Method, device and medium for quantitatively evaluating energy-saving benefits of an enterprise based on multi-dimensional indexes

Abstract

This application provides a method, equipment, and medium for quantitatively assessing enterprise energy-saving benefits based on multi-dimensional indicators, belonging to the field of energy-saving assessment technology. The method includes: acquiring various production energy consumption data; clustering these data according to pre-constructed multi-dimensional evaluation indicators; calculating the contribution rate of each dimension of the evaluation indicators to the enterprise's energy-saving benefits based on the relationship between the multi-dimensional evaluation indicators and the enterprise's energy-saving benefits; fusing the multi-dimensional evaluation indicators according to the contribution rate and the similarity of different dimensions to obtain a comprehensive quantitative score for the enterprise's energy-saving benefits; and generating energy-saving benefit improvement suggestions based on the comprehensive quantitative score, combined with a dynamic knowledge graph and expert experience decision tree. This application's technical solution addresses the problems of existing technologies where the quantification of enterprise energy-saving benefits is not accurate enough, making it difficult to accurately convert energy conservation and emission reduction into economic benefits, thus reducing enterprises' enthusiasm for energy conservation.

Description

Technical Field

[0001] This application belongs to the field of energy conservation assessment technology, specifically involving a method, equipment, and medium for quantitative assessment of enterprise energy conservation benefits based on multi-dimensional indicators. Background Technology

[0002] Currently, while methods for quantitatively assessing corporate energy efficiency can collect multi-dimensional data related to energy conservation, such as energy consumption data (electricity, water, and gas), equipment operation data, environmental data, and carbon emission data, they do not comprehensively consider the contribution of these data to corporate energy efficiency and conduct quantitative assessments. Instead, they simply perform weighted fusion for multi-attribute quantitative assessments.

[0003] The above methods are prone to inaccurate quantification of energy-saving benefits for enterprises, making it even more difficult to accurately convert energy conservation and emission reduction into economic benefits, thus reducing enterprises' enthusiasm for energy conservation. Summary of the Invention

[0004] The technical solution described in this application aims to provide a method, equipment, and medium for quantitatively evaluating enterprise energy-saving benefits based on multi-dimensional indicators. This solution can solve the problems of insufficient accuracy in quantifying enterprise energy-saving benefits in existing technologies, making it even more difficult to accurately convert energy conservation, emission reduction, and economic benefits, thus reducing enterprises' enthusiasm for energy conservation.

[0005] According to a first aspect of this application, this application provides a method for quantitatively evaluating enterprise energy-saving benefits based on multi-dimensional indicators, including: Acquire various production energy consumption data and cluster them according to pre-constructed multidimensional evaluation indicators; Based on the relationship between multidimensional evaluation indicators and enterprise energy-saving benefits, the contribution rate of each dimension of evaluation indicators to enterprise energy-saving benefits is calculated. Based on the contribution rate and the similarity of evaluation indicators from different dimensions, data fusion is performed on the multi-dimensional evaluation indicators to obtain a comprehensive quantitative score of the enterprise's energy-saving benefits. Based on the comprehensive quantitative score, combined with dynamic knowledge graph and expert experience decision tree, suggestions for improving energy-saving benefits are generated.

[0006] Preferably, in the above-mentioned quantitative assessment method for enterprise energy-saving benefits, based on the comprehensive quantitative score, combined with dynamic knowledge graphs and expert experience decision trees, suggestions for improving energy-saving benefits are generated, including: Based on the comprehensive quantitative scoring, the multi-dimensional evaluation indicators are matched with similar cases in the dynamic knowledge graph in multiple dimensions; Based on the degree of matching across multiple dimensions, the cosine similarity between the multidimensional evaluation index and similar cases is calculated. Similar cases with a cosine similarity score above the similarity threshold are extracted and used as energy efficiency reference cases. Using expert experience decision trees, and processing the uncertain conditions corresponding to energy efficiency reference cases through fuzzy membership functions, suggestions for improving energy-saving benefits are obtained.

