Construction method for commercial analysis model of integrated energy station and commercial analysis method thereof

Abstract

The invention discloses a construction method for a business analysis model of a comprehensive energy station and a business analysis method thereof, and relates to the technical field of information processing. The problem that an existing business analysis method cannot meet business analysis requirements of the current comprehensive energy station industry is solved. The method comprises the following steps: establishing a commercial analysis index model; according to the business analysis index model, key indexes are split according to business scenes, and key index templates are formed; establishing an index evaluation model according to the key index template and a quantitative evaluation method; constructing a business analysis template according to the key index template and the index evaluation model; determining the weight of each index in the index evaluation model, and optimizing the weight to obtain an optimal weight; and endowing the optimal weight into an index evaluation model to form a commercial analysis model. And realizing business analysis of the comprehensive energy station according to the business analysis model. The method is suitable for site selection and scheme selection of a newly-built comprehensive energy station in the product oil sales industry, and a transformation scheme is provided for a traditional gas station.

Description

Technical Field

[0001] The present invention relates to the technical field of information processing. Background Art

[0002] Traditional business analysis mainly relies on classic business analysis models and methods, such as PEST analysis, Porter's Five Forces Model, SWOT analysis, etc. The analyst's experience and ability play a key role in the analysis. In the gas station industry, traditional business analysis models are relatively mature, and analysts can provide new construction and renovation plans based on these models and experience.

[0003] However, there are problems and shortcomings: 1. Limitations: Traditional business analysis models are often relatively static and cannot adapt to the dynamic changes of the market in a timely manner. 2. Subjectivity: The results are affected by the subjective judgment of analysts and may contain errors. 3. Lack of data: For some industries or fields, traditional business analysis is constrained by the lack of data and it is difficult to conduct in-depth quantitative analysis.

[0004] With the development of the times, modern business analysis methods have emerged.

[0005] Modern business analysis makes full use of big data technology and adopts methods such as business intelligence and data mining. This includes real-time data analysis, machine learning algorithms, artificial intelligence, etc. to improve the depth and breadth of analysis.

[0006] However, there are problems and shortcomings: 1. Data privacy and security: Big data analysis involves a large amount of sensitive information, which requires stronger privacy protection and data security measures. 2. Technical barriers: Implementing big data analysis requires high-level technical support, which may be a certain threshold for enterprises. 3. High cost: The cost of building and maintaining big data infrastructure is high, which may be difficult for small and medium-sized enterprises to bear.

[0007] In the integrated energy station industry, business analysis mainly involves fuel demand forecasting, customer behavior analysis, site selection optimization, etc. With the development of the times and the popularization of new energy vehicles, the gas station industry is facing the pressure of energy transformation, and traditional models may not be able to effectively cope with it.

[0008] Therefore, both traditional business analysis methods and modern business analysis methods have problems and shortcomings for integrated energy stations.

[0009] Traditional AHP modeling is a common and effective method for converting expert experience into scientific methods. It is widely used, but there are cases where consistency tests fail, and it is difficult for experts to give definite values, and sensitivity analysis is rarely performed. At the same time, there are other problems and shortcomings, such as: 1. Difficulty in consistency testing: It is a complex task for experts to ensure consistency when giving judgment matrices. If the matrix provided by the expert does not meet the consistency requirements, it needs to be adjusted, which may require multiple iterations, increasing the difficulty of modeling. 2. Subjectivity of expert-determined values: Expert experience is used in the AHP to determine the relative weights of elements in the judgment matrix. However, there may be certain subjectivity and uncertainty in the subjective judgment of experts, resulting in the modeling results being affected by the subjective factors of experts. 3. Limitations of sensitivity analysis: Traditional AHP usually lacks in-depth analysis of model sensitivity. In practical applications, evaluating the sensitivity of the model to input changes is crucial to ensuring the robustness and reliability of the model.

[0010] In summary, a new business analysis method is urgently needed for the commercial analysis of integrated energy stations to face the development of the times. Summary of the invention

[0011] The purpose of the present invention is to provide a method for constructing a business analysis model for an integrated energy station, and to conduct business analysis on the integrated energy station according to the constructed business analysis model, so as to solve the problem that the existing business analysis methods do not meet the business analysis needs of the current integrated energy station industry. At the same time, the present invention also solves the problem that in the traditional hierarchical analysis method, experts are usually required to determine the relative weights of the elements in the judgment matrix. Since the determined values ​​are affected by subjectivity, the modeling results are inaccurate and the consistency requirements of the matrix need to be judged by experts multiple times, which in turn requires multiple iterations, increases the difficulty of modeling and is inefficient.

