Multi-dimensional query analysis method and system based on coal mine production operation data integration

Abstract

The invention discloses a multi-dimensional query analysis method and system based on coal mine production operation data integration, and relates to the technical field of data query analysis, and the method comprises the steps: collecting and preprocessing coal mine production data of different data sources, fusing the preprocessed data, and generating a coal mine data set; obtaining a distinguishing feature vector and a target variable of each type of data in the coal mine data set, and carrying out modeling according to the relevance of the distinguishing feature vector and the target variable to obtain a data query model; obtaining a business data demand of a user, determining a data attribute dimension according to the business data demand by using the data query model, and determining to-be-queried data based on the data attribute dimension; and extracting to-be-queried data from the coal mine data set, and analyzing a service decision and an optimization process according to a data change trend and a service development state. According to the method, the multi-source coal mine production data are integrated, the intelligent query model is established, efficient multi-dimensional data analysis is realized, and the data sharing and query efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data query and analysis, and in particular to a multi-dimensional query and analysis method and system based on coal mine production operation data integration. Background Art

[0002] At present, with the development of science and technology, the degree of modernization of coal mines is getting higher and higher, the number of systems in coal mines is gradually increasing, the number of data sources is also increasing, and the amount of coal mine data collected is also relatively large. Through the collection of information, we can better grasp the operation of each link of underground production. The coal mine field is composed of multiple business departments, and each business department will generate a large amount of coal mine data, and the file types of coal mine data from different business departments are mostly different. At present, the coal mine data generated by different business departments are stored separately, and due to the different file types, data sharing is difficult, and users need to query from different databases when querying, which is not only cumbersome but also inefficient, reducing the user experience. Summary of the invention

[0003] In view of the above-mentioned problems, the present invention is proposed.

[0004] Therefore, the technical problem solved by the present invention is: how to provide a multi-dimensional query and analysis method and system based on coal mine production operation data integration to solve the problem mentioned in the background technology that separate data storage makes data sharing difficult and users have cumbersome operations and low query efficiency when querying data, thereby reducing the user experience.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: a multi-dimensional query and analysis method based on coal mine production operation data integration, comprising: collecting coal mine production data from different data sources and preprocessing them, fusing the preprocessed data to generate a coal mine data set; obtaining distinguishing feature vectors and target variables for each type of data in the coal mine data set, modeling according to the correlation between the distinguishing feature vectors and the target variables, and obtaining a data query model; obtaining the user's business data requirements, determining the data attribute dimensions according to the business data requirements using the data query model, and determining the data to be queried based on the data attribute dimensions; extracting the data to be queried from the coal mine data set and analyzing business decisions and optimization processes based on data change trends and business development status.

[0006] As a preferred solution of the multi-dimensional query and analysis method based on coal mine production operation data integration described in the present invention, wherein: the coal mine production data from different data sources are collected and preprocessed, and the preprocessed data are merged to generate a coal mine data set, including: obtaining preset data requirements, and collecting required coal mine production data from the included data of different data sources according to the preset data requirements; performing data cleaning, deduplication and conversion preprocessing on the coal mine production data to obtain the preprocessed data; determining the data format of the preprocessed data, and selecting an adaptive open source data integration framework based on the data format; dividing the preprocessed data into multiple batches of data according to data attributes, and performing data fusion on the multiple batches of data through the open source data integration framework to generate a coal mine data set.

[0007] As a preferred solution of the multidimensional query and analysis method based on coal mine production operation data integration described in the present invention, wherein: the obtaining of distinguishing feature vectors and target variables for each type of data in the coal mine data set, modeling based on the correlation between the distinguishing feature vectors and the target variables, and obtaining a data query model, includes: performing principal component analysis on each type of data in the coal mine data set to obtain data features and data variables for each type of data, and determining the target variable of the distinguishing feature vector of the data based on the data features and data variables of each type of data; determining the associated business attributes of each type of data, and selecting an adaptive learning algorithm and deep learning model based on the associated business attributes; determining the correlation coefficient between the distinguishing feature vector and the target variable, determining the correlation index between the distinguishing feature vector and the target variable based on the correlation coefficient, and binding the distinguishing feature vector and the target variable based on the correlation index; training the deep learning model based on the learning algorithm using the bound distinguishing feature vectors and target variables, cross-validating the trained model, and obtaining the data query model after the validation.