[0007] Preferably, in the above-mentioned quantitative assessment method for enterprise energy-saving benefits, multiple production energy consumption data are clustered according to pre-constructed multi-dimensional evaluation indicators, including: Based on the multidimensional evaluation indicators including energy efficiency level, carbon emission performance, load characteristics and management capabilities, various production energy consumption data are clustered. An initial evaluation matrix is ​​constructed using clustered production energy consumption data, and the various production energy consumption data in the initial evaluation matrix are normalized to obtain a standardized evaluation matrix.

[0008] Preferably, in the above-mentioned quantitative assessment method for enterprise energy-saving benefits, based on the quantitative relationship between multi-dimensional evaluation indicators and enterprise energy-saving benefits, the contribution rate of each dimension of evaluation indicators to enterprise energy-saving benefits is calculated, including: Principal component analysis is used to decompose the standardized evaluation matrix into eigenvalues, and the eigenvalues ​​and eigenvectors corresponding to all production energy consumption data in the principal component direction are obtained. Sort the feature values ​​from largest to smallest, and select the top k production energy consumption data values ​​that satisfy the relationship between the cumulative variance contribution rate and the variance contribution rate threshold under the same evaluation index. The cumulative variance contribution rate corresponding to the first k production energy consumption data values ​​is used as the contribution rate of the corresponding dimension evaluation index to the enterprise's energy-saving benefits.

[0009] Preferably, in the above-mentioned quantitative evaluation method for enterprise energy-saving benefits, data fusion is performed on multi-dimensional evaluation indicators according to the contribution rate and the similarity of evaluation indicators of different dimensions to obtain a comprehensive quantitative score of enterprise energy-saving benefits, including: Various production energy consumption data are vectorized to obtain production energy consumption vectors; Calculate the similarity between production energy consumption vectors in different dimensions of evaluation indicators. When the similarity is less than or equal to a predetermined similarity threshold, reduce the contribution rate of the evaluation indicator according to a predetermined contribution rate decay algorithm. Using the final contribution rate and multi-dimensional evaluation indicators, a comprehensive quantitative score of the enterprise's energy-saving benefits is calculated using weighted average. Determine the rating level corresponding to the comprehensive quantitative score, and match the dynamic knowledge graph and expert experience decision tree according to the rating level.

[0010] Preferably, in the above-mentioned quantitative assessment method for enterprise energy-saving benefits, multiple production energy consumption data are clustered according to pre-constructed multi-dimensional evaluation indicators, including: The K-distance function is used to calculate the neighborhood distance between various production energy consumption data and standard data points in multidimensional evaluation indicators. Determine whether the neighborhood distance is less than or equal to a predetermined neighborhood threshold; If the neighborhood distance is less than or equal to the predetermined neighborhood threshold, the production energy consumption data will be classified into the evaluation index of the corresponding dimension. After classifying production energy consumption data into the corresponding evaluation indicators, the silhouette coefficient, Davidson-Bolding index, and complexity of each evaluation indicator are calculated. Clustering and scoring were performed on the evaluation indicators for each dimension according to the silhouette coefficient, Davidson-Bolding index, complexity, and scoring criteria. If the cluster score is less than or equal to the predetermined score threshold, the production energy consumption data will be clustered again.

[0011] Preferably, in the above-mentioned quantitative evaluation method for enterprise energy-saving benefits, data fusion is performed on multi-dimensional evaluation indicators according to the contribution rate and the similarity of evaluation indicators of different dimensions to obtain a comprehensive quantitative score of enterprise energy-saving benefits, including: Construct a contribution indicator matrix using contribution rate and corresponding dimensional evaluation indicators; The contribution index matrix is ​​input into the pre-trained XGBoost quality prediction model, and the output is the index data quality. The quality status of each production energy consumption data in the indicator is evaluated using the corresponding dimension of the indicator data quality estimation, and fluctuations in the quality status are given early warning.

