A zero-shot signal modulation recognition method and device based on deep attribute extraction

Abstract

This application proposes a zero-shot signal modulation recognition method based on deep attribute extraction, relating to the field of deep learning technology. The method includes: extracting the true attribute representations of each modulation category from simulated signal samples using a feature extraction module of a pre-trained classification model; extracting temporal features of the input data using a Long Short-Term Memory (LSTM) network, and mapping these temporal features to an attribute space through a linear transformation layer to obtain predicted attribute representations of the input data; projecting the predicted attribute representations of the input data and the true attribute representations of each modulation category into the same embedding space, calculating the similarity between the predicted and true attributes, and determining the category of the input data based on the similarity. This invention, employing the above scheme, achieves zero-shot signal modulation recognition.

Description

Technical Field

[0001] This application relates to the field of deep learning technology, and in particular to a zero-sample signal modulation recognition method and apparatus based on deep attribute extraction. Background Technology

[0002] With the rapid development of wireless communication technology, the number of wireless devices is growing exponentially, and the communication environment is becoming increasingly complex and harsh. Signals are reshaped by various adversarial factors such as noise, multipath interference, and channel fading during transmission, severely weakening or distorting their original characteristics and placing higher demands on accurate signal identification. Simultaneously, signal modulation methods are becoming increasingly complex and diverse, further increasing the difficulty of modulation identification. Traditional modulation identification methods rely on domain experts manually extracting features based on experience. This process is not only time-consuming but also limited by prior knowledge of the received signal, potentially leading to a significant decline in modulation identification performance in today's increasingly complex communication systems. Signal modulation identification is facing unprecedented and severe challenges.

[0003] In recent years, inspired by the tremendous success of deep learning in fields such as image recognition and natural language processing, scholars have introduced deep learning into the field of automatic modulation recognition. Deep learning-based methods can automatically learn the latent features of signals, overcoming the limitations of traditional methods that rely on manual feature extraction and achieving high recognition accuracy. However, the performance of deep learning largely depends on large-scale labeled datasets, and its recognition capabilities are usually limited to the categories already included in the training data. In practical applications, signal data available for certain signal categories is extremely scarce, resulting in an incomplete coverage of signal categories in the training set, thus limiting the modulation recognition capabilities of deep learning models.

[0004] Zero-Shot Learning (ZSL) is an effective method to address the aforementioned challenges. By utilizing semantic descriptions or attribute information of categories, it transfers knowledge from known classes to unknown classes, enabling the model to recognize categories never seen during training. This solves the problem of models being unable to effectively identify unknown classes in situations of scarce data and has been widely applied in the image processing domain. However, in the field of signal modulation recognition, signal modulation types are extremely complex and diverse, lacking clear semantic distinctions between different modulation types, making it difficult to capture their complexity with simple and clear natural language descriptions. The uninterpretability of modulated signals poses a significant challenge to zero-shot scenarios, making the development of an effective zero-shot classification method for signal modulation recognition imperative. Summary of the Invention

[0005] This application aims to at least partially address one of the technical problems in the related art.

[0006] Therefore, the first objective of this application is to propose a zero-shot signal modulation recognition method based on deep attribute extraction. To address the uninterpretability of modulation signals, the method extracts semantic information representing different modulation modes based on a pre-trained attribute extraction method. Furthermore, it identifies unknown classes by predicting and matching attributes, without relying on labeled samples of unknown classes, thus providing an effective solution for modulation signal recognition in zero-shot scenarios.

[0007] The second objective of this application is to propose a zero-sample signal modulation recognition device based on deep attribute extraction.

[0008] The third objective of this application is to propose a computer device.

[0009] The fourth objective of this application is to provide a non-transitory computer-readable storage medium.

[0010] To achieve the above objectives, the first aspect of this application proposes a zero-sample signal modulation recognition method based on deep attribute extraction, comprising:

[0011] The feature extraction module of the pre-trained classification model extracts the true attribute representations of each modulation category from the simulated signal samples;

[0012] The temporal features of the input data are extracted using a Long Short-Term Memory (LSTM) network, and then mapped to the attribute space through a linear transformation layer to obtain the predicted attribute representation of the input data.

