Method and device for analyzing importance of cost influence factors based on boosting tree

Abstract

The invention discloses a method and device for analyzing the importance of cost influence factors based on a boosting tree, and the method comprises the steps: obtaining a plurality of pieces of equipment collection data and corresponding labels, and enabling each piece of equipment collection data to comprise a plurality of cost influence factors which are connected with one another; preprocessing the equipment acquisition data to obtain a training data set; the training data set is input into a lifting tree model for training to obtain a trained importance analysis model, the lifting tree model initializes the weight according to the training data set, a decision tree of the lifting tree model is trained according to the weight, the weight is updated according to an error value of a prediction result after training is completed, and the importance analysis model is obtained. When an error value of a prediction result reaches a set threshold value, tree building is stopped; acquiring to-be-analyzed equipment acquisition data, and inputting the to-be-analyzed equipment acquisition data into the trained importance analysis model; therefore, the influence degree of the cost influence factor which is not easy to observe on the cost is obtained.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and particularly relates to an analysis method for the importance of cost impact factors based on boosting trees, a computer-readable storage medium, a computer device, and an analysis device for the importance of cost impact factors based on boosting trees. Background Art

[0002] In the related art, analyzing the impact of mine production data on costs to help business managers identify cost sources is an important part of mine production and intelligent construction. However, the operation of on-site equipment in mine production is complex, and the collected mine production data contains relatively complex interconnections and relatively unstable fluctuations. For example, the higher the vehicle load, the greater the fuel consumption, but the fewer the round-trip driving times, etc. It is difficult to observe the impact degree of such fine-grained data on costs, and thus it is difficult to directly observe the problem of the data distribution pattern. Summary of the Invention

[0003] The present invention aims to at least partly solve one of the technical problems in the above technologies. For this purpose, an object of the present invention is to propose an analysis method for the importance of cost impact factors based on boosting trees, which calculates the weights of data features used for decision-making in each decision tree through a boosting tree model, so as to obtain the impact degree of cost impact factors that are not easily observable on costs.

[0004] A second object of the present invention is to propose a computer-readable storage medium.

[0005] A third object of the present invention is to propose a computer device.

[0006] A fourth object of the present invention is to propose an analysis device for the importance of cost impact factors based on boosting trees.

[0007] To achieve the above object, an embodiment of the first aspect of the present invention provides an analysis method for the importance of cost impact factors based on boosting trees, including obtaining a plurality of device acquisition data and corresponding labels, where each device acquisition data includes a plurality of interrelated cost impact factors; preprocessing the device acquisition data to obtain a training data set; inputting the training data set into a boosting tree model for training to obtain a trained importance analysis model, where, during the training process, the boosting tree model initializes weights according to the training data set, and trains the decision trees of the boosting tree model according to the weights, and updates the weights according to the error value of the prediction result after training is completed to perform the training of the next decision tree, and stops building the tree when the error value of the prediction result reaches a set threshold; obtaining the device acquisition data to be analyzed, and inputting the device acquisition data to be analyzed into the trained importance analysis model to obtain the label corresponding to the device acquisition data to be analyzed and the importance ranking of each cost impact factor in the device acquisition data to be analyzed.

[0008] According to the analysis method for the importance of cost impact factors based on boosting trees of the embodiment of the present invention, first, a plurality of device acquisition data and corresponding labels are obtained, where each device acquisition data includes a plurality of interrelated cost impact factors; then, the device acquisition data is preprocessed to obtain a training data set; then, the training data set is input into a boosting tree model for training to obtain a trained importance analysis model, where, during the training process, the boosting tree model initializes weights according to the training data set, and trains the decision trees of the boosting tree model according to the weights, and updates the weights according to the error value of the prediction result after training is completed to perform the training of the next decision tree, and stops building the tree when the error value of the prediction result reaches a set threshold; finally, the device acquisition data to be analyzed is obtained, and the device acquisition data to be analyzed is input into the trained importance analysis model to obtain the label corresponding to the device acquisition data to be analyzed and the importance ranking of each cost impact factor in the device acquisition data to be analyzed; thus, the boosting tree model calculates the weights of the data features used for decision-making of each decision tree, so as to obtain the influence degree of the cost impact factors that are not easy to observe on the cost.

