Coal sample classification processing method and device, computer equipment and readable storage medium

Abstract

The invention relates to a coal sample classification processing method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring coal quality data of a plurality of coal samples corresponding to a plurality of coal quality parameters respectively; performing principal component analysis on the quality of the coal samples according to the coal quality data, and determining parameter data, corresponding to each coal sample, of the target parameter; the target parameters are represented by at least a part of the coal quality parameters; and according to the mapping position of each parameter data in the classification feature space, determining the coal sample category to which each coal sample belongs. By adopting the method, the classification processing accuracy of the coal samples can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of coal sample detection and analysis, and in particular to a coal sample classification processing method and device, computer equipment, a computer readable storage medium and a computer program product. BACKGROUND

[0002] With the development of coal sample detection and analysis technology, coal sample classification processing technology appears, which can classify and process raw coal and wind-oxidized coal caused by long-term exposure to the outside world, so as to mine and use them separately and improve the value of coal utilization.

[0003] In the traditional technology, the process of identifying the types of wind-oxidized coal and raw coal needs to sample along the coal seam from shallow to deep, and a series of unconventional chemical analysis and process property determination are performed on the sampling samples. Therefore, the traditional technology for coal sample classification processing has the problem of high cost. SUMMARY

[0004] Therefore, it is necessary to provide a coal sample classification processing method, device, computer equipment, computer readable storage medium and computer program product capable of reducing cost in view of the above technical problems.

[0005] In a first aspect, the present application provides a coal sample classification processing method, comprising:

[0006] Obtaining coal quality data corresponding to a plurality of coal quality parameters of a plurality of coal samples respectively;

[0007] Performing principal component analysis on the quality of the coal samples according to the coal quality data to determine parameter data corresponding to each of the coal samples, wherein the target parameters are represented by at least part of the coal quality parameters;

[0008] According to the mapping position of each of the parameter data in the classification feature space, determining the coal sample category to which each of the coal samples belongs.

[0009] In one of the embodiments, obtaining coal quality data corresponding to a plurality of coal quality parameters of a plurality of coal samples respectively, comprises:

[0010] Obtaining initial coal quality data corresponding to a plurality of coal quality parameters of a plurality of candidate coal samples respectively;

[0011] For each of the candidate coal samples, comparing each of the initial coal quality data of the candidate coal sample with the standard coal quality data corresponding to each of the initial coal quality data, to obtain a data comparison result of each of the initial coal quality data;

[0012] If at least one of the data comparison results does not satisfy the comparison condition, the candidate coal sample is rejected, and coal quality data of the coal samples corresponding to the coal quality parameters are obtained.

[0013] In one of the embodiments, if at least one of the data comparison results does not satisfy the comparison condition, the candidate coal sample is rejected, and coal quality data of the coal samples corresponding to the coal quality parameters are obtained, including:

[0014] If at least one of the data comparison results does not satisfy the comparison condition, the candidate coal sample is rejected, and cleaning data of the coal samples corresponding to the coal quality parameters are obtained.

[0015] The data mean and the data standard deviation of the cleaning data are determined.

[0016] For each of the cleaning data, the cleaning data is normalized according to the data mean and the data standard deviation, and the coal quality data corresponding to each of the cleaning data is obtained.

[0017] In one of the embodiments, principal component analysis is performed on the coal sample quality according to the coal quality data, and parameter data of a target parameter corresponding to each of the coal samples is determined, including:

[0018] Based on the coal quality data, an initial matrix corresponding to each of the coal samples is constructed, and each of the coal quality data corresponding to the same coal quality parameter is located in the same column in the initial matrix.

[0019] Based on a covariance matrix corresponding to the initial matrix, a plurality of eigenvalues and an eigenvector corresponding to each of the eigenvalues are determined.

[0020] According to the numerical value of each of the eigenvalues, each of the eigenvectors is arranged to form an eigenvector sequence.

[0021] According to a preset number condition matched with the target parameter, an eigenvector matrix is selected from the eigenvector sequence.

[0022] Based on the eigenvector matrix, the parameter data of the target parameter corresponding to each of the coal samples is determined.

[0023] In one of the embodiments, according to the mapping position of each of the parameter data in a classification feature space, a coal sample category to which each of the coal samples belongs is determined, including:

[0024] A classification feature space matched with the target parameter is determined.

[0025] For each coal sample, the parameter data corresponding to the target parameter of the coal sample is mapped to the classification feature space to determine the mapping position of the coal sample;

[0026] Clustering is performed on each of the aforementioned mapping locations to obtain multiple coal sample clusters;

[0027] Based on the coal sample cluster to which each coal sample belongs, the coal sample category to which each coal sample belongs is determined.

[0028] In one embodiment, clustering the mapped locations to obtain multiple coal sample clusters includes:

[0029] Two target coal samples are selected from each coal sample, and the target mapping position of the target coal sample is used as the initial cluster center to determine two coal sample clusters.

[0030] For each coal sample other than the target coal sample, the coal sample cluster to which the remaining coal sample belongs is determined from each coal sample cluster based on the spatial distance between the mapping position of the remaining coal sample and each of the target mapping positions.

[0031] Update the updated cluster centers of each coal sample cluster. If at least one updated cluster center is inconsistent with the initial cluster center, return to the step of selecting two target coal samples from each coal sample and using the target mapping position of the target coal samples as the initial cluster center.