[0013] The predicted attribute representations of the input data and the true attribute representations of each modulation category are projected into the same embedding space. The similarity between the predicted attributes and the true attributes is calculated, and the category of the input data is determined based on the similarity.

[0014] Optionally, in one embodiment of this application, the pre-trained classification model includes:

[0015] We select a labeled dataset of known classes as input and pre-train the classification model using a supervised learning method. During pre-training, the input data is classified by passing it through an LSTM and a linear transformation layer. The classification model is optimized by minimizing the cross-entropy loss function.

[0016] The feature extraction module is obtained by removing the fully connected layer from the classification model;

[0017] The process of generating signal samples includes:

[0018] Based on the generation mechanism of the modulation signal, signal samples are simulated and generated for all modulation categories. A signal sample set is constructed based on the signal samples, which includes signal samples of known classes and signal samples of unknown classes.

[0019] The feature extraction module extracts the true attribute representations of each modulation category from the signal samples, including:

[0020] The signal samples in the signal sample set are input into the feature extraction module to extract the true attribute representation of each signal sample.

[0021] Optionally, in one embodiment of this application, the signal sample set is D. S,U The signal sample set includes signal samples D of known classes. S and unknown class of signal samples D U D S The true attributes are represented as:

[0022] Att S =E(D) S ;θ * )

[0023] D U The true attributes are represented as:

[0024] Att U =E(D) U ;θ * )

[0025] Among them, Att S It is the attribute matrix of a known class, Att U It is the attribute matrix of the unknown class, E is the attribute extraction function, and θ is the attribute extraction function. * These are the optimal parameters learned during pre-training.

[0026] Optionally, in one embodiment of this application, a Long Short-Term Memory (LSTM) network is used to extract temporal features of the input data, and a linear transformation layer is used to map the temporal features to the attribute space to obtain a predicted attribute representation of the input data, including:

[0027] Use LSTM to extract temporal features from the input data;

[0028] The last time step of the time series feature is selected and mapped to the attribute space through a linear transformation layer to obtain the predicted attribute representation of the input data.

[0029] Optionally, in one embodiment of this application, the temporal characteristics of the input data are represented as follows:

[0030] h i =f(x) i )

[0031] Where, x i For input data, h i For time-series features, f(·) represents the LSTM feature extraction function;

[0032] The predicted attributes of the input data are represented as follows:

[0033] a pi =fc(h i [:,-1,:])

[0034] Where fc represents the linear transformation function, h i [:,-1,:] represents the last time step of the time series feature.

[0035] Optionally, in one embodiment of this application, calculating the similarity between the predicted attribute and the true attribute includes:

[0036] The similarity score between the predicted attributes of the input data and the true attributes of each modulation category is calculated by performing matrix multiplication.

[0037] The category of input data is determined based on similarity, including:

[0038] Using the softmax activation function for multi-class classification, the similarity is converted into a probability distribution to obtain the class prediction results of the input data.

[0039] Optionally, in one embodiment of this application, the similarity score is represented as:

[0040] z i,n =a pi ·Att S,U

[0041] Among them, z i,n Input data x i Att is the similarity score between the predicted attribute and the true attribute of the nth category. S,U It is an attribute matrix that includes all categories, including known and unknown classes;

[0042] The probability distribution is as follows:

[0043]

[0044] Among them, P i,n Input data x i The probability of belonging to category n, where C is the number of categories.

[0045] To achieve the above objectives, a second aspect of the present invention provides a zero-sample signal modulation recognition device based on deep attribute extraction, comprising:

[0046] The real attribute extraction module is used to extract the real attribute representations of each modulation category from the simulated signal samples through the feature extraction module in the pre-trained classification model;

[0047] The attribute prediction module is used to extract the temporal features of the input data using the Long Short-Term Memory (LSTM) network, and then map the temporal features to the attribute space through a linear transformation layer to obtain the predicted attribute representation of the input data.

[0048] The classification module projects the predicted attribute representations of the input data and the true attribute representations of each modulation category into the same embedding space, calculates the similarity between the predicted attributes and the true attributes, and determines the category of the input data based on the similarity.

[0049] To achieve the above objectives, a third aspect of the present invention provides a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-described zero-sample signal modulation recognition method based on deep attribute extraction.