[0012] Preferably, the above-mentioned method for quantitatively evaluating enterprise energy-saving benefits, after obtaining suggestions for improving energy-saving benefits, further includes: Integrate multi-dimensional evaluation indicators, comprehensive quantitative scores, and energy-saving benefit improvement suggestions to output a PDF report; Based on relevant energy-saving benefit standards, the PDF report was compiled and output.

[0013] According to a second aspect of this application, this application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor, when executing the program, implements the enterprise energy-saving benefit quantitative assessment method provided by any of the above technical solutions.

[0014] According to a third aspect of this application, this application also provides a computer storage medium having a computer program stored thereon, which, when executed, implements the enterprise energy-saving benefit quantitative assessment method provided by any of the above technical solutions.

[0015] The technical solution of this application has at least the following technical effects: The enterprise energy conservation benefit quantitative assessment scheme provided in this application obtains various production energy consumption data, clusters the data according to pre-constructed multi-dimensional evaluation indicators, and then calculates the contribution rate of each dimension of the evaluation indicators to the enterprise's energy conservation benefits based on the relationship between the multi-dimensional evaluation indicators and the enterprise's energy conservation benefits. The multi-dimensional evaluation indicators are then fused according to this contribution rate and the similarity of the evaluation indicators across different dimensions to obtain a comprehensive quantitative score for the enterprise's energy conservation benefits. Based on this comprehensive quantitative score, combined with a dynamic knowledge graph and expert experience decision tree, accurate suggestions for improving energy conservation benefits can be generated. This method can accurately quantify enterprise energy conservation benefits, thereby enabling accurate energy conservation, emission reduction, and economic benefit conversion, and improving enterprises' enthusiasm for energy conservation. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A flowchart illustrating the enterprise energy-saving benefit quantification assessment method provided in this application embodiment; Figure 2 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0017] To more clearly illustrate the overall concept of this application, a detailed explanation is provided below with reference to the accompanying drawings.

[0018] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on its differences from other embodiments. For those skilled in the art, various modifications and variations can be made to this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0019] Many specific details are set forth in the following description to provide a thorough understanding of this application. However, this application may also be implemented in other ways different from those described herein. Therefore, the scope of protection of this application is not limited to the specific embodiments disclosed below. It should be noted that, unless otherwise specified, the embodiments of this application and the features thereof can be combined with each other.

[0020] In this application, unless otherwise expressly specified and limited, the terms "above" and "below" the second feature can refer to direct contact between the first and second features, or indirect contact between the first and second features through an intermediate medium. In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described can be combined in any suitable manner in one or more embodiments or examples.

[0021] The existing technology has the following drawbacks: Existing methods for quantitatively assessing corporate energy efficiency, after acquiring the aforementioned multi-dimensional data, do not comprehensively consider the contribution of this data to corporate energy efficiency or perform a simple weighted fusion for multi-attribute quantitative assessment. This approach easily leads to inaccurate quantification of corporate energy efficiency benefits, making it even more difficult to accurately translate energy conservation, emission reduction, and economic gains into tangible results, thus reducing companies' incentive to conserve energy.

[0022] To solve the above problems, see [link to relevant documentation]. Figure 1 , Figure 1 A flowchart illustrating a method for quantitatively evaluating enterprise energy-saving benefits based on multi-dimensional indicators, as provided in this application embodiment, is shown below. Figure 1 As shown, this method for quantitatively evaluating enterprise energy-saving benefits based on multi-dimensional indicators includes: S110: Acquire various production energy consumption data and cluster them according to pre-constructed multi-dimensional evaluation indicators.

[0023] The technical solution provided in this application embodiment acquires various production energy consumption data, such as electricity, water and gas, equipment operation data and carbon emission data, and clusters these various production energy consumption data according to pre-constructed multi-dimensional evaluation indicators. This allows for the assessment of the impact of these various production energy consumption data on the energy-saving benefits of enterprises in the park according to the multi-dimensional evaluation indicators.

