Industrial production data model construction method and system based on coal mine enterprise production data

Abstract

The invention relates to the technical field, and discloses an industry production data model construction method and system based on coal mine enterprise production data, and the method comprises the steps: obtaining all types of production data of all production regions of a coal mine enterprise in a preset time period; analyzing regional gradient features and time sequence gradient features of each type of production data; and analyzing data relationships in all types of production data of all production areas in the coal mine enterprise in a preset time period to obtain data entity connection features, and generating a multi-dimensional data model of the production data of the coal mine enterprise. According to the method, the regional gradient features and the time sequence gradient features of all types of production data in the coal mine enterprise are combined with the entity connection features in all types of production data in all production regions in the coal mine enterprise in the preset time period, so that the multi-dimensional data model capable of accurately reflecting the coal mine production law and trend is constructed; more comprehensive decision support is provided for the coal mine industry, and production optimization and safety management of coal mine enterprises are assisted.

Description

Technical Field

[0001] The present invention relates to the technical field of data models, and in particular to a method and system for constructing an industry production data model based on production data of coal mining enterprises. Background Art

[0002] At present, in the process of building an industry production data model based on the production data of coal mining enterprises, existing technologies provide strong support for data analysis and prediction. The following are several commonly used technologies and methods: machine learning, data mining, deep learning, big data platform, etc. The existing technologies and methods provide us with a wealth of choices for building an industry production data model based on the production data of coal mining enterprises. We can choose appropriate tools and technologies according to specific tasks and data characteristics, so as to achieve more accurate and efficient prediction and optimization.

[0003] However, the existing industry production data models for coal mining enterprise production data often only consider the data characteristics of a single type of data that changes over time or changes over regions. The production laws and trends of coal mining enterprises can only be represented by a single-dimensional data model, and it is impossible to present a multi-dimensional data model to represent the production laws and trends of coal mining enterprises. As a result, the dimensions of the represented production laws and trends are too thin, which is not conducive to the all-round decision-making of coal mining enterprises' production optimization and safety management. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the above existing problems, the present invention is proposed. Therefore, the present invention provides a method for constructing an industry production data model based on production data of coal mining enterprises to solve the problem that a multi-dimensional data model cannot be presented to represent the production laws and trends of coal mining enterprises.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a method for constructing an industry production data model based on production data of a coal mining enterprise, comprising: obtaining all types of production data of all production areas of the coal mining enterprise within a preset time period;

[0008] Based on the acquired data, analyze the regional and temporal gradient characteristics of each type of production data;

[0009] Analyze the data relationships among all types of production data in all production areas within a coal mining enterprise within a preset period of time to obtain data entity connection characteristics;

[0010] Based on the data entity connection characteristics and the regional gradual change characteristics and time series gradual change characteristics of each type of production data, a multi-dimensional data model of the coal mining enterprise production data is generated.

[0011] As a preferred solution of the method for constructing an industry production data model based on coal mining enterprise production data of the present invention, the analysis of regional gradual change characteristics and temporal gradual change characteristics of each type of production data includes:

[0012] Analyze the local time series gradual change characteristics of each type of production data in each production area;

[0013] Based on the local time series gradual change feature, obtaining the time series gradual change feature of each type of production data;

[0014] Obtain a GIS map of a coal mining enterprise, mark each type of production data and the corresponding local time-series gradient characteristics of each production area in the corresponding production area in the GIS map of the coal mining enterprise, and obtain a distribution map of the production data of the coal mining enterprise;

[0015] Based on the production data distribution map of the coal mining enterprise, the regional gradient characteristics of each type of production data are analyzed.

[0016] As a preferred solution of the method for constructing an industry production data model based on coal mining enterprise production data of the present invention, the analysis of the local temporal gradient characteristics of each type of production data in each production area includes:

[0017] Extract all attribute values ​​of each entity attribute of each data entity within a preset time period from each type of production data in each production area;

[0018] Calculate the growth ratio between all adjacent attribute values ​​of each entity attribute in all attribute values ​​within a preset period, sort them in time series, obtain the growth ratio sequence of each entity attribute, and use it as the local time series gradual change feature of the corresponding class production data of the corresponding production area;

[0019] Among them, all attribute values ​​of each entity attribute within a preset time period are the corresponding class production data in the corresponding production area, and the number of entity attributes is the same as the total number of classes of production data.

