Coal enterprise digital transformation evaluation method and system

Abstract

The invention belongs to the technical field of coal enterprise digital transformation evaluation, and discloses a coal enterprise digital transformation evaluation method and system, and the method comprises the steps: dynamically setting an evaluation domain for each evaluation dimension through a multi-target genetic algorithm according to the organization structure and core business process of a coal enterprise; based on the key driving factors of the evaluation domain, correspondingly setting an evaluation sub-domain, a refined index and a coal enterprise digital transformation maturity grade, and setting scoring rules of the refined index and the coal enterprise digital transformation maturity grade; and constructing a comprehensive evaluation model of the coal enterprise digital transformation evaluation indexes, calculating a coal enterprise digital transformation comprehensive score, and determining a coal enterprise digital transformation maturity level. According to the invention, enterprise competitiveness can be improved, digital transformation is accelerated, industrial standard formulation is promoted, and market competitiveness is enhanced.

Description

Technical Field

[0001] This invention relates to the field of evaluation technology for digital transformation of coal enterprises, and in particular to an evaluation method and system for digital transformation of coal enterprises. Background Technology

[0002] With the sweeping wave of digitalization, the coal industry is also actively seeking digital transformation, hoping to improve production efficiency, enhance safety, reduce environmental impact, and achieve high-quality development. In this process, many coal companies have invested heavily in exploring digital transformation paths suitable for their own circumstances. From the application of intelligent mining equipment to the construction of big data management platforms, from the upgrading of mine safety monitoring systems to the optimization of intelligent transportation and logistics systems, significant results have been achieved in each stage. However, the digital transformation of coal enterprises is a complex and systematic project, involving changes across multiple levels and fields.

[0003] Currently, the industry lacks a scientific, unified, and comprehensive evaluation system to accurately measure the effectiveness and progress of digital transformation in coal enterprises. Although some enterprises have attempted relevant assessments, these often suffer from incomplete indicators, unscientific methods, and incomplete systems, making it difficult to conduct accurate and objective evaluations of digital transformation. This results in enterprises being unable to clearly understand their current stage of transformation and struggling to develop targeted strategies for the next phase.

[0004] Therefore, how to provide an evaluation method and system for the digital transformation of coal enterprises is an urgent problem to be solved. Summary of the Invention

[0005] This invention provides a method and system for evaluating the digital transformation of coal enterprises, addressing the problem that the lack of a scientific, unified, and comprehensive evaluation system in the existing technology is insufficient to accurately measure the effectiveness and progress of the digital transformation of coal enterprises. This results in enterprises being unable to clearly understand the stage of their transformation and making it difficult to formulate targeted construction strategies for the next stage.

[0006] According to a first aspect of the present invention, a method for evaluating the digital transformation of coal enterprises is provided.

[0007] In one embodiment, a method for evaluating the digital transformation of coal enterprises includes: dynamically setting evaluation domains for each evaluation dimension based on the organizational structure and core business processes of the coal enterprise using a multi-objective genetic algorithm; setting evaluation subdomains, detailed indicators, and digital transformation maturity levels of the coal enterprise based on the key driving factors of the evaluation domains, and setting scoring rules for the detailed indicators and digital transformation maturity levels of the coal enterprise; constructing a comprehensive evaluation model for the evaluation indicators of digital transformation of coal enterprises, calculating the comprehensive score of digital transformation of coal enterprises, and determining the digital transformation maturity level of the coal enterprise.

[0008] In one embodiment, based on the organizational structure and core business processes of a coal enterprise, a multi-objective genetic algorithm is used to dynamically set the evaluation domain for each evaluation dimension, including: randomly generating an initial population, where each individual represents the selection state of a set of primary indicators; evaluating the fitness of each individual; calculating the comprehensive score of each individual; and calculating the minimum resource consumption; based on the obtained fitness, performing a fast non-dominated sort on the population, dividing individuals into different front layers according to non-dominated relationships; calculating the crowding degree of individuals in each non-dominated layer; and selecting the individual with the highest fitness to form a new parent population based on crowding degree and ranking; performing elite retention on the new parent population to ensure that the individual with the highest fitness enters the next generation population; and performing selection, crossover, and mutation operations on the new parent population to generate a offspring population, thus obtaining a new population; determining whether the maximum number of iterations has been reached; if so, outputting the optimized population and its corresponding evaluation domain combination, and selecting the optimal solution on the Pareto front.

[0009] In one embodiment, setting evaluation subdomains, detailed indicators, and maturity levels for digital transformation of coal enterprises based on key driving factors of the evaluation domain includes: constructing an evaluation domain using several primary indicators based on the digital transformation needs of coal enterprises, serving as key driving factors for digital transformation; setting several secondary indicators as evaluation subdomains for each primary indicator, ensuring that each primary indicator includes corresponding secondary indicators; setting several tertiary indicators as detailed indicators for each secondary indicator, and detailing the evaluation content of each secondary indicator; constructing an evaluation system for digital transformation of coal enterprises based on the primary, secondary, and tertiary indicators; classifying the maturity of digital transformation of coal enterprises into several maturity levels based on the set evaluation domains, evaluation subdomains, and detailed indicators, reflecting the transformation maturity of enterprises at different stages; and classifying and organizing the descriptions of each maturity level according to the several maturity levels of digital transformation of coal enterprises, corresponding to different stages of digital transformation of coal enterprises.

[0010] In one embodiment, the scoring rules for setting detailed indicators and the maturity level of digital transformation of coal enterprises include: determining the evaluation value based on the digital transformation needs of coal enterprises using both objective assignment and numerical calculation methods; constructing a judgment matrix using the analytic hierarchy process (AHP) and determining the weight coefficients; calculating the maximum eigenvalue and the vector of the corresponding eigenvalue of the judgment matrix, and calculating the weight of each factor on the digital transformation of coal enterprises; calculating the consistency ratio of the judgment matrix, and if the consistency ratio is less than or equal to a preset value, the judgment matrix is ​​considered consistent; otherwise, the judgment matrix is ​​reconstructed.

[0011] In one embodiment, the determination of evaluation values ​​based on the digital transformation needs of coal enterprises, using both objective assignment and numerical calculation methods, includes: assigning values ​​to the evaluation domain using the objective assignment method based on the digital transformation needs of coal enterprises, resulting in a unified evaluation weight system; dividing the maturity levels of digital transformation of coal enterprises into several maturity evaluation intervals using the interval assignment method based on industry comparison needs; and assigning values ​​to detailed indicators using the numerical calculation method based on the operational data of coal enterprises, resulting in a quantitative calculation model covering several third-level indicators.

[0012] In one embodiment, the analytic hierarchy process (AHP) is used to construct a judgment matrix and determine the weight coefficients. This includes: dividing the digital transformation of coal enterprises into a hierarchical structure, and using the comprehensive score of digital transformation of coal enterprises, several evaluation domains, several evaluation sub-domains, and several detailed indicators as the target layer, criterion layer, sub-criterion layer, and solution layer, respectively; based on the evaluation sub-domains of the sub-criterion layer, pairwise comparisons are made between the detailed indicators under the same evaluation sub-domain to construct a judgment matrix for the detailed indicators, and the respective weights of the evaluation sub-domains and detailed indicators are determined; the elements of the judgment matrix are quantitatively assigned using a matrix judgment scale to obtain a numerical comparison result reflecting relative importance; based on the expert evaluation results, the geometric mean method is used to summarize all expert scoring matrices to obtain a comprehensive judgment matrix.

