conductivity recognition device, please refer to Figure 9 , the single-molecule conductance recognition device comprises:

[0129] An acquisition module 10 is configured to acquire source domain data, target domain data, and a real conductance label of the source domain data, wherein the source domain data and the target domain data are single-molecule conductance data in different scenarios, and the real conductance label represents the real conductance state of the single molecule corresponding to the source domain data;

[0130] A prediction module 20 is configured to input the source domain data and the target domain data into a to-be-trained model to obtain conductivity features and predicted conductivity labels of the source domain data and the target domain data, respectively;

[0131] The transfer learning module 30 is used to optimize the model to be trained based on each of the conductivity features, each of the predicted conductivity labels and the true conductivity labels to obtain a new model to be trained, and return to execute the step of inputting the source domain data and the target domain data into the model to be trained until the model to be trained meets the preset training termination condition, thereby obtaining a transfer learning model to perform single-molecule conductivity state identification through the transfer learning model.

[0132] Optionally, the conductivity feature includes a global conductivity feature and a subdomain conductivity feature, and the prediction module 20 is further configured to:

[0133] Inputting the source domain data and the target domain data into a to-be-trained model, performing feature extraction on the source domain data and the target domain data through a feature extraction module of the to-be-trained model, and obtaining global conductance features of the source domain data and the target domain data;

[0134] Performing dimensionality reduction processing on each of the global conductance features through the linear module of the to-be-trained model to obtain subdomain conductance features of the source domain data and the target domain data;

[0135] The conductivity state of each of the subdomain conductivity features is classified by the classification module of the model to be trained to obtain predicted conductivity labels of the source domain data and the target domain data.

[0136] Optionally, the single-molecule conductance recognition device further includes a global adaptive module, and the global adaptive module is configured to:

[0137] The global adaptive module of the model to be trained is used to align the global spatial distribution of the source domain data and the target domain data based on the global conductivity features, so that the model to be trained can learn the global conductivity features of the target domain data.

[0138] Optionally, the single-molecule conductance recognition device further includes a subdomain adaptation module, and the subdomain adaptation module is used to:

[0139] The subdomain adaptation module of the model to be trained is used to align the subdomain spatial distribution of the source domain data and the target domain data based on the subdomain conductance features, the predicted conductance labels of the target domain data, and the true conductance labels, so that the model to be trained can learn the subdomain conductance features of the target domain data, wherein each subdomain space is composed of data corresponding to a type of conductance label.

[0140] Optionally, the transfer learning module 30 is further configured to:

[0141] Determining a loss value of the to-be-trained model based on each of the conductance features, each of the predicted conductance labels, and the true conductance label;

[0142] The model to be trained is optimized based on the loss value to obtain a new model to be trained.

[0143] Optionally, the transfer learning module 30 is further configured to:

[0144] Determining a source domain classification loss value based on a first conductance label and the true conductance label, wherein the first conductance label is a predicted conductance label corresponding to the source domain data;

[0145] Determining a domain adaptation loss value based on each of the conductance features, a second conductance label, and the true conductance label, wherein the second conductance label is a predicted conductance label corresponding to the target domain data;

[0146] The sum of the source domain classification loss value and the domain adaptation loss value is used as the loss value of the model to be trained.

[0147] Optionally, the domain adaptation loss value includes a global domain adaptation loss value and a subdomain adaptation loss value, and the transfer learning module 30 is further configured to:

[0148] Performing spatial distribution difference measurement on each of the global conductivity features to obtain the global adaptive loss value;

[0149] The spatial distribution difference of each of the sub-domain conductivity features, the second conductivity label and the true conductivity label is measured to obtain the sub-domain adaptive loss value.

[0150] The single-molecule conductance recognition device provided in the embodiments of this application, employing the single-molecule conductance recognition method described in the aforementioned embodiments, can address the technical problem of improving the generalization capabilities of models used for single-molecule conductance state recognition. Compared to the prior art, the single-molecule conductance recognition device provided in the embodiments of this application achieves the same beneficial effects as the single-molecule conductance recognition method described in the aforementioned embodiments. Other technical features of the single-molecule conductance recognition device are the same as those disclosed in the aforementioned embodiments and are not further elaborated here.

[0151] The present application provides a single-molecule conductance recognition device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the single-molecule conductance recognition method of the above-mentioned embodiment 1.