[0020] As a preferred solution of the method for constructing an industry production data model based on coal mining enterprise production data of the present invention, the method of obtaining the temporal gradient characteristics of each type of production data includes:

[0021] Among all production areas in the coal mining enterprise, all production areas containing the same type of production data are screened out as all coverage areas of the corresponding type of production data;

[0022] In the local time series gradual change characteristics of each type of production data in each production area, the growth ratio sequence of each entity attribute is obtained;

[0023] Calculate the similarity between the growth ratio series of every two coverage areas of each type of production data, and determine the correlation coefficient between every two coverage areas;

[0024] Based on the correlation coefficient between every two coverage areas of each type of production data, the local time-series gradual change features of all coverage areas of each type of production data are merged to obtain the time-series gradual change features of each type of production data.

[0025] As a preferred solution of the method for constructing an industry production data model based on coal mining enterprise production data of the present invention, the analysis of regional gradient characteristics of each type of production data includes:

[0026] Obtaining a regional gradient feature analysis model;

[0027] The production data distribution map of coal mining enterprises is input into the regional gradient characteristic analysis model to obtain the regional gradient characteristics of each type of production data.

[0028] As a preferred solution of the method for constructing an industry production data model based on coal mining enterprise production data of the present invention, the obtaining of data entity connection features includes:

[0029] Obtain all data tables of all types of production data in all production areas of a coal mining enterprise within a preset period, and obtain all in-table entity relationships and all cross-table entity relationships of all data tables;

[0030] The same entities in all the intra-table entity relationships and all the cross-table entity relationships are overlapped to obtain data entity relationship features.

[0031] As a preferred solution of the method for constructing an industry production data model based on coal mining enterprise production data of the present invention, wherein: the multi-dimensional data model for generating coal mining enterprise production data includes:

[0032] Binding the entity attributes contained in the data entity connection features with the regional gradient features of the corresponding class production data to obtain a coal mining enterprise production data model of the regional dimension;

[0033] Binding the entity attributes contained in the data entity connection features with the time series gradual change features of the corresponding class production data to obtain a coal mining enterprise production data model in the time series dimension;

[0034] The multi-dimensional data model of the coal mining enterprise production data includes a coal mining enterprise production data model of a regional dimension and a coal mining enterprise production data model of a time series dimension.

[0035] In a second aspect, the present invention provides an industry production data model construction system based on coal mining enterprise production data, comprising:

[0036] The acquisition module is used to obtain all types of production data of all production areas of coal mining enterprises within a preset period of time;

[0037] An analysis module, used to analyze the regional gradual change characteristics and the temporal gradual change characteristics of each type of production data based on the acquired data;

[0038] The parsing module is used to parse the data relationship among all types of production data in all production areas within the coal mining enterprise within a preset period of time to obtain data entity connection characteristics;

[0039] The model building module is used to generate a multi-dimensional data model of coal mining enterprise production data based on the data entity connection characteristics and the regional gradual change characteristics and time series gradual change characteristics of each type of production data.

[0040] In a third aspect, the present invention provides an electronic device, comprising:

[0041] Memory and processor;

[0042] The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the method for constructing an industry production data model based on the production data of coal mining enterprises are implemented.

[0043] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the method for constructing an industry production data model based on the production data of coal mining enterprises.

[0044] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention combines the regional gradient characteristics and time series gradient characteristics of all types of production data within a coal mining enterprise with the entity connection characteristics of all types of production data in all production areas within a coal mining enterprise within a preset time period, and constructs a multi-dimensional data model that can accurately reflect the production laws and trends of coal mines, providing more comprehensive decision-making support for the coal mining industry and helping coal mining enterprises in production optimization and safety management. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] 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 labor.

[0046] Figure 1 It is a schematic diagram of the overall process of a method for constructing an industry production data model based on production data of a coal mining enterprise according to an embodiment of the present invention;

[0047] Figure 2 It is a schematic diagram of the overall process of analyzing the regional gradual change characteristics and the time series gradual change characteristics of each type of production data according to the method for constructing an industry production data model based on the production data of coal mining enterprises described in an embodiment of the present invention. DETAILED DESCRIPTION

[0048] 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.

[0049] 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.

[0050] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0051] The present invention is described in detail with reference to the schematic diagram. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0052] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0053] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0054] Reference Figure 1-Figure 2 , which is an embodiment of the present invention, provides a method for constructing an industry production data model based on production data of a coal mining enterprise, comprising:

[0055] S100, obtaining all types of production data of all production areas of the coal mining enterprise within a preset time period.