[0013] In one embodiment, calculating the largest eigenvalue and the vector of the corresponding eigenvalue of the judgment matrix, and calculating the weight of each factor on the digital transformation of coal enterprises, includes: normalizing the columns of the judgment matrix, and mapping the original scores to a standardized space through linear transformation to eliminate differences in expert scoring scales; summing the normalized judgment matrix to obtain the weight of each factor on the digital transformation of coal enterprises.

[0014] In one embodiment, calculating the consistency ratio of the judgment matrix, if the consistency ratio is less than or equal to a preset value, the judgment matrix is ​​consistent; otherwise, reconstructing the judgment matrix includes: calculating the product of the judgment matrix and the weight vector to obtain the largest eigenvalue of the judgment matrix; calculating the consistency index and the order of the judgment matrix based on the largest eigenvalue, and calculating the consistency ratio; if the consistency ratio is less than or equal to the preset value, the judgment matrix is ​​consistent; otherwise, reconstructing the judgment matrix.

[0015] In one embodiment, constructing a comprehensive evaluation model for the digital transformation evaluation indicators of coal enterprises, calculating the comprehensive score of digital transformation of coal enterprises, and determining the maturity level of digital transformation of coal enterprises includes: dividing the digital transformation of coal enterprises into a hierarchical structure, and taking the comprehensive score of digital transformation of coal enterprises, several evaluation domains, several evaluation sub-domains, and several detailed indicators as the target layer, criterion layer, sub-criterion layer, and solution layer, respectively; determining the weight of each evaluation domain, constructing a judgment matrix through scoring rules and expert opinions, and calculating the weight coefficients; calculating the weights of the evaluation sub-domains and detailed indicators, and performing consistency checks to ensure the consistency of the matrix; inputting the weight coefficients of each evaluation domain, evaluation sub-domain, and detailed indicator into the comprehensive evaluation mathematical model of digital transformation, calculating the comprehensive score, and determining the maturity level of digital transformation of coal enterprises through the calculated comprehensive score.

[0016] According to a second aspect of the present invention, a digital transformation evaluation system for coal enterprises is provided.

[0017] In one embodiment, a digital transformation evaluation system for coal enterprises includes: a data storage module for storing data related to the digital transformation of coal enterprises, and cleaning and preprocessing the data to ensure its accuracy and integrity; an indicator system establishment module for establishing primary, secondary, and tertiary indicators required for the evaluation process of digital transformation of coal enterprises; an evaluation value calculation module for calculating the evaluation values ​​of each level of indicators and obtaining scores for each collected item through evaluation verification and scoring; a weight coefficient calculation module for calculating the weight coefficients of each level of indicators in the digital transformation evaluation indicator system; and a comprehensive evaluation module for calculating the comprehensive score of the digital transformation of coal enterprises based on the evaluation values ​​and weight coefficients of each indicator, and determining the maturity level of the digital transformation of coal enterprises.

[0018] According to a third aspect of the present invention, a computer device is provided.

[0019] In some embodiments, the computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method described above.

[0020] According to a fourth aspect of the present invention, a computer-readable storage medium is provided.

[0021] In one embodiment, a computer program is stored on the computer-readable storage medium, which, when executed by a processor, implements the steps of the above method.

[0022] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects:

[0023] 1. The evaluation system of this invention is comprehensive and scientific, covering multiple dimensions and employing multi-objective genetic algorithms and hierarchical analysis to ensure the relevance and rationality of the evaluation; the evaluation results are objective and accurate, based on clear scoring rules and actual data, clearly classifying maturity levels; the system functions are complete and practical, with modular design supporting data storage, backup and indicator adjustment, providing correlation analysis and decision support; it can improve enterprise competitiveness, accelerate digital transformation, promote the formulation of industry standards, and enhance market competitiveness.

[0024] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0025] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0026] Figure 1 This is a flowchart illustrating an evaluation method for the digital transformation of coal enterprises according to an exemplary embodiment;

[0027] Figure 2 This is a schematic diagram illustrating the principle of a digital transformation evaluation system for coal enterprises, based on an exemplary embodiment.

[0028] Figure 3 This is a schematic diagram of the structure of a computer device according to an exemplary embodiment;

[0029] Figure 4 This is a framework for an evaluation index system for the digital transformation of coal enterprises, illustrated according to an exemplary embodiment.

[0030] Figure 5 This is a flowchart illustrating a multi-objective genetic algorithm according to an exemplary embodiment. Detailed Implementation

[0031] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0032] Figure 1 An embodiment of the evaluation method for digital transformation of coal enterprises according to the present invention is shown.

[0033] In this optional embodiment, the evaluation method for the digital transformation of coal enterprises includes:

[0034] Step S101: Based on the organizational structure and core business processes of coal enterprises, the evaluation domain is dynamically set for each evaluation dimension using a multi-objective genetic algorithm.

[0035] Specifically, based on the organizational structure of coal enterprises (including functional units such as safety production supervision departments, production technology departments, equipment management departments, human resources departments, and finance departments) and core business processes (covering key links such as coal mining operation processes, transportation scheduling processes, inventory management processes, safety monitoring processes, and sales service processes), a multi-objective genetic algorithm (NSGA-II) is introduced to dynamically set the evaluation domain for each evaluation dimension.

[0036] Step S102: Based on the key driving factors of the evaluation domain, set up corresponding evaluation subdomains, detailed indicators and maturity levels of digital transformation of coal enterprises, and set scoring rules for detailed indicators and maturity levels of digital transformation of coal enterprises.

[0037] Step S103: Construct a comprehensive evaluation model for the evaluation indicators of digital transformation of coal enterprises, calculate the comprehensive score of digital transformation of coal enterprises, and determine the maturity level of digital transformation of coal enterprises.

[0038] In this optional embodiment, when dynamically setting the evaluation domain for each evaluation dimension using a multi-objective genetic algorithm based on the organizational structure and core business processes of the coal enterprise, an initial population can be randomly generated. Each individual represents the selection state of a set of primary indicators. The fitness of each individual is evaluated, the comprehensive score of each individual is calculated, and the minimum resource consumption is calculated. It is then determined whether a first-generation subpopulation has been generated. If not, based on the obtained fitness, a fast non-dominated sort is performed on the population, dividing individuals into different frontier layers according to non-dominated relationships. The crowding degree of individuals in each non-dominated layer is calculated, and the individual with the highest fitness is selected based on the crowding degree and ranking. Each generation forms a new parent population. If generated, the evolutionary generation GEN = 2 (Generation, representing the generation of the current iteration, used to track the progress of the algorithm). Elite retention is performed on the new parent population to ensure that the individuals with the highest fitness enter the next generation. Selection, crossover, and mutation operations are performed on the new parent population to generate offspring populations, resulting in a new population. It is then determined whether the maximum number of iterations has been reached. If it has, the optimized population and its corresponding evaluation domain combination are output, and the optimal solution on the Pareto front is selected. If not, evolution continues until GEN reaches the maximum number of generations.

[0039] Specifically, such as Figure 5 As shown, firstly, an initial population is randomly generated with a population size of P, and each individual represents a selection state (0 or 1) of a set of primary indicators; secondly, fitness is evaluated, and the comprehensive score of each individual is calculated:

[0040]

[0041] In the formula, F1 represents the overall score; z i Indicates the selection state (0 or 1) of the i-th primary indicator; Wi G represents the weight of the i-th primary indicator; i This represents the evaluation value of the i-th primary indicator.

[0042] Calculate the minimum resource consumption:

[0043]

[0044] In the formula, F2 represents the minimum resource consumption, which is the number of primary indicators selected.