[0024] Specifically, as a preferred embodiment, in the above-mentioned method for quantitatively evaluating enterprise energy-saving benefits, step S110: clustering various production energy consumption data according to pre-constructed multi-dimensional evaluation indicators, including: S111: Cluster various production energy consumption data according to the energy efficiency level, carbon emission performance, load characteristics and management capabilities included in the multi-dimensional evaluation indicators; S112: Construct an initial evaluation matrix using clustered production energy consumption data of various types, and normalize the various production energy consumption data in the initial evaluation matrix to obtain a standardized evaluation matrix.

[0025] The technical solutions provided in this application include multi-dimensional evaluation indicators such as energy efficiency level, carbon emission performance, load characteristics, and management capability. See Table 1 for details. Table 1 - Multidimensional Evaluation Indicators

[0026] By clustering various production energy consumption data according to multidimensional evaluation indicators, an initial evaluation matrix can be constructed using the clustered production energy consumption data, and then normalized to obtain a standardized evaluation matrix. This allows the multidimensional evaluation indicators to be normalized into a unified evaluation standard. Furthermore, using this standardized evaluation matrix, the energy-saving benefits of enterprises in the park can be quantitatively scored.

[0027] Specifically, as a preferred embodiment, in the above-mentioned method for quantitatively evaluating enterprise energy-saving benefits, S110: clustering various production energy consumption data according to pre-constructed multi-dimensional evaluation indicators, including: S113: Use the K-distance function to calculate the neighborhood distance between various production energy consumption data and standard data points in multidimensional evaluation indicators; S114: Determine whether the neighborhood distance is less than or equal to a predetermined neighborhood threshold; S115: If the neighborhood distance is less than or equal to the predetermined neighborhood threshold, the production energy consumption data will be classified into the evaluation index of the corresponding dimension. S116: After classifying the production energy consumption data into the corresponding evaluation indicators, calculate the profile coefficient, Davidson-Bolding index and complexity for each evaluation indicator. S117: Cluster the evaluation metrics for each dimension according to the silhouette coefficient, Davidson-Bolding index, complexity, and scoring criteria. S118: If the cluster score is less than or equal to the predetermined score threshold, then the production energy consumption data will be clustered again.

[0028] The technical solution provided in this application calculates the neighborhood distance between various production energy consumption data and the standard data points of the above-mentioned multi-dimensional evaluation indicators using a distance algorithm. Then, when the neighborhood distance is less than or equal to a predetermined neighborhood threshold, the production energy consumption data is classified into the evaluation indicator of the corresponding dimension. In this way, production energy consumption data with high similarity can be accurately captured. The classification index is then used to calculate the silhouette coefficient, Davidson-Bolding knowledge, and complexity for each dimension of the evaluation index. The clustering effect is scored according to the scoring criteria corresponding to the three-dimensional evaluation index. This allows for the accurate classification of production energy consumption data of the same type and with high similarity into the same evaluation index. When the clustering score is less than or equal to the predetermined scoring threshold, the production energy consumption data is re-clustered. This improves the accuracy of multi-dimensional evaluation indexes in clustering various types of production energy consumption data.

[0029] Figure 1 The technical solution provided in the illustrated embodiment, after clustering various production energy consumption data according to pre-constructed multidimensional evaluation indicators in step S110, further includes: S120: Based on the relationship between multidimensional evaluation indicators and enterprise energy-saving benefits, calculate the contribution rate of each dimension of evaluation indicators to enterprise energy-saving benefits.

[0030] The technical solution provided in this application calculates the contribution rate of each evaluation indicator to the enterprise's energy-saving benefits based on the relationship between multi-dimensional evaluation indicators and enterprise energy-saving benefits. In this way, the contribution rate can accurately quantify the contribution of each evaluation indicator to the enterprise's energy-saving benefits.

[0031] Specifically, as a preferred embodiment, in the above-mentioned quantitative assessment method for enterprise energy-saving benefits, S120: based on the quantitative relationship between multi-dimensional evaluation indicators and enterprise energy-saving benefits, the contribution rate of each dimension of evaluation indicators to enterprise energy-saving benefits is calculated, including: S121: Using principal component analysis, the standardized evaluation matrix is ​​decomposed into eigenvalues ​​to obtain the eigenvalues ​​and eigenvectors corresponding to all production energy consumption data in the principal component direction.

