Transformer oil chromatography offline abnormal data identification method and system

Abstract

The invention discloses a transformer oil chromatography offline abnormal data identification method and system, and the method comprises the steps: carrying out the explanatory analysis of sample data with the confidence coefficient smaller than a preset threshold value, generating an anti-fact sample, and filtering the prediction change of the anti-fact sample through a data feature selection model to obtain boundary sample data; removing boundary sample data in the at least one piece of sample data to obtain at least one piece of target sample data, inputting the at least one piece of target sample data into a data feature selection model for iterative training and verification of model performance until the model performance reaches a preset condition, and obtaining an oil chromatography offline abnormal data model; and acquiring real-time transformer oil chromatographic data, inputting the real-time transformer oil chromatographic data into the oil chromatography offline abnormal data model, and outputting the real-time transformer oil chromatographic data by the oil chromatography offline abnormal data model to obtain a recognition result. And when new data is received, potential false samples can be efficiently identified, so that the accuracy of abnormal data identification is enhanced.

Description

Technical Field

[0001] The invention belongs to the technical field of data analysis, and in particular relates to a transformer oil chromatogram offline abnormal data recognition method and system. Background Art

[0002] Maintaining and monitoring power equipment can not only prevent power outages, but also ensure the continuity and stability of power supply. In modern power systems, more and more intelligent monitoring and fault detection technologies are being used to effectively reduce the incidence of equipment failures through big data analysis and predictive maintenance. For example, the use of real-time monitoring systems can promptly detect abnormalities such as excessive temperature and excessive current in equipment, and preventive inspections and maintenance can be performed to reduce the risk of power outages. Therefore, strengthening the safety, reliability and maintenance level of power equipment is of great significance to ensuring the stable operation of the power system and the normal operation of social production and life.

[0003] In the process of monitoring and evaluating power equipment, a large amount of data will inevitably be generated, collected and stored, and with the development and diversification of monitoring methods and technologies, these data are still showing explosive growth. To a large extent, the status assessment of power equipment is to combine various standards and historical experience and rely on these data for more in-depth analysis. The importance of these power equipment status data is self-evident. The quality of the data will have a significant impact on the safe and stable operation of power equipment, and then affect the reliability of the entire power system. Therefore, improving the quality of power equipment status data and ensuring the data quality is an important issue for the safe operation of the power system.

[0004] In the current research on data quality, it can be summarized into the following two aspects: one is the evaluation and monitoring of data quality; the other is the improvement of data quality. In terms of improving data quality, data cleaning is a very important part. The purpose of data cleaning is to purify the data, which generally includes two steps: removing redundant data and eliminating erroneous data. Since most of the power equipment status data are multi-source heterogeneous, and there may be mutual coupling between the data, its rules are difficult to explore, resulting in low accuracy in data anomaly identification. Summary of the invention

[0005] The present invention provides a transformer oil chromatogram offline abnormal data identification method and system, which are used to solve the technical problem that most power equipment status data are multi-source heterogeneous and there may be mutual coupling between the data, resulting in low accuracy in data abnormality identification.

[0006] In a first aspect, the present invention provides a method for identifying off-line abnormal data of transformer oil chromatogram, comprising:

[0007] Acquire at least one transformer oil chromatogram data, and pre-process the at least one transformer oil chromatogram data to obtain at least one sample data;

[0008] Inputting the at least one sample data into a preset data feature selection model for training, and calculating the confidence of each sample data;

[0009] The sample data with confidence less than the preset threshold is subjected to explanatory analysis and counterfactual samples are generated. The predicted changes of the counterfactual samples are filtered out through the data feature selection model to obtain the boundary sample data. The expression of the explanatory analysis is:

[0010]

[0011] In the formula, φ i is the result contribution value of the original eigenvalue of the i-th sample, indicating the marginal contribution of the original eigenvalue of the i-th sample to the output of the data feature selection model. S is a subset of the feature combination, but does not include feature i. N is the set of all features. f(S∪{i}) is the output of prediction after adding feature i. f(S) is the output when only the features in subset S are used for prediction. |S| is the size of subset S. ! is the factorial symbol. ω s is the importance weight of feature subset S,

[0012] Removing boundary sample data from the at least one sample data to obtain at least one target sample data, and inputting the at least one target sample data into the data feature selection model for iterative training and model performance verification until the model performance reaches a preset condition, thereby obtaining an oil chromatogram offline abnormal data model;

[0013] Real-time transformer oil chromatogram data is acquired, and the real-time transformer oil chromatogram data is input into an oil chromatogram offline abnormal data model, and the oil chromatogram offline abnormal data model outputs a recognition result.