[0045] Finally, a fast non-dominated sorting, selection, crossover, and mutation process is performed to generate offspring populations, and the two populations are combined to form a population of size 2P. Non-dominated sorting is a sorting method in multi-objective optimization used to divide individuals in the population into different frontier layers. The selection operation uses a tournament selection method to choose parent individuals from the current population. Tournament selection is a method that randomly selects two individuals for comparison, choosing the individual with higher fitness as the parent, where fitness is determined by both the individual's ranking and crowding. The crossover operation involves crossover of the selected parent individuals to generate offspring individuals, using a single-point crossover method, a common crossover method that randomly selects a crossover point and exchanges some genes of the parent individuals. The mutation operation involves mutating the offspring individuals to increase population diversity, using position flipping mutation, a common mutation method that flips each gene with a certain probability.

[0046] First, a fast non-dominated sort is performed, and the crowding degree of individuals in each non-dominated layer is calculated. Suitable individuals are then selected to form a new parent population. The specific formula is as follows:

[0047]

[0048] In the formula, and L represents the maximum and minimum values ​​of the j-th objective function, respectively; j ′ represents the number of individuals with the j-th objective function in the current frontier layer.

[0049] Next, elite retention is performed. This strategy ensures that the individual with the highest fitness in the current population can enter the next generation, thus preserving excellent solutions. The merged population size is 2P. P individuals are selected as the new generation population through non-dominated sorting and crowding. Finally, selection, crossover, and mutation operations are performed on the new parent population.

[0050] A termination condition check is performed to check whether the maximum number of iterations or population convergence has been reached. The maximum number of iterations is a preset termination condition; the algorithm stops when the number of iterations reaches its maximum value. Population convergence can be determined by comparing the changes in the population over several consecutive generations; if the changes are less than a certain threshold, the population is considered to have converged. Finally, the optimized population is output, which is the selected evaluation domain combination. Optimal solutions are selected from the Pareto front; these solutions are the optimal solutions in multi-objective optimization that cannot simultaneously improve all objectives.

[0051] In this optional embodiment, when setting evaluation subdomains, detailed indicators, and maturity levels of digital transformation for coal enterprises based on the key driving factors of the evaluation domain, the evaluation domain can be constructed using several primary indicators based on the digital transformation needs of coal enterprises, serving as the key driving factors for digital transformation. For each primary indicator, several secondary indicators are set as evaluation subdomains, ensuring that each primary indicator includes corresponding secondary indicators. For each secondary indicator, several tertiary indicators are set as detailed indicators, and the evaluation content of each secondary indicator is refined. Based on the primary, secondary, and tertiary indicators, an evaluation system for the digital transformation of coal enterprises is constructed. Based on the set evaluation domains, evaluation subdomains, and detailed indicators, the maturity of digital transformation of coal enterprises is graded into several maturity levels, reflecting the transformation maturity of enterprises at different stages. Based on the several maturity levels of digital transformation of coal enterprises, the descriptions of each level are categorized and organized, corresponding to different stages of digital transformation for coal enterprises.

[0052] Specifically, based on the key drivers of the evaluation domain, key drivers that can be collected (including data such as departmental proportions and the degree of digital transformation coverage) are set around the core pain points of the evaluation domain, such as coal production safety, complex underground environment, and management of high-energy-consuming equipment.

[0053] Specifically, the evaluation domain is the primary indicator, the evaluation subdomain is the secondary indicator, and the detailed indicators are the tertiary indicators.

[0054] like Figure 4 As shown, Figure 4 This is a framework for an evaluation index system for the digital transformation of coal enterprises. Only the primary and secondary indicators of this invention are shown. The primary, secondary, and tertiary indicators, and the maturity levels of digital transformation for coal industry enterprises include:

[0055] There are 6 primary indicators, 20 secondary indicators, 49 tertiary indicators, and 5 maturity levels for digital transformation of coal industry enterprises.

[0056] The primary indicators include: technology focus (A), management structure (B), data management (C), technology application (D), business transformation (E), and overall results (F).

[0057] The secondary indicators include: Technology Focus: The primary evaluation indicator includes two secondary evaluation indicators: Cognitive Determination (A1) and Path Planning (A2). Management Structure: The primary evaluation indicator includes six secondary evaluation indicators: Organizational Structure (B1), Management System (B2), Process Management (B3), Talent Development (B4), Cultural Development (B5), and Operations Management (B6). Data Management: The primary evaluation indicator includes three secondary evaluation indicators: Data Resources (C1), Data Governance (C2), and Data Application (C3). Technology Application: The primary evaluation indicator includes three secondary evaluation indicators: Operational Technology (OT) Equipment (D1), Information Technology (IT) Infrastructure (D2), and Cybersecurity (D3). Business Transformation: The primary evaluation indicator includes three secondary evaluation indicators: Digital Production (E1), Digital Management (E2), and Digital Business (E3). Comprehensive Results: The primary evaluation indicator includes three secondary evaluation indicators: Quality and Efficiency Improvement (F1), Satisfaction (F2), and Demonstration Creation (F3).

[0058] The third-level indicators include: Cognitive determination, which comprises two third-level evaluation indicators: Leadership Cognition (A) 11 Meeting frequency (A) 12 ). Route planning includes two tertiary evaluation indicators: planning preparation (A). 21 ), planning and execution (A) 22 Organizational structure includes two tertiary evaluation indicators: leadership structure (B) 11 ), Departmental Ratio (B) 12 The management system includes two three-tiered evaluation indicators: assessment score (B) 21 ), institutional coverage (B 22 Process management includes two tertiary evaluation indicators: process optimization (B) 31 ), process control (B) 32 Talent development includes two tertiary evaluation indicators: number of personnel (B) 41 ), number of training sessions (B) 42 Cultural development includes two tertiary evaluation indicators: cultural creation (B) 51 ), propaganda positions (B) 52 Operations and maintenance management includes one three-level evaluation indicator: team building (B). 61 Data resources include three tertiary evaluation indicators: automatic collection (C) 11 ), data source integration (C) 12 ), New data volume (C) 13 Data governance includes four tertiary evaluation indicators: data convergence rate (C). 21 ), standard coverage (C 22 ), data sharing (C 23 ), quality inspection (C 24Data application includes two tertiary evaluation indicators: application scenario (C) 31 Service Management (C) 32 ). OT equipment includes two tertiary evaluation indicators: intelligent terminal (D ). 11 ), equipment operation (D) 12 IT infrastructure includes three tertiary evaluation indicators: platform support (D) 21 ), system architecture (D) 22 Network construction (D) 23 Cybersecurity includes two tertiary evaluation indicators: cybersecurity (D). 31 Safety drills (D) 32 Production digitalization includes eight tertiary evaluation indicators: equipment digitalization (E...). 11 ), device network connectivity (E 12 Equipment linkage rate (E) 13 ), platform access rate (E) 14 Remote scheduling (E) 15 ), degree of centralized control (E 16 AI applications (E) 17 ), video coverage (E) 18 Digital management includes two tertiary evaluation indicators: business systems (E) 21 ), System Integration (E) 22 Digital business comprises two tertiary performance indicators: revenue (E) 31 ), E-commerce share (E) 32 Improving quality and efficiency includes three tertiary evaluation indicators: labor productivity (F...). 11 ), reduction ratio (F) 12 ), work time (F) 13 Satisfaction includes one three-level evaluation indicator: employee satisfaction (F). 21 The demonstration project includes two tertiary evaluation indicators: pilot demonstration (F) 31 ), Science and Technology Awards (F 32 The maturity level of digital transformation for enterprises in the coal industry is divided into 5 levels: L1, L2, L3, L4, and L5.