[0032] S122: Sort the feature values ​​from largest to smallest, and select the top k production energy consumption data values ​​that satisfy the size relationship between the cumulative variance contribution rate and the variance contribution rate threshold under the same evaluation index.

[0033] S123: The cumulative variance contribution rate corresponding to the first k production energy consumption data values ​​is used as the contribution rate of the corresponding dimension evaluation index to the enterprise's energy-saving benefits.

[0034] In the technical solution provided in this application embodiment, principal component analysis is used to decompose the above-mentioned standardized evaluation matrix into eigenvalues ​​to obtain the eigenvalues ​​and eigenvectors corresponding to all production energy consumption data in the principal component direction. Then, the eigenvalues ​​are sorted from largest to smallest. Based on the cumulative variance contribution rate and the variance contribution rate threshold, the top k production energy consumption data values ​​that satisfy the size relationship under the same evaluation index are selected. The cumulative variance contribution rate corresponding to the top k production energy consumption data values ​​is agreed to be the contribution rate of the corresponding dimension evaluation index to the energy-saving benefits of the above-mentioned enterprise. In this way, representative production energy consumption data can be selected by principal component analysis, and their cumulative variance contribution rate can be statistically evaluated to assess the contribution rate of the enterprise's energy-saving benefits, thereby improving the accuracy of the contribution rate assessment.

[0035] Figure 1 The technical solution provided in the illustrated embodiment, after step S120: calculating the contribution rate of each dimension of the evaluation index to the enterprise's energy-saving benefits based on the relationship between multi-dimensional evaluation indicators and enterprise energy-saving benefits, further includes: S130: Based on the contribution rate and the similarity of evaluation indicators in different dimensions, data fusion is performed on the multi-dimensional evaluation indicators to obtain a comprehensive quantitative score of the enterprise's energy-saving benefits.

[0036] Specifically, the comprehensive quantitative score of the energy-saving benefits of the above-mentioned enterprises is used to automatically generate a star rating (1-5 stars) and generate TOP3 improvement suggestions (such as "It is recommended to replace the air compressor with a permanent magnet variable frequency model, which is expected to save 80,000 yuan in electricity costs per year").

[0037] The technical solution provided in this application integrates the above-mentioned multi-dimensional evaluation indicators according to the contribution rate and the similarity of different dimension evaluation indicators, so as to obtain a comprehensive quantitative score of the enterprise's energy-saving benefits. Because the comprehensive quantitative score obtained by integrating the data according to the contribution rate and similarity can accurately reflect the contribution of each dimension evaluation indicator to the enterprise's energy-saving benefits.

[0038] Specifically, as a preferred embodiment, in the above-mentioned quantitative evaluation method for enterprise energy-saving benefits, S130: based on the contribution rate and the similarity of evaluation indicators of different dimensions, data fusion is performed on the multi-dimensional evaluation indicators to obtain a comprehensive quantitative score of enterprise energy-saving benefits, including: S131: Vectorize various production energy consumption data to obtain a production energy consumption vector.

[0039] S132: Calculate the similarity between production energy consumption vectors in different dimensions of evaluation indicators. When the similarity is less than or equal to a predetermined similarity threshold, reduce the contribution rate of the evaluation indicator according to a predetermined contribution rate decay algorithm.

[0040] S133: Using the final contribution rate and multi-dimensional evaluation indicators, calculate the comprehensive quantitative score of the enterprise's energy-saving benefits using a weighted average.

[0041] S134: Determine the rating level corresponding to the comprehensive quantitative score, and match the dynamic knowledge graph and expert experience decision tree according to the rating level.