[0014] In a second aspect, the present invention provides a transformer oil chromatogram offline abnormal data identification system, comprising:

[0015] An acquisition module is configured to acquire at least one transformer oil chromatogram data, and pre-process the at least one transformer oil chromatogram data to obtain at least one sample data;

[0016] A calculation module, configured to input the at least one sample data into a preset data feature selection model for training, and calculate the confidence of each sample data;

[0017] The filtering module is configured to perform explanatory analysis on sample data with a confidence level less than a preset threshold and generate counterfactual samples, and filter out boundary sample data by using a data feature selection model to predict changes in the counterfactual samples, wherein the expression of the explanatory analysis is:

[0018]

[0019] In the formula, φ i is the result contribution value of the original eigenvalue of the i-th sample, indicating the marginal contribution of the original eigenvalue of the i-th sample to the output of the data feature selection model. S is a subset of the feature combination, but does not include feature i. N is the set of all features. f(S∪{i}) is the output of prediction after adding feature i. f(S) is the output when only the features in subset S are used for prediction. |S| is the size of subset S. ! is the factorial symbol. ω s is the importance weight of feature subset S,

[0020] a removal module configured to remove boundary sample data from the at least one sample data to obtain at least one target sample data, and input the at least one target sample data into the data feature selection model to iteratively train and verify model performance until the model performance reaches a preset condition, thereby obtaining an oil chromatogram offline abnormal data model;

[0021] The identification module is configured to obtain real-time transformer oil chromatogram data and input the real-time transformer oil chromatogram data into an oil chromatogram offline abnormal data model, and the oil chromatogram offline abnormal data model outputs an identification result.

[0022] In a third aspect, an electronic device is provided, comprising: 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 so that the at least one processor can perform the steps of the transformer oil chromatogram offline abnormal data identification method of any embodiment of the present invention.

[0023] In a fourth aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor executes the steps of the transformer oil chromatogram offline abnormal data identification method of any embodiment of the present invention.

[0024] The present invention discloses a transformer oil chromatogram offline abnormal data identification method and system, which effectively identifies and removes low-confidence and boundary samples through confidence screening and counterfactual sample generation, ensures that the model maintains reasonable sensitivity control on key features, and enhances the detection capability of abnormal data. With the help of model interpretability analysis and counterfactual sample generation, the model has stronger interpretability and robustness when identifying abnormal data. The overall method not only significantly improves the accuracy and reliability of fault diagnosis, but also realizes dynamic optimization of the model, so that it can efficiently identify potential false samples when receiving new data, thereby enhancing the accuracy of abnormal data identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0026] Figure 1 A flowchart of a transformer oil chromatogram offline abnormal data identification method provided by an embodiment of the present invention;

[0027] Figure 2 A structural block diagram of a transformer oil chromatogram offline abnormal data identification system provided by an embodiment of the present invention;

[0028] Figure 3 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0030] See also Figure 1 , which shows a flow chart of a transformer oil chromatogram offline abnormal data identification method of the present application.

[0031] like Figure 1 As shown, the transformer oil chromatogram offline abnormal data identification method specifically includes the following steps:

[0032] Step S101: acquiring at least one transformer oil chromatogram data, and preprocessing the at least one transformer oil chromatogram data to obtain at least one sample data.

[0033] In this step, the obtained transformer oil chromatogram data (the data content is the concentration of different oil chromatogram gases and the corresponding fault type) is preprocessed, including deleting missing values ​​and obvious outliers, selecting the contents of five characteristic gases, hydrogen, methane, ethane, ethylene, and acetylene, as key features, and standardizing these features. The expression for standardization is:

[0034]

[0035] In the formula, z i is the i-th sample after standardization, x i is the original eigenvalue of the i-th sample, μ is the mean of the feature, and σ is the standard deviation of the feature.

[0036] Step S102: input the at least one sample data into a preset data feature selection model for training, and calculate the confidence of each sample data.

[0037] In this step, the preprocessed data is divided into a training set and a validation set according to 80% and 20%, and the random forest model is used for preliminary training. The confidence of the random forest model on the validation set is recorded. The confidence is calculated as follows:

[0038] Confidence(x′ i )=max(P(y=c|x′ i )),

[0039] In the formula, (P(y=c|x′ i ) is the predicted sample x′ i The probability of belonging to class c.