[0008] As a preferred solution of the multi-dimensional query and analysis method based on coal mine production operation data integration described in the present invention, wherein: the user's business data needs are obtained, the data attribute dimensions are determined according to the business data needs using a data query model, and the data to be queried is determined based on the data attribute dimensions, including: obtaining the user's query request, determining the data source subject according to the query request, and determining the user's business data needs according to the data source subject; using the data query model to determine the data feature variables to be queried by the user according to the business data needs, and determining the filtering data range according to the data feature variables; determining data limitation conditions based on the business data needs, determining limitation condition parameters according to the data limitation conditions, and determining data attribute dimensions according to the limitation condition parameters; setting data tags for the data to be retrieved based on the data attribute dimensions, and determining the data to be queried within the filtering data range according to the data tags.

[0009] As a preferred solution of the multi-dimensional query and analysis method based on coal mine production operation data integration described in the present invention, wherein: the data to be queried is extracted from the coal mine data set and business decisions and optimization processes are analyzed based on data change trends and business development status, including: determining the data type of the data to be queried, selecting a data retrieval method based on the data type, and extracting the data to be queried from the coal mine data set based on the data retrieval method; performing data analysis on the data to be queried to determine the data change trend, and determining the business development situation based on the data change trend and the correlation parameters between the data to be queried and the business; obtaining expected situation parameters based on the business development status, determining current situation parameters based on the business development situation, and analyzing business decisions based on the current situation parameters and expected situation parameters; determining process indicators based on the data to be retrieved, performing normal gain evaluation on the process indicators and production indicators, determining process optimization items based on the evaluation results, and analyzing the optimized process based on the process optimization items.

[0010] To further solve the above technical problems, the present invention provides the following technical solutions: a multi-dimensional query and analysis system based on coal mine production operation data integration, including: a generation module, used to collect coal mine production data from different data sources and pre-process them, fuse the pre-processed data to generate a coal mine data set; a modeling module, used to obtain the distinguishing feature vectors and target variables of each type of data in the coal mine data set, modeling according to the correlation between the distinguishing feature vectors and the target variables, and obtain a data query model; a determination module, used to obtain the user's business data requirements, determine the data attribute dimensions according to the business data requirements using the data query model, and determine the data to be queried based on the data attribute dimensions; an analysis module, used to extract the data to be queried from the coal mine data set and analyze business decisions and optimization processes based on data change trends and business development status.

[0011] As a preferred solution of the multi-dimensional query and analysis system based on coal mine production operation data integration described in the present invention, the generation module includes: a collection submodule, which is used to obtain preset data requirements and collect the required coal mine production data from the data contained in different data sources according to the preset data requirements; a preprocessing submodule, which is used to perform data cleaning, deduplication and conversion preprocessing on the coal mine production data to obtain the preprocessed data; a first selection submodule, which is used to determine the data format of the preprocessed data and select an adaptive open source data integration framework based on the data format; a generation submodule, which is used to divide the preprocessed data into multiple batches of data according to data attributes, and fuse the multiple batches of data through the open source data integration framework to generate a coal mine data set.

[0012] As a preferred solution of the multi-dimensional query and analysis system based on coal mine production operation data integration described in the present invention, the modeling module includes: a first determination submodule, which is used to perform principal component analysis on each data in the coal mine data set to obtain data characteristics and data variables of each data, and determine the target variable of the distinguishing feature vector of this data according to the data characteristics and data variables of each data; a second selection submodule, which is used to determine the associated business attributes of each data, and select an adaptive learning algorithm and deep learning model according to the associated business attributes; a second determination submodule, which is used to determine the correlation coefficient between the distinguishing feature vector and the target variable, determine the correlation index between the distinguishing feature vector and the target variable according to the correlation coefficient, and bind the distinguishing feature vector and the target variable according to the correlation index; a model training and verification submodule, which is used to train the deep learning model based on the learning algorithm using the bound distinguishing feature vector and target variable, cross-validate the trained model, and obtain the data query model after verification.

[0013] A computer device includes a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, the steps of the multi-dimensional query and analysis method based on coal mine production operation data integration as described above are implemented.