[0059] Specifically, the maturity levels of digital transformation for coal industry enterprises include: L1: Enterprises regard technology application as an important part of innovation and development. Technology is applied in major business activities. A support system for digital construction and management has been formed. Core business activities are fully integrated. L2: Enterprises have formulated relevant plans for digital transformation, with clear goals and tasks. Digital transformation is regarded as an important part of enterprise innovation and development. A management architecture supporting the digital construction and management of business has been established. Basic data management and application capabilities are available. Efficiency of core business activities has been improved. L3: Enterprises have clear and effective digital transformation path goals. A management architecture that meets the requirements of digital transformation has been established. Digital infrastructure effectively supports transformation needs. Data management and application capabilities have been significantly improved, and data from major business activities is interconnected. Digital empowerment of major business activities has yielded significant results. L4: Enterprises' digital transformation is highly integrated with their overall development path, and the digital transformation management architecture provides strong support. A complete data management architecture and high-level data application management capabilities are available, achieving overall data interconnection. Overall business transformation with data as the core element has been achieved, resulting in significant improvements in efficiency and quality. L5: Enterprises regard digital transformation as the core content of their transformation and development, and have built a mature digital enterprise management architecture. Possessing agile response capabilities across all enterprise domains and business lines, achieving world-leading productivity, innovation, and security in its industry. As an industry digitalization leader, it delivers effective digital empowerment for the industry.

[0060] In this optional embodiment, when setting detailed indicators and scoring rules for the maturity level of digital transformation of coal enterprises, the evaluation values ​​can be determined by objective assignment method and numerical calculation method respectively, based on the digital transformation needs of coal enterprises; a judgment matrix is ​​constructed using the analytic hierarchy process (AHP) and the weight coefficients are determined; the maximum eigenvalue and the vector of the corresponding feature of the judgment matrix are calculated, and the weight of each factor on the digital transformation of coal enterprises is calculated; the consistency ratio of the judgment matrix is ​​calculated, and if the consistency ratio is less than or equal to the preset value, the judgment matrix is ​​consistent; otherwise, the judgment matrix is ​​reconstructed.

[0061] Specifically, the evaluation values ​​are determined using both objective assignment and numerical calculation methods. The evaluation domain indicators and maturity levels are determined using the objective assignment method, while the detailed indicators are determined using the numerical calculation method.

[0062] Taking into account the evaluation purpose, principles, and business areas of participating companies, an objective assignment method is used to assign evaluation values ​​to the evaluation domains. Fixed weights are adopted to reduce the complexity of self-evaluation by companies, avoid increasing management costs due to dynamic adjustments, and facilitate cross-company and cross-mining area comparisons to form industry benchmarks. Specifically, the weights are: technology focus (10%), management structure (20%), data management (15%), technology application (15%), business transformation (35%), and comprehensive results (5%).

[0063] The maturity level evaluation values ​​are assigned as follows: L1[0.5, 1.5), L2[1.5, 2.5), L3[2.5, 3.5), L4[3.5, 4.5), L5[4.5, 5.0].

[0064] The detailed indicator evaluation values ​​are assigned using numerical calculation methods, where:

[0065] Leadership cognition (A) 11 The formula for calculating A is: 11 = N1 / N0; where N1 represents the number of senior and middle-level leaders who understand digital transformation, and N0 represents the total number of senior and middle-level leaders. Meeting frequency (A 12 The formula for calculating A is: 12 =N3 / N2; where N3 represents the number of special working meetings on digital transformation chaired by the company's main responsible person and the leader in charge, and N2 represents the total number of special working meetings chaired by the company's main responsible person and the leader in charge.

[0066] Planning (A) 21 The calculation method for A is as follows: 21 =N5 / N4; where N5 represents the number of specific documents on digital transformation that have been released, and N4 represents the total number of planning documents. (Leadership Organization (B)) 11 The calculation method for B is as follows: 11 =N9 / N8; where N9 represents the number of digital transformation-related leadership organizations set up at the corporate headquarters and the number of digital (informatization) departments set up in subordinate units, and N8 represents the total number of corporate headquarters organizations.

[0067] Departmental Ratio (B) 12 The calculation method for B is as follows: 12 =M1 / M0; where M1 represents the number of digital (information technology) departments in the affiliated unit, and M0 represents the total number of departments in the affiliated unit. Assessment Score (B) 21 The calculation method for B is as follows: 21 =M3 / M2; where M3 represents the performance evaluation score for digital transformation, and M2 represents the total performance evaluation score.

[0068] Institutional Coverage (B) 22 The calculation method for B is as follows: 22 =M5 / M4; where M5 represents the number of important areas involved in the digital (information-based) management system, and M4 represents the number of important areas in the digital transformation system. Process optimization (B 31 The calculation method for B is as follows: 31 =M7 / M6; where M7 represents the number of processes optimized in the past 5 years, and M6 represents the total number of processes streamlined in the past 5 years.

[0069] Process control (B) 32 The calculation method for B is as follows: 32 =M9 / M8; where M9 represents the number of business processes for which the enterprise has implemented digital management and control, and M8 represents the total number of streamlined processes. Number of personnel (B 41 The calculation method for B is as follows: 41 =O1 / O0; where O1 represents the number of employees related to the company's digitalization (informatization) and O0 represents the total number of employees in the company.

[0070] Training sessions (B) 42 The calculation method for B is as follows: 42 =O3 / O2; where O3 represents the number of people who participated in digital (information technology) training throughout the year, and O2 represents the number of people who participated in digital (information technology) training throughout the year. Cultural Creation (B 51 The calculation method for B is as follows: 51 =O5 / O4; where O5 represents the total investment in digitalization (informatization) in the past 5 years, and O4 represents the main business revenue in the past 5 years.

[0071] Propaganda Position (B) 52 The calculation method for B is as follows: 52 =O7 / O6; where O7 represents the actual number of digital cultural activities held, and O6 represents the planned number of digital cultural activities held. Team building (B 61 The calculation method for B is as follows: 61 =O9 / O8; where O9 represents the number of channels used to promote digital transformation, and O8 represents the total number of all promotional channels.

[0072] Automatic data collection (C) 11 The calculation method for C is as follows: 11 =P1 / P0; where P1 represents the number of data indicators automatically collected by the enterprise, and P0 represents the total number of data indicators of the enterprise. Data source integration (C 12 The calculation method for ) is as follows:

[0073] C 12 =P3 / P2; where P3 represents the number of successfully integrated data sources and P2 represents the total number of data sources.

[0074] New data volume (C) 13 The calculation method for C is as follows: 13 =P5 / P4; where P5 represents the average monthly increase in data, and P4 represents 12 months. Data aggregation rate (C 21 The calculation method for C is as follows: 21 =P7 / P6; where P7 represents the number of data items (or data attributes) that have been uniformly incorporated into the platform for data asset management, and P6 represents the total number of data items (or data attributes) of the enterprise.

[0075] Standard Coverage (C) 22 The calculation method for C is as follows: 22 =P9 / P8; where P9 represents the number of major areas involved in the data standards built by the enterprise, and P8 represents the number of important data standard areas for digital transformation. Data sharing (C 23 The calculation method for C is as follows: 23 =V1 / V0; where V1 represents the number of datasets that have been shared within the enterprise, and V0 represents the total number of datasets in the enterprise.

[0076] Quality Inspection (C) 24 The calculation method for C is as follows: 24 =V3 / V2; where V3 represents the number of times the data quality check passed, and V2 represents the total number of data quality checks performed. Application Scenario (C 31 The calculation method for C is as follows: 31 =V5 / V4; where V5 represents the number of data application scenarios that the enterprise has successfully launched and is running, and V4 represents the total number of data application scenarios that the enterprise plans to develop. Service Management (C 32 The calculation method for C is as follows: 32 =V7 / V6; where V7 represents the total user satisfaction rating for the data service, and V6 represents the total number of times the data service is used.