[0032] Secondly, this application also provides a coal sample sorting and processing device, comprising:

[0033] The coal quality data acquisition module is used to acquire coal quality data corresponding to multiple coal quality parameters for multiple coal samples;

[0034] The parameter data determination module is used to perform principal component analysis on the coal sample quality based on the coal quality data of each coal sample, and determine the target parameters corresponding to the parameter data of each coal sample; the target parameters are characterized by at least a portion of the coal quality parameters.

[0035] The coal sample category determination module is used to determine the coal sample category to which each coal sample belongs based on the mapping position of each parameter data in the classification feature space.

[0036] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method described above.

[0037] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the method described above.

[0038] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the method described above.

[0039] The aforementioned coal sample classification and processing method, apparatus, computer equipment, computer-readable storage medium, and computer program product acquire coal quality data corresponding to multiple coal quality parameters for multiple coal samples. This allows for the determination of the coal quality parameters for each coal sample. Principal component analysis is performed on the coal sample quality based on the coal quality data to determine the target parameters corresponding to each coal sample. These target parameters are characterized by at least a portion of the coal quality parameters, identifying the most influential parameters on coal sample quality. Subsequent coal sample classification is then performed based on these target parameters, reducing unnecessary data processing. Finally, the coal sample category is determined based on the mapping position of each parameter data in the classification feature space. This allows for accurate classification of coal sample types without requiring complex chemical analysis of the acquired coal quality data, thereby reducing the cost of coal sample classification and processing. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 This is an application environment diagram of a coal sample classification and processing method in one embodiment;

[0042] Figure 2 This is a flowchart illustrating a coal sample classification and processing method in one embodiment;

[0043] Figure 3 This is a flowchart illustrating the implementation steps of principal component analysis in one embodiment;

[0044] Figure 4 This is a graph showing the intersection of the first target parameter and the second target parameter in one embodiment;

[0045] Figure 5 This is a schematic diagram of the K-means algorithm in one embodiment;

[0046] Figure 6This is a clustering result diagram of the mapped locations in one embodiment;

[0047] Figure 7 This is a flowchart illustrating the coal sample classification and processing method in another embodiment;

[0048] Figure 8 This is a flowchart illustrating the coal sample classification and processing method in yet another embodiment;

[0049] Figure 9 This is a structural block diagram of a coal sample sorting and processing device in one embodiment;

[0050] Figure 10 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0051] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0052] The coal sample classification and processing method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or located on the cloud or other network servers. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, projection devices, etc. Portable wearable devices can include smartwatches, smart bracelets, head-mounted devices, etc. Head-mounted devices can be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. Server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. Specifically, during the coal sample classification process, terminal 102 acquires coal quality data corresponding to multiple coal quality parameters for multiple coal samples and transmits it to server 104. Server 104 performs principal component analysis on the coal sample quality based on each coal quality data to determine the target parameters corresponding to the parameter data of each coal sample. The target parameters are characterized by at least a part of each coal quality parameter. Based on the mapping position of each parameter data in the classification feature space, the coal sample category to which each coal sample belongs is determined.

[0053] It should be noted that, provided the data processing capability of terminal 102 meets the requirements, terminal 102 can also implement the coal sample classification processing method of this application. Specifically, during the coal sample classification processing, terminal 102 can acquire coal quality data corresponding to multiple coal quality parameters for multiple coal samples; perform principal component analysis on the coal sample quality based on each coal quality data to determine the target parameters corresponding to the parameter data of each coal sample; the target parameters are characterized by at least a portion of each coal quality parameter; and determine the coal sample category to which each coal sample belongs based on the mapping position of each parameter data in the classification feature space.

[0054] In one exemplary embodiment, such as Figure 2 As shown, a method for classifying and processing coal samples is provided, which can be applied to... Figure 1 Taking server 104 as an example, the explanation includes:

[0055] Step S202: Obtain coal quality data for multiple coal samples corresponding to multiple coal quality parameters.

[0056] A coal sample refers to a representative portion of coal taken according to regulations to determine certain characteristics of the coal. Analyzing coal samples can determine the type and quality characteristics of the coal, as well as its processing and utilization characteristics and industrial applications.

[0057] Coal quality refers to the chemical properties and combustion performance of a coal sample. Coal quality parameters refer to the chemical property parameters and combustion performance parameters of a coal sample, such as apparent density, calorific value, ash content, total water content, volatile matter content, or major element parameters in the ash (Na₂O, K₂O, MgO, Al₂O₃, SiO₂, CaO, Fe₂O₃, P₂O₅, TiO₂). Coal quality data refers to the data of coal quality parameters of a coal sample. For example, if the measured ash content of a coal sample is 2.33%, then 2.33% is the coal quality data corresponding to the coal quality parameter of "ash content".

[0058] Specifically, to classify coal samples and ensure accuracy, it is necessary to acquire coal quality data for multiple coal samples corresponding to multiple coal quality parameters. With a sufficient number of coal samples and a wide variety of coal quality parameter types, the classification results obtained from the coal sample classification process can be guaranteed to have a certain accuracy. In one specific embodiment, initial coal quality data for multiple candidate coal samples corresponding to multiple coal quality parameters can be acquired first. Abnormal data in the initial coal quality data is then cleaned to obtain coal quality data for each coal sample corresponding to each coal quality parameter. In another specific embodiment, after cleaning abnormal data from the initial coal quality data, the cleaned data can be standardized to obtain coal quality data for each coal sample corresponding to each coal quality parameter.

[0059] Step S204: Perform principal component analysis on the coal sample quality based on the coal quality data to determine the target parameters corresponding to the parameter data of each coal sample.