[0056] Specifically, the production area within the coal mining enterprise is the area where production operations are carried out in the coal mining enterprise, and the preset time period is a preset, longer time period, such as a time period within one year before the current moment.

[0057] All types of production data refer to the data types related to production within coal mining enterprises, such as the daily output data, annual output data, daily number of staff involved, and daily power consumption of coal mine A; the daily profit and daily cost of all coal mines in area S, etc.

[0058] Exemplarily, the average power consumption of coal mining operations, the average power consumption of other production support system operations and the average power consumption of life are separated from the total power consumption and evaluated. The power consumption of mining operations mainly includes the power consumption of coal mining and tunneling operations. The average power consumption of other production support system operations mainly includes the power consumption of coal mine transportation, hoisting, drainage, gas extraction and other operations. The average power consumption of living areas is the power consumption required to maintain normal operation when the coal mine is shut down, which mainly includes ventilation, drainage, industrial square living electricity, etc.

[0059] S200, based on the acquired data, analyzing the regional gradual change characteristics and the time series gradual change characteristics of each type of production data.

[0060] Preferably, analyzing the regional gradual change characteristics and the temporal gradual change characteristics of each type of production data includes:

[0061] S201, analyzing the local time series gradual change characteristics of each type of production data in each production area;

[0062] S202, based on the local time series gradual change feature, obtain the time series gradual change feature of each type of production data;

[0063] S203, obtaining a GIS map of the coal mining enterprise, marking each type of production data of each production area and the corresponding local time-series gradient characteristics in the corresponding production area in the GIS map of the coal mining enterprise, and obtaining a production data distribution map of the coal mining enterprise;

[0064] S204, based on the distribution map of production data of coal mining enterprises, analyzing the regional gradient characteristics of each type of production data.

[0065] Specifically, the regional gradual change feature is the feature that a single type of production data changes with the change of the region, and the temporal gradual change feature is the feature that a single type of production data changes with the change of time.

[0066] The GIS map of coal mining enterprises is an electronic map showing the actual distribution of all production areas within a coal mining enterprise. The service layer in the production situation analysis system architecture of coal industry enterprises provides geographic information GIS services. Geographic information GIS services provide underlying technical support for the system, provide geographic data services and business integration technologies to various business application systems on the platform, uniformly manage the geographic information data of coal mining enterprises, provide spatial location data for coal mine power big data analysis and calculation, and provide visualization support for the analysis results.

[0067] The local time-series gradual change feature of each type of production data in each production area is a feature that represents the change of a single type of production data in a single production area over time.

[0068] For example, the model combines spatial geographic information data to conduct spatial regional cluster analysis of coal mining enterprises, dynamically generates and displays the status of coal mines in production, suspension, closure, illegal operation, etc., the distribution of regional power consumption within a certain time period, the regional distribution of abnormal power consumption, and the frequent production operation intervals of regional coal mines within a day, etc., to understand the production trends of coal mines and provide auxiliary decision-making support for remote supervision and inspection of coal mines.

[0069] In this embodiment, the industry production data model construction system based on the production data of coal mining enterprises is linked with the power big data visualization platform to deeply mine the key information between the data from multiple dimensions such as time, space, business field, early warning alarm level, supervision and inspection level, production status, and illegal production type for the power big data analysis results, and use chart services to realize big data visualization, providing functions such as data level drilling down, cause tracing, illegal and irregular behavior portrait retrieval, and related information query.

[0070] It should be noted that by first analyzing the local time series gradient characteristics of each type of production data in each production area, the time series gradient characteristics of each type of production data are obtained, and based on the coal mining enterprise production data distribution map containing each type of production data in each production area and the corresponding local time series gradient characteristics, the regional gradient characteristics of each type of production data can be analyzed.

[0071] Preferably, in step S201, analyzing the local time-series gradual change characteristics of each type of production data in each production area includes:

[0072] Extract all attribute values ​​of each entity attribute of each data entity within a preset time period from each type of production data in each production area;

[0073] Calculate the growth ratio between all adjacent attribute values ​​of each entity attribute in all attribute values ​​within a preset period, sort them in time series, obtain the growth ratio sequence of each entity attribute, and use it as the local time series gradual change feature of the corresponding class production data of the corresponding production area;

[0074] Among them, all attribute values ​​of each entity attribute within a preset time period are the corresponding class production data in the corresponding production area, and the number of entity attributes is the same as the total number of classes of production data.

[0075] Specifically, data entities are things that exist objectively and can be distinguished from each other in the actual problems contained in the data table. Data entities are objects in the real world and can be specific to people, things, and objects. For example: coal mines, regions, enterprises, etc.