[0014] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of the multi-dimensional query and analysis method based on coal mine production operation data integration as described above are implemented.

[0015] The beneficial effects of the present invention are as follows: by collecting and preprocessing coal mine production data from different data sources, the data is integrated into a unified coal mine data set, and then a data query model is established. According to the business needs of the user, the model is used to determine the data attribute dimensions and the data to be queried, and finally relevant data is extracted from the data set to analyze business decisions and optimize processes. This method realizes the efficient integration and query of coal mine production data, solves the problems of difficult data sharing, cumbersome query operations and low efficiency, and at the same time improves the accuracy and practicality of data analysis, providing strong support for the decision-making and process optimization of coal mine enterprises. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0017] Figure 1This is a workflow diagram of a multi-dimensional query and analysis method based on coal mine production operation data integration provided by the present invention. DETAILED DESCRIPTION

[0018] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0019] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0020] Example 1, reference Figure 1 , which is an embodiment of the present invention, provides a multi-dimensional query and analysis method based on coal mine production operation data integration, including:

[0021] S1: Collect coal mine production data from different data sources and preprocess them, then fuse the preprocessed data to generate a coal mine data set.

[0022] Specifically, in this embodiment, the coal mine production data from different data sources are represented by all statistical data sources of coal mine production, including: personnel information, equipment status, production volume, safety monitoring data, etc.

[0023] The working principle of the above technical solution is: collect coal mine production data from different data sources and preprocess them, merge the preprocessed data to generate a coal mine data set; obtain the distinguishing feature vectors and target variables of each type of data in the coal mine data set, model according to the correlation between the distinguishing feature vectors and the target variables, and obtain a data query model; obtain the user's business data needs, use the data query model to determine the data attribute dimensions according to the business data needs, and determine the data to be queried based on the data attribute dimensions; extract the data to be queried from the coal mine data set and analyze business decisions and optimization processes based on data change trends and business development status.

[0024] The beneficial effects of the above technical solution are: by fusing different data about coal mine production to generate a coal mine data set and then determining the distinguishing feature vectors and target variables of each data for modeling, the model can locate and query the adapted data according to the user's data retrieval needs and then analyze it to achieve data integration and storage, thereby improving data storage efficiency and data query efficiency, eliminating the need for tedious manual operations, improving practicality and user experience, and solving the problem mentioned in the prior art that separate data storage makes data sharing difficult and that users have cumbersome operations and low query efficiency when querying data, thereby reducing user experience.

[0025] In one embodiment, the coal mine production data from different data sources are collected and preprocessed, and the preprocessed data are merged to generate a coal mine data set, including:

[0026] Obtain preset data requirements, and collect required coal mine production data from data contained in different data sources according to the preset data requirements;

[0027] Perform data cleaning, deduplication and conversion preprocessing on coal mine production data to obtain preprocessed data;

[0028] Determine the data format of the preprocessed data and select an appropriate open source data integration framework based on the data format;

[0029] The preprocessed data is divided into multiple batches of data according to data attributes, and the multiple batches of data are fused through the open source data integration framework to generate a coal mine data set.

[0030] In this embodiment, the preset data requirement is expressed as what kind of data is needed in the coal mine production data, such as: personnel allocation data, equipment status data, equipment working data, daily coal production data, etc., which can be determined by the coal mine related data search items in the big database by the relevant users, or by comprehensively analyzing the historical production data of multiple coal mines to determine the key statistical data of all coal mines, and determine the data requirements according to the key statistical data;

[0031] In this embodiment, data cleaning includes: data outlier removal and data missing value supplementation, and data deduplication algorithms include but are not limited to hash algorithms, distributed deduplication algorithms, and cardinality estimation algorithms;

[0032] In this embodiment, data conversion means converting all coal mine production data into a unified data format, for example, into a picture format or a table format.

[0033] The beneficial effects of the above technical solution are: obtaining coal mine production data according to preset data requirements, preprocessing, selecting an adaptive open source data integration framework, and integrating the data. The data integration framework can ensure that a large amount of data can be merged into a single data set in the shortest time, which can save time and cost, and reduce the need for manual intervention. At the same time, it can ensure the data integrity and uniformity.