[0040] Step S103, performing explanatory analysis on sample data with a confidence level less than a preset threshold and generating counterfactual samples, and filtering out boundary sample data from predicted changes of the counterfactual samples through a data feature selection model.

[0041] In this step, samples with a confidence level lower than 0.6 are screened out. Some of the screened sample data are shown in Table 1.

[0042] Table 1:

[0043]

[0044] The expression of explanatory analysis is:

[0045]

[0046] In the formula, φ iis the result contribution value of the original eigenvalue of the i-th sample, indicating the marginal contribution of the original eigenvalue of the i-th sample to the output of the data feature selection model. S is a subset of the feature combination, but does not include feature i. N is the set of all features. f(S∪{i} is the output of prediction after adding feature i. fS) is the output when only the features in subset S are used for prediction. |S| is the size of subset S. ! is the factorial symbol. ω s is the importance weight of feature subset S,

[0047] Step S104, removing the boundary sample data in the at least one sample data to obtain at least one target sample data, and inputting the at least one target sample data into the data feature selection model for iterative training and verification of model performance until the model performance reaches a preset condition, thereby obtaining an oil chromatogram offline abnormal data model.

[0048] In this step, at least one target sample data is input into the data feature selection model for iterative training; the trained data feature selection model is verified for model performance using the boundary sample stability index and the counterfactual consistency index, wherein the expression of the boundary sample stability index is:

[0049]

[0050] Where BS is the boundary sample stability index, N BS N is the number of stable boundary samples. TB is the total number of boundary samples;

[0051] The expression of the counterfactual consistency index is:

[0052]

[0053] Where CC is the counterfactual consistency index, N CP The number of samples whose model prediction categories do not change before and after the counterfactual sample generation, N TC is the total number of counterfactual samples.

[0054] Step S105, acquiring real-time transformer oil chromatogram data, and inputting the real-time transformer oil chromatogram data into an oil chromatogram offline abnormal data model, and the oil chromatogram offline abnormal data model outputs a recognition result.

[0055] In summary, the transformer oil chromatogram offline abnormal data identification method and system of the present application effectively identify and remove low-confidence and boundary samples through confidence screening and counterfactual sample generation, ensure that the model maintains reasonable sensitivity control on key features, and enhance the detection ability of abnormal data. With the help of model interpretability analysis and counterfactual sample generation, the model has stronger interpretability and robustness when identifying abnormal data. The overall method not only significantly improves the accuracy and reliability of fault diagnosis, but also realizes dynamic optimization of the model, so that it can efficiently identify potential false samples when receiving new data, thereby enhancing the accuracy of abnormal data identification.

[0056] See also Figure 2 , which shows a structural block diagram of a transformer oil chromatogram offline abnormal data identification system of the present application.

[0057] like Figure 2 As shown, the offline abnormal data identification system 200 includes an acquisition module 210 , a calculation module 220 , a filtering module 230 , a removal module 240 and an identification module 250 .

[0058] The acquisition module 210 is configured to acquire at least one transformer oil chromatogram data, pre-process the at least one transformer oil chromatogram data, and obtain at least one sample data;

[0059] The calculation module 220 is configured to input the at least one sample data into a preset data feature selection model for training, and calculate the confidence of each sample data;

[0060] The filtering module 230 is configured to perform an explanatory analysis on sample data with a confidence level less than a preset threshold and generate counterfactual samples, and filter out boundary sample data by using a data feature selection model to predict changes in the counterfactual samples, wherein the expression of the explanatory analysis is:

[0061]

[0062] In the formula, φ i is the result contribution value of the original eigenvalue of the i-th sample, indicating the marginal contribution of the original eigenvalue of the i-th sample to the output of the data feature selection model. S is a subset of the feature combination, but does not include feature i. N is the set of all features. f(S∪{i}) is the output of prediction after adding feature i. f(S) is the output when only the features in subset S are used for prediction. |S| is the size of subset S. ! is the factorial symbol. ω s is the importance weight of feature subset S,

[0063] The removal module 240 is configured to remove the boundary sample data in the at least one sample data to obtain at least one target sample data, and input the at least one target sample data into the data feature selection model to iteratively train and verify the model performance until the model performance reaches a preset condition, thereby obtaining an oil chromatogram offline abnormal data model;

[0064] The identification module 250 is configured to obtain real-time transformer oil chromatogram data, and input the real-time transformer oil chromatogram data into an oil chromatogram offline abnormal data model, and the oil chromatogram offline abnormal data model outputs an identification result.

[0065] It should be understood that Figure 2 Modules and references documented in Figure 1 Therefore, the operations and features described above for the method and the corresponding technical effects are also applicable to Figure 2 The modules in it will not be described in detail here.