[0060] Here, coal sample quality refers to the quality attributes of the coal sample. Target parameters are characterized by at least a portion of the various coal quality parameters. For example, target parameters might include 40% of the apparent density parameter, 20% of the calorific value parameter, ..., and 0.5% of the ash content parameter, etc. Parameter data refers to the parameter data corresponding to the target parameters.

[0061] Specifically, while analyzing coal quality data across multiple parameters can improve the accuracy of coal sample classification, it undoubtedly increases the workload of data collection to some extent. Furthermore, the potential correlation between many coal quality data points further complicates the classification process. Therefore, it is crucial to minimize the loss of data from the original coal quality parameters while reducing the number of parameters requiring analysis, thus achieving a comprehensive analysis of the collected coal quality data. That is, principal component analysis can be performed on the coal sample quality based on the individual coal quality data to determine the target parameters corresponding to each coal sample. It can be understood that the number of target parameters is less than the number of coal quality parameters, and the target parameters can be directly or indirectly represented by a portion of the coal quality parameters. For example, a target parameter can be one of the coal quality parameters or a parameter derived from a combination of multiple coal quality parameters.

[0062] In one specific embodiment, an initial matrix corresponding to each coal sample can be constructed based on the coal quality data. Coal quality data corresponding to the same coal quality parameter are located in the same column of the initial matrix. Based on the covariance matrix corresponding to the initial matrix, multiple eigenvalues ​​and their corresponding eigenvectors are determined. The eigenvectors are arranged according to the magnitude of the eigenvalues ​​to form an eigenvector sequence. According to a preset quantity condition matching the target parameter, eigenvectors are selected from the eigenvector sequence to form an eigenvector matrix. Based on the eigenvector matrix, the parameter data corresponding to each coal sample for the target parameter are determined. In another specific embodiment, a principal component analysis model can be established. Principal component analysis is performed on the coal quality data according to this model to determine the parameter data corresponding to each coal sample for the target parameter.

[0063] Step S206: Determine the coal sample category of each coal sample based on the mapping position of each parameter data in the classification feature space.

[0064] The classification feature space refers to the feature vector space used to classify coal samples. Its spatial dimension is determined by the number of target parameters. For example, if there are two target parameters, the classification feature space is two-dimensional, where the first target parameter corresponds to the x-axis and the second target parameter corresponds to the y-axis. The mapping position refers to the location of the parameter data in the feature vector space, which can be represented by coordinates. The coal sample category refers to the type of coal sample, such as raw coal or weathered coal.

[0065] Specifically, after determining the parameter data corresponding to each coal sample for the target parameters, the parameter data can be mapped into a classification feature space. Based on the positional differences of the parameter data in the classification feature space, the coal sample category to which each coal sample belongs is determined. In one specific embodiment, a classification feature space matching the target parameters can be determined. For each coal sample, the parameter data corresponding to the target parameters is mapped into the classification feature space to determine the mapping position of the coal sample. Clustering is performed on each mapping position to obtain multiple coal sample clusters. Based on the coal sample cluster to which each coal sample belongs, the coal sample category to which each coal sample belongs is determined. In another specific embodiment, the coal sample category to which each coal sample belongs can also be determined based on the mapping position characteristics of each parameter data in the classification feature space.

[0066] In the above-mentioned coal sample classification and processing method, coal quality data corresponding to multiple coal quality parameters for multiple coal samples are obtained. The coal quality parameters corresponding to each coal sample can be determined. Principal component analysis is performed on the coal sample quality based on each coal quality data to determine the target parameters corresponding to the parameter data of each coal sample. The target parameters are characterized by at least a part of each coal quality parameter, and the target parameters that have the greatest impact on the coal sample quality can be determined. Subsequent coal sample classification is performed based on the target parameters, reducing unnecessary data processing. Finally, based on the mapping position of each parameter data in the classification feature space, the coal sample category to which each coal sample belongs can be determined. The coal sample type can be accurately classified without the need for complex chemical analysis of the obtained coal quality data, thereby reducing the cost of coal sample classification and processing.

[0067] In an exemplary embodiment, obtaining coal quality data corresponding to multiple coal quality parameters for multiple coal samples includes: obtaining initial coal quality data corresponding to multiple candidate coal samples for multiple coal quality parameters; for each candidate coal sample, comparing each initial coal quality data of the candidate coal sample with the standard coal quality data corresponding to each initial coal quality data to obtain the data comparison result of each initial coal quality data; if at least one data comparison result does not meet the comparison condition, the candidate coal sample is removed to obtain coal quality data corresponding to multiple coal samples for multiple coal quality parameters.

[0068] Candidate coal samples refer to coal samples awaiting selection. Initial coal quality data refers to coal quality data in its initial state, without data processing. Standard coal quality data refers to coal quality data under standard conditions. Data comparison results can be used to characterize the comparison between initial coal quality data and standard coal quality data. Comparison conditions refer to the conditions that the data comparison results must meet, such as meeting a data comparison threshold.

[0069] Specifically, to improve the quality of coal quality data and thus the accuracy of coal sample classification, data cleaning can be performed on the initial coal quality data corresponding to multiple coal quality parameters for each candidate coal sample. Candidate coal samples with abnormal or duplicate initial coal quality data can be removed. In other words, initial coal quality data for multiple candidate coal samples corresponding to multiple coal quality parameters can be obtained. For each candidate coal sample, the initial coal quality data of the candidate coal sample is compared with the corresponding standard coal quality data to obtain the data comparison results for each initial coal quality data. If at least one data comparison result does not meet the comparison conditions, the initial coal quality data is considered abnormal, and the candidate coal sample corresponding to that initial coal quality data is removed. The remaining candidate coal sample data represents the coal quality data for each coal sample corresponding to multiple coal quality parameters.