[0034] S2: Obtain the distinguishing feature vector and target variable of each data in the coal mine data set, build a model based on the correlation between the distinguishing feature vector and the target variable, and obtain a data query model.

[0035] Specifically, principal component analysis is performed on each data in the coal mine data set to obtain data features and data variables of each data, and the target variable of the distinguishing feature vector of each data is determined according to the data features and data variables of each data;

[0036] Determine the associated business attributes of each type of data, and select the appropriate learning algorithm and deep learning model based on the associated business attributes;

[0037] Determine the correlation coefficient between the distinguishing feature vector and the target variable, determine the association index between the distinguishing feature vector and the target variable according to the correlation coefficient, and bind the distinguishing feature vector and the target variable according to the association index;

[0038] Based on the learning algorithm, the deep learning model is trained using the bound distinguishing feature vector and target variable, and the trained model is cross-validated. After the validation, the data query model is obtained.

[0039] In this embodiment, principal component analysis is represented by performing key component analysis on the data components of each data;

[0040] In this embodiment, the associated business attributes are represented by business attributes corresponding to the related source business of each type of data;

[0041] In this embodiment, the correlation coefficient is determined based on the relative change weight between the distinguishing feature vector and the target variable;

[0042] In this embodiment, when training the deep learning model, the learning rate and training round hyperparameters are set according to the target variable frequency of the distinguishing feature vector, and the model training is performed by extracting learning features through the deep machine learning algorithm.

[0043] The beneficial effects of the above technical solution are: determining the data characteristics, data variables and related business attributes of each type of data, determining the correlation index between the distinguishing feature vector and the target variable, and binding them, training the deep learning model and performing cross-validation, which can better evaluate the model performance and ensure the reliability of the data query model. At the same time, it also ensures the screening accuracy of the divided data of each type of data, thereby improving work efficiency and stability.

[0044] S3: Obtain the user's business data requirements, use the data query model to determine the data attribute dimensions according to the business data requirements, and determine the data to be queried based on the data attribute dimensions.

[0045] Specifically, obtain the user's query request, determine the data source subject according to the query request, and determine the user's business data needs according to the data source subject;

[0046] Use the data query model to determine the data feature variables to be queried by the user according to the business data requirements, and determine the data filtering range based on the data feature variables;

[0047] Determine data limiting conditions based on business data requirements, determine limiting condition parameters based on the data limiting conditions, and determine data attribute dimensions based on the limiting condition parameters;

[0048] The data label of the data to be retrieved is set based on the data attribute dimension, and the data to be queried is determined within the filtered data range according to the data label.

[0049] The beneficial effects of the above technical solution are: determining the user's business data needs according to the user's query needs, and determining the data range, setting the data label of the data to be retrieved according to the data limitation condition parameters, so as to determine the data to be queried within the data range, which can improve the quality and accuracy of the acquired data. At the same time, setting data labels can improve the efficiency of querying data.

[0050] S4: Extract the data to be queried from the coal mine data set and analyze business decisions and optimize processes based on data change trends and business development status.

[0051] Specifically, determine the data type of the data to be queried, select a data retrieval method according to the data type, and extract the data to be queried from the coal mine data set based on the data retrieval method;

[0052] Analyze the data to be queried to determine the data change trend, and determine the business development situation based on the data change trend and the correlation parameters between the data to be queried and the business;

[0053] Obtain expected situation parameters according to the business development status, determine current situation parameters according to the business development situation, and analyze business decisions based on the current situation parameters and expected situation parameters;

[0054] Determine process indicators based on the data to be retrieved, conduct normal gain evaluation on process indicators and production indicators, determine process optimization items based on the evaluation results, and analyze the optimized process based on the process optimization items.

[0055] In this embodiment, the data types include: structured data, unstructured data, and time series data;

[0056] In this embodiment, the data retrieval method retrieves data based on the storage method of data according to the data type;

[0057] In this embodiment, the data change trend is determined by performing periodic sequence analysis on the data to determine the data indicator value change curve, and the data change trend is determined according to the change curve;

[0058] In this embodiment, the normal gain evaluation is expressed as a gain evaluation of the process index and the production index developing normally in the same direction.