[0152] Reference below Figure 10 , which shows a schematic diagram of the structure of a single-molecule conductance recognition device suitable for implementing embodiments of the present application. The single-molecule conductance recognition device in the embodiments of the present application can include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), and fixed terminals such as digital TVs and desktop computers. Figure 10 The single-molecule conductivity recognition device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0153] like Figure 10As shown, the single-molecule conductance recognition device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory 1002 or programs loaded from a storage device 1003 into a random access memory 1004. The random access memory 1004 also stores various programs and data required for the operation of the single-molecule conductance recognition device. The processing device 1001, the read-only memory 1002, and the random access memory 1004 are interconnected via a bus 1005. An input / output interface 1006 is also connected to the bus. Typically, the following systems can be connected to the input / output interface 1006: an input device 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; a storage device 1003 including, for example, a magnetic tape or hard disk; and a communication device 1009. Communication device 1009 can allow the single-molecule conductance recognition device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a single-molecule conductance recognition device with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems can be implemented or have alternatively.

[0154] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a read-only memory 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are performed.

[0155] The single-molecule conductance recognition device provided herein, employing the single-molecule conductance recognition method described in the aforementioned embodiments, addresses the technical problem of improving the generalization capabilities of models used for single-molecule conductance state recognition. Compared to the prior art, the single-molecule conductance recognition device provided herein achieves the same beneficial effects as the single-molecule conductance recognition method described in the aforementioned embodiments. Other technical features of this single-molecule conductance recognition device are the same as those disclosed in the aforementioned embodiments and are not further elaborated here.

[0156] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0157] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0158] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, a computer program) stored thereon, wherein the computer-readable program instructions are used to execute the single-molecule conductance recognition method in the above-mentioned embodiment.

[0159] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0160] The computer-readable storage medium may be included in the single-molecule conductance recognition device; or may exist independently without being incorporated into the single-molecule conductance recognition device.

[0161] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the single-molecule conductance recognition device, the single-molecule conductance recognition device: obtains source domain data, target domain data and the real conductance label of the source domain data, wherein the source domain data and the target domain data are single-molecule conductance data in different scenarios, and the real conductance label represents the real conductance state of the single molecule corresponding to the source domain data; inputs the source domain data and the target domain data into the model to be trained to obtain the conductance characteristics and predicted conductance labels of the source domain data and the target domain data respectively; optimizes the model to be trained based on each of the conductance characteristics, each of the predicted conductance labels and the real conductance label to obtain a new model to be trained, and returns to execute the step of inputting the source domain data and the target domain data into the model to be trained until the model to be trained meets the preset training termination condition, thereby obtaining a transfer learning model, so as to perform single-molecule conductance state recognition through the transfer learning model.

[0162] Computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0163] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0164] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0165] The computer-readable storage medium provided herein stores computer-readable program instructions (i.e., a computer program) for executing the above-described single-molecule conductance identification method. This computer-readable storage medium addresses the technical problem of improving the generalization capabilities of models for single-molecule conductance state identification. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided herein are similar to those of the single-molecule conductance identification method provided in the above-described embodiments and are not further elaborated here.

[0166] An embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the single-molecule conductance recognition method as described above.

[0167] The computer program product provided herein can improve the generalization capabilities of models for identifying single-molecule conductance states. Compared to the prior art, the beneficial effects of the computer program product provided in the embodiments of this application are similar to those of the single-molecule conductance identification method provided in the aforementioned embodiments and are not further elaborated here.

[0168] The above are only preferred embodiments of the present application and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent processing scope of the present application.

Claims

1. A single molecule conductivity recognition method, characterized in that: The single molecule conductance recognition method comprises: Obtaining source domain data, target domain data, and real conductance labels of the source domain data, wherein the source domain data and the target domain data are single-molecule conductance data under different scenarios, the real conductance labels represent the real conductance states of the single molecules corresponding to the source domain data, and the real conductance labels are conductive or non-conductive, and different scenarios refer to different experimental environments or different molecular types; Inputting the source domain data and the target domain data into a to-be-trained model to obtain conductivity features and predicted conductivity labels of the source domain data and the target domain data; The model to be trained is optimized based on each of the conductivity features, each of the predicted conductivity labels, and the true conductivity label to obtain a new model to be trained, and the step of inputting the source domain data and the target domain data into the model to be trained is returned to be executed until the model to be trained meets a preset training termination condition, thereby obtaining a transfer learning model to perform single-molecule conductance state identification through the transfer learning model.