[0070] In one specific embodiment, 28 coal samples were collected from the north side of an open-pit coal mine in the first ten days of a certain month. Based on the gloss level, the coal samples were categorized into five grades (dull to noticeably glossy) and numbered before being sent for testing. The tested coal quality parameters included conventional coal quality indicators (apparent density, calorific value, ash content, total moisture, volatile matter) and major elements in the ash (Na₂O, K₂O, MgO, Al₂O₃, SiO₂, CaO, Fe₂O₃, P₂O₅, TiO₂). Coal samples B1 and B2, whose coal types had been determined, were selected as standard samples for subsequent testing. The initial coal quality data for the various candidate coal samples corresponding to different coal quality parameters are shown in Tables 1 and 2.

[0071] Table 1 Physical properties and industrial analysis of coal samples

[0072]

[0073] Table 2. Major elemental analysis of coal ash content

[0074]

[0075] Table 3. Physical properties and industrial analysis of coal samples (after data cleaning)

[0076]

[0077] Table 4. Major elemental analysis of coal ash (after data cleaning)

[0078]

[0079] After the initial coal quality data was returned, its accuracy was checked, including whether the initial coal quality data was consistent with the characteristics of its corresponding standard coal quality data. Untested items, outliers (too large or too small), and duplicate standard coal quality data were removed to improve data quality. Based on historical data, the apparent density of raw coal is 1.26-1.42 g / cm³, and the apparent density of oxidized coal is 1.20-1.32 g / cm³, with a maximum calorific value on a dry basis of not less than 12.55 MJ / Kg. Coal samples M14, M15, M26, and M28 were discarded due to anomalies in apparent density and calorific value after the initial coal quality data was returned. In the analysis of major elements in coal ash, sample M13 had a SiO₂ content of 0, and sample M17 had a NaO₂ content of 0, indicating obvious errors, and were therefore discarded. The cleaned data are shown in Tables 3 and 4 above.

[0080] In this embodiment, cleaning the initial coal quality data can improve the quality of the coal quality data, thereby improving the accuracy of coal sample classification and processing.

[0081] In an exemplary embodiment, if at least one data comparison result does not meet the comparison conditions, the candidate coal sample is removed, resulting in multiple coal samples corresponding to multiple coal quality parameters. This includes: if at least one data comparison result does not meet the comparison conditions, the candidate coal sample is removed, resulting in multiple coal samples corresponding to multiple coal quality parameters; determining the data mean and data standard deviation of the cleaned data; and for each cleaned data, standardizing the cleaned data according to the data mean and data standard deviation to obtain the coal quality data corresponding to each cleaned data.

[0082] Here, "cleaned data" refers to the initial coal quality data that has undergone data cleaning and is free of outliers and duplicates. The data mean is the average of all cleaned data. The data standard deviation is the standard deviation of all cleaned data.

[0083] Specifically, to unify the dimensions, smooth the gradients between different batches and layers of data, prevent model gradient explosion, eliminate the negative impact of noisy data on the model, and prevent model overfitting, the cleaned data can be standardized. That is, if at least one data comparison result does not meet the comparison conditions, the candidate coal sample is removed. First, cleaned data corresponding to multiple coal samples and multiple coal quality parameters are obtained. Then, the mean and standard deviation of the cleaned data are determined, and each cleaned data is standardized using the mean and standard deviation to obtain the coal quality data corresponding to each cleaned data.

[0084] In one specific embodiment, Z-score standardization was chosen as the data standardization method. This method standardizes the data based on the mean and standard deviation of the original data. The standardized data fluctuates around 0, with values ​​greater than 0 indicating above-average performance and values ​​less than 0 indicating below-average performance. The coal quality data obtained after standardizing the clean data is shown in Table 5. Z-score standardization is a data processing method that transforms data by subtracting the dataset's mean (μ) from the data point values ​​and dividing by the standard deviation (σ), resulting in a dataset with zero mean and unit variance. This method is suitable for converting data with different magnitudes and units into comparable standard scores.

[0085] Table 5 Standardized data (dimensionless)

[0086]

[0087] In this embodiment, after the clean data is obtained through data cleaning, the clean data is also standardized to unify the dimensions of the coal quality data, making the subsequent analysis of the coal quality data simpler and more accurate.

[0088] In an exemplary embodiment, principal component analysis is performed on the coal sample quality based on the coal quality data to determine the target parameters corresponding to the parameter data of each coal sample. This includes: constructing an initial matrix corresponding to each coal sample based on the coal quality data; determining multiple eigenvalues ​​and their respective eigenvectors based on the covariance matrix corresponding to the initial matrix; arranging the eigenvectors according to the numerical value of each eigenvalue to form an eigenvector sequence; selecting eigenvectors from the eigenvector sequence to form an eigenvector matrix according to a preset quantity condition matching the target parameters; and determining the target parameters corresponding to the parameter data of each coal sample based on the eigenvector matrix.

[0089] In this matrix, coal quality data corresponding to the same coal quality parameter are located in the same column of the initial matrix. The initial matrix is ​​a matrix established for each coal sample based on the coal quality data. For example, the coal quality data can be arranged from left to right and from top to bottom according to the order of the coal samples to form the initial matrix. The process of determining the covariance matrix is ​​as follows: first, subtract the average value of the data in each column of the initial matrix to form a zero-mean matrix, and then determine the covariance matrix of this zero-mean matrix.