[0012] To achieve the above object, the present invention provides the following solutions:

[0013] The present invention provides a method for constructing a commercial analysis model for an integrated energy station, the method comprising the following steps:

[0014] Step S1: Establish a business analysis indicator model;

[0015] Step S2: According to the business analysis indicator model, key indicators are split according to business scenarios to form a key indicator template;

[0016] Step S3: Establish an indicator evaluation model based on the key indicator template and quantitative evaluation method;

[0017] Step S4: construct a business analysis template based on the key indicator template and indicator evaluation model;

[0018] Step S5: Determine the weight of each indicator in the indicator evaluation model, and optimize the weight to obtain the optimal weight;

[0019] Step S6: assigning the optimal weight to the indicator evaluation model to form a business analysis model.

[0020] Furthermore, in a preferred embodiment, the business analysis indicator model in the above step S1 includes a target layer, a criterion layer and a factor layer.

[0021] Furthermore, in another preferred embodiment, the above step S5 specifically includes the following steps:

[0022] Step S51: using the improved analytic hierarchy process 1 to determine the weights of various indicators in the indicator evaluation model, and using the Bayesian optimization algorithm to optimize the weights;

[0023] Step S52: assigning the optimized weights to the indicator evaluation model, and then performing sensitivity analysis on the indicator evaluation model, and optimizing the indicator evaluation model according to the analysis results until a determined weight is obtained;

[0024] Step S53: Determine whether there is historical data;

[0025] Step S54: if not, directly assign the determined weights to the index evaluation model, and then use the Bayesian optimization algorithm to optimize the index evaluation model after the assigned indexes to obtain multiple judgment matrices;

[0026] Step S55: determining the optimal judgment matrix, and optimizing the index evaluation model again according to the optimal judgment matrix until the optimal index evaluation model is obtained, and then the optimal weight is obtained;

[0027] Step S56: If yes, the historical data is input into the business analysis template, and the evaluation model is used to score and obtain the forecast data;

[0028] Step S57: Calculate the variance of the predicted data and the real data to form a Bayesian optimization objective function, use the improved analytic hierarchy process 2 to determine the weight, and then use the Bayesian optimization objective function to optimize the weight;

[0029] Step S58: assigning the optimized weights to the indicator evaluation model, then performing sensitivity analysis on the indicator evaluation model, and optimizing the indicator evaluation model again according to the analysis results to obtain re-determined weights;

[0030] Step S59: assign the re-determined weights to the indicator evaluation model, and repeat steps S57-S58 until the optimal weights are obtained.

[0031] Furthermore, in a preferred embodiment, the evaluation model in the above step S56 includes fuzzy comprehensive evaluation, hierarchical analysis method and entropy method.

[0032] Furthermore, in a preferred embodiment, the specific steps of using the evaluation model for scoring in the above step S56 are: scoring by using subjective evaluation, objective evaluation and a combination of subjective and objective evaluation.

[0033] The present invention further provides an analysis method based on a business analysis model, wherein the analysis method is implemented based on any one of the above-mentioned integrated energy station business analysis models, and the analysis method comprises the following steps:

[0034] Step S1: Collect Internet data, third-party interface data, field exploration data and data estimation results, and continuously accumulate and establish a scientific knowledge base;

[0035] Step S2: using a business analysis model to analyze the data in the scientific knowledge base to obtain analysis results;

[0036] Step S3: Incorporate the analysis results into a scientific knowledge base and repeat step 2 until the optimal analysis results are obtained.

[0037] The present invention also provides a business analysis method for an integrated energy station, the analysis method is implemented based on any one of the business analysis models and analysis methods described above, and the analysis method comprises the following steps:

[0038] Step S1: Building a business analysis model;

[0039] Step S2: performing business analysis on the business analysis model, and incorporating the analysis results into a business analysis knowledge base;

[0040] Step S3: Incorporate other cases into the business analysis knowledge base, perform correlation analysis, incorporate the correlation analysis results into the business analysis knowledge base again, and repeat the business analysis according to the business analysis knowledge base until the optimal result is obtained.

[0041] The method for constructing a business analysis model for an integrated energy station described in the present invention can be implemented entirely by computer software. Accordingly, the present invention also provides a system for constructing a business analysis model for an integrated energy station, the system comprising:

[0042] A storage device for establishing a business analysis indicator model;

[0043] A storage device for splitting key indicators according to business scenarios based on the business analysis indicator model to form a key indicator template;

[0044] A storage device for establishing an indicator evaluation model based on a key indicator template and a quantitative evaluation method;

[0045] A storage device for constructing a business analysis template based on a key indicator template and an indicator evaluation model;

[0046] A storage device for determining the weights of various indicators in the indicator evaluation model and optimizing the weights to obtain the optimal weights;

[0047] A storage device for assigning the optimal weight to an indicator evaluation model to form a business analysis model.