[0042] The technical solution provided in this application involves vectorizing various production energy consumption data to obtain production energy consumption vectors. Then, the similarity between these vectors is calculated, and the contribution rate is used to screen cases based on a contribution rate threshold. This allows for accurate differentiation of production energy consumption vectors and their contributions across different evaluation dimensions. Finally, the final contribution rate and multi-dimensional evaluation indicators are used to weightedly calculate a comprehensive quantitative score for the enterprise's energy-saving benefits. The corresponding score level is then determined, and a dynamic knowledge graph and expert experience decision tree are matched. This allows for matching relevant cases in the dynamic knowledge graph based on expert experience decisions, resulting in corresponding enterprise energy-saving cases and recommendations.

[0043] Specifically, as a preferred embodiment, in the above-mentioned quantitative evaluation method for enterprise energy-saving benefits, step S130: according to the contribution rate and the similarity of evaluation indicators of different dimensions, data fusion is performed on the multi-dimensional evaluation indicators to obtain a comprehensive quantitative score of enterprise energy-saving benefits, including: S135: Construct a contribution indicator matrix using contribution rate and corresponding dimensional evaluation indicators; S136: Input the contribution index matrix into the pre-trained XGBoost quality prediction model and output the index data quality. S137: Use the indicator data quality estimation to evaluate the quality status of each production energy consumption data in the corresponding dimension of the indicator, and provide early warning of fluctuations in the quality status.

[0044] In the technical solution provided in this application embodiment, a contribution index matrix is ​​constructed using contribution rate and corresponding dimension evaluation indicators. Then, the contribution index matrix is ​​input into the XGBoost quality prediction model to output the index data quality. The index data quality is used to estimate the quality status of each production energy consumption data, thereby providing early warning of fluctuations in the quality status. Through the above method, the index data quality of each evaluation indicator can be predicted, and the quality status of each production energy consumption data in each dimension evaluation indicator can be evaluated.

[0045] Figure 1 The technical solution provided in the illustrated embodiment, after step S130: performing data fusion on multi-dimensional evaluation indicators according to contribution rate and similarity of evaluation indicators of different dimensions to obtain a comprehensive quantitative score of enterprise energy-saving benefits, further includes: S140: Based on the comprehensive quantitative score, combined with dynamic knowledge graph and expert experience decision tree, generate suggestions for improving energy-saving benefits.

[0046] Specifically, as a preferred embodiment, in the above-mentioned quantitative assessment method for enterprise energy-saving benefits, S140: based on the comprehensive quantitative score, combined with dynamic knowledge graphs and expert experience decision trees, energy-saving benefit improvement suggestions are generated, including: S141: Based on the comprehensive quantitative score, the multi-dimensional evaluation indicators are matched with similar cases in the dynamic knowledge graph in multiple dimensions.

[0047] S142: Calculate the cosine similarity between the multidimensional evaluation index and similar cases based on the degree of multidimensional matching.

[0048] S143: Extract similar cases with cosine similarity above the similarity threshold as energy efficiency reference cases.

[0049] S144: Using expert experience decision trees, uncertain conditions corresponding to energy efficiency reference cases are processed through fuzzy membership functions to obtain suggestions for improving energy-saving benefits.

[0050] In the technical solution provided in this application embodiment, multi-dimensional evaluation indicators are matched with similar cases in the dynamic knowledge graph according to a comprehensive quantitative score. Cosine similarity is calculated according to the degree of matching, which can quantify the similarity between multi-dimensional evaluation indicators and similar cases. Then, similar cases with cosine similarity above the similarity threshold are extracted as energy efficiency reference cases. Then, an expert experience decision tree is used to process the uncertain conditions corresponding to the above energy consumption reference cases through a fuzzy velocity function, thereby accurately obtaining suggestions for improving energy-saving benefits and providing accurate reference for the energy-saving benefits of enterprises in the park.

[0051] In addition, as a preferred embodiment, the above-mentioned enterprise energy-saving benefit quantitative assessment method further includes, after step S140: obtaining energy-saving benefit improvement suggestions: S150: Integrates multi-dimensional evaluation indicators, comprehensive quantitative scores, and energy-saving benefit improvement suggestions to output a PDF report; S160: Organize and output PDF reports in accordance with relevant energy-saving benefit standards.