[0050] To achieve the above objectives, a fourth aspect of the present invention provides a non-transitory computer-readable storage medium that, when instructions in the storage medium are executed by a processor, enables the execution of the above-described zero-sample signal modulation recognition method based on deep attribute extraction.

[0051] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0052] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0053] Figure 1 This is a flowchart illustrating a zero-sample signal modulation recognition method based on deep attribute extraction provided in Embodiment 1 of this application;

[0054] Figure 2 This is a schematic diagram of a zero-sample signal modulation recognition device based on deep attribute extraction, provided in an embodiment of this application. Detailed Implementation

[0055] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0056] When humans recognize images, they map target categories to an attribute space and then classify the images based on the most discriminative attributes. Inspired by human decision-making processes, this application proposes a zero-shot signal modulation recognition method based on deep attribute extraction. Since signal semantics are uninterpretable, a pre-trained attribute extraction method is proposed. This method utilizes the feature extraction capabilities learned by the model during pre-training to extract representative attribute representations for each modulation category from simulated signal samples. The temporal feature extraction capabilities of the Long Short-Term Memory (LSTM) network and the mapping capabilities of the linear transform layer are used to predict signal attributes. Unknown classes are identified through attribute prediction and matching, without relying on labeled samples of unknown classes, significantly improving the model's generalization ability to new categories and providing an effective solution for modulation signal recognition in zero-shot scenarios.

[0057] The following describes, with reference to the accompanying drawings, a zero-sample signal modulation recognition method and apparatus based on deep attribute extraction according to embodiments of this application.

[0058] Figure 1 This is a flowchart illustrating a zero-sample signal modulation recognition method based on deep attribute extraction, as provided in Embodiment 1 of this application.

[0059] like Figure 1 As shown, this zero-sample signal modulation recognition method based on deep attribute extraction includes the following steps:

[0060] Step 101: Extract the true attribute representation of each modulation category from the simulated signal samples using the feature extraction module of the pre-trained classification model;

[0061] Step 102: Use the Long Short-Term Memory (LSTM) network to extract the temporal features of the input data, and use a linear transformation layer to map the temporal features to the attribute space to obtain the predicted attribute representation of the input data.

[0062] Step 103: Project the predicted attribute representation of the input data and the true attribute representation of each modulation category into the same embedding space, calculate the similarity between the predicted attributes and the true attributes, and determine the category of the input data based on the similarity.

[0063] Optionally, in one embodiment of this application, the pre-trained classification model includes:

[0064] Select a large-scale labeled dataset S with known classes s As input, a classification model is pre-trained using a supervised learning method, and the input data is used as input. The model is then classified using an LSTM and a linear transformation layer, and optimized by minimizing the cross-entropy loss function.

[0065] After pre-training, the model learned powerful feature extraction capabilities. By removing its last fully connected layer, the classifier is transformed into a powerful attribute extractor E, which is then used as the feature extraction module.

[0066] The process of generating signal samples includes:

[0067] Based on the generation mechanism of modulation signals, signal samples were simulated and generated for all modulation categories using the MATLAB platform, constructing a small-scale signal sample set D. S,U This includes signal samples D of known classes. S And the signal sample D of the unknown class U ;

[0068] The feature extraction module extracts the true attribute representations of each modulation category from the signal samples, including:

[0069] These simulated signal samples are input into the attribute extractor E, which loads the optimal parameters θ learned during the pre-training phase. * Extract representative attribute representations.

[0070] Optionally, in one embodiment of this application, D S The true attributes are represented as:

[0071] Att S =E(D) S ;θ * )

[0072] D U The true attributes are represented as:

[0073] Att U =E(D) U ;θ * )

[0074] Where E is the attribute extraction function, Att S It is a matrix of attributes for a known class, containing N S Att is a vector of attributes of a known class. U It is an attribute matrix of unknown class, containing N U An attribute vector of an unknown class. Each category has a D. e A dimensional attribute vector.

[0075] Optionally, in one embodiment of this application, a Long Short-Term Memory (LSTM) network is used to extract temporal features of the input data, and a linear transformation layer is used to map the temporal features to the attribute space to obtain a predicted attribute representation of the input data, including:

[0076] LSTM is used to extract rich temporal features from the input data;

[0077] The last time step of the time series feature is selected, and it is further mapped to the attribute space through a linear transformation layer to predict the signal attributes and obtain the predicted attributes of the input data.