[0077] Smart terminal (D) 11 The calculation method for ) is: D 11 =Q1 / Q0; where Q1 represents the total number of smart terminals in the enterprise, and Q0 represents the total number of employees in the enterprise. Equipment operation (D 12 The calculation method for ) is: D 12 =Q3 / Q2; where Q3 represents the time the OT equipment operates in a fault-free state, and Q2 represents the total actual usage time of the OT equipment. Platform Support (D 21 The calculation method for ) is: D 21 =Q5 / Q4; where Q5 represents the number of applications supported by the enterprise-level technology application platform, and Q4 represents the total number of enterprise applications.

[0078] System Architecture (D) 22 The calculation method for ) is: D 22 =Q7 / Q6; where Q7 represents the degree of modularity in the system architecture, and Q6 represents the complexity of the system architecture. Network Construction (D 23 The calculation method for ) is as follows:

[0079] D 23 =Q9 / Q8; where Q9 represents the used network bandwidth and Q8 represents the total network bandwidth. Network security (D 31 The calculation method for ) is: D31 =Q 11 / Q 10 In the formula, Q 11 Q represents the number of network attacks successfully defended. 10 Indicates the number of network attacks. Security Drills (D 32 The calculation method for ) is: D 32 =Q 13 / Q 12 In the formula, Q 13 Q represents the number of safety drills actually conducted. 12 This indicates the total number of planned safety drills.

[0080] Equipment digitization (E 11 The calculation method for E is: 11 =R1 / R0; where R1 represents the digital production equipment and R2 represents the number of coal mine production equipment. Equipment linkage rate (E 13 The calculation method for E is: 13 =R5 / R4; where R5 represents the number of upstream and downstream equipment in the production system that achieve linkage control and mutual logical interlocking, and R4 represents the number of main equipment in the production system.

[0081] Platform access rate (E) 14 The calculation method for E is: 14 =R7 / R6; where R7 represents the number of business systems connected to the automation platform, and R6 represents the total number of business systems. Remote Dispatch (E 15 The calculation method for E is: 15 =R9 / R8; where R9 represents the number of intelligent subsystems in the mine that have achieved remote centralized monitoring and dispatch, and R8 represents the number of main intelligent subsystems in the mine.

[0082] Degree of centralized control (E 16 The calculation method for E is: 16 =R 11 / R 10 In the formula, R 11 R represents the number of intelligent subsystems that have been implemented in the coal preparation plant for remote centralized monitoring and dispatching. 10 This indicates the number of major intelligent subsystems in a coal preparation plant. AI applications (E) 17 The calculation method for E is: 17 =S1 / S0; where S1 represents the number of violations discovered through AI and other means, and S0 represents the total number of violations discovered.

[0083] Video coverage (E) 18 The calculation method for E is: 18=S3 / S2; where S3 represents the number of areas already covered by the enterprise video, and S2 represents the number of areas the enterprise video should cover. Business System (E 21 The calculation method for E is: 21 =S5 / S4; where S5 represents the number of systems already built, and S4 represents the number of business systems. System Integration (E 22 The calculation method for E is: 22 =S7 / S6; where S7 represents the number of integrated systems and S6 represents the total number of systems.

[0084] Operating revenue (E) 31 The calculation method is: E 31 = S9 / S8; where S9 represents the revenue directly generated by the company through digital transformation, and S8 represents the total revenue of all the company's businesses. E-commerce share (E 32 The calculation method for E is: 32 =S 11 / S 10 In the formula, S 11 S represents the value of e-commerce transactions. 10 This indicates revenue from main business operations.

[0085] Labor productivity (F) 11 The calculation method for F is: 11 =T1 / T0; where T1 represents the total production output of the enterprise in one year, and T0 represents the number of workers employed in one year. Staff reduction ratio (F) 12 The calculation method for F is: 12 =T3 / T2; where T3 represents the number of employees replaced in production positions in the past 5 years, and T2 represents the total number of employees in the company 5 years ago.

[0086] Work time (F) 13 The calculation method for F is: 13 =T5 / T4; where T5 represents the actual time spent completing the mining face, and T4 represents the planned time to complete the mining face. Employee satisfaction (F 21 The calculation method for F is: 21 =T7 / T6; where T7 represents the number of employees who are satisfied with the digital transformation, and T6 represents the total number of employees in the company.

[0087] Pilot demonstration (F 31 The calculation method for F is: 31 =T9 / T8; where T9 represents the number of pilot demonstration projects successfully obtained by the enterprise, and T8 represents the total number of pilot demonstration projects applied for by the enterprise. Science and Technology Awards (F 32 The calculation method for F is: 32 =T 11 / T10 In the formula, T 11 This indicates the number of industry science and technology awards received for scientific and technological achievements in the past three years. 10 This indicates the number of science and technology awards applied for by the company in the past three years.

[0088] In this optional embodiment, when determining the evaluation value based on the digital transformation needs of coal enterprises using both objective assignment and numerical calculation methods, the evaluation domain can be assigned values ​​using the objective assignment method based on the digital transformation needs of coal enterprises to obtain a unified evaluation weight system; based on industry comparison needs, the maturity level of digital transformation of coal enterprises can be divided using the interval assignment method to obtain several maturity evaluation intervals; based on the operational data of coal enterprises, the detailed indicators can be assigned values ​​using the numerical calculation method to obtain a quantitative calculation model covering several third-level indicators.

[0089] In this optional embodiment, when constructing the judgment matrix using the analytic hierarchy process (AHP) and determining the weight coefficients, the digital transformation of coal enterprises can be divided into hierarchical structures. The comprehensive score of digital transformation of coal enterprises, several evaluation domains, several evaluation sub-domains, and several detailed indicators are respectively used as the target layer, criterion layer, sub-criterion layer, and scheme layer. Based on the evaluation sub-domains of the sub-criterion layer, the detailed indicators under the same evaluation sub-domain are compared pairwise to construct the judgment matrix of the detailed indicators and determine the respective weights of the evaluation sub-domains and detailed indicators. The elements of the judgment matrix are quantitatively assigned using the matrix judgment scale (1-9 scale method) to obtain numerical comparison results reflecting relative importance. Based on the expert evaluation results, the geometric mean method is used to summarize all expert scoring matrices to obtain the comprehensive judgment matrix.

[0090] Specifically, the comprehensive scoring system for digital transformation of coal enterprises is set as the target layer; 6 evaluation domains serve as the criterion layer; 20 evaluation subdomains serve as the sub-criterion layer; and 49 detailed indicators serve as the solution layer.

[0091] After setting the hierarchy, a judgment matrix is ​​established to determine the weights of the evaluation subdomains and detailed indicators, specifically including:

[0092] Construct k judgment matrices B, and select different detailed indicators under the same evaluation subdomain to compare their relative importance pairwise. The judgment matrices are as follows:

[0093]

[0094] In the formula, I = 1, 2, ..., k, i = 1, 2, ..., n, j = 1, 2, ..., n, where B I Representing different evaluation subdomains; X i X j This represents two different refinement indicators for the same evaluation subdomain; X ijThis indicates the result of comparing the refined indicators at the same level.

[0095] To quantify the importance of each element in the matrix, a matrix judgment scale (1-9 scale) is introduced. The scale ranges from 1 to 9, where 1 indicates that two elements are equally important, and 9 indicates that one element is significantly more important than the other. In this assignment method, a larger number indicates a higher importance in pairwise comparisons, and vice versa, as shown in Table 1 below.

