Household urine smell monitoring method and device based on electronic nose

Abstract

The invention relates to the technical field of biomedical engineering, in particular to a household urine smell monitoring method and device based on an electronic nose. The method comprises the following steps: firstly, acquiring urine smell data of a current user, then preprocessing the urine smell data to obtain preprocessed data of urine smell, inputting the preprocessed data of urine smell into a trained recurrent neural network model to obtain a directional disease monitoring result, performing PCA analysis on the urine smell data, and obtaining a directional disease monitoring result. According to the method, a directional disease monitoring result is obtained, an overall disease monitoring result is obtained, a final monitoring result is determined according to the directional disease monitoring result and the overall disease monitoring result, through the configuration mode of organically combining PCA analysis and a recurrent neural network model, the disease of a user can be detected from multiple dimensions, the disease monitoring accuracy is remarkably improved, and the user experience is improved. And a more reliable basis is provided for health diagnosis of the user.

Description

Technical Field

[0001] The invention relates to the technical field of biomedical engineering, and in particular to a method and device for monitoring household urine odor based on an electronic nose. Background Art

[0002] Health status has always been a concern. Urine testing is one of the commonly used examination methods in pediatric clinical diagnosis. Urine contains a lot of information reflecting the physiological and pathological state of the body. Through the analysis of urine, a variety of diseases can be detected, such as urinary tract infection, kidney disease, diabetes, etc. Timely and accurate urine testing is of great significance for early detection of diseases, formulation of treatment plans and evaluation of treatment effects.

[0003] However, most of the time, hospitals only conduct urine tests when patients themselves realize that they are unwell, which is a serious lag, and few people can go to the hospital for urine tests regularly. Therefore, it is of great significance to develop a simple and convenient urine monitoring technology.

[0004] Studies have shown that physical changes caused by some diseases can cause changes in urine composition, ultimately leading to abnormal urine odor. Therefore, if the odor of urine can be monitored in real time, it will play a very important role in the early detection of some diseases.

[0005] Based on this, the present invention proposes a household urine odor monitoring method and device based on an electronic nose to solve the above technical problems. Summary of the invention

[0006] The present invention describes a method and device for monitoring urine odor at home based on an electronic nose, which can accurately monitor the user's symptoms.

[0007] According to a first aspect, the present invention provides a method for monitoring urine odor at home based on an electronic nose, the method comprising:

[0008] Get the urine odor data of the current user;

[0009] Preprocessing the urine odor data to obtain preprocessed urine odor data;

[0010] Inputting the pre-processed data of urine odor into a trained recurrent neural network model to obtain a directional disease monitoring result;

[0011] Performing PCA analysis on the urine odor data to obtain overall symptom monitoring results;

[0012] Based on the targeted symptom monitoring results and the overall symptom monitoring results, a final monitoring result is determined.

[0013] According to a second aspect, the present invention provides a household urine odor monitoring device based on an electronic nose, comprising:

[0014] an acquisition unit, configured to acquire urine odor data of a current user;

[0015] a first data processing unit, configured to pre-process the urine odor data to obtain pre-processed urine odor data;

[0016] A second data processing unit is configured to input the pre-processed data of urine odor into a trained recurrent neural network model to obtain a directional disease monitoring result;

[0017] A third data processing unit is configured to perform PCA analysis on the urine odor data to obtain an overall symptom monitoring result;

[0018] The fourth data processing unit is configured to determine a final monitoring result based on the targeted symptom monitoring result and the overall symptom monitoring result.

[0019] In a third aspect, an embodiment of this specification further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method described in any embodiment of this specification is implemented.

[0020] In a fourth aspect, an embodiment of the present specification further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed in a computer, the computer is caused to execute the method described in any embodiment of the present specification.