[0076] An entity attribute is a characteristic of a data entity. In an ER diagram, attributes are used to describe entities. For example, coal mine A can be described by its name, location, daily output, daily power consumption, and daily profit.

[0077] All attribute values ​​of the entity attributes within the preset time period are the performance values ​​of the entity attributes within the preset time period recorded in the data table, and can be the specific values ​​of all daily outputs of Coal Mine A within the preset time period.

[0078] The growth ratio of adjacent attribute values ​​is the ratio of the difference between the later attribute value and the earlier attribute value in the adjacent attribute values ​​to the earlier attribute value.

[0079] For example, through the joint analysis of real-time monitoring data of coal mine enterprises' power monitoring data, personnel positioning data, safety monitoring data and a large amount of historical data, the data fluctuation changes are analyzed based on the time dimension, the time period and operation scope of coal mine mining activities are evaluated, and the normal fluctuation range and estimated average value of the coal mine enterprise's mining operation power consumption, other production support system operation power consumption and basic living power consumption are calculated, providing basic data support for coal mine production behavior monitoring and early warning.

[0080] It should be noted that by calculating the growth ratio of all adjacent attribute values ​​of each entity attribute of each data entity among all attribute values ​​within a preset long period of time, and sorting them in time series, a growth ratio sequence of each entity attribute is generated, and the characteristics that can accurately represent the changes of the corresponding type of production data of the corresponding production area over time are obtained.

[0081] Preferably, in step S202, obtaining the temporal gradual change characteristics of each type of production data includes:

[0082] Among all production areas in the coal mining enterprise, all production areas containing the same type of production data are screened out as all coverage areas of the corresponding type of production data;

[0083] In the local time series gradual change characteristics of each type of production data in each production area, the growth ratio sequence of each entity attribute is obtained;

[0084] Calculate the similarity between the growth ratio series of every two coverage areas of each type of production data, and determine the correlation coefficient between every two coverage areas;

[0085] Based on the correlation coefficient between every two coverage areas of each type of production data, the local time-series gradual change features of all coverage areas of each type of production data are merged to obtain the time-series gradual change features of each type of production data.

[0086] Specifically, the similarity between the growth ratio sequences of each two coverage areas of each type of production data is calculated using the existing dot product ratio formula (i.e., the sum of the products of two numbers at corresponding positions of the two sequences divided by the sum of the squares of the numbers in the sequences).

[0087] For example, based on a large amount of personnel positioning data of coal mining enterprises, cluster analysis is performed on areas where personnel activities are concentrated, and suspected mining operations are determined in combination with the personnel substation name and personnel type information. By performing correlation analysis between changes in the number of people at the suspected mining operations and changes in electricity consumption data, the coal mining operations site can be further determined. When the mining operations site exceeds the requirements of regulations and specifications, an early warning message for excessively high-intensity production violations is generated. When an over-limit alarm occurs at a mining operations site and the number of excess personnel is greater than the national limit of 20%, an early warning message for excessively high-intensity production violations is generated.

[0088] For example, by monitoring the power consumption data of suspended coal mining enterprises, the normal fluctuation range of basic electricity consumption of coal mines can be analyzed and calculated. When the power consumption of coal mines exceeds a certain threshold within the normal range, it is determined that the coal mining enterprise is suspected of illegal suspension of production and illegal mining.

[0089] It should be noted that by calculating the similarity between the growth ratio sequences of every two coverage areas of each type of production data, the correlation coefficient between every two coverage areas is obtained, and based on the correlation coefficient between every two coverage areas of each type of production data, the local time series gradient characteristics of all coverage areas of each type of production data are merged to simplify the local time series gradient characteristics of all coverage areas of each type of production data, thereby obtaining the time series gradient characteristics of each type of production data.

[0090] Preferably, calculating the similarity between the growth ratio sequences of every two coverage areas of each type of production data, and determining the correlation coefficient between every two coverage areas comprises:

[0091] When the similarity between the growth ratio sequences of two coverage areas exceeds the similarity threshold, the correlation coefficient between the corresponding two coverage areas is determined to be 1;

[0092] When the similarity between the growth ratio sequences of two coverage areas does not exceed the similarity threshold, it is determined that the correlation coefficient between the corresponding two coverage areas is 0.

[0093] Specifically, the similarity threshold is a threshold used when comparing the similarities between the growth ratio sequences of the two coverage areas when determining the correlation coefficient between the two coverage areas.