[0009] In addition, the analysis method for the importance of cost impact factors based on boosting trees proposed in the above embodiment of the present invention may further have the following additional technical features:

[0010] Optionally, preprocessing the device acquisition data to obtain a training data set includes: dividing the device acquisition data according to different dimensions; preprocessing the divided device acquisition data of different dimensions with different encodings to obtain a training data set; where the different dimensions after dividing the device acquisition data include device type, device working condition, device maintenance, and device cost elements.

[0011] Optionally, the multiple cost impact factors of the device type include mining cards, electric shovels, and drill types; the multiple cost impact factors of the device operating conditions include production conditions, standby conditions, and fault conditions; the multiple cost impact factors of the device maintenance include maintenance and overhaul; and the multiple cost impact factors of the device cost elements include fuel consumption, power consumption, maintenance material consumption, repair material consumption, and repair costs.

[0012] Optionally, the trained importance analysis model adds up the weights of each cost impact factor of each decision tree to obtain the weight of each cost impact factor; and the trained importance analysis model outputs the importance of each cost impact factor according to the weight of each cost impact factor.

[0013] To achieve the above object, an embodiment of the second aspect of the present invention provides a computer-readable storage medium, on which an analysis program for the importance of cost impact factors based on a boosting tree is stored. When the analysis program for the importance of cost impact factors based on a boosting tree is executed by a processor, the analysis method for the importance of cost impact factors based on a boosting tree as described above is implemented.

[0014] To achieve the above object, an embodiment of the third aspect of the present invention provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the analysis method for the importance of cost impact factors based on a boosting tree as described above is implemented.

[0015] To achieve the above object, an embodiment of the fourth aspect of the present invention provides an analysis device for the importance of cost impact factors based on a boosting tree, including an acquisition module for acquiring a plurality of device acquisition data and corresponding labels, where the device acquisition data includes a plurality of interrelated cost impact factors; a preprocessing module for preprocessing the device acquisition data to obtain a training data set; a model training module for inputting the training data set into a boosting tree model for training to obtain a trained importance analysis model. During the training process, the boosting tree model initializes weights according to the training data set, trains the decision trees of the boosting tree model according to the weights, updates the weights according to the error value of the prediction result after training is completed to perform the training of the next decision tree, and stops building the tree when the error value of the prediction result reaches a set threshold; and an analysis module for acquiring the device acquisition data to be analyzed and inputting the device acquisition data to be analyzed into the trained importance analysis model to obtain the label corresponding to the device acquisition data to be analyzed and the importance ranking of each cost impact factor in the device acquisition data to be analyzed.

[0016] In addition, the analysis device for the importance of cost impact factors based on boosting trees proposed in the above embodiments of the present invention may further have the following additional technical features:

[0017] Optionally, the preprocessing module is further configured to divide the device acquisition data according to different dimensions; preprocess the divided device acquisition data of different dimensions with different encodings to obtain a training data set; wherein, the different dimensions after the device acquisition data is divided include device type, device working condition, device maintenance, and device cost elements.

[0018] Optionally, the multiple cost impact factors of the device type include mining trucks, electric shovels, and drill rig types, the multiple cost impact factors of the device working condition include production working condition, standby working condition, and fault working condition, the multiple cost impact factors of the device maintenance include maintenance and overhaul maintenance, and the multiple cost impact factors of the device cost elements include fuel consumption, power consumption, maintenance material consumption, repair material consumption, and repair cost.

[0019] Optionally, the trained importance analysis model adds the weights of each cost impact factor of each decision tree to obtain the weight of each cost impact factor; the trained importance analysis model outputs the importance of each cost impact factor according to the weight of each cost impact factor. Description of the Drawings

[0020] Figure 1 It is a schematic flowchart of an analysis method for the importance of cost impact factors based on boosting trees according to an embodiment of the present invention;

[0021] Figure 2 It is a schematic structural diagram of a data acquisition system according to an embodiment of the present invention;

[0022] Figure 3 It is a schematic structural diagram of a cost impact factor analysis system according to an embodiment of the present invention;

[0023] Figure 4 It is a schematic diagram of the prediction results of each decision tree in the boosting tree according to an embodiment of the present invention;

[0024] Figure 5 It is a schematic block diagram of an analysis device for the importance of cost impact factors based on boosting trees according to an embodiment of the present invention. Detailed Embodiments

[0025] The embodiments of the present invention will be described in detail below. The examples of the embodiments are shown in the drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention.