[0090] An eigenvector is a vector, while an eigenvalue is a scalar; their relationship can be represented using matrix multiplication in linear algebra. An eigenvector represents a direction invariant under matrix transformations, while an eigenvalue represents the scaling factor in that direction. An eigenvector sequence refers to a sequence of eigenvectors arranged sequentially. In this embodiment, the target parameter refers to the principal components, which may include, for example, the first principal component and the second principal component. Preset quantity conditions refer to pre-defined quantity conditions for the target parameter, such as one or two conditions. An eigenvector matrix is ​​a matrix composed of multiple eigenvectors.

[0091] Specifically, principal component analysis (PCA) is a dimensionality reduction method that retains the most important features from high-dimensional data while removing noise and unimportant features, thereby improving data processing speed. Therefore, an initial matrix can be constructed for each coal sample based on the coal quality data. Coal quality data corresponding to the same coal quality parameter are located in the same column of the initial matrix. Based on the covariance matrix of the initial matrix, multiple eigenvalues ​​and their corresponding eigenvectors are determined. The eigenvectors are then arranged according to the magnitude of the eigenvalues ​​to form an eigenvector sequence. Then, based on a pre-defined number of conditions matching the target parameter, eigenvectors are selected from the eigenvector sequence to form an eigenvector matrix. The selected eigenvector matrix is ​​the eigenvector matrix corresponding to the target parameter. Finally, based on the eigenvector matrix, the parameter data corresponding to each coal sample for the target parameter are determined.

[0092] In one specific embodiment, standardized dimensionless data can be used as input data for principal component analysis, such as... Figure 3 The steps for implementing principal component analysis are as follows:

[0093] Step S301: Arrange the coal quality data into an initial matrix X of m rows and n columns;

[0094] Step S302: Zero-mean normalize each column of X (representing a coal quality parameter), that is, subtract the mean of that column;

[0095] Step S303: Calculate the covariance matrix;

[0096] Step S304: Find the eigenvalues ​​of the covariance matrix and the corresponding eigenvectors r;

[0097] Step S305: Arrange the eigenvectors into a matrix from left to right according to the size of their corresponding eigenvalues, and take the first k columns to form matrix P;

[0098] Step S306: Calculate the parameter data reduced to k dimensions (k represents the preset number of conditions that match the target parameters).

[0099] Principal component analysis (PCA) is used to determine the eigenvalues ​​and eigenvectors of the covariance matrix of the initial matrix. The direction of the eigenvectors of the covariance matrix is ​​the projection direction required by PCA. Projecting the coal quality data to a lower dimension allows for better representation of the original data. A linear transformation is used to transform the coal quality dataset into a new coordinate system, ensuring that the largest variance of any projected coal quality data lies on the first coordinate (called the first principal component), the second largest variance on the second coordinate (the second principal component), and so on, thus reducing the dimensionality of the coal quality data. A total of 16 test data points are used, meaning a maximum of 16 principal components representing the overall dataset can be calculated. In practice, it is always desirable to maximize the variance of the coal quality data in the projected coordinate dimensions, thereby using fewer dimensions while retaining more dimensions of the original coal quality data. Therefore, the first principal component (PC1, the first objective parameter) and the second principal component (PC2, the second objective parameter) are selected as the overall dataset indicators. The data is shown in Table 6 below, and the intersection plot is shown below. Figure 4 .

[0100] Table 6 First Target Parameters, Second Target Parameters

[0101]

[0102] In this embodiment, after constructing the initial matrix and determining the covariance matrix, the eigenvectors are searched from the eigenvector sequence of the covariance matrix according to the preset quantity conditions that match the target parameters, and the parameter data corresponding to each coal sample are finally determined, which can improve the accuracy of principal component analysis of coal quality data.

[0103] In an exemplary embodiment, determining the coal sample category of each coal sample based on the mapping position of each parameter data in the classification feature space includes: determining the classification feature space that matches the target parameter; for each coal sample, mapping the parameter data of the coal sample corresponding to the target parameter to the classification feature space to determine the mapping position of the coal sample; clustering each mapping position to obtain multiple coal sample clusters; and determining the coal sample category of each coal sample based on the coal sample cluster to which each coal sample belongs.

[0104] Clustering is the process of classifying data into different classes or clusters. Therefore, objects within the same cluster have high similarity, while objects in different clusters have high dissimilarity. A coal sample cluster is a group of multiple coal samples with similar characteristics.

[0105] Specifically, each coal sample has parameter data corresponding to the target parameters. However, the parameter data lacks spatial features. Therefore, the parameter data can be mapped to a classification feature space that matches the target parameters, thus determining the mapping position of each coal sample. Then, clustering can be performed on each mapping position to divide each coal sample into its corresponding coal sample cluster, resulting in multiple coal sample clusters. Finally, based on the coal sample cluster to which each coal sample belongs, its respective coal sample category can be determined. It should be noted that this preset clustering algorithm can be either the K-means algorithm or the K-medoids algorithm.

[0106] Table 7 Results of coal sample classification and processing

[0107]

[0108] In a specific embodiment, as shown in Table 7, coal sample B1, identified as wind-oxidized coal, and coal sample B2, identified as raw coal, are verified using other detection methods based on the K-means algorithm calculation results. Coal sample B1 is located in the first coal sample cluster, and coal sample B2 is located in the second coal sample cluster. Since any two objects within the generated coal sample cluster have a high similarity, and any two objects outside the generated coal sample cluster have a high dissimilarity, it is determined that the coal sample in the first coal sample cluster is wind-oxidized coal, the same as coal sample B1, and the coal sample in the second coal sample cluster is raw coal, the same as coal sample B2.