[0096] Table 1. Judgment Matrix

[0097]

[0098] In constructing the judgment matrix, experts in the field of digital transformation were invited to compare the importance of elements and assign scores. The judgment matrix was then completed, and the scores were calculated using the geometric mean method from the questionnaire. This approach aimed to ensure scientific rigor while effectively balancing the diversity of expert opinions with the needs of industry practice. Ultimately, a judgment matrix for the evaluation subdomain was constructed, specifically including:

[0099] Suppose there are m experts participating in the scoring, and we need to compare n indicators at the same level pairwise to construct a judgment matrix; each expert provides a judgment matrix:

[0100]

[0101] In the formula, This represents the importance score that the k-th expert considers to indicator i relative to indicator j, satisfying the following condition. and

[0102] Take the geometric mean of each element in the rating matrix for each expert:

[0103]

[0104] In the formula, This represents the geometric mean of the elements in the judgment matrix.

[0105] Similarly, the judgment matrix of the evaluation subdomain can be obtained by constructing the judgment matrix of the evaluation domain.

[0106] In this optional embodiment, when calculating the maximum eigenvalue and the vector of the corresponding eigenvalue of the judgment matrix, and calculating the weight of each factor on the digital transformation of coal enterprises, the columns of the judgment matrix can be normalized, and the original scores can be mapped to the standardized space through linear transformation to eliminate the differences in expert scoring scales; the normalized judgment matrix is ​​summed to obtain the weight of each factor on the digital transformation of coal enterprises.

[0107] Specifically, by solving for the largest eigenvalue and the corresponding eigenvector of the judgment matrix, the weights of each factor's impact on the digital transformation of coal enterprises are calculated. The specific process is as follows:

[0108] The columns of the judgment matrix are normalized. Column normalization maps the original scores to a standardized space through a linear transformation, ensuring that the weight calculation is not affected by extreme values ​​and eliminating differences in expert scoring scales.

[0109]

[0110] In the formula, This represents the result after normalizing the elements in each column. This represents the element in the i-th row and j-th column of the judgment matrix.

[0111] Normalizing the rows of the judgment matrix aims to eliminate differences in units and standardize the data, preventing an indicator from being overweighted due to excessive expert bias.

[0112]

[0113] In the formula, u i This represents the sum of the elements in each row. This represents the weight vector.

[0114] In this optional embodiment, when calculating the consistency ratio of the judgment matrix, if the consistency ratio is less than or equal to a preset value, the judgment matrix is ​​considered consistent; otherwise, when reconstructing the judgment matrix, the product of the judgment matrix and the weight vector can be calculated to obtain the maximum eigenvalue of the judgment matrix; the consistency index and the order of the judgment matrix are calculated based on the maximum eigenvalue, and the consistency ratio is calculated; if the consistency ratio is less than or equal to the preset value, the judgment matrix is ​​considered consistent; otherwise, the judgment matrix is ​​reconstructed.

[0115] Specifically, the consistency ratio CR is calculated to test the consistency of the judgment matrix. If CR ≤ 0.1, the matrix is ​​considered to have satisfactory consistency; otherwise, the consistency test fails, and the judgment matrix needs to be reconstructed. The largest eigenvalue is calculated.

[0116]

[0117] In the formula, Represents the judgment matrix A and the weight vector The product of, U i These are the elements of the weight vector.

[0118] Calculate the consistency ratio (CR):

[0119]

[0120] In the formula, λ maxrepresents the largest eigenvalue of the judgment matrix; n represents the order of the judgment matrix; RI represents the average random consistency index. In addition, when n=1, the analytic hierarchy process assumes complete consistency and there is no need to calculate CR.

[0121] In this optional embodiment, when constructing a comprehensive evaluation model for the digital transformation evaluation indicators of coal enterprises, calculating the comprehensive score of digital transformation of coal enterprises, and determining the maturity level of digital transformation of coal enterprises, the digital transformation of coal enterprises can be divided into a hierarchical structure. The comprehensive score of digital transformation of coal enterprises, several evaluation domains, several evaluation sub-domains, and several detailed indicators are respectively used as the target layer, criterion layer, sub-criterion layer, and solution layer. The weight of each evaluation domain is determined, and a judgment matrix is ​​constructed and the weight coefficients are calculated through scoring rules and expert opinions. The weights of the evaluation sub-domains and detailed indicators are calculated and a consistency check is performed to ensure the consistency of the matrix. The weight coefficients of each evaluation domain, evaluation sub-domain, and detailed indicator are substituted into the comprehensive evaluation mathematical model of digital transformation to calculate the comprehensive score. The maturity level of digital transformation of coal enterprises is determined by the calculated comprehensive score.

[0122] Specifically, the weights are determined using the scoring rules and based on the analytic hierarchy process (AHP):

[0123] The hierarchical structure is constructed as follows: the comprehensive score of digital transformation of coal enterprises serves as the target layer; 6 primary indicators serve as the criteria layer; 20 secondary indicators serve as the sub-criteria layer; and 49 tertiary indicators serve as the solution layer.

[0124] The evaluation domain weights are:

[0125] W = [w A ,w B ,w C ,w D ,w E ,w F = [0.10, 0.20, 0.15, 0.15, 0.35, 0.05];

[0126] In the formula, w A w B w C w D w E w F These represent the weights for technology focus, management structure, data management, technology application, business transformation, and overall results evaluation, respectively.

[0127] Construct a judgment matrix to determine the evaluation subdomains and refine the indicator weights: Use the 1-9 scale method and invite experts to compare the importance of each indicator at the same level pairwise; integrate the opinions of multiple experts and calculate the geometric mean to construct the judgment matrix.

[0128] Calculate the weight vector: Normalize the elements of each column of the judgment matrix, sum the rows of the normalized matrix and normalize them again to obtain the weight vector. Consistency check: CR≤0.1, pass the check; otherwise, the judgment matrix needs to be adjusted until all evaluation subdomains and refined index weights are confirmed.

[0129] By substituting the evaluation indicators of digital transformation of coal enterprises into the comprehensive assessment mathematical model, the overall score can be obtained:

[0130]

[0131] In the formula, W A W B W C W D W E W F These represent the overall scores for technology focus, management structure, data management, technology application, business transformation, and comprehensive results; A i a 1i a 2i B represents the value of the i-th detailed indicator in the technology focus, the weight of the evaluation subdomain, and the weight of the detailed indicator, respectively; j b 1j b 2j Represent the value, evaluation subdomain weight, and detailed indicator weight corresponding to the j-th item of the detailed indicator in the management structure, respectively; C k c 1k c 2k D represents the value, evaluation subdomain weight, and detailed indicator weight corresponding to the k-th item of the detailed indicator in data management, respectively; l d 1l d 2l These represent the numerical value, evaluation subdomain weight, and detailed indicator weight corresponding to the l-th item of the detailed indicator in the technical application, respectively; E m e 1m e 2m These represent the value, evaluation subdomain weight, and detailed indicator weight corresponding to the m-th detailed indicator in the business transformation, respectively; F n f 1n f 2n Represent the value of the nth detailed indicator in the comprehensive results, the weight of the evaluation subdomain, and the weight of the detailed indicator, respectively; N A N B N C N D N E N F These represent the total number of evaluation subdomains included in each of the following indicators: technology focus, management structure, data management, technology application, business transformation, and comprehensive results evaluation.

[0132] Specifically, the total score for the digital transformation of coal enterprises is obtained by calculating the evaluation values ​​and weight coefficients corresponding to the evaluation domain, evaluation subdomain, and refined indicators, and then inputting them into the comprehensive evaluation mathematical model of the evaluation indicators for the digital transformation of coal enterprises.

[0133] Specifically, the maturity level of digital transformation of coal enterprises is divided into five levels: L1 (0.5≤W<1.5), L2 (1.5≤W<2.5), L3 (2.5≤W<3.5), L4 (3.5≤W<4.5), and L5 (4.0≤W<5.0).