[0078] Optionally, in one embodiment of this application, the temporal characteristics of the input data are represented as follows:

[0079] h i =f(x) i )

[0080] Where, x i For input data, h i For time-series features, f(·) represents the LSTM feature extraction function;

[0081] The predicted attributes of the input data are:

[0082] a pi =fc(h i [:,-1,:])

[0083] Where fc represents the linear transformation function, h i [:,-1,:] represents the last time step of the time series feature.

[0084] Optionally, in one embodiment of this application, calculating the similarity between the predicted attribute and the true attribute includes:

[0085] The similarity score between the predicted attributes of the input data and the true attributes of each modulation category is calculated by performing matrix multiplication.

[0086] The category of input data is determined based on similarity, including:

[0087] The softmax activation function is used for multi-class classification, and the output similarity is converted into a probability distribution to obtain the class prediction results of the samples.

[0088] Optionally, in one embodiment of this application, the similarity score is represented as:

[0089] z i,n =a pi ·Att S,U

[0090] Among them, z i,n Input data x i Att is the similarity score between the predicted attribute and the true attribute of the nth category. S,U It is an attribute matrix that includes all categories, including known and unknown classes;

[0091] The probability distribution is as follows:

[0092]

[0093] Among them, P i,n Input data x i The probability of belonging to category n, where C is the number of categories.

[0094] The zero-shot signal modulation recognition method based on deep attribute extraction in this application, after a thorough study of the principles of deep learning and signal modulation classification, utilizes a pre-trained attribute extraction method. Leveraging the attribute extraction capabilities learned during the pre-training phase, it extracts representative real attribute representations for each modulation category from simulated signal samples, achieving knowledge transfer from known to unknown categories and solving the problem of uninterpretable signal semantics. By utilizing the temporal feature extraction capabilities of the Long Short-Term Memory (LSTM) network and the mapping capabilities of the linear transform layer, it predicts signal attributes. Classification is performed by comparing the similarity between predicted and real attributes, enabling the model not only to identify known signal categories but also to effectively classify unknown categories through attribute prediction and comparison. This significantly improves the model's generalization ability to new categories, which is of great significance for rapidly adapting to new categories without the need to re-collect and relabel large amounts of data.

[0095] To achieve the above embodiments, this application also proposes a zero-sample signal modulation recognition device based on deep attribute extraction.

[0096] Figure 2 This is a schematic diagram of a zero-sample signal modulation recognition device based on deep attribute extraction, provided in an embodiment of this application.

[0097] like Figure 2 As shown, the zero-sample signal modulation recognition device based on deep attribute extraction includes:

[0098] The real attribute extraction module is used to extract the real attribute representations of each modulation category from the simulated signal samples through the feature extraction module in the pre-trained classification model;

[0099] The attribute prediction module is used to extract the temporal features of the input data using the Long Short-Term Memory (LSTM) network, and then map the temporal features to the attribute space through a linear transformation layer to obtain the predicted attribute representation of the input data.

[0100] The classification module projects the predicted attribute representations of the input data and the true attribute representations of each modulation category into the same embedding space, calculates the similarity between the predicted attributes and the true attributes, and determines the category of the input data based on the similarity.

[0101] It should be noted that the foregoing explanation of the embodiment of the zero-sample signal modulation recognition method based on depth attribute extraction also applies to the zero-sample signal modulation recognition device based on depth attribute extraction in this embodiment, and will not be repeated here.

[0102] To implement the above embodiments, the present invention also proposes a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the methods described in the above embodiments.

[0103] To implement the above embodiments, the present invention also proposes a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method of the above embodiments.