[0052] The technical solution provided in this application integrates multi-dimensional evaluation indicators, comprehensively quantifies the scoring, and combines the above-mentioned energy-saving benefit improvements to output a PDF report. By combining the above-mentioned PDF report with relevant energy-saving benefit standards, it can provide technical support for enterprises to demonstrate their energy-saving benefits and for enterprises to use for ESG disclosure or green credit applications.

[0053] In summary, the enterprise energy-saving benefit quantitative assessment method provided in this application obtains various production energy consumption data, clusters the production energy consumption data according to pre-constructed multi-dimensional evaluation indicators, and then calculates the contribution rate of each dimension of the evaluation indicators to the enterprise's energy-saving benefits based on the relationship between the multi-dimensional evaluation indicators and the enterprise's energy-saving benefits. By fusing the above multi-dimensional evaluation indicators according to the contribution rate and the similarity of the evaluation indicators of different dimensions, a comprehensive quantitative score of the enterprise's energy-saving benefits can be obtained. Based on this comprehensive quantitative score, combined with a dynamic knowledge graph and expert experience decision tree, accurate suggestions for improving energy-saving benefits can be generated. This method can accurately quantify the enterprise's energy-saving benefits, thereby enabling accurate energy conservation, emission reduction, and economic benefit transformation, and improving the enterprise's enthusiasm for energy conservation.

[0054] In addition, the following embodiments of this application provide product embodiments, which have the same beneficial effects as the enterprise energy-saving benefit quantitative evaluation method provided in the above embodiments, and other technical features in the product embodiments are the same as the features disclosed in the methods of the above embodiments, and will not be repeated here.

[0055] See Figure 2 , Figure 2 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 2 As shown, the electronic device includes: A memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor, when executing the program, implements a method for quantitatively evaluating enterprise energy-saving benefits as provided by any of the above technical solutions.

[0056] like Figure 2As shown, the electronic device can include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory ROM 1002 or a program loaded from a storage device 1003 into a random access memory RAM 1004. The RAM 1004 also stores various programs and data required for the operation of the electronic device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. The communication device 1009 can operate the electronic device to exchange data with other devices wirelessly or via wired communication. Although the diagram shows a model building device with various systems, it should be understood that it is not required to implement or have all of the systems shown. It is possible to implement or have more or fewer systems alternatively.

Claims

1. A method for quantitatively evaluating enterprise energy-saving benefits based on multi-dimensional indicators, characterized in that, include: Acquire various production energy consumption data, and cluster the various production energy consumption data according to the pre-constructed multidimensional evaluation indicators; Based on the relationship between the multidimensional evaluation indicators and the enterprise's energy-saving benefits, the contribution rate of each dimension of the evaluation indicators to the enterprise's energy-saving benefits is calculated respectively. Based on the contribution rate and the similarity of evaluation indicators of different dimensions, the multi-dimensional evaluation indicators are fused to obtain a comprehensive quantitative score of the enterprise's energy-saving benefits. Based on the comprehensive quantitative score, combined with dynamic knowledge graph and expert experience decision tree, suggestions for improving energy-saving benefits are generated.

2. The method as described in claim 1, characterized in that, Based on the comprehensive quantitative score, combined with dynamic knowledge graphs and expert experience decision trees, suggestions for improving energy-saving benefits are generated, including: Based on the comprehensive quantitative score, the multidimensional evaluation indicators are matched with similar cases in the dynamic knowledge graph in multiple dimensions. Based on the degree of multi-dimensional matching, the cosine similarity between the multi-dimensional evaluation index and the similar cases is calculated; Similar cases with a cosine similarity score above the similarity threshold are extracted and used as energy efficiency reference cases; Using the expert experience decision tree, the uncertain conditions corresponding to the energy efficiency reference case are processed through the fuzzy membership function to obtain the energy-saving benefit improvement suggestions.

3. The method as described in claim 1, characterized in that, The clustering of the various production energy consumption data according to the pre-constructed multidimensional evaluation indicators includes: Based on the energy efficiency level, carbon emission performance, load characteristics and management capabilities included in the multidimensional evaluation indicators, the various production energy consumption data are clustered. An initial evaluation matrix is ​​constructed using clustered production energy consumption data, and the various production energy consumption data in the initial evaluation matrix are normalized to obtain a standardized evaluation matrix.