[0094] It should be noted that the correlation coefficient between two coverage areas with greater similarity between the corresponding two growth ratio sequences is determined to be 1, which facilitates the subsequent merging of local time series gradual change features of all coverage areas of each type of production data.

[0095] Preferably, based on the correlation coefficient between every two coverage areas of each type of production data, the local time-series gradual change features of all coverage areas of each type of production data are merged to obtain the time-series gradual change features of each type of production data, including:

[0096] Based on the correlation coefficient between every two coverage areas of each type of production data, a correlation matrix of all coverage areas of each type of production data is constructed, and singular value decomposition is performed to obtain an orthogonal matrix of each type of production data. The orthogonal matrix of each type of production data is normalized to obtain a dense matrix of each type of production data.

[0097] Determine a vector space graph corresponding to each row vector in a dense matrix of each type of production data, and calculate the vector space distance between each two coverage areas in the vector space graph, and calculate the average vector space distance between each two coverage areas based on the vector space distance between each two coverage areas in the vector space graph corresponding to all row vectors;

[0098] Two coverage areas whose vector space spacing average value does not exceed the vector space spacing average threshold value are determined as a coverage area group to be merged for the corresponding type of production data;

[0099] Based on all the to-be-merged coverage area groups of each type of production data, the local time-series gradual change features of all the coverage areas of each type of production data are merged to obtain the time-series gradual change features of each type of production data.

[0100] Specifically, based on the correlation coefficient between every two coverage areas of each type of production data, a correlation matrix of all coverage areas of each type of production data is constructed, including:

[0101] The number of rows and columns of the correlation matrix for each type of production data is the same as the total number of areas covered by each type of production data;

[0102] When the correlation coefficient between the first coverage area and the third coverage area is 1, the value at the third column of the first row and the value at the third row of the first column in the correlation matrix are set to 1. Based on this principle, the correlation matrix of all coverage areas of each type of production data is determined.

[0103] Specifically, determine the vector space graph corresponding to each row vector in the dense matrix of each type of production data, including:

[0104] After marking the numerical value corresponding to each coverage area contained in each row vector in the dense matrix as the horizontal coordinate value and the vertical coordinate value of the coordinate point in the two-dimensional coordinate system, the vector space diagram corresponding to each row vector is obtained. For example, if the numerical value corresponding to a single coverage area contained in the row vector is 0.3, the coordinate point at (0.3, 0.3) in the two-dimensional coordinate system is regarded as the coordinate point of the corresponding coverage area;

[0105] The two-dimensional coordinate graph containing the coordinate points of all coverage areas in the row vector is regarded as the vector space graph corresponding to the row vector;

[0106] Among them, the row vector is a vector consisting of a single row of data in the dense matrix.

[0107] Specifically, calculating the vector space distance between each two coverage areas in the vector space graph includes:

[0108] The distance between the coordinate points corresponding to each two coverage areas in the vector space diagram is regarded as the vector space distance between the corresponding coverage areas in the next year.

[0109] Specifically, the average vector space distance between each two coverage areas is calculated based on the vector space distance between each two coverage areas in the vector space graph corresponding to all row vectors, including:

[0110] The average value of the vector space distance between every two coverage areas in the vector space graph corresponding to all row vectors is regarded as the average value of the vector space distance between the two coverage areas.

[0111] In this embodiment, the vector space spacing average threshold is a value that the vector space spacing average value of two coverage areas of the coverage area group to be merged that are determined to be corresponding to the type of production data cannot exceed.

[0112] It should be noted that, based on the correlation coefficient between every two coverage areas of each type of production data, a correlation matrix of all coverage areas of each type of production data is constructed, and by performing singular value decomposition and normalization on the correlation matrix of each type of production data, a vector space graph is constructed, and the correlation between different coverage areas in each type of production data is represented by a multidimensional vector space. Based on the multidimensional vector space graph, multidimensional quantification of the correlation between different coverage areas of each type of production data is realized, and based on the quantification results, it is determined whether it can be merged, thereby ensuring the accuracy of the obtained time series gradient characteristics of each type of production data.