[0021] According to the household urine odor monitoring method and device based on electronic nose provided by the present invention, the present invention first obtains urine odor data of the current user, then pre-processes the urine odor data to obtain pre-processed data of urine odor, inputs the pre-processed data of urine odor into a trained recurrent neural network model to obtain a directional symptom monitoring result, performs PCA analysis on the urine odor data to obtain an overall symptom monitoring result, and determines the final monitoring result based on the directional symptom monitoring result and the overall symptom monitoring result. Through this configuration method of organically combining PCA analysis and recurrent neural network model, the present invention can detect the user's symptom from multiple dimensions, significantly improves the accuracy of symptom monitoring, and provides a more reliable basis for the user's health diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 paying creative work.

[0023] Figure 1 A schematic diagram of a process of a household urine odor monitoring method based on an electronic nose according to an embodiment is shown;

[0024] Figure 2 A schematic block diagram of a household urine odor monitoring device based on an electronic nose according to one embodiment is shown. DETAILED DESCRIPTION

[0025] The solution provided by the present invention is described below in conjunction with the accompanying drawings.

[0026] Figure 1 FIG. 1 is a flow chart of a method for monitoring urine odor in a household based on an electronic nose according to an embodiment. It is understood that the method can be performed by any device, equipment, platform, or device cluster with computing and processing capabilities. Figure 1 As shown, the method includes:

[0027] Step 100, obtaining urine odor data of the current user;

[0028] Step 102, preprocessing the urine odor data to obtain preprocessed urine odor data;

[0029] Step 104: input the pre-processed data of urine odor into the trained recurrent neural network model to obtain a directional disease monitoring result;

[0030] Step 106, performing PCA analysis on the urine odor data to obtain overall symptom monitoring results;

[0031] Step 108: Determine the final monitoring result based on the targeted symptom monitoring result and the overall symptom monitoring result.

[0032] In this embodiment, first, the urine odor data of the current user is obtained, and then the urine odor data is preprocessed to obtain preprocessed data of the urine odor, and the preprocessed data of the urine odor is input into the trained recurrent neural network model to obtain a directional disease monitoring result, and PCA analysis is performed on the urine odor data to obtain an overall disease monitoring result, and the final monitoring result is determined based on the directional disease monitoring result and the overall disease monitoring result. Through this configuration method of organically combining PCA analysis and recurrent neural network model, the present invention can detect the user's disease from multiple dimensions, significantly improve the accuracy of disease monitoring, and provide a more reliable basis for the user's health diagnosis.

[0033] In this embodiment, preprocessing may include dimensionality reduction, feature extraction and denoising. For example, an autoencoder may be used to perform nonlinear dimensionality reduction on the data, thereby reducing data complexity, extracting data features and eliminating the influence of noise. x For example, the autoencoder will implement the encoder h = f(x) and the decoder r = g(h), because the dimension h is larger than x The dimension is small, so the present invention can extract the key features in the urine odor information through the autoencoder and eliminate irrelevant noise information. After that, r and label y are input into the convolutional neural network, which can effectively realize the prediction and classification of the disease.

[0034] In this embodiment, urine odor data is collected by a multi-channel electronic nose, taking 8 channels as an example, wherein the sensor materials of each channel are respectively as shown in Table 1:

[0035] Table 1

[0036]

[0037]

[0038] In one embodiment of the present invention, PCA analysis is performed on urine odor data to obtain overall symptom monitoring results, including:

[0039] Performing dimension expansion processing on the urine odor data to obtain dimension-expanded urine odor data;

[0040] Based on the urine odor data after dimension expansion, a kernel function matrix is ​​determined;

[0041] Centralize the kernel function matrix to obtain a centralized kernel function matrix;

[0042] Based on the kernel function matrix after centralization, the characteristic matrix of urine odor data is determined;

[0043] Based on the characteristic matrix, determining the contribution index; wherein the contribution index includes a first contribution index and a second contribution index;

[0044] Based on the contribution indicators, the overall disease monitoring results are determined.

[0045] In this embodiment, the urine odor data y is subjected to dimension expansion processing to obtain the urine odor data after dimension expansion According to the urine odor data after dimension expansion, the kernel function matrix k = {k j},in, Then k is centralized. Where I is a The vector of And calculate the feature matrix for urine odor data:

[0046] In one embodiment of the present invention, the contribution index is determined by the following formula:

[0047]

[0048] Where, T 2 is the first contribution index, SPE is the second contribution index, t is the characteristic matrix of urine odor data, is the load matrix, is the kernel function matrix after centralization, is the square matrix corresponding to the load matrix.