[0026] To better understand the above technical solution, the exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present invention can be more thoroughly understood and the scope of the present invention can be completely conveyed to those skilled in the art.

[0027] To better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings of the specification and specific implementation manners.

[0028] Figure 1 It is a flowchart of an analysis method for the importance of cost impact factors based on boosting trees according to an embodiment of the present invention, as Figure 1 shown, the analysis method for the importance of cost impact factors based on boosting trees includes the following steps:

[0029] S101, Obtain a plurality of device acquisition data and corresponding labels, where each device acquisition data includes a plurality of interrelated cost impact factors.

[0030] As an embodiment, a plurality of device acquisition data are obtained through mine equipment sensors or manually, as Figure 2 shown, and the device acquisition data are sent to the cost analysis system through a wireless signal receiver; wherein, according to the time period of the uploaded data, various device acquisition data are divided by time, and are labeled with the corresponding increase / decrease / unchanged label of the cost relative to the previous time period (for example: year) according to the cost statistical time period, or directly use the cost value of the device in this time period as the label, so that the trained model can directly predict the cost of the device.

[0031] S102, Preprocess the device acquisition data to obtain a training data set.

[0032] As an embodiment, the device acquisition data are divided according to different dimensions; different encodings are used to preprocess the device acquisition data of different dimensions after division to obtain a training data set; wherein, the different dimensions after the device acquisition data are divided include device type, device working condition, device maintenance, and device cost elements.

[0033] It should be noted that the device acquisition data can be divided into different dimensions according to the actual on-site acquisition conditions, so as to obtain a data type that uniformly applies to the model input format through different encodings, thereby making a data set; whether to use all-dimensional data can be selected according to actual needs during training.

[0034] As an example, the multiple cost impact factors of equipment types include mining trucks, electric shovels, and drill rig types; the multiple cost impact factors of equipment operating conditions include production conditions, standby conditions, and fault conditions; the multiple cost impact factors of equipment maintenance include routine maintenance and major overhaul maintenance; the multiple cost impact factors of equipment cost elements include fuel consumption, power consumption, maintenance material consumption, repair material consumption, and repair costs.

[0035] It should be noted that the above corresponding cost impact factors are determined according to the requirements of on-site sensor collection. For example, according to the core processes of open-pit mining (drilling, loading, transportation, and pushing through) and the functions and uses of equipment, mobile equipment is divided into mining trucks, electric shovels, and drill rig types; according to the usage status of equipment, the equipment operating conditions are divided into production conditions, standby conditions, and fault conditions; according to the maintenance content of equipment, equipment maintenance is divided into routine maintenance and major overhaul maintenance; according to the cost composition of equipment, equipment cost elements are divided into fuel consumption, power consumption, maintenance material consumption, repair material consumption, and repair costs.

[0036] S103. Input the training data set into the boosting tree model for training to obtain a trained importance analysis model. During the training process, the boosting tree model initializes the weights according to the training data set, trains the decision trees of the boosting tree model according to the weights, updates the weights according to the error value of the prediction result after training is completed to train the next decision tree, and stops building the tree when the error value of the prediction result reaches the set threshold.

[0037] As an example, taking a single piece of equipment as the cost center, the model calculates the production cost statistics for specific equipment of different types, such as Figure 4 As shown, assuming that there are three cost impact factors in the data set, namely the first cost impact factor A, the second cost impact factor B, and the third cost impact factor C, there are four decision trees and corresponding prediction results in the boosting tree. The nodes of the decision tree represent judging a certain cost impact factor. The closer the node is to the root node, the greater the weight, and the more decision trees the node is selected by, the greater the weight.

[0038] S104. Obtain the equipment collection data to be analyzed, and input the equipment collection data to be analyzed into the trained importance analysis model to obtain the labels corresponding to the equipment collection data to be analyzed and the importance ranking of each cost impact factor in the equipment collection data to be analyzed.