[0134] Figure 2 An embodiment of the coal enterprise digital transformation evaluation system of the present invention is shown.

[0135] In this optional embodiment, the digital transformation evaluation system for coal enterprises includes:

[0136] Data storage module 201 is used to store data related to the digital transformation of coal enterprises, and to clean and preprocess the data to ensure the accuracy and integrity of the data.

[0137] Module 202, which establishes the indicator system, is used to establish the primary, secondary, and tertiary indicators required for the evaluation of digital transformation of coal enterprises.

[0138] The evaluation value calculation module 203 is used to calculate the evaluation value of each level of indicator and obtain the score of each collection item through evaluation verification scoring;

[0139] The weight coefficient calculation module 204 is used to calculate the weight coefficients of each level of indicators in the digital transformation evaluation index system.

[0140] The comprehensive evaluation module 205 is used to calculate the comprehensive score of the digital transformation of coal enterprises based on the evaluation value and weight coefficient of each indicator, and to determine the maturity level of the digital transformation of coal enterprises.

[0141] Specifically, the evaluation system for digital transformation of coal enterprises includes 5 primary modules and 11 secondary modules, among which:

[0142] The five primary modules include: data storage module 201(G), indicator system establishment module 202(H), evaluation value calculation module 203(I), weight coefficient calculation module 204(J), and comprehensive evaluation module 205(K).

[0143] The 11 secondary modules include: Data storage module 201, which contains two secondary modules: data classification and storage module (G1) and data backup and recovery module (G2). Indicator system establishment module 202, which contains two secondary modules: indicator system adjustment module (H1) and indicator correlation analysis module (H2). Evaluation value calculation module 203, which contains two secondary modules: evaluation value calculation module (I1) and indicator scoring module (I2). Weight coefficient calculation module 204, which contains three secondary modules: judgment matrix construction module (J1), eigenvector calculation module (J2), and consistency verification module (J3). Comprehensive evaluation module 205, which contains two secondary modules: evaluation model calculation module (K1) and maturity level classification module (K2).

[0144] Specifically, the data storage module 201 is used to store data related to the digital transformation of coal enterprises, and to clean and preprocess the data to ensure the accuracy and integrity of the data, and to ensure that the collected evaluation data is easy to collect and analyze.

[0145] The indicator system establishment module 202 is used to establish key indicators involved in the evaluation process of digital transformation of coal enterprises, including six primary indicators: technology focus, management structure, data management, technology application, business transformation, and comprehensive results, as well as corresponding secondary and tertiary indicators.

[0146] The evaluation value calculation module 203 is used to calculate the evaluation values ​​of the key indicators involved in the digital transformation evaluation index system, and obtains the scores of each collection item through on-site evaluation and verification scoring.

[0147] The weight coefficient calculation module 204 is used to calculate the weight coefficient of each level indicator in the digital transformation evaluation index system. Taking into account factors such as the evaluation purpose, principles and business areas of participating companies, it determines appropriate weights to calculate the scores of the secondary indicators, primary indicators and comprehensive scores.

[0148] The comprehensive evaluation module 205 is used to calculate the comprehensive score of the digital transformation of coal enterprises based on the evaluation value and weight coefficient of each indicator, determine the level of digital transformation, and provide a basis for evaluation of the digital transformation of coal enterprises.

[0149] Specifically, the data classification and storage module classifies and stores data related to the digital transformation of coal enterprises, covering production data, management data, equipment data, and other aspects, to facilitate subsequent querying and analysis.

[0150] Data backup and recovery module: Establishes a multi-copy backup mechanism, performs regular data backups, and has rapid recovery capabilities to prevent data loss.

[0151] The indicator system adjustment module updates the indicator system based on the latest developments and industry trends in the digital transformation of coal enterprises, ensuring the timeliness and accuracy of the indicators. At the same time, an internal feedback mechanism is established to adjust the indicator system based on actual application effects and user feedback, ensuring its adaptability.

[0152] Indicator Correlation Analysis Module: Through data analysis technology, this module identifies the relationships between indicators, identifies key indicators and influencing factors, provides a basis for enterprises to formulate digital transformation strategies, and analyzes the causal relationships between indicators to help enterprise managers understand the internal logic of digital transformation and optimize resource allocation.

[0153] Evaluation value calculation module: Evaluation values ​​are determined using both objective assignment and numerical calculation methods. Objective assignment is used for evaluation domain indicators and maturity levels, while numerical calculation is used for detailed indicators.

[0154] Indicator scoring module: The score for each data collection item is obtained through on-site evaluation and verification scoring, and the evaluation value of the detailed indicators is calculated according to the set calculation formula.

[0155] Judgment Matrix Construction Module: Using the analytic hierarchy process (AHP), a judgment matrix is ​​constructed by selecting different detailed indicators under the same evaluation subdomain and comparing their relative importance pairwise to establish the judgment matrix.

[0156] Eigenvector Calculation Module: By solving for the largest eigenvalue and the corresponding eigenvector of the judgment matrix, the module calculates the weight of each factor's impact on the digital transformation of coal enterprises.

[0157] Consistency check module: Calculates the consistency ratio CR to check the consistency of the judgment matrix. If CR≤0.1, the matrix is ​​considered to have satisfactory consistency; otherwise, the judgment matrix needs to be reconstructed.

[0158] Evaluation model calculation module: Based on the analytic hierarchy process, the weights of the indicators are determined, a comprehensive evaluation mathematical model for the digital transformation of coal enterprises is constructed, and the evaluation values ​​and weight coefficients of each indicator are input into the comprehensive evaluation model to calculate the comprehensive score of the digital transformation of coal enterprises.

[0159] Maturity Level Classification Module: The digital transformation maturity level of coal enterprises is determined based on the comprehensive score, and is divided into five levels: L1, L2, L3, L4 and L5.

[0160] Specifically, the data analysis techniques in the indicator correlation analysis module include:

[0161] The system obtains raw data for all third-level indicators from enterprise databases, IoT devices, and management systems, removes invalid data (such as abnormal records when equipment malfunctions), fills in missing values ​​(using average values ​​or industry standard values ​​as substitutes), and converts all indicator data to the same dimension (such as the range of 0 to 1) to facilitate subsequent comparisons.

[0162] Analyze the correlation between indicators: Use tools (such as Excel, Python) to automatically calculate the correlation strength between each pair of indicators, generate heatmaps to visually display the high correlation between indicators, and combine expert experience to confirm key indicators.

[0163] Uncovering causal relationships: Observe the changes in indicators in chronological order to determine whether there are causal relationships. Hypothesize causal chain (such as "path planning → system improvement → process optimization") and verify the validity of the path through data. This helps enterprise managers understand the internal logic of digital transformation and optimize resource allocation.

[0164] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 3 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database stores static and dynamic information data. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements the steps in the above method embodiments.

[0165] Those skilled in the art will understand that Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present invention and does not constitute a limitation on the computer device to which the present invention is applied. A specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0166] In addition, the present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0167] In addition, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0168] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. Any references to memory, storage, databases, or other media used in the embodiments provided by this invention can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0169] This invention is not limited to the structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this invention is limited only by the appended claims.

Claims

1. A method for evaluating the digital transformation of coal enterprises, characterized in that, include: Based on the organizational structure and core business processes of coal enterprises, a multi-objective genetic algorithm is used to dynamically set the evaluation domain for each evaluation dimension. Based on the key driving factors of the evaluation domain, corresponding evaluation subdomains, detailed indicators, and maturity levels of digital transformation of coal enterprises are set, and scoring rules for detailed indicators and maturity levels of digital transformation of coal enterprises are set. A comprehensive evaluation model for digital transformation evaluation indicators of coal enterprises is constructed to calculate the comprehensive score of digital transformation of coal enterprises and determine the maturity level of digital transformation of coal enterprises.