[0049] In one embodiment of the present invention, based on the contribution index, determining the overall symptom monitoring result includes:

[0050] When the first contribution index is greater than the first preset threshold or the second contribution index is greater than the second preset threshold, determining the overall symptom monitoring result as the presence of an overall symptom;

[0051] When the first contribution index is less than or equal to the first preset threshold and the second contribution index is less than or equal to the second preset threshold, it is determined that the overall symptom monitoring result is that the overall symptom does not exist.

[0052] In this embodiment, those skilled in the art may customize the first preset threshold and the second preset threshold according to actual usage.

[0053] In one embodiment of the present invention, based on the targeted symptom monitoring results and the overall symptom monitoring results, determining the final monitoring results includes:

[0054] When the directional symptom monitoring result is that the directional symptom does not exist and the overall symptom monitoring result is that the overall symptom does not exist, determining that the final monitoring result is normal;

[0055] When the directional symptom monitoring result is that one or more directional symptoms exist and the overall symptom monitoring result is that the overall symptom exists, determining that the final monitoring result is abnormal, and taking the directional symptom monitoring result as the final monitoring result;

[0056] When the directional symptom monitoring result is that one or more directional symptoms exist and the overall symptom monitoring result is that the overall symptom does not exist, determining that the final monitoring result is abnormal, and taking the directional symptom monitoring result as the final monitoring result;

[0057] When the directional symptom monitoring result is that the directional symptom does not exist and the overall symptom monitoring result is that the overall symptom does not exist, it is determined that the final monitoring result is abnormal, and the overall symptom monitoring result is used as the final monitoring result.

[0058] In this embodiment, the overall monitoring can detect abnormal problems, but cannot determine the symptoms; the targeted symptom screening can detect the marked symptoms, but cannot screen out the symptoms that are not labeled in advance. Therefore, it is necessary to combine the two: when the targeted symptom monitoring result is that the targeted symptom does not exist and the overall symptom monitoring result is that the overall symptom does not exist, the final monitoring result is determined to be normal; when the targeted symptom monitoring result is that one or more targeted symptoms exist and the overall symptom monitoring result is that the overall symptom exists, the final monitoring result is determined to be abnormal, and the targeted symptom monitoring result is the final monitoring result; when the targeted symptom monitoring result is that one or more targeted symptoms exist and the overall symptom monitoring result is that the overall symptom does not exist, the final monitoring result is determined to be abnormal, and the targeted symptom monitoring result is the final monitoring result; when the targeted symptom monitoring result is that the targeted symptom does not exist and the overall symptom monitoring result is that the overall symptom does not exist, the final monitoring result is determined to be abnormal, and the overall symptom monitoring result is the final monitoring result, but the symptom does not belong to the symptom type that has been marked, and it is necessary to go to the hospital for follow-up diagnosis and determination.

[0059] In one embodiment of the invention, the targeted disorders include phenylketonuria, diabetes mellitus, methionine malabsorption syndrome, hypermethioninemia, hypermethioninemia, hypermethioninemia, trimethylaminuria, 3-methylcrotonylglycinuria, and cystinuria;

[0060] Urine odor data included phenylacetic acid, phenylacetic acid, short-chain fatty acids, hydroxybutyric acid, methyl sulfide, trimethylamine, β-hydroxyisovaleric acid, cadaverine, piperidine, putrescine, and pyrrolidine;

[0061] Among them, phenylketonuria corresponds to phenylacetic acid and phenylacetic acid, diabetes corresponds to short-chain fatty acids, methionine malabsorption syndrome corresponds to hydroxybutyric acid, methionine malabsorption syndrome, hypermethioninemia, hypermethioninemia and methyl sulfide correspond to, trimethylamineuria corresponds to trimethylamine, 3-methylcrotonylglycinuria corresponds to β-hydroxyisovaleric acid, and cystic aciduria corresponds to cadaverine, piperidine, putrescine, and pyrrolidine.