[0066] In some other embodiments, the embodiments of the present invention further provide a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor is caused to execute the transformer oil chromatogram offline abnormal data identification method in any of the above method embodiments;

[0067] As an implementation mode, the computer-readable storage medium of the present invention stores computer-executable instructions, and the computer-executable instructions are configured as follows:

[0068] Acquire at least one transformer oil chromatogram data, and pre-process the at least one transformer oil chromatogram data to obtain at least one sample data;

[0069] Inputting the at least one sample data into a preset data feature selection model for training, and calculating the confidence of each sample data;

[0070] The sample data with confidence less than the preset threshold is subjected to explanatory analysis and counterfactual samples are generated. The predicted changes of the counterfactual samples are filtered out through the data feature selection model to obtain the boundary sample data. The expression of the explanatory analysis is:

[0071]

[0072] In the formula, φ iis the result contribution value of the original eigenvalue of the i-th sample, indicating the marginal contribution of the original eigenvalue of the i-th sample to the output of the data feature selection model. S is a subset of the feature combination, but does not include feature i. N is the set of all features. f(S∪{i}) is the output of prediction after adding feature i. f(S) is the output when only the features in subset S are used for prediction. |S| is the size of subset S. ! is the factorial symbol. ω s is the importance weight of feature subset S,

[0073] Removing boundary sample data from the at least one sample data to obtain at least one target sample data, and inputting the at least one target sample data into the data feature selection model for iterative training and model performance verification until the model performance reaches a preset condition, thereby obtaining an oil chromatogram offline abnormal data model;

[0074] Real-time transformer oil chromatogram data is acquired, and the real-time transformer oil chromatogram data is input into an oil chromatogram offline abnormal data model, and the oil chromatogram offline abnormal data model outputs a recognition result.

[0075] The computer-readable storage medium may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required by at least one function; the data storage area may store data created according to the use of the transformer oil chromatogram offline abnormal data identification system, etc. In addition, the computer-readable storage medium may include a high-speed random access memory, and may also include a memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the computer-readable storage medium may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the transformer oil chromatogram offline abnormal data identification system via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0076] Figure 3 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Figure 3 As shown, the device includes: a processor 310 and a memory 320. The electronic device may also include: an input device 330 and an output device 340. The processor 310, the memory 320, the input device 330 and the output device 340 may be connected via a bus or other means. Figure 3In the example, the bus connection is used. The memory 320 is the above-mentioned computer-readable storage medium. The processor 310 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory 320, that is, the transformer oil chromatogram offline abnormal data identification method of the above-mentioned method embodiment is realized. The input device 330 can receive input digital or character information, and generate key signal input related to user settings and function control of the transformer oil chromatogram offline abnormal data identification system. The output device 340 may include display devices such as display screens.

[0077] The electronic device can execute the method provided by the embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not described in detail in this embodiment, please refer to the method provided by the embodiment of the present invention.

[0078] As an implementation mode, the electronic device is applied to a transformer oil chromatogram offline abnormal data identification system, and is used for a client, and includes: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can:

[0079] Acquire at least one transformer oil chromatogram data, and pre-process the at least one transformer oil chromatogram data to obtain at least one sample data;

[0080] Inputting the at least one sample data into a preset data feature selection model for training, and calculating the confidence of each sample data;

[0081] The sample data with confidence less than the preset threshold is subjected to explanatory analysis and counterfactual samples are generated. The predicted changes of the counterfactual samples are filtered out through the data feature selection model to obtain the boundary sample data. The expression of the explanatory analysis is:

[0082]

[0083] In the formula, φ i is the result contribution value of the original eigenvalue of the i-th sample, indicating the marginal contribution of the original eigenvalue of the i-th sample to the output of the data feature selection model. S is a subset of the feature combination, but does not include feature i. N is the set of all features. f(S∪{i}) is the output of prediction after adding feature i. f(S) is the output when only the features in subset S are used for prediction. |S| is the size of subset S. ! is the factorial symbol. ω s is the importance weight of feature subset S,

[0084] Removing boundary sample data from the at least one sample data to obtain at least one target sample data, and inputting the at least one target sample data into the data feature selection model for iterative training and model performance verification until the model performance reaches a preset condition, thereby obtaining an oil chromatogram offline abnormal data model;

[0085] Real-time transformer oil chromatogram data is acquired, and the real-time transformer oil chromatogram data is input into an oil chromatogram offline abnormal data model, and the oil chromatogram offline abnormal data model outputs a recognition result.