[0059] The beneficial effects of the above technical solution are: selecting the data retrieval method according to the data type of the data to be queried can ensure the efficiency and accuracy of data acquisition, further determine the changing trend of the data to be queried, determine the business development situation in combination with the business correlation parameters, determine the process indicators of the data to be retrieved and perform normal gain evaluation, determine the process optimization items, and quickly identify the deficiencies of business decisions, ensure targeted process optimization, and ensure the reliability of the optimization results.

[0060] Embodiment 2 is an embodiment of the present invention, which provides a multi-dimensional query and analysis system based on coal mine production operation data integration, including a generation module, a modeling module, a determination module, and an analysis module.

[0061] The generation module is used to collect coal mine production data from different data sources and preprocess them, fuse the preprocessed data, and generate a coal mine data set.

[0062] Specifically, the generation module includes: a collection submodule, which is used to obtain preset data requirements and collect required coal mine production data from included data of different data sources according to the preset data requirements;

[0063] The preprocessing submodule is used to perform data cleaning, deduplication and conversion preprocessing on coal mine production data to obtain preprocessed data;

[0064] The first selection submodule is used to determine the data format of the preprocessed data and select an adaptive open source data integration framework based on the data format;

[0065] The generation submodule is used to divide the preprocessed data into multiple batches of data according to data attributes, and fuse the multiple batches of data through the open source data integration framework to generate a coal mine data set.

[0066] The modeling module is used to obtain the distinguishing feature vectors and target variables of each type of data in the coal mine data set, and to build a model based on the correlation between the distinguishing feature vectors and the target variables to obtain a data query model.

[0067] Specifically, the modeling module includes:

[0068] The first determination submodule is used to perform principal component analysis on each type of data in the coal mine data set to obtain data features and data variables of each type of data, and determine the target variable of the distinguishing feature vector of the data according to the data features and data variables of each type of data;

[0069] The second selection submodule is used to determine the associated business attributes of each type of data and select an adaptive learning algorithm and deep learning model according to the associated business attributes;

[0070] The second determination submodule is used to determine the correlation coefficient between the distinguishing feature vector and the target variable, determine the correlation index between the distinguishing feature vector and the target variable according to the correlation coefficient, and bind the distinguishing feature vector and the target variable according to the correlation index;

[0071] The model training and verification submodule is used to train the deep learning model based on the learning algorithm using the bound distinguishing feature vector and target variable, cross-validate the trained model, and obtain the data query model after the verification.

[0072] The determination module is used to obtain the user's business data requirements, use the data query model to determine the data attribute dimensions according to the business data requirements, and determine the data to be queried based on the data attribute dimensions.

[0073] Specifically, the determination module includes: a third determination submodule, which is used to obtain a query request from a user, determine a data source subject according to the query request, and determine the user's business data demand according to the data source subject;

[0074] A fourth determination submodule is used to determine the data feature variables to be queried by the user according to the business data requirements by using the data query model, and to determine the data range to be screened according to the data feature variables;

[0075] A fifth determination submodule is used to determine data limiting conditions based on business data requirements, determine limiting condition parameters according to the data limiting conditions, and determine data attribute dimensions according to the limiting condition parameters;

[0076] The sixth determination submodule is used to set data labels of the data to be retrieved based on the data attribute dimension, and determine the data to be queried within the filtered data range according to the data labels.

[0077] The analysis module is used to extract the data to be queried from the coal mine data set and analyze business decisions and optimize processes based on data change trends and business development status.

[0078] Specifically, the extraction submodule is used to determine the data type of the data to be queried, select a data retrieval method according to the data type, and extract the data to be queried from the coal mine data set based on the data retrieval method;

[0079] A seventh determination submodule is used to perform data analysis on the query data to determine the data change trend, and determine the business development trend based on the data change trend and the correlation parameters between the query data and the business;

[0080] The first analysis submodule is used to obtain expected situation parameters according to the business development status, determine the current situation parameters according to the business development situation, and analyze the business decision based on the current situation parameters and the expected situation parameters;

[0081] The second analysis submodule is used to determine the process indicators based on the data to be retrieved, perform normal gain evaluation on the process indicators and production indicators, determine the process optimization items based on the evaluation results, and analyze the optimized process based on the process optimization items.