[0062] In this embodiment, when a human body has some pathological changes, the urine will have a specific odor, as shown in Table 2. As can be seen from Table 2, some diseases can be characterized by the concentration of odor.

[0063] Table 2

[0064]

[0065]

[0066] In one embodiment of the present invention, the trained recurrent neural network model is determined by the following steps:

[0067] Get historical data sets;

[0068] The initial recurrent neural network model is trained based on the historical data set to obtain a trained recurrent neural network model;

[0069] Among them, the initial recurrent neural network model is obtained by migrating data from the existing model.

[0070] In this embodiment, a historical data set is established by the data in Table 1, that is, the odor components (urine odor data) are labeled with corresponding diseases, and the initial recurrent neural network model is trained according to the historical data set to obtain a trained recurrent neural network model. In terms of model training, the initial recurrent neural network model used in the present invention is obtained by data migration with the help of an existing model. The recurrent neural network itself has unique advantages. Its information transmission and memory mechanism enable it to efficiently characterize the correlation between the urine odor state of each person and the time period. Transfer learning plays another key role. It can deeply mine universal features from the label data set and effectively apply these features to the training process of the personal disease model. The present invention uses the constructed historical data set to train the initial recurrent neural network model. After multiple rounds of training processes, the trained recurrent neural network model is finally successfully obtained. By organically combining the two methods of recurrent neural network and transfer learning, the present invention successfully realizes the migration of the model of the label data set to the personal disease model (i.e., the trained recurrent neural network model). More importantly, this model has the ability to describe the normal change characteristics of each person's urine odor over time, so as to accurately monitor the user's disease.

[0071] The historical data set comes from different patients and may not be applicable to everyone. For example, the urine concentration of some people is higher than that of most people. In addition, the urine condition of each person changes periodically over time. For example, the urine will be thicker and have a stronger smell in the morning. Therefore, the present invention adopts the technical solution of recurrent neural network + transfer learning to solve the above problems.

[0072] According to another embodiment, the present invention provides a household urine odor monitoring device based on an electronic nose. Figure 2 A schematic block diagram of a household urine odor monitoring device based on an electronic nose according to an embodiment is shown. It is understood that the device can be implemented by any device, equipment, platform and device cluster with computing and processing capabilities. Figure 2 As shown, the device includes: an acquisition unit 200, a first data processing unit 202, a second data processing unit 204, a third data processing unit 206, and a fourth data processing unit 208. The main functions of each component unit are as follows:

[0073] The acquisition unit 200 is configured to acquire urine odor data of the current user;

[0074] A first data processing unit 202 is configured to pre-process the urine odor data to obtain pre-processed urine odor data;

[0075] The second data processing unit 204 is configured to input the pre-processed data of urine odor into the trained recurrent neural network model to obtain a directional disease monitoring result;

[0076] The third data processing unit 206 is configured to perform PCA analysis on the urine odor data to obtain an overall symptom monitoring result;

[0077] The fourth data processing unit 208 is configured to determine a final monitoring result based on the targeted symptom monitoring result and the overall symptom monitoring result.

[0078] In one embodiment of the present invention, the third data processing unit 206 is configured to perform the following steps:

[0079] Performing dimension expansion processing on the urine odor data to obtain dimension-expanded urine odor data;

[0080] Determining a kernel function matrix based on the urine odor data after dimension expansion;

[0081] Centralizing the kernel function matrix to obtain a kernel function matrix after centralization;

[0082] Determining a feature matrix of urine odor data based on the kernel function matrix after the centralization process;

[0083] Based on the characteristic matrix, determining a contribution index; wherein the contribution index includes a first contribution index and a second contribution index;

[0084] Based on the contribution index, the overall symptom monitoring result is determined.

[0085] In one embodiment of the present invention, the contribution index is determined by the following formula:

[0086]

[0087] Where, T 2 is the first contribution index, SPE is the second contribution index, t is the characteristic matrix of the urine odor data, is the load matrix, is the kernel function matrix after the centralization process, is a square matrix corresponding to the load matrix.