[0104] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0105] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0106] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0107] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0108] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0109] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0110] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0111] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A zero-sample signal modulation recognition method based on deep attribute extraction, characterized in that, include: The feature extraction module of the pre-trained classification model extracts the true attribute representations of each modulation category from the simulated signal samples. The pre-training of the classification model includes: A labeled dataset of known classes is selected as input, and the classification model is pre-trained using a supervised learning method. During pre-training, the input data is classified by passing through an LSTM and a linear transformation layer, and the classification model is optimized by minimizing the cross-entropy loss function. The feature extraction module obtains the feature by removing the fully connected layer from the classification model; The process of generating the signal sample includes: Based on the generation mechanism of the modulation signal, signal samples are simulated and generated for all modulation categories. A signal sample set is constructed based on the signal samples, wherein the signal sample set includes signal samples of known classes and signal samples of unknown classes. The feature extraction module extracts the true attribute representations of each modulation category from the signal samples, including: The signal samples in the signal sample set are input into the feature extraction module to extract the true attribute representation of each signal sample; Temporal features of the input data are extracted using a Long Short-Term Memory (LSTM) network, and these temporal features are mapped to an attribute space through a linear transformation layer to obtain a predicted attribute representation of the input data, including: Use LSTM to extract temporal features from the input data; The last time step of the time series feature is selected and mapped to the attribute space through a linear transformation layer to obtain the predicted attribute representation of the input data. The predicted attribute representations of the input data and the true attribute representations of each modulation category are projected into the same embedding space. The similarity between the predicted attributes and the true attributes is calculated, and the category of the input data is determined based on the similarity.

2. The method as described in claim 1, characterized in that, The signal sample set is The signal sample set includes signal samples of known classes. and unknown signal samples , The true attributes are represented as: The true attributes are represented as: in, It is a matrix of attributes of a known class. It is an attribute matrix of an unknown class. It is an attribute extraction function. These are the optimal parameters learned during pre-training.

3. The method as described in claim 1, characterized in that, The temporal characteristics of the input data are represented as follows: in, For input data, As a time series feature, This represents the LSTM feature extraction function; The predicted attributes of the input data are represented as follows: in, Represents a linear transformation function. This is the last time step of the time series feature.

4. The method as described in claim 1, characterized in that, Calculate the similarity between predicted and true attributes, including: The similarity score between the predicted attributes of the input data and the true attributes of each modulation category is calculated by performing matrix multiplication. The category of input data is determined based on similarity, including: Using the softmax activation function for multi-class classification, the similarity is converted into a probability distribution to obtain the class prediction results of the input data.

5. The method as described in claim 4, characterized in that, The similarity score is represented as: in, For input data The similarity score between the predicted attribute and the true attribute of the nth category. It is an attribute matrix that includes all categories, including known and unknown classes; The probability distribution is as follows: in, For input data The probability of belonging to category n. It represents the number of categories.

6. A zero-sample signal modulation recognition device based on deep attribute extraction, characterized in that, include: A true attribute extraction module is used to extract true attribute representations of each modulation category from the simulated signal samples through a feature extraction module in a pre-trained classification model, wherein the pre-trained classification model includes: A labeled dataset of known classes is selected as input, and the classification model is pre-trained using a supervised learning method. During pre-training, the input data is classified by passing through an LSTM and a linear transformation layer, and the classification model is optimized by minimizing the cross-entropy loss function. The feature extraction module obtains the feature by removing the fully connected layer from the classification model; The process of generating the signal sample includes: Based on the generation mechanism of the modulation signal, signal samples are simulated and generated for all modulation categories. A signal sample set is constructed based on the signal samples, wherein the signal sample set includes signal samples of known classes and signal samples of unknown classes. The feature extraction module extracts the true attribute representations of each modulation category from the signal samples, including: The signal samples in the signal sample set are input into the feature extraction module to extract the true attribute representation of each signal sample; The attribute prediction module is used to extract the temporal features of the input data using a Long Short-Term Memory (LSTM) network, and to map the temporal features to the attribute space through a linear transformation layer to obtain the predicted attribute representation of the input data. The attribute prediction module is specifically used for: Use LSTM to extract temporal features from the input data; The last time step of the time series feature is selected and mapped to the attribute space through a linear transformation layer to obtain the predicted attribute representation of the input data. The classification module projects the predicted attribute representations of the input data and the true attribute representations of each modulation category into the same embedding space, calculates the similarity between the predicted attributes and the true attributes, and determines the category of the input data based on the similarity.

7. A computer device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it implements the method as described in any one of claims 1-5.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-5.

Images