4. The method as described in claim 3, characterized in that, The step involves calculating the contribution rate of each dimension of the evaluation index to the enterprise's energy-saving benefits based on the quantitative relationship between the multidimensional evaluation indicators and the enterprise's energy-saving benefits, including: Principal component analysis was used to perform eigenvalue decomposition on the standardized evaluation matrix to obtain the eigenvalues ​​and eigenvectors corresponding to all production energy consumption data in the principal component direction. Sort the feature values ​​from largest to smallest, and select the top k production energy consumption data values ​​that satisfy the relationship between the cumulative variance contribution rate and the variance contribution rate threshold under the same evaluation index. The cumulative variance contribution rate corresponding to the first k production energy consumption data values ​​is used as the contribution rate of the corresponding dimension evaluation index to the enterprise's energy-saving benefits.

5. The method as described in claim 1, characterized in that, The process involves fusing data from the multi-dimensional evaluation indicators based on the contribution rate and the similarity of different evaluation indicators to obtain a comprehensive quantitative score for the enterprise's energy-saving benefits, including: The various production energy consumption data are vectorized to obtain a production energy consumption vector; Calculate the similarity between production energy consumption vectors in different evaluation indicators. When the similarity is less than or equal to a predetermined similarity threshold, reduce the contribution rate of the evaluation indicator according to a predetermined contribution rate decay algorithm. Using the final contribution rate and the multidimensional evaluation indicators, a comprehensive quantitative score of the enterprise's energy-saving benefits is calculated using a weighted average. Determine the rating level corresponding to the comprehensive quantitative score, and match the dynamic knowledge graph and expert experience decision tree according to the rating level.

6. The method as described in claim 1, characterized in that, The clustering of the various production energy consumption data according to the pre-constructed multidimensional evaluation indicators includes: The K-distance function is used to calculate the neighborhood distance between the various production energy consumption data and the standard data points in the multidimensional evaluation index. Determine whether the neighborhood distance is less than or equal to a predetermined neighborhood threshold; If the neighborhood distance is less than or equal to the predetermined neighborhood threshold, the production energy consumption data will be classified into the evaluation index of the corresponding dimension. After classifying the production energy consumption data into the corresponding evaluation indicators, the contour coefficient, Davidson-Bolding index, and complexity of each evaluation indicator are calculated. Clustering and scoring are performed on the evaluation indicators of each dimension according to the outline coefficient, Davidson-Bolding index, complexity, and scoring criteria. If the clustering score is less than or equal to a predetermined score threshold, then the production energy consumption data is clustered again.

7. The method as described in claim 1, characterized in that, The process involves fusing data from the multi-dimensional evaluation indicators based on the contribution rate and the similarity of different evaluation indicators to obtain a comprehensive quantitative score for the enterprise's energy-saving benefits, including: Construct a contribution indicator matrix using the contribution rate and corresponding dimension evaluation indicators; The contribution index matrix is ​​input into the pre-trained XGBoost quality prediction model, and the output is the index data quality. The quality status of each production energy consumption data in the indicator is evaluated using the corresponding dimension of the indicator data quality estimation, and fluctuation warnings are issued for the quality status.

8. The method as described in claim 1, characterized in that, After obtaining the energy-saving benefit improvement suggestions, the method further includes: The multi-dimensional evaluation indicators, comprehensive quantitative scores, and energy-saving benefit improvement suggestions are integrated to output a PDF report. Based on relevant energy-saving benefit standards, the PDF report was compiled and output.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the program, it implements the enterprise energy-saving benefit quantitative evaluation method as described in any one of claims 1 to 8.

10. A computer storage medium having a computer program stored thereon, characterized in that, When the computer program is executed, it implements the enterprise energy-saving benefit quantitative evaluation method as described in any one of claims 1 to 8.

Images