2. The single-molecule conductivity recognition method according to claim 1, wherein The conductance feature includes a global conductance feature and a subdomain conductance feature. The step of inputting the source domain data and the target domain data into a to-be-trained model to obtain the conductance features and predicted conductance labels of the source domain data and the target domain data includes: Inputting the source domain data and the target domain data into a to-be-trained model, performing feature extraction on the source domain data and the target domain data through a feature extraction module of the to-be-trained model, and obtaining global conductance features of the source domain data and the target domain data; Performing dimensionality reduction processing on each of the global conductance features through the linear module of the to-be-trained model to obtain subdomain conductance features of the source domain data and the target domain data; The conductivity state of each of the subdomain conductivity features is classified by the classification module of the model to be trained to obtain predicted conductivity labels of the source domain data and the target domain data.

3. The single molecule conductivity recognition method according to claim 2, wherein: After the step of extracting features from the source domain data and the target domain data using the feature extraction module of the model to be trained to obtain global conductance features of the source domain data and the target domain data, the method further includes: The global adaptive module of the model to be trained is used to align the global spatial distribution of the source domain data and the target domain data based on the global conductivity features, so that the model to be trained can learn the global conductivity features of the target domain data.

4. The single molecule conductivity recognition method according to claim 2, wherein: After the step of performing conductivity state classification on each of the subdomain conductivity features using the classification module of the to-be-trained model to obtain respective predicted conductivity labels for the source domain data and the target domain data, the method further comprises: The subdomain adaptation module of the model to be trained is used to align the subdomain spatial distribution of the source domain data and the target domain data based on the subdomain conductance features, the predicted conductance labels of the target domain data, and the true conductance labels, so that the model to be trained can learn the subdomain conductance features of the target domain data, wherein each subdomain space is composed of data corresponding to a type of conductance label.

5. The single molecule conductance recognition method according to claim 2, wherein: The step of optimizing the model to be trained based on each of the conductance features, each of the predicted conductance labels, and the true conductance label to obtain a new model to be trained comprises: Determining a loss value of the to-be-trained model based on each of the conductance features, each of the predicted conductance labels, and the true conductance label; The model to be trained is optimized based on the loss value to obtain a new model to be trained.

6. The single-molecule conductance recognition method according to claim 5, wherein: The step of determining the loss value of the to-be-trained model based on each of the conductance features, each of the predicted conductance labels, and the true conductance label comprises: Determining a source domain classification loss value based on a first conductance label and the true conductance label, wherein the first conductance label is a predicted conductance label corresponding to the source domain data; Determining a domain adaptation loss value based on each of the conductance features, a second conductance label, and the true conductance label, wherein the second conductance label is a predicted conductance label corresponding to the target domain data; The sum of the source domain classification loss value and the domain adaptation loss value is used as the loss value of the model to be trained.

7. The single-molecule conductance recognition method according to claim 6, wherein: The domain adaptation loss value includes a global domain adaptation loss value and a subdomain adaptation loss value. The step of determining the domain adaptation loss value based on each of the conductance features, the second conductance label, and the true conductance label includes: Performing spatial distribution difference measurement on each of the global conductivity features to obtain the global adaptive loss value; The spatial distribution difference of each of the sub-domain conductivity features, the second conductivity label and the true conductivity label is measured to obtain the sub-domain adaptive loss value.

8. A single-molecule conductivity recognition device, characterized in that: The single-molecule conductance recognition device comprises: an acquisition module, configured to acquire source domain data, target domain data, and a real conductance label of the source domain data, wherein the source domain data and the target domain data are single-molecule conductance data under different scenarios, and the real conductance label represents the real conductance state of the single molecule corresponding to the source domain data, wherein the real conductance label is conductive or non-conductive, and different scenarios refer to different experimental environments or different molecular types; A prediction module, configured to input the source domain data and the target domain data into a to-be-trained model to obtain conductance features and predicted conductance labels for the source domain data and the target domain data, respectively; A transfer learning module is used to optimize the model to be trained based on each of the conductivity features, each of the predicted conductivity labels and the true conductivity labels to obtain a new model to be trained, and return to execute the step of inputting the source domain data and the target domain data into the model to be trained until the model to be trained meets the preset training termination condition, thereby obtaining a transfer learning model to perform single-molecule conductivity state identification through the transfer learning model.

9. A single molecule conductivity recognition device, characterized in that The single-molecule conductance recognition device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the single-molecule conductance recognition method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the single-molecule conductance recognition method according to any one of claims 1 to 7 are implemented.

Images