2. The evaluation method for digital transformation of coal enterprises according to claim 1, characterized in that, The process of dynamically setting the evaluation domain for each evaluation dimension based on the organizational structure and core business processes of coal enterprises, using a multi-objective genetic algorithm, includes: An initial population is randomly generated, with each individual representing a set of primary indicators of selection state. The fitness of each individual is evaluated, the comprehensive score of each individual is calculated, and the minimum resource consumption is calculated. Based on the obtained fitness, the population is subjected to fast non-dominated sorting, and individuals are divided into different front layers according to non-dominated relations. The crowding degree of individuals in each non-dominated layer is calculated, and the individuals with the highest fitness are selected to form a new parent population based on crowding degree and ranking. The new parent population is subjected to elite preservation to ensure that the most fit individuals enter the next generation population. Selection, crossover and mutation operations are performed on the new parent population to generate offspring populations and obtain a new population. Determine whether the maximum number of iterations has been reached. If it has, output the optimized population and its corresponding evaluation domain combination, and select the optimal solution on the Pareto front.

3. The evaluation method for digital transformation of coal enterprises according to claim 1, characterized in that, The key driving factors based on the evaluation domain, corresponding to the setting of evaluation subdomains, detailed indicators, and maturity levels of digital transformation for coal enterprises, include: Based on the digital transformation needs of coal enterprises, an evaluation domain is constructed using several primary indicators as key drivers of digital transformation. For each primary indicator, several secondary indicators are set as evaluation subdomains to ensure that each primary indicator contains corresponding secondary indicators. Based on each secondary indicator, several tertiary indicators are set as detailed indicators, and the evaluation content of each secondary indicator is further refined. Based on primary, secondary, and tertiary indicators, an evaluation system for the digital transformation of coal enterprises is constructed. Based on the established evaluation domains, subdomains, and detailed indicators, the maturity of digital transformation of coal enterprises is graded into several maturity levels, reflecting the transformation maturity of enterprises at different stages. Based on several maturity levels of digital transformation in coal enterprises, the descriptions of each level are categorized and organized to correspond to different stages of digital transformation in coal enterprises.

4. The evaluation method for digital transformation of coal enterprises according to claim 3, characterized in that, The detailed indicators and scoring rules for the maturity level of digital transformation of coal enterprises include: Based on the digital transformation needs of coal enterprises, the evaluation value is determined by both the objective assignment method and the numerical calculation method. Construct a judgment matrix using the analytic hierarchy process (AHP) and determine the weight coefficients; Calculate the largest eigenvalue and the vector of the corresponding eigenvalue of the judgment matrix, and calculate the weight of each factor on the digital transformation of coal enterprises. Calculate the consistency ratio of the judgment matrix. If the consistency ratio is less than or equal to the preset value, the judgment matrix is ​​consistent; otherwise, reconstruct the judgment matrix.

5. The evaluation method for digital transformation of coal enterprises according to claim 4, characterized in that, The determination of evaluation values ​​based on the digital transformation needs of coal enterprises, using both objective assignment and numerical calculation methods, includes: Based on the digital transformation needs of coal enterprises, the evaluation domain is assigned values ​​using an objective assignment method to obtain a unified evaluation weight system. Based on the need for industry comparison, the maturity level of digital transformation of coal enterprises is divided into several maturity evaluation intervals using the interval assignment method. Based on coal enterprise operation data, a numerical calculation method is used to assign values ​​to detailed indicators, resulting in a quantitative calculation model covering several tertiary indicators.

6. The evaluation method for digital transformation of coal enterprises according to claim 5, characterized in that, The process of constructing the judgment matrix using the analytic hierarchy process (AHP) and determining the weight coefficients includes: The digital transformation of coal enterprises is divided into hierarchical structures, and the comprehensive score of digital transformation of coal enterprises, several evaluation domains, several evaluation sub-domains and several detailed indicators are respectively used as the target layer, the criterion layer, the sub-criterion layer and the scheme layer. Based on the evaluation subdomain of the sub-criteria layer, pairwise comparisons are made between the refined indicators under the same evaluation subdomain to construct the judgment matrix of the refined indicators and determine the respective weights of the evaluation subdomain and the refined indicators. The elements of the judgment matrix are quantified and assigned values ​​using a matrix judgment scale to obtain numerical comparison results that reflect relative importance; Based on the expert evaluation results, the geometric mean method was used to summarize all the expert rating matrices to obtain the comprehensive judgment matrix.

7. The evaluation method for digital transformation of coal enterprises according to claim 6, characterized in that, The calculation of the maximum eigenvalue and the corresponding eigenvector of the judgment matrix, and the calculation of the weights of each factor on the digital transformation of coal enterprises, include: The columns of the judgment matrix are normalized, and the original scores are mapped to the standardized space through linear transformation to eliminate differences in expert scoring scales. The normalized judgment matrix is ​​summed to obtain the weights of each factor on the digital transformation of coal enterprises.

8. The evaluation method for digital transformation of coal enterprises according to claim 7, characterized in that, The process of calculating the consistency ratio of the judgment matrix, if the consistency ratio is less than or equal to a preset value, indicates that the judgment matrix is ​​consistent; otherwise, the process of reconstructing the judgment matrix includes: Calculate the product of the judgment matrix and the weight vector to obtain the largest eigenvalue of the judgment matrix; Calculate the consistency index based on the largest eigenvalue, determine the order of the matrix, and calculate the consistency ratio. If the consistency ratio is less than or equal to the preset value, the judgment matrix is ​​consistent; otherwise, the judgment matrix is ​​reconstructed.

9. The evaluation method for digital transformation of coal enterprises according to claim 8, characterized in that, The comprehensive evaluation model for constructing evaluation indicators for the digital transformation of coal enterprises, calculating the comprehensive score of digital transformation of coal enterprises, and determining the maturity level of digital transformation of coal enterprises includes: The digital transformation of coal enterprises is divided into hierarchical structures, and the comprehensive score of digital transformation of coal enterprises, several evaluation domains, several evaluation sub-domains and several detailed indicators are respectively used as the target layer, the criterion layer, the sub-criterion layer and the scheme layer. Determine the weight of each evaluation domain, construct a judgment matrix based on scoring rules and expert opinions, and calculate the weight coefficients; The weights of the evaluation subdomains and refined indicators are calculated, and a consistency check is performed to ensure the consistency of the matrix. The weight coefficients of each evaluation domain, evaluation subdomain, and detailed indicator are input into the mathematical model for comprehensive evaluation of digital transformation to calculate the comprehensive score. The maturity level of digital transformation of coal enterprises is then determined based on the calculated comprehensive score.

10. A digital transformation evaluation system for coal enterprises, characterized in that, include: The data storage module is used to store data related to the digital transformation of coal enterprises, and to perform data cleaning and preprocessing to ensure the accuracy and integrity of the data. The indicator system establishment module is used to establish the primary, secondary, and tertiary indicators required in the evaluation process of digital transformation of coal enterprises. The evaluation value calculation module is used to calculate the evaluation value of each level of indicators and obtain the score of each collection item through evaluation verification and scoring; The weight coefficient calculation module is used to calculate the weight coefficients of each level of indicators in the digital transformation evaluation index system. The comprehensive evaluation module is used to calculate the comprehensive score of the digital transformation of coal enterprises based on the evaluation value and weight coefficient of each indicator, and to determine the maturity level of the digital transformation of coal enterprises.

Images