[0082] Embodiment 3 is an embodiment of the present invention, which is different from the previous embodiment in that: if the function is implemented in the form of a software function unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0083] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0084] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0085] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0086] Example 4 is an embodiment of the present invention, which provides a multi-dimensional query and analysis method based on coal mine production operation data integration. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0087] In order to verify the effectiveness of the present invention, this embodiment designed a set of comparative experiments. This embodiment selected 5 coal mining enterprises of different sizes, and used the existing technical solutions and the present invention to carry out data integration, query and analysis for 3 months. During the experiment, this embodiment collected various key indicator data, including data integration time, query response time, data sharing efficiency, query accuracy, etc. At the same time, this embodiment also simulated a variety of complex business scenarios to test the analysis depth and decision support capabilities of the two methods.

[0088] During the experiment, this embodiment summarizes and analyzes the data every week, and conducts a final statistical comparison after the experiment. To ensure the reliability of the data, this embodiment adopts a cross-validation method, that is, two methods are used alternately in different time periods to eliminate the influence of other factors. In addition, this embodiment also conducts a user satisfaction survey and invites managers and data analysts at all levels to evaluate the system. The experimental results show that the present invention has achieved significant improvements in various indicators, especially in data integration efficiency, query response speed and analysis depth.

[0089] Table 1 Comparison of existing technologies

[0090]

[0091]

[0092] As shown in Table 1, the data integration time was shortened from 48 hours to 6 hours, an increase of 87.5%; the data query response time was reduced from 30 seconds to 5 seconds, an increase of 83.3%. These two items greatly improved the efficiency of data processing and access. The data sharing efficiency was increased by 58.3% to 95%, which greatly improved the information flow. The query accuracy rate was increased to 97%, an increase of 14.1%, providing more reliable data support. The data analysis depth increased from 2 dimensions to 5 dimensions, an increase of 150%, significantly enhancing the analysis capability. The decision support capability and system adaptability were improved from a low level to a high level, reflecting the comprehensive optimization of the system. User satisfaction increased from 70% to 92%, an increase of 31.4%, highlighting the practicality and ease of use of the new system. These data comprehensively reflect that the present invention has made significant progress in efficiency, accuracy, depth and user experience, providing strong technical support for data management and decision support of coal mining enterprises.

[0093] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A multi-dimensional query and analysis method based on coal mine production operation data integration, characterized in that: include: Collect coal mine production data from different data sources and preprocess them, then fuse the preprocessed data to generate a coal mine data set; Obtain the distinguishing feature vector and target variable of each data in the coal mine data set, build a model based on the correlation between the distinguishing feature vector and the target variable, and obtain a data query model; Obtain the user's business data requirements, use the data query model to determine the data attribute dimensions according to the business data requirements, and determine the data to be queried based on the data attribute dimensions; Extract the data to be queried from the coal mine data set and analyze business decisions and optimize processes based on data change trends and business development status.

2. The multi-dimensional query and analysis method based on coal mine production operation data integration according to claim 1, characterized in that: The coal mine production data from different data sources are collected and preprocessed, and the preprocessed data are merged to generate a coal mine data set, including: Obtain preset data requirements, and collect required coal mine production data from data contained in different data sources according to the preset data requirements; Perform data cleaning, deduplication and conversion preprocessing on coal mine production data to obtain preprocessed data; Determine the data format of the preprocessed data and select an appropriate open source data integration framework based on the data format; The preprocessed data is divided into multiple batches of data according to data attributes, and the multiple batches of data are fused through the open source data integration framework to generate a coal mine data set.

3. The multi-dimensional query and analysis method based on coal mine production operation data integration according to claim 2 is characterized in that: The method of obtaining a distinguishing feature vector and a target variable for each type of data in the coal mine data set, modeling according to the correlation between the distinguishing feature vector and the target variable, and obtaining a data query model includes: Perform principal component analysis on each data in the coal mine data set to obtain the data characteristics and data variables of each data, and determine the target variable of the distinguishing feature vector of each data according to the data characteristics and data variables of each data; Determine the associated business attributes of each type of data, and select the appropriate learning algorithm and deep learning model based on the associated business attributes; Determine the correlation coefficient between the distinguishing feature vector and the target variable, determine the association index between the distinguishing feature vector and the target variable according to the correlation coefficient, and bind the distinguishing feature vector and the target variable according to the association index; Based on the learning algorithm, the deep learning model is trained using the bound distinguishing feature vector and target variable, and the trained model is cross-validated. After the validation, the data query model is obtained.