[0088] In one embodiment of the present invention, determining the overall symptom monitoring result based on the contribution index includes:

[0089] When the first contribution index is greater than a first preset threshold or the second contribution index is greater than a second preset threshold, determining that the overall symptom monitoring result is the presence of an overall symptom;

[0090] When the first contribution index is less than or equal to the first preset threshold and the second contribution index is less than or equal to the second preset threshold, it is determined that the overall symptom monitoring result is that there is no overall symptom.

[0091] In one embodiment of the present invention, the fourth data processing unit 208 is configured to perform the following steps:

[0092] When the directional symptom monitoring result is that the directional symptom does not exist and the overall symptom monitoring result is that the overall symptom does not exist, determining that the final monitoring result is normal;

[0093] When the directional symptom monitoring result is that one or more directional symptoms exist and the overall symptom monitoring result is that an overall symptom exists, determining that the final monitoring result is abnormal, and taking the directional symptom monitoring result as the final monitoring result;

[0094] When the directional symptom monitoring result indicates that one or more directional symptoms exist and the overall symptom monitoring result indicates that there is no overall symptom, determining that the final monitoring result is abnormal, and using the directional symptom monitoring result as the final monitoring result;

[0095] When the directional symptom monitoring result is that a directional symptom does not exist and the overall symptom monitoring result is that an overall symptom does not exist, the final monitoring result is determined to be abnormal, and the overall symptom monitoring result is used as the final monitoring result.

[0096] In one embodiment of the present invention, the targeted disorders include phenylketonuria, diabetes, methionine malabsorption syndrome, hypermethioninemia, hypermethioninemia, hypermethioninemia, trimethylamineuria, 3-methylcrotonylglycinuria, and cystinuria;

[0097] The urine odor data include phenylacetic acid, phenylacetic acid, short-chain fatty acids, hydroxybutyric acid, methyl sulfide, trimethylamine, β-hydroxyisovaleric acid, cadaverine, piperidine, putrescine, and pyrrolidine;

[0098] Among them, phenylketonuria corresponds to phenylacetic acid and phenylacetic acid, diabetes corresponds to short-chain fatty acids, methionine malabsorption syndrome corresponds to hydroxybutyric acid, methionine malabsorption syndrome, hypermethioninemia, hypermethioninemia and methyl sulfide correspond to, trimethylamineuria corresponds to trimethylamine, 3-methylcrotonylglycinuria corresponds to β-hydroxyisovaleric acid, and cystic aciduria corresponds to cadaverine, piperidine, putrescine, and pyrrolidine.

[0099] In one embodiment of the present invention, the trained recurrent neural network model is determined by the following steps:

[0100] Get historical data sets;

[0101] Training the initial recurrent neural network model based on the historical data set to obtain the trained recurrent neural network model;

[0102] The initial recurrent neural network model is obtained by migrating data from an existing model.

[0103] According to another embodiment, there is also provided a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to execute a combination of Figure 1 The method described.

[0104] According to another embodiment of the present invention, there is also provided an electronic device, comprising a memory and a processor, wherein the memory stores an executable code, and when the processor executes the executable code, the Figure 1 The method described.

[0105] The various embodiments of the present invention are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0106] Those skilled in the art should be aware that in one or more of the above examples, the functions described in the present invention can be implemented by hardware, software, firmware or any combination thereof. When implemented by software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium.

[0107] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made on the basis of the technical solution of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for monitoring urine odor in a household based on an electronic nose, characterized in that: include: Get the urine odor data of the current user; Preprocessing the urine odor data to obtain preprocessed urine odor data; Inputting the pre-processed data of urine odor into a trained recurrent neural network model to obtain a directional disease monitoring result; Performing PCA analysis on the urine odor data to obtain overall symptom monitoring results; Based on the targeted symptom monitoring results and the overall symptom monitoring results, a final monitoring result is determined.