[0048] The present invention also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the computer program executes any one of the above-mentioned methods for constructing a business analysis model for an integrated energy station, the above-mentioned analysis method based on a business analysis model, or the above-mentioned business analysis method for an integrated energy station.

[0049] The present invention also provides a computer device, which includes a memory and a processor, wherein a computer program is stored in the memory. When the processor runs the computer program stored in the memory, the processor executes any one of the above-mentioned methods for constructing a business analysis model for an integrated energy station, the above-mentioned analysis method based on a business analysis model, or the above-mentioned business analysis method for an integrated energy station.

[0050] The beneficial effects of the present invention are:

[0051] 1. The present invention provides a method for constructing a commercial analysis model for an integrated energy station. By constructing a commercial analysis indicator model, key indicators are split according to business scenarios to form a key indicator template, that is, to form the indicator part in the commercial analysis template; the key indicator template is combined with a quantitative evaluation method to establish an indicator evaluation model, that is, to form the indicator evaluation part in the commercial analysis template. At the same time, the weights of various indicators in the indicator evaluation model are continuously optimized by using an improved hierarchical analysis method, a Bayesian optimization algorithm, and a sensitivity analysis, so as to obtain the optimal weights, and the weights are optimized again by using an evaluation model formed by integrating fuzzy comprehensive evaluation, hierarchical analysis method, and entropy method according to historical data, so as to obtain a commercial analysis model, so as to solve the problem that the existing commercial analysis method usually requires experts to determine the relative weights of elements in the judgment matrix. Since the determined values ​​are affected by subjectivity, the modeling results are inaccurate and multiple iterations are required, which increases the difficulty of modeling.

[0052] 2. Traditional analytic hierarchy process modeling converts expert experience into a scientific method, but it usually requires experts to determine the relative weights of the elements in the judgment matrix. Since the determined values ​​are affected by subjectivity, the modeling results are inaccurate and experts are required to judge the consistency requirements of the matrix multiple times, which in turn requires multiple iterations, increasing the difficulty and efficiency of modeling. The present invention provides a method for constructing a commercial analysis model for an integrated energy station, which improves the determined values ​​of the relative weights in the analytic hierarchy process into range values, thereby improving decision-making efficiency, and combining the Bayesian optimization algorithm to continuously optimize the weights of various indicators in the indicator evaluation model, so that it is more in line with the actual situation, improve the accuracy of the model, and do not need to consider the problem of unqualified consistency ratios, thereby improving modeling efficiency. At the same time, based on historical data, an evaluation model is used for scoring, and the variance between the predicted data and the real data is used to form a Bayesian optimization objective function, and the weights are optimized again to improve the accuracy of the model.

[0053] The present invention is applicable to the site selection and scheme selection of new integrated energy stations in the finished oil sales industry, and provides transformation schemes and commercial analysis for traditional gas stations. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 is a schematic diagram of the structure of the business analysis model described in the first implementation mode;

[0055] Figure 2 It is a flowchart diagram of a method for constructing a commercial analysis model for an integrated energy station according to embodiments one and three;

[0056] Figure 3 is a schematic diagram of the structure of the business analysis indicator model described in the second implementation mode;

[0057] Figure 4 It is a flowchart of the improved analytic hierarchy process 1 combined with the Bayesian optimization algorithm described in the third implementation mode;

[0058] Figure 5 is a schematic diagram of a process of scoring historical data using an evaluation model as described in Implementation Method 3;

[0059] Figure 6 This is a schematic diagram of a scoring structure using an evaluation model as described in Implementation Mode 5;

[0060] Figure 7 is a flow chart of a commercial analysis method for an integrated energy station according to Embodiment 6;

[0061] Figure 8 is a schematic diagram of the structure of the scientific knowledge base described in Implementation Method 6;

[0062] Fig. 9 is a schematic diagram of the structure of the scientific knowledge base described in Implementation Method 6;

[0063] Fig.10 is a structural schematic diagram of a commercial analysis method for an integrated energy station according to Embodiment 7;

[0064] Fig.11 This is a flowchart of the analysis using five business analysis templates as described in the eleventh embodiment. DETAILED DESCRIPTION

[0065] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0066] It should be understood that when used in this specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0067] The specific implementation mode of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples will help those skilled in the art to further understand the present invention, but are not intended to limit the present invention in any form. It should be noted that, for those of ordinary skill in the art, several changes and improvements can also be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention.