4. The multi-dimensional query and analysis method based on coal mine production operation data integration according to claim 3 is characterized in that: The obtaining of the user's business data requirements, determining the data attribute dimensions according to the business data requirements using the data query model, and determining the data to be queried based on the data attribute dimensions include: Obtain the user's query request, determine the data source subject based on the query request, and determine the user's business data needs based on the data source subject; Use the data query model to determine the data feature variables to be queried by the user according to the business data requirements, and determine the data filtering range based on the data feature variables; Determine data limiting conditions based on business data requirements, determine limiting condition parameters based on the data limiting conditions, and determine data attribute dimensions based on the limiting condition parameters; The data label of the data to be retrieved is set based on the data attribute dimension, and the data to be queried is determined within the filtered data range according to the data label.

5. The multi-dimensional query and analysis method based on coal mine production operation data integration according to claim 4 is characterized in that: The method of extracting the data to be queried from the coal mine data set and analyzing the business decision and optimization process according to the data change trend and business development status includes: Determine the data type of the data to be queried, select a data retrieval method according to the data type, and extract the data to be queried from the coal mine data set based on the data retrieval method; Analyze the data to be queried to determine the data change trend, and determine the business development situation based on the data change trend and the correlation parameters between the data to be queried and the business; Obtain expected situation parameters according to the business development status, determine current situation parameters according to the business development situation, and analyze business decisions based on the current situation parameters and expected situation parameters; Determine process indicators based on the data to be retrieved, conduct normal gain evaluation on process indicators and production indicators, determine process optimization items based on the evaluation results, and analyze the optimized process based on the process optimization items.

6. A system using the multi-dimensional query and analysis method based on coal mine production operation data integration as described in any one of claims 1 to 5, characterized in that: include: The generation module is used to collect coal mine production data from different data sources and preprocess them, and fuse the preprocessed data to generate a coal mine data set; A modeling module is used to obtain the distinguishing feature vector and target variable of each data in the coal mine data set, and to perform modeling based on the correlation between the distinguishing feature vector and the target variable to obtain a data query model; The determination module is used to obtain the business data requirements of the user, determine the data attribute dimensions according to the business data requirements using the data query model, and determine the data to be queried based on the data attribute dimensions; The analysis module is used to extract the data to be queried from the coal mine data set and analyze business decisions and optimize processes based on data change trends and business development status.

7. The system of multi-dimensional query and analysis method based on coal mine production operation data integration according to claim 6, characterized in that: The generation module comprises: The collection submodule is used to obtain preset data requirements and collect the required coal mine production data from the included data of different data sources according to the preset data requirements; The preprocessing submodule is used to perform data cleaning, deduplication and conversion preprocessing on coal mine production data to obtain preprocessed data; The first selection submodule is used to determine the data format of the preprocessed data and select an adaptive open source data integration framework based on the data format; The generation submodule is used to divide the preprocessed data into multiple batches of data according to data attributes, and fuse the multiple batches of data through the open source data integration framework to generate a coal mine data set.

8. The system of multi-dimensional query and analysis method based on coal mine production operation data integration according to claim 7, characterized in that: The modeling module includes: The first determination submodule is used to perform principal component analysis on each type of data in the coal mine data set to obtain data features and data variables of each type of data, and determine the target variable of the distinguishing feature vector of the data according to the data features and data variables of each type of data; The second selection submodule is used to determine the associated business attributes of each type of data and select an adaptive learning algorithm and deep learning model according to the associated business attributes; The second determination submodule is used to determine the correlation coefficient between the distinguishing feature vector and the target variable, determine the correlation index between the distinguishing feature vector and the target variable according to the correlation coefficient, and bind the distinguishing feature vector and the target variable according to the correlation index; The model training and verification submodule is used to train the deep learning model based on the learning algorithm using the bound distinguishing feature vector and target variable, cross-validate the trained model, and obtain the data query model after the verification.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the multi-dimensional query and analysis method based on coal mine production operation data integration described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the multi-dimensional query and analysis method based on coal mine production operation data integration described in any one of claims 1 to 7 are implemented.

Images