2. The method according to claim 1, characterized in that The PCA analysis of the urine odor data is performed to obtain the overall symptom monitoring results, including: Performing dimension expansion processing on the urine odor data to obtain dimension-expanded urine odor data; Determining a kernel function matrix based on the urine odor data after dimension expansion; Centralizing the kernel function matrix to obtain a kernel function matrix after centralization; Determining a feature matrix of urine odor data based on the kernel function matrix after the centralization process; Based on the characteristic matrix, determining a contribution index; wherein the contribution index includes a first contribution index and a second contribution index; Based on the contribution index, the overall symptom monitoring result is determined.

3. The method according to claim 2, characterized in that The contribution index is determined by the following formula: Where, T 2 is the first contribution index, SPE is the second contribution index, t is the characteristic matrix of the urine odor data, is the load matrix, is the kernel function matrix after the centralization process, is a square matrix corresponding to the load matrix.

4. The method according to claim 3, characterized in that Determining the overall symptom monitoring result based on the contribution index includes: When the first contribution index is greater than a first preset threshold or the second contribution index is greater than a second preset threshold, determining that the overall symptom monitoring result is the presence of an overall symptom; When the first contribution index is less than or equal to the first preset threshold and the second contribution index is less than or equal to the second preset threshold, it is determined that the overall symptom monitoring result is that there is no overall symptom.

5. The method according to claim 4, characterized in that The determining of the final monitoring result based on the targeted symptom monitoring result and the overall symptom monitoring result comprises: When the directional symptom monitoring result is that the directional symptom does not exist and the overall symptom monitoring result is that the overall symptom does not exist, determining that the final monitoring result is normal; When the directional symptom monitoring result is that one or more directional symptoms exist and the overall symptom monitoring result is that an overall symptom exists, determining that the final monitoring result is abnormal, and taking the directional symptom monitoring result as the final monitoring result; When the directional symptom monitoring result indicates that one or more directional symptoms exist and the overall symptom monitoring result indicates that there is no overall symptom, determining that the final monitoring result is abnormal, and using the directional symptom monitoring result as the final monitoring result; When the directional symptom monitoring result is that a directional symptom does not exist and the overall symptom monitoring result is that an overall symptom does not exist, the final monitoring result is determined to be abnormal, and the overall symptom monitoring result is used as the final monitoring result.

6. The method according to claim 5, characterized in that The targeted conditions include phenylketonuria, diabetes mellitus, methionine malabsorption syndrome, hypermethioninemia, hypermethioninemia, hypermethioninemia, trimethylaminuria, 3-methylcrotonylglycinuria, and cystinuria; The urine odor data include phenylacetic acid, phenylacetic acid, short-chain fatty acids, hydroxybutyric acid, methyl sulfide, trimethylamine, β-hydroxyisovaleric acid, cadaverine, piperidine, putrescine, and pyrrolidine; Among them, phenylketonuria corresponds to phenylacetic acid and phenylacetic acid, diabetes corresponds to short-chain fatty acids, methionine malabsorption syndrome corresponds to hydroxybutyric acid, methionine malabsorption syndrome, hypermethioninemia, hypermethioninemia and methyl sulfide correspond to, trimethylamineuria corresponds to trimethylamine, 3-methylcrotonylglycinuria corresponds to β-hydroxyisovaleric acid, and cystic aciduria corresponds to cadaverine, piperidine, putrescine, and pyrrolidine.

7. The method according to claim 6, characterized in that The trained recurrent neural network model is determined by the following steps: Get historical data sets; Training the initial recurrent neural network model based on the historical data set to obtain the trained recurrent neural network model; The initial recurrent neural network model is obtained by performing data migration on an existing model.

8. A household urine odor monitoring device based on an electronic nose, characterized in that: include: an acquisition unit, configured to acquire urine odor data of a current user; A first data processing unit is configured to pre-process the urine odor data to obtain pre-processed urine odor data; A second data processing unit is configured to input the pre-processed data of urine odor into a trained recurrent neural network model to obtain a directional disease monitoring result; A third data processing unit is configured to perform PCA analysis on the urine odor data to obtain an overall symptom monitoring result; The fourth data processing unit is configured to determine a final monitoring result based on the targeted symptom monitoring result and the overall symptom monitoring result.

9. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed in a computer, the computer is caused to execute the method according to any one of claims 1 to 7.

Images