[0039] As an example, the trained importance analysis model adds up the weights of each cost impact factor of each decision tree to obtain the weight of each cost impact factor; the trained importance analysis model outputs the importance of each cost impact factor according to the weight of each cost impact factor.

[0040] As a specific example, such as Figure 3As shown, input the data into the boosting tree; generate a decision tree based on the data; the boosting tree increases or decreases the weights of different trees according to the prediction error; repeat the above steps until the error rate is lower than the threshold; add up the weights of each cost impact factor of each decision tree in the boosting tree to obtain the weight of each cost impact factor in the boosting tree, and output the importance of each cost impact factor.

[0041] In summary, the data sent by the mining equipment, after being cleaned and encoded, is input into the boosting tree model (for example: XGBOOST); multiple decision trees in the boosting tree will sequentially predict which label the data belongs to (for example: cost increase / decrease / remain unchanged), one decision tree obtains the prediction probability, and the next tree predicts the error between the prediction probability of the previous tree and the true probability; multiple decision trees are continuously generated in this way, and then the results of all decision trees are summed, so that the final prediction probability can approximate the true probability; during the prediction process, the model will calculate the influence degree of each decision tree and decision node on the final prediction result, and finally calculate the importance of each feature of the input data to the prediction result. Among them, each feature of the input data is the cost impact factor.

[0042] To implement the above embodiments, an embodiment of the present invention also proposes a computer-readable storage medium, on which an analysis program for the importance of cost impact factors based on the boosting tree is stored. When the analysis program for the importance of cost impact factors based on the boosting tree is executed by a processor, the analysis method for the importance of cost impact factors based on the boosting tree as described above is implemented.

[0043] According to the computer-readable storage medium of the embodiment of the present invention, by storing the analysis program for the importance of cost impact factors based on the boosting tree, when the processor executes the analysis program for the importance of cost impact factors based on the boosting tree, the analysis method for the importance of cost impact factors based on the boosting tree as described above is implemented. Thus, the weight of the data features used for decision-making by each decision tree is calculated through the boosting tree model, so as to obtain the influence degree of the cost impact factors that are not easily observed on the cost.

[0044] To implement the above embodiments, an embodiment of the present invention proposes a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the analysis method for the importance of cost impact factors based on the boosting tree as described above is implemented.

[0045] A computer device according to an embodiment of the present invention stores an analysis program for the importance of cost impact factors based on a boosting tree in a memory, so that when the processor executes the analysis program for the importance of cost impact factors based on a boosting tree, the analysis method for the importance of cost impact factors as described above is implemented. Thus, the weight of the data features used for decision-making by each decision tree is calculated through the boosting tree model, and the impact degree of the cost impact factors that are not easily observable on the cost is obtained.

[0046] To implement the above embodiment, an embodiment of the present invention proposes an analysis device for the importance of cost impact factors based on a boosting tree, as Figure 5 shown. The analysis device for the importance of cost impact factors based on a boosting tree includes: an acquisition module 10, a preprocessing module 20, a model training module 30, and an analysis module 40.

[0047] Among them, the acquisition module 10 is used to acquire a plurality of device acquisition data and corresponding labels, where the device acquisition data includes a plurality of interrelated cost impact factors; the preprocessing module 20 is used to preprocess the device acquisition data to obtain a training data set; the model training module 30 is used to input the training data set into a boosting tree model for training to obtain a trained importance analysis model. During the training process, the boosting tree model initializes weights according to the training data set, and trains the decision trees of the boosting tree model according to the weights. After the training is completed, the weights are updated according to the error value of the prediction result to perform the training of the next decision tree, and the tree building stops when the error value of the prediction result reaches a set threshold; the analysis module 40 is used to acquire the device acquisition data to be analyzed, and input the device acquisition data to be analyzed into the trained importance analysis model to obtain the labels corresponding to the device acquisition data to be analyzed and the importance ranking of each cost impact factor in the device acquisition data to be analyzed.

[0048] Optionally, the preprocessing module 20 is further used to divide the device acquisition data according to different dimensions; different encodings are used to preprocess the device acquisition data of different divided dimensions to obtain a training data set; among them, the different dimensions after the device acquisition data is divided include device type, device working condition, device maintenance, and device cost elements.