[0109] In this embodiment, each coal sample is divided into coal sample clusters based on the mapping position of the parameter data of each coal sample in the classification feature space that matches the target parameters, thereby determining the coal sample category. This can effectively distinguish the types of coal samples and improve the accuracy of coal sample classification.

[0110] In an exemplary embodiment, clustering is performed on each mapped location to obtain multiple coal sample clusters, including: selecting two target coal samples from each coal sample, using the target mapped location of the target coal samples as the initial cluster center, and determining two coal sample clusters; for each remaining coal sample in each coal sample other than the target coal samples, determining the coal sample cluster to which the remaining coal samples belong from each coal sample cluster based on the spatial distance between the mapped location of the remaining coal samples and each target mapped location; updating the updated cluster center of each coal sample cluster, and if at least one updated cluster center is inconsistent with the initial cluster center, then returning to the step of selecting two target coal samples from each coal sample and using the target mapped location of the target coal samples as the initial cluster center.

[0111] In this context, the target coal sample refers to the coal sample selected as the target. The initial cluster center refers to the cluster center of the coal sample cluster determined in the initial state. The target mapping position is the mapping position of the target coal sample in the classification feature space. Spatial distance refers to the distance between the mapping positions of other coal samples and the target mapping position in the classification feature space. The updated cluster center refers to the average of the mapping positions of all coal samples in the coal sample cluster after determining all coal samples; this average value is the updated cluster center of the coal sample cluster.

[0112] Specifically, clustering is performed on each mapped location. The distance between each mapped location and the target mapped location can be calculated, and then clusters can be divided. The updated cluster centers of the clustered coal sample clusters are calculated. If the updated cluster centers are inconsistent with the initial cluster centers, the clustering steps are repeated until the final clustering result is obtained. That is, two target coal samples can be selected from each coal sample, and the target mapped locations of the target coal samples are used as the initial cluster centers to determine two coal sample clusters. For each coal sample other than the target coal samples, the coal sample cluster to which the remaining coal samples belong is determined based on the spatial distance between the mapped locations of the remaining coal samples and each target mapped location. The updated cluster centers of each coal sample cluster are updated. If at least one updated cluster center is inconsistent with the initial cluster center, the process returns to the step of selecting two target coal samples from each coal sample and using the target mapped locations of the target coal samples as the initial cluster centers.

[0113] In a specific embodiment, the K-means algorithm is used for clustering. K-means is a commonly used clustering algorithm. Clustering is the process of dividing data into multiple classes based on their "similarity." The subsets generated by clustering are called clusters, and any two objects within a cluster have a high degree of similarity. The principle of the K-means algorithm is as follows: Figure 5 As shown:

[0114] Step S501: Randomly select k coal samples as initial cluster centers;

[0115] Step S502: For the remaining coal samples, classify them into the nearest coal sample cluster based on their spatial distance from each initial cluster center;

[0116] Step S503: For each coal sample cluster, calculate the mean of all coal samples as the updated cluster center;

[0117] Step S504: Determine whether there is at least one updated cluster center that is inconsistent with the initial cluster center;

[0118] If so, return to step S501;

[0119] If not, proceed to step S505 to determine the final clustering result.

[0120] Based on the K-means algorithm, the first principal component (first objective parameter) and the second principal component (second objective parameter), which represent the comprehensive index of coal sample parameters, are used as input data. The calculation is performed with a given cluster size of 2 (raw coal and wind-oxidized coal). The calculation results are shown in Table 8 below. Based on the PC1-PC2 cross plot, clustering results are plotted for the first and second coal sample clusters as two sets of data, as shown in the figure below. Figure 6 ,Depend on Figure 6 The clustering results show that the two clusters are significantly different. The first coal sample cluster has fewer data points and is located in the upper right of the figure; the second coal sample cluster has more data points and is concentrated in the lower left of the figure.

[0121] Table 8 Clustering Results

[0122]

[0123] In this embodiment, by clustering each mapping location, multiple coal sample clusters with the greatest similarity within multiple clusters are finally determined, which can improve the accuracy of coal sample cluster division results.

[0124] In a specific embodiment, such as Figure 7 As shown, a method for classifying and processing coal samples is also provided, including:

[0125] Step S701: Take coal samples and conduct a semi-quantitative evaluation of the color and looseness of the coal samples on site. After packaging and numbering, send the samples for testing. The test items include multiple coal quality parameters (calorific value, ash content, total water, volatile matter) and major elements in ash (Na2O, K2O, MgO, Al2O3, SiO2, CaO, Fe2O3, P2O5, TiO2).

[0126] Step S702: Clean the initial coal quality data, check whether the initial coal quality data is consistent with the characteristics of its corresponding standard coal quality data, remove untested items, outliers that are too large or too small, and duplicate initial coal quality data to improve data quality.

[0127] Step S703: Standardize the cleaned data, unify the units, smooth the gradients between different batches and different layers of data, prevent gradient explosion in the model, eliminate the negative impact of noisy data on the model, and prevent the model from overfitting.

[0128] Step S704: Based on principal component analysis, the coal quality data are transformed into a new classification feature space through linear transformation, so that the first largest variance of any coal quality data projection is on the first coordinate (called the first principal component) and the second largest variance is on the second coordinate (the second principal component), thus reducing the dimensionality of the coal quality data.

[0129] Step S705: Based on the K-means algorithm, the first principal component and the second principal component, which reflect the quality of the coal sample, are used as input data. Given two computational clusters (raw coal and wind-oxidized coal), clustering calculation is performed.