[0113] Specifically, based on all the coverage area groups to be merged for each type of production data, the local time series gradual change features of all coverage areas of each type of production data are merged to obtain the time series gradual change features of each type of production data, including:

[0114] Among all the coverage area groups to be merged for each type of production data, the coverage area groups to be merged that have overlapping coverage areas are merged to obtain a new coverage area for each type of production data;

[0115] Merging the local temporal gradient features of the two coverage areas contained in each new coverage area to obtain a new local temporal gradient feature of each new coverage area;

[0116] Using all the new coverage areas of each type of production data to replace the coverage areas included in all the new coverage areas of all the coverage areas of the corresponding type of production data, to obtain all the new coverage areas of each type of production data;

[0117] The local temporal gradient characteristics of the new coverage area that has not been replaced are regarded as new local temporal gradient characteristics corresponding to the new coverage area;

[0118] The new local time-series gradient characteristics of all new coverage areas of each type of production data continue to be merged until there are no groups of coverage areas to be merged in all new coverage areas of each type of production data. Then the new local time-series gradient characteristics of all new coverage areas of each type of production data that are most recently obtained are regarded as the time-series gradient characteristics of each type of production data.

[0119] The local temporal gradient features of the two coverage areas contained in each new coverage area are merged to obtain a new local temporal gradient feature of each new coverage area, including:

[0120] The average of the two growth ratios at each same position in the growth ratio sequence of the local temporal gradient characteristics of the two coverage areas contained in each new coverage area is taken as the value of the corresponding position in the new growth ratio sequence of the new local temporal gradient characteristics of the new coverage area, thereby obtaining the new local temporal gradient characteristics of each new coverage area.

[0121] In this embodiment, the manner of continuing to merge the new local time-series gradual change features of all new coverage areas of each type of production data is the same as the manner of merging the local time-series gradual change features of all coverage areas of each type of production data.

[0122] It should be noted that by continuously determining new groups of coverage areas to be merged in all coverage areas of each type of production data, and continuously merging the local time-series gradient characteristics of two coverage areas in the new groups of coverage areas to be merged, the local time-series gradient characteristics of multiple coverage areas of each type of production data are continuously merged and simplified.

[0123] Preferably, in step S204, analyzing the regional gradient characteristics of each type of production data includes:

[0124] First, obtain the regional gradient feature analysis model, including:

[0125] Extracting multiple groups of regional gradient features of each type of production data manually analyzed in the manual analysis example of coal mine production data, and generating corresponding coal mine enterprise production data distribution map based on all types of production data of all production areas in the coal mine enterprise contained in the manual analysis example within a preset long period of time;

[0126] The distribution diagrams of multiple groups of coal mining enterprise production data (as model input) and the corresponding regional gradient characteristics of all types of production data (as model output) are used as training samples to train the neural network model and obtain the regional gradient characteristic analysis model;

[0127] Secondly, the production data distribution map of coal mining enterprises is input into the regional gradient characteristic analysis model to obtain the regional gradient characteristics of each type of production data.

[0128] It should be noted that by introducing artificial intelligence algorithms, accurate analysis of the regional gradient characteristics of each type of production data can be achieved.

[0129] S300, analyzing the data relationship among all types of production data in all production areas within the coal mining enterprise within a preset time period to obtain data entity connection characteristics.

[0130] Preferably, obtaining the data entity connection feature includes:

[0131] Obtain all data tables of all types of production data in all production areas of a coal mining enterprise within a preset period, and obtain all in-table entity relationships and all cross-table entity relationships of all data tables;

[0132] The same entities in all entity relationships within a table and all entity relationships across tables are overlapped to obtain data entity relationship features.

[0133] Specifically, a data table contains at least one attribute value of at least one entity attribute of at least one data entity, an intra-table entity relationship within a data table is an entity relationship diagram used to represent the relationship between at least one data entity and at least one entity attribute contained in a single data table, a cross-table entity relationship is an entity relationship diagram used to represent the relationship between at least one data entity and at least one entity attribute belonging to different tables, and the same entity is the same data entity.

[0134] It should be noted that this step can realize the sorting and diagramming of entity relationships in all types of production data in all production areas within a coal mining enterprise within a preset time period.

[0135] S400, generating a multi-dimensional data model of the production data of the coal mining enterprise based on the data entity connection characteristics and the regional gradual change characteristics and time series gradual change characteristics of each type of production data.

[0136] Preferably, the multi-dimensional data model for generating production data of coal mining enterprises includes:

[0137] Bind the entity attributes contained in the data entity connection features with the regional gradient features of the corresponding class production data to obtain the coal mining enterprise production data model of the regional dimension;

[0138] For example, this model can reflect the online status of power data in the monitoring area for the past seven days. Based on the data quality dynamic monitoring and analysis model, the stability and integrity of the access data can be monitored in real time, and the monitoring and analysis results can be displayed through a visualization page. The current transmission status, access data volume, number of accessed coal mining enterprises, data qualification rate, enterprise data stability analysis, etc. can be dynamically viewed. At the same time, the historical data access status can be traced back to provide data verification support for model research and system development.