[0049] Optionally, the multiple cost impact factors of the device type include mining trucks, electric shovels, and drill rig types, the multiple cost impact factors of the device working condition include production working condition, standby working condition, and fault working condition, the multiple cost impact factors of the device maintenance include maintenance and overhaul, and the multiple cost impact factors of the device cost elements include fuel consumption, power consumption, maintenance material consumption, repair material consumption, and repair cost.

[0050] Optionally, the trained importance analysis model adds up the weights of each cost impact factor of each decision tree to obtain the weight of each cost impact factor; the trained importance analysis model outputs the importance of each cost impact factor according to the weight of each cost impact factor.

[0051] It should be noted that the above description of the analysis method for the importance of cost impact factors based on boosting trees in Figure 1 also applies to the analysis device for the importance of cost impact factors based on boosting trees, and will not be elaborated here.

[0052] In summary, according to the analysis device for the importance of cost impact factors based on boosting trees in the embodiments of the present invention, the acquisition module acquires a plurality of device acquisition data and corresponding labels, wherein the device acquisition data includes a plurality of interrelated cost impact factors; the preprocessing module preprocesses the device acquisition data to obtain a training data set; the model training module inputs the training data set into the boosting tree model for training to obtain a trained importance analysis model. During the training process, the boosting tree model initializes the weights according to the training data set, and trains the decision trees of the boosting tree model according to the weights. After the training is completed, the weights are updated according to the error value of the prediction result to perform the training of the next decision tree, and the tree building stops when the error value of the prediction result reaches the set threshold; the analysis module acquires the device acquisition data to be analyzed, and inputs the device acquisition data to be analyzed into the trained importance analysis model to obtain the labels corresponding to the device acquisition data to be analyzed and the importance ranking of each cost impact factor in the device acquisition data to be analyzed; thus, the boosting tree model calculates the weights of the data features used for decision-making of each decision tree, so as to obtain the influence degree of the cost impact factors that are not easy to observe on the cost.

[0053] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0054] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, such that the instructions executed by the processor of the computer or other programmable data processing device generate means for implementing the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 or means for implementing the functions specified in multiple blocks.

[0055] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including instruction means that implement the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 or means for implementing the functions specified in multiple blocks.

[0056] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 or means for implementing the functions specified in multiple blocks.

[0057] It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in the claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention can be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In a unit claim listing several means, several of these means can be embodied by the same item of hardware. The use of the words first, second, and third, etc. does not denote any order. These words can be interpreted as names.

[0058] Although the preferred embodiments of the present invention have been described, additional changes and modifications can be made by those skilled in the art once they learn the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments and all changes and modifications falling within the scope of the present invention.

[0059] Obviously, those skilled in the art can make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

[0060] In the description of the present invention, it should be understood that the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present invention, "a plurality of" means two or more unless otherwise specifically defined.

[0061] In the present invention, unless otherwise clearly specified and defined, the terms such as "mounted", "connected", "connected to", "fixed" and the like should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or integrated; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0062] In the present invention, unless otherwise clearly specified and defined, the first feature being "on" or "under" the second feature may be that the first and second features are in direct contact, or the first and second features are indirectly in contact through an intermediate medium. Moreover, the first feature being "above", "over" and "on top of" the second feature may be that the first feature is directly above or obliquely above the second feature, or merely indicates that the first feature has a higher horizontal height than the second feature. The first feature being "under", "below" and "beneath" the second feature may be that the first feature is directly below or obliquely below the second feature, or merely indicates that the first feature has a lower horizontal height than the second feature.

[0063] In the description of this specification, the descriptions with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic descriptions of the above terms should not be understood as necessarily referring to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0064] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for analyzing the importance of cost influencing factors based on a boosting tree, characterized in that: The following steps are involved: Acquire multiple device collection data and corresponding labels, wherein each device collection data includes multiple interrelated cost impact factors; Preprocess the data collected by the device to obtain a training data set; The training data set is input into the boosting tree model for training to obtain a trained importance analysis model, wherein during the training process, the boosting tree model initializes weights according to the training data set, and trains the decision tree of the boosting tree model according to the weights, and after the training is completed, the weights are updated according to the error value of the prediction result to train the next decision tree, and the tree construction is stopped when the error value of the prediction result reaches a set threshold; The device collection data to be analyzed is obtained, and the device collection data to be analyzed is input into the trained importance analysis model to obtain labels corresponding to the device collection data to be analyzed and importance ranking of each cost influencing factor in the device collection data to be analyzed.