[0130] Step S706: Determine the coal sample of the wind-oxidized coal through other detection methods, and verify the coal sample according to the calculation results of the K-means algorithm to determine the coal sample cluster to which the wind-oxidized coal belongs;

[0131] Step S707: Determine that the coal sample type of the coal sample in the coal sample cluster to which the wind-oxidized coal belongs is wind-oxidized coal.

[0132] In another specific embodiment, such as Figure 8 As shown, a method for classifying and processing coal samples is also provided, including:

[0133] Step S801: Obtain the initial coal quality data of multiple candidate coal samples corresponding to multiple coal quality parameters. For each candidate coal sample, compare the initial coal quality data of the candidate coal sample with the standard coal quality data corresponding to each initial coal quality data to obtain the data comparison results of each initial coal quality data.

[0134] Step S802: If at least one data comparison result does not meet the comparison conditions, the candidate coal sample is removed, and multiple coal samples are obtained, each corresponding to multiple coal quality parameters. The mean and standard deviation of the cleaned data are then determined.

[0135] Step S803: For each cleaning data, standardize the cleaning data according to the data mean and data standard deviation to obtain the coal quality data corresponding to each cleaning data. Based on each coal quality data, construct the initial matrix corresponding to each coal sample.

[0136] Among them, the coal quality data corresponding to the same coal quality parameter are located in the same column of the initial matrix;

[0137] Step S804: Based on the covariance matrix corresponding to the initial matrix, determine multiple eigenvalues ​​and the eigenvectors corresponding to each eigenvalue. Arrange the eigenvectors according to the magnitude of each eigenvalue to form an eigenvector sequence.

[0138] Step S805: According to the preset quantity conditions that match the target parameters, select feature vectors from the feature vector sequence to form a feature vector matrix. Based on the feature vector matrix, determine the parameter data corresponding to each coal sample for the target parameters.

[0139] The target parameters are characterized by at least a portion of the coal quality parameters.

[0140] Step S806: Determine the classification feature space that matches the target parameters. For each coal sample, map the parameter data of the coal sample corresponding to the target parameters to the classification feature space to determine the mapping position of the coal sample.

[0141] Step S807: Select two target coal samples from each coal sample, take the target mapping position of the target coal sample as the initial cluster center, and determine two coal sample clusters. For each coal sample other than the target coal sample, determine the coal sample cluster to which the remaining coal sample belongs from each coal sample cluster based on the spatial distance between the mapping position of the remaining coal sample and each target mapping position.

[0142] Step S808: Update the cluster centers of each coal sample cluster;

[0143] Step S809: Determine whether there is at least one updated cluster center that is inconsistent with the initial cluster center;

[0144] If so, return to step S807;

[0145] If not, proceed to step S810: determine the coal sample category of each coal sample based on the coal sample cluster to which each coal sample belongs.

[0146] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0147] Based on the same inventive concept, this application also provides a coal sample classification and processing device for implementing the coal sample classification and processing method described above. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more coal sample classification and processing device embodiments provided below can be found in the limitations of the coal sample classification and processing method above, and will not be repeated here.

[0148] In one exemplary embodiment, such as Figure 9 As shown, a coal sample classification and processing device 900 is provided, including: a coal quality data acquisition module 902, a parameter data determination module 904, and a coal sample category determination module 906, wherein:

[0149] The coal quality data acquisition module 902 is used to acquire coal quality data corresponding to multiple coal quality parameters for multiple coal samples;

[0150] The parameter data determination module 904 is used to perform principal component analysis on the coal sample quality based on each coal quality data to determine the target parameters corresponding to the parameter data of each coal sample; the target parameters are characterized by at least a portion of each coal quality parameter.

[0151] The coal sample category determination module 906 is used to determine the coal sample category to which each coal sample belongs based on the mapping position of each parameter data in the classification feature space.

[0152] In an exemplary embodiment, the coal quality data acquisition module 902 includes: an initial coal quality data acquisition unit, used to acquire initial coal quality data of multiple candidate coal samples corresponding to multiple coal quality parameters; a data comparison result determination unit, used to compare each initial coal quality data of each candidate coal sample with the standard coal quality data corresponding to each initial coal quality data to obtain the data comparison result of each initial coal quality data; and a coal quality data determination unit, used to remove the candidate coal sample if at least one data comparison result does not meet the comparison conditions, thereby obtaining coal quality data of multiple coal samples corresponding to multiple coal quality parameters.

[0153] In an exemplary embodiment, the coal quality data determination unit is specifically used to: if at least one data comparison result does not meet the comparison conditions, then remove the candidate coal sample to obtain cleaning data for multiple coal samples corresponding to multiple coal quality parameters; determine the data mean and data standard deviation of the cleaning data; and for each cleaning data, perform standardization processing on the cleaning data according to the data mean and data standard deviation to obtain the coal quality data corresponding to each cleaning data.

[0154] In an exemplary embodiment, the parameter data determination module 904 is specifically used for: constructing an initial matrix corresponding to each coal sample based on each coal quality data; each coal quality data corresponding to the same coal quality parameter is located in the same column of the initial matrix; determining multiple eigenvalues ​​and eigenvectors corresponding to each eigenvalue based on the covariance matrix corresponding to the initial matrix; arranging each eigenvector according to the numerical value of each eigenvalue to form a eigenvector sequence; selecting eigenvectors from the eigenvector sequence to form a eigenvector matrix according to a preset quantity condition matching the target parameter; and determining the parameter data corresponding to each coal sample for the target parameter based on the eigenvector matrix.