[0139] Bind the entity attributes contained in the data entity connection features with the time series gradual change features of the corresponding class production data to obtain the coal mining enterprise production data model in the time series dimension;

[0140] For example, the production data model of a coal mining enterprise in the time series dimension may record and represent the electricity consumption in the three time dimensions of day, month and year in time series.

[0141] The multi-dimensional data model of coal mining enterprise production data includes a coal mining enterprise production data model of regional dimension and a coal mining enterprise production data model of time series dimension.

[0142] Specifically, the data entity connection feature is the ER diagram, also known as the entity relationship diagram, which is used to show the relationship between entity sets. It provides a method to represent entity types, attributes and connections; it is used to describe the conceptual model of the real world. The coal mining enterprise production data model in the regional dimension is a data model used to represent the characteristics of coal mining enterprise production data that belongs to multiple entities and has multiple entity attributes and changes with changes in the region; the coal mining enterprise production data model in the time series dimension is a data model used to represent the characteristics of coal mining enterprise production data that belongs to multiple entities and has multiple entity attributes and changes with time.

[0143] It should be noted that building a multi-dimensional data model that can accurately reflect the production laws and trends of coal mines can provide more comprehensive decision-making support for the coal mining industry and assist in production optimization and safety management of coal mining enterprises.

[0144] In the present invention, the regional gradual change characteristics and time-series gradual change characteristics of all types of production data within a coal mining enterprise are combined with the entity connection characteristics of all types of production data in all production areas within a coal mining enterprise within a preset long period of time, so as to construct a multi-dimensional data model that can accurately reflect the production laws and trends of coal mines, provide more comprehensive decision-making support for the coal mining industry, and assist in production optimization and safety management of coal mining enterprises.

[0145] The above is a schematic scheme of a method for constructing an industry production data model based on production data of coal mining enterprises in this embodiment. It should be noted that the technical scheme of the industry production data model construction system based on production data of coal mining enterprises and the technical scheme of the method for constructing an industry production data model based on production data of coal mining enterprises mentioned above belong to the same concept. For details not described in detail in the technical scheme of the industry production data model construction system based on production data of coal mining enterprises in this embodiment, please refer to the description of the technical scheme of the method for constructing an industry production data model based on production data of coal mining enterprises mentioned above.

[0146] In this embodiment, the industry production data model construction system based on the production data of coal mining enterprises includes:

[0147] The acquisition module is used to obtain all types of production data of all production areas of coal mining enterprises within a preset period of time;

[0148] An analysis module, used to analyze the regional gradual change characteristics and the temporal gradual change characteristics of each type of production data based on the acquired data;

[0149] The parsing module is used to parse the data relationship among all types of production data in all production areas within the coal mining enterprise within a preset period of time to obtain data entity connection characteristics;

[0150] The model building module is used to generate a multi-dimensional data model of coal mining enterprise production data based on the data entity connection characteristics and the regional gradual change characteristics and time series gradual change characteristics of each type of production data.

[0151] This embodiment also provides an electronic device, which is applicable to the construction of an industry production data model based on production data of a coal mining enterprise, and includes:

[0152] Memory and processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the method for constructing an industry production data model based on the production data of coal mining enterprises as proposed in the above embodiment.

[0153] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for constructing an industry production data model based on the production data of coal mining enterprises as proposed in the above embodiment is implemented.

[0154] The storage medium proposed in this embodiment and the method for constructing an industry production data model based on the production data of coal mining enterprises proposed in the above embodiment belong to the same inventive concept. The technical details not described in detail in this embodiment can be found in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0155] Through the above description of the implementation method, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ReadOnly, Memory, ROM), random access memory (RandomAccessMemory, RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform the methods of various embodiments of the present invention.

[0156] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. 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 method for constructing an industry production data model based on production data of coal mining enterprises, characterized in that: include: Obtain all types of production data of all production areas of coal mining enterprises within a preset period of time; Based on the acquired data, analyze the regional and temporal gradient characteristics of each type of production data; Analyze the data relationships among all types of production data in all production areas within a coal mining enterprise within a preset period of time to obtain data entity connection characteristics; Based on the data entity connection characteristics and the regional gradual change characteristics and time series gradual change characteristics of each type of production data, a multi-dimensional data model of the coal mining enterprise production data is generated.