[0086] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiment.

[0087] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for identifying abnormal data of transformer oil chromatogram offline, characterized in that: include: Acquire at least one transformer oil chromatogram data, and pre-process the at least one transformer oil chromatogram data to obtain at least one sample data; Inputting the at least one sample data into a preset data feature selection model for training, and calculating the confidence of each sample data; The sample data with confidence less than the preset threshold is subjected to explanatory analysis and counterfactual samples are generated. The predicted changes of the counterfactual samples are filtered out through the data feature selection model to obtain the boundary sample data. The expression of the explanatory analysis is: In the formula, φ i is the result contribution value of the original eigenvalue of the i-th sample, indicating the marginal contribution of the original eigenvalue of the i-th sample to the output of the data feature selection model. S is a subset of the feature combination, but does not include feature i. N is the set of all features. f(S∪{i}) is the output of prediction after adding feature i. f(S) is the output when only the features in subset S are used for prediction. |S| is the size of subset S. ! is the factorial symbol. ω s is the importance weight of feature subset S, Removing boundary sample data from the at least one sample data to obtain at least one target sample data, and inputting the at least one target sample data into the data feature selection model for iterative training and model performance verification until the model performance reaches a preset condition, thereby obtaining an oil chromatogram offline abnormal data model; Real-time transformer oil chromatogram data is acquired, and the real-time transformer oil chromatogram data is input into an oil chromatogram offline abnormal data model, and the oil chromatogram offline abnormal data model outputs a recognition result.

2. A transformer oil chromatogram offline abnormal data identification method according to claim 1, characterized in that: The preprocessing of the at least one compressor oil chromatogram data comprises: The at least one compressor oil chromatogram data is standardized, and the expression is: In the formula, z i is the i-th sample after standardization, x i is the original eigenvalue of the i-th sample, μ is the mean of the feature, and σ is the standard deviation of the feature.

3. A transformer oil chromatogram offline abnormal data identification method according to claim 1, characterized in that: The expression for calculating the confidence of each sample data is: Confidence(x′ i )=max(P(y=c|x′ i )), In the formula, (P(y=c|x′ i ) is the predicted sample x′ i The probability of belonging to class c.

4. A transformer oil chromatogram offline abnormal data identification method according to claim 1, characterized in that: The step of inputting the at least one target sample data into the data feature selection model for iterative training and verifying the model performance comprises: Inputting the at least one target sample data into the data feature selection model for iterative training; The boundary sample stability index and counterfactual consistency index are used to verify the performance of the trained data feature selection model. The expression of the boundary sample stability index is: Where BS is the boundary sample stability index, N BS N is the number of stable boundary samples. TB is the total number of boundary samples; The expression of the counterfactual consistency index is: Where CC is the counterfactual consistency index, N CP The number of samples whose model prediction categories do not change before and after the counterfactual sample generation, N TC is the total number of counterfactual samples.

5. A transformer oil chromatogram offline abnormal data identification system, characterized in that: include: An acquisition module is configured to acquire at least one transformer oil chromatogram data, and pre-process the at least one transformer oil chromatogram data to obtain at least one sample data; A calculation module, configured to input the at least one sample data into a preset data feature selection model for training, and calculate the confidence of each sample data; The filtering module is configured to perform explanatory analysis on sample data with a confidence level less than a preset threshold and generate counterfactual samples, and filter out boundary sample data by using a data feature selection model to predict changes in the counterfactual samples, wherein the expression of the explanatory analysis is: In the formula, φ i is the result contribution value of the original eigenvalue of the i-th sample, indicating the marginal contribution of the original eigenvalue of the i-th sample to the output of the data feature selection model. S is a subset of the feature combination, but does not include feature i. N is the set of all features. f(S∪{i}) is the output of prediction after adding feature i. f(S) is the output when only the features in subset S are used for prediction. |S| is the size of subset S. ! is the factorial symbol. ω s is the importance weight of feature subset S, a removal module, configured to remove boundary sample data from the at least one sample data to obtain at least one target sample data, and input the at least one target sample data into the data feature selection model for iterative training and model performance verification until the model performance reaches a preset condition, thereby obtaining an oil chromatogram offline abnormal data model; The identification module is configured to obtain real-time transformer oil chromatogram data and input the real-time transformer oil chromatogram data into an oil chromatogram offline abnormal data model, and the oil chromatogram offline abnormal data model outputs an identification result.

6. An electronic device, characterized in that: include: 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 method described in any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images