2. The method for analyzing the importance of cost impact factors based on a boosting tree according to claim 1, characterized in that: Preprocess the data collected by the device to obtain a training data set, including: Dividing the data collected by the device according to different dimensions; Different encodings are used to pre-process the equipment acquisition data of different dimensions after division to obtain a training data set; wherein the different dimensions after the equipment acquisition data is divided include equipment type, equipment working condition, equipment maintenance and equipment cost elements.

3. The method for analyzing the importance of cost impact factors based on a boosting tree according to claim 2, characterized in that: The multiple cost influencing factors of the equipment types include mining trucks, electric shovels and drilling rigs; the multiple cost influencing factors of the equipment operating conditions include production conditions, standby conditions and fault conditions; the multiple cost influencing factors of equipment maintenance include maintenance and overhaul maintenance; the multiple cost influencing factors of the equipment cost elements include fuel consumption, electricity consumption, maintenance material consumption, repair material consumption and maintenance costs.

4. The method for analyzing the importance of cost impact factors based on a boosting tree according to claim 1, characterized in that: The trained importance analysis model adds the weight of each cost influencing factor of each decision tree to obtain the weight of each cost influencing factor; The trained importance analysis model outputs the importance of each cost impact factor according to the weight of each cost impact factor.

5. A computer-readable storage medium, characterized in that: A program for analyzing the importance of cost impact factors based on a boosting tree is stored thereon, and when the program for analyzing the importance of cost impact factors based on a boosting tree is executed by a processor, the method for analyzing the importance of cost impact factors based on a boosting tree as described in any one of claims 1-4 is implemented.

6. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method for analyzing the importance of cost impact factors based on a boosting tree according to any one of claims 1 to 4 is implemented.

7. A device for analyzing the importance of cost impact factors based on a boosting tree, characterized in that: include An acquisition module, used to acquire a plurality of device collection data and corresponding labels, wherein the device collection data includes a plurality of interrelated cost impact factors; A preprocessing module is used to preprocess the data collected by the device to obtain a training data set; A model training module, used for inputting the training data set into the boosting tree model for training to obtain a trained importance analysis model, wherein during the training process, the boosting tree model initializes weights according to the training data set, and trains the decision tree of the boosting tree model according to the weights, and after the training is completed, the weights are updated according to the error value of the prediction result to train the next decision tree, and the tree construction is stopped when the error value of the prediction result reaches a set threshold; The analysis module is used to obtain the equipment collection data to be analyzed, and input the equipment collection data to be analyzed into the trained importance analysis model to obtain the label corresponding to the equipment collection data to be analyzed and the importance ranking of each cost influencing factor in the equipment collection data to be analyzed.

8. The device for analyzing the importance of cost impact factors based on a boosting tree according to claim 7, characterized in that: The preprocessing module is also used to divide the equipment collected data according to different dimensions; use different codes to preprocess the equipment collected data of different dimensions after division to obtain a training data set; wherein the different dimensions after the equipment collected data is divided include equipment type, equipment operating condition, equipment maintenance and equipment cost elements.

9. The device for analyzing the importance of cost impact factors based on a boosting tree according to claim 8, characterized in that: The multiple cost influencing factors of the equipment types include mining trucks, electric shovels and drilling rigs; the multiple cost influencing factors of the equipment operating conditions include production conditions, standby conditions and fault conditions; the multiple cost influencing factors of equipment maintenance include maintenance and overhaul maintenance; the multiple cost influencing factors of the equipment cost elements include fuel consumption, electricity consumption, maintenance material consumption, repair material consumption and maintenance costs.

10. The device for analyzing the importance of cost impact factors based on boosting tree according to claim 7, characterized in that: The trained importance analysis model adds the weight of each cost impact factor of each decision tree to obtain the weight of each cost impact factor; the trained importance analysis model outputs the importance of each cost impact factor according to the weight of each cost impact factor.

Images