[0155] In an exemplary embodiment, the coal sample category determination module 906 includes: a classification feature space determination unit, used to determine a classification feature space that matches the target parameters; a mapping position determination unit, used to map the parameter data of the coal sample corresponding to the target parameters to the classification feature space for each coal sample, and determine the mapping position of the coal sample; a coal sample cluster determination unit, used to cluster each mapping position to obtain multiple coal sample clusters; and a coal sample category determination unit, used to determine the coal sample category to which each coal sample belongs based on the coal sample cluster to which each coal sample belongs.

[0156] In an exemplary embodiment, the coal sample cluster determination unit is specifically used for: selecting two target coal samples from each coal sample, using the target mapping position of the target coal samples as the initial cluster center, and determining two coal sample clusters; for each remaining coal sample in each coal sample other than the target coal samples, determining the coal sample cluster to which the remaining coal samples belong from each coal sample cluster based on the spatial distance between the mapping position of the remaining coal samples and each target mapping position; updating the updated cluster center of each coal sample cluster, and if at least one updated cluster center is inconsistent with the initial cluster center, returning to the step of selecting two target coal samples from each coal sample and using the target mapping position of the target coal samples as the initial cluster center.

[0157] Each module in the aforementioned coal sample sorting and processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0158] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 10As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a coal sample classification processing method. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0159] Those skilled in the art will understand that Figure 10 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0160] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described above.

[0161] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method.

[0162] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method described above.

[0163] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0164] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0165] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0166] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for classifying and processing coal samples, characterized in that, The method includes: Obtain coal quality data for multiple coal samples, each corresponding to a different coal quality parameter; Principal component analysis is performed on the coal sample quality based on the coal quality data of each coal sample to determine the target parameters corresponding to the parameter data of each coal sample; the target parameters are characterized by at least a portion of the coal quality parameters. Based on the mapping position of each parameter data in the classification feature space, the coal sample category to which each coal sample belongs is determined.

2. The method according to claim 1, characterized in that, The acquisition of coal quality data corresponding to multiple coal quality parameters for multiple coal samples includes: Obtain initial coal quality data for multiple candidate coal samples, each corresponding to multiple coal quality parameters; For each candidate coal sample, the initial coal quality data of the candidate coal sample are compared with the standard coal quality data corresponding to each initial coal quality data to obtain the data comparison results of each initial coal quality data. If at least one of the data comparison results does not meet the comparison conditions, the candidate coal sample is removed, resulting in multiple coal samples corresponding to multiple coal quality parameters.

3. The method according to claim 2, characterized in that, If at least one of the data comparison results does not meet the comparison conditions, the candidate coal sample is removed, resulting in coal quality data for multiple coal samples corresponding to multiple coal quality parameters, including: If at least one of the data comparison results does not meet the comparison conditions, the candidate coal sample is removed, and multiple coal samples are obtained, each corresponding to a multiple coal quality parameter. Determine the mean and standard deviation of the cleaning data; For each cleaning data point, the cleaning data is standardized based on the data mean and the data standard deviation to obtain the coal quality data corresponding to each cleaning data point.

4. The method according to claim 1, characterized in that, The step of performing principal component analysis on the coal sample quality based on the coal quality data of each coal sample to determine the target parameters corresponding to the parameter data of each coal sample includes: Based on the coal quality data, an initial matrix corresponding to each coal sample is constructed; the coal quality data corresponding to the same coal quality parameter are located in the same column of the initial matrix. Based on the covariance matrix corresponding to the initial matrix, multiple eigenvalues ​​and the eigenvectors corresponding to each eigenvalue are determined. The eigenvectors are arranged according to the magnitude of each eigenvalue to form a sequence of eigenvectors; According to a preset number of conditions that match the target parameters, feature vectors are selected from the feature vector sequence to form a feature vector matrix; Based on the feature vector matrix, the target parameters are determined to correspond to the parameter data of each coal sample.

5. The method according to claim 1, characterized in that, The step of determining the coal sample category of each coal sample based on the mapping position of each parameter data in the classification feature space includes: Determine the classification feature space that matches the target parameters; For each coal sample, the parameter data corresponding to the target parameter of the coal sample is mapped to the classification feature space to determine the mapping position of the coal sample; Clustering is performed on each of the aforementioned mapping locations to obtain multiple coal sample clusters; Based on the coal sample cluster to which each coal sample belongs, the coal sample category to which each coal sample belongs is determined.

6. The method according to claim 5, characterized in that, The clustering of each of the mapped locations yields multiple coal sample clusters, including: Two target coal samples are selected from each coal sample, and the target mapping position of the target coal sample is used as the initial cluster center to determine two coal sample clusters. For each coal sample other than the target coal sample, the coal sample cluster to which the remaining coal sample belongs is determined from each coal sample cluster based on the spatial distance between the mapping position of the remaining coal sample and each of the target mapping positions. Update the updated cluster centers of each coal sample cluster. If at least one updated cluster center is inconsistent with the initial cluster center, return to the step of selecting two target coal samples from each coal sample and using the target mapping position of the target coal samples as the initial cluster center.

7. A coal sample sorting and processing device, characterized in that, The device includes: The coal quality data acquisition module is used to acquire coal quality data corresponding to multiple coal quality parameters for multiple coal samples; The parameter data determination module is used to perform principal component analysis on the coal sample quality based on the coal quality data of each coal sample, and determine the target parameters corresponding to the parameter data of each coal sample; the target parameters are characterized by at least a portion of the coal quality parameters. The coal sample category determination module is used to determine the coal sample category to which each coal sample belongs based on the mapping position of each parameter data in the classification feature space.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A 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 steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images