2. The method for constructing an industry production data model based on production data of a coal mining enterprise according to claim 1, characterized in that: The analysis of regional gradual change characteristics and temporal gradual change characteristics of each type of production data includes: Analyze the local time series gradual change characteristics of each type of production data in each production area; Based on the local time series gradual change feature, obtaining the time series gradual change feature of each type of production data; Obtain a GIS map of a coal mining enterprise, mark each type of production data and the corresponding local time-series gradient characteristics of each production area in the corresponding production area in the GIS map of the coal mining enterprise, and obtain a distribution map of the production data of the coal mining enterprise; Based on the production data distribution map of the coal mining enterprise, the regional gradient characteristics of each type of production data are analyzed.

3. The method for constructing an industry production data model based on production data of a coal mining enterprise according to claim 2, characterized in that: The analysis of the local time series gradual change characteristics of each type of production data in each production area includes: Extract all attribute values ​​of each entity attribute of each data entity within a preset time period from each type of production data in each production area; Calculate the growth ratio between all adjacent attribute values ​​of each entity attribute in all attribute values ​​within a preset period, sort them in time series, obtain the growth ratio sequence of each entity attribute, and use it as the local time series gradual change feature of the corresponding class production data of the corresponding production area; Among them, all attribute values ​​of each entity attribute within a preset time period are the corresponding class production data in the corresponding production area, and the number of entity attributes is the same as the total number of classes of production data.

4. The method for constructing an industry production data model based on production data of a coal mining enterprise according to claim 3, characterized in that: The step of obtaining the time series gradual change characteristics of each type of production data includes: Among all production areas in the coal mining enterprise, all production areas containing the same type of production data are screened out as all coverage areas of the corresponding type of production data; In the local time series gradual change characteristics of each type of production data in each production area, the growth ratio sequence of each entity attribute is obtained; Calculate the similarity between the growth ratio series of every two coverage areas of each type of production data, and determine the correlation coefficient between every two coverage areas; Based on the correlation coefficient between every two coverage areas of each type of production data, the local time-series gradual change features of all coverage areas of each type of production data are merged to obtain the time-series gradual change features of each type of production data.

5. The method for constructing an industry production data model based on coal mining enterprise production data according to claim 2 or 4, characterized in that: The analysis of regional gradient characteristics of each type of production data includes: Obtaining a regional gradient feature analysis model; The production data distribution map of coal mining enterprises is input into the regional gradient characteristic analysis model to obtain the regional gradient characteristics of each type of production data.

6. The method for constructing an industry production data model based on production data of a coal mining enterprise according to claim 1, characterized in that: The obtaining of data entity contact characteristics comprises: Obtain all data tables of all types of production data in all production areas of a coal mining enterprise within a preset period, and obtain all in-table entity relationships and all cross-table entity relationships of all data tables; The same entities in all the intra-table entity relationships and all the cross-table entity relationships are overlapped to obtain data entity relationship features.

7. The method for constructing an industry production data model based on production data of a coal mining enterprise according to claim 1, characterized in that: The multi-dimensional data model for generating coal mining enterprise production data includes: Binding the entity attributes contained in the data entity connection features with the regional gradient features of the corresponding class production data to obtain a coal mining enterprise production data model of the regional dimension; Binding the entity attributes contained in the data entity connection features with the time series gradual change features of the corresponding class production data to obtain a coal mining enterprise production data model in the time series dimension; The multi-dimensional data model of the coal mining enterprise production data includes a coal mining enterprise production data model of a regional dimension and a coal mining enterprise production data model of a time series dimension.

8. A system for constructing an industry production data model based on production data of coal mining enterprises, characterized in that: include: The acquisition module is used to obtain all types of production data of all production areas of coal mining enterprises within a preset period of time; An analysis module, used to analyze the regional gradual change characteristics and the temporal gradual change characteristics of each type of production data based on the acquired data; The parsing module is used to parse the data relationship among all types of production data in all production areas within the coal mining enterprise within a preset period of time to obtain data entity connection characteristics; The model building module is used to generate a multi-dimensional data model of coal mining enterprise production data based on the data entity connection characteristics and the regional gradual change characteristics and time series gradual change characteristics of each type of production data.

9. An electronic device, characterized in that: include: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the method for constructing an industry production data model based on coal mining enterprise production data as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: It stores computer executable instructions, which, when executed by a processor, implement the steps of the method for constructing an industry production data model based on the production data of coal mining enterprises as described in any one of claims 1 to 7.

Images