[0068] Implementation method 1, see Figures 1 to 3 This embodiment describes a method for constructing a commercial analysis model for an integrated energy station, the method comprising the following steps:

[0069] Step S1: Establish a business analysis indicator model;

[0070] Step S2: According to the business analysis indicator model, key indicators are split according to business scenarios to form a key indicator template;

[0071] Step S3: Establish an indicator evaluation model based on the key indicator template and quantitative evaluation method;

[0072] Step S4: construct a business analysis template based on the key indicator template and indicator evaluation model;

[0073] Step S5: Determine the weight of each indicator in the indicator evaluation model, and optimize the weight to obtain the optimal weight;

[0074] Step S6: assigning the optimal weight to the indicator evaluation model to form a business analysis model.

[0075] In practical application, if Figure 1 and Figure 2 As shown, it can be more specific as follows:

[0076] Step S1: Establish a business analysis indicator model;

[0077] Specifically, in actual application, we can form a clear target layer, criterion layer and factor layer based on expert experience, and then construct a business analysis indicator tree, that is, establish a business analysis indicator model, such as Figure 3 As shown, it provides a basic framework for the subsequent indicator confirmation and evaluation. According to the actual situation, the factor layer can be further decomposed into a specific factor layer and an evaluation influencing specific factor layer, and a business analysis indicator tree can be accurately established through multi-layer decomposition.

[0078] Step S2: According to the business analysis indicator model, key indicators are split according to business scenarios to form a key indicator template;

[0079] Specifically: Based on the business analysis indicator tree and expert experience, key indicators are split according to business scenarios to form a key indicator template, which is used to construct the indicator part of the business analysis template.

[0080] Step S3: Establish an indicator evaluation model based on the key indicator template and quantitative evaluation method;

[0081] Specifically: Based on the established key indicator template, that is, the indicator part in the business analysis template, combined with expert experience and quantitative evaluation methods, an indicator evaluation model is established to construct the indicator evaluation part in the business analysis template.

[0082] Step S4: construct a business analysis template based on the key indicator template and indicator evaluation model;

[0083] Specifically: construct a business analysis template based on the key indicator template and the indicator evaluation model, that is, construct a business analysis template based on the indicator part and the indicator evaluation part.

[0084] Step S5: Determine the weight of each indicator in the indicator evaluation model, and optimize the weight to obtain the optimal weight;

[0085] Specifically:

[0086] Step S51: using the improved analytic hierarchy process 1 to determine the weights of each indicator in the indicator evaluation model, and using the Bayesian optimization algorithm to optimize the weights; Step S52: assigning the optimized weights to the indicator evaluation model, and then performing a sensitivity analysis on the indicator evaluation model, optimizing the indicator evaluation model according to the analysis results, until a determined weight is obtained; Step S53: determining whether there is historical data; Step S54: if not, directly assigning the determined weights to the indicator evaluation model, and then using the Bayesian optimization algorithm to optimize the indicator evaluation model after the assigned indicators, to obtain multiple judgment matrices; Step S55: determining the optimal judgment matrix, and optimizing the indicator evaluation model again according to the optimal judgment matrix, until the optimal indicator is obtained. Step S56: if any, input the historical data into the business analysis template, use the evaluation model to score, and obtain the predicted data; Step S57: calculate the variance of the predicted data and the real data, form a Bayesian optimization objective function, use the improved hierarchical analysis method 2 to determine the weight, and then use the Bayesian optimization objective function to optimize the weight; Step S58: assign the optimized weight to the indicator evaluation model, and then perform a sensitivity analysis on the indicator evaluation model, optimize the indicator evaluation model again according to the analysis results, and obtain the re-determined weight; Step S59: assign the re-determined weight to the indicator evaluation model, repeat steps S57-S58 until the optimal weight is obtained.

[0087] Step S6: assigning the optimal weight to the indicator evaluation model to form a business analysis model.

[0088] This embodiment provides a method for constructing a business analysis model for an integrated energy station. By constructing a business analysis indicator model, key indicators are split according to business scenarios to form a key indicator template, that is, to form the indicator part of the business analysis template; the key indicator template is combined with a quantitative evaluation method to establish an indicator evaluation model, that is, to form the indicator evaluation part of the business analysis template. At the same time, the weights of various indicators in the indicator evaluation model are continuously optimized by using an improved hierarchical analysis method, a Bayesian optimization algorithm, and a sensitivity analysis, so as to obtain the optimal weights, and the weights are optimized again by using an evaluation model formed by integrating fuzzy comprehensive evaluation, hierarchical analysis, and entropy value method based on historical data, so as to obtain a business analysis model, so as to solve the problem that the existing business analysis method usually requires experts to determine the relative weights of elements in the judgment matrix. Since the determined values ​​are affected by subjectivity, the modeling results are inaccurate and multiple iterations are required, which increases the difficulty of modeling.

[0089] Implementation method 2: This implementation method is to illustrate the business analysis indicator model of step S1 in the method for constructing a business analysis model for an integrated energy station described in implementation method 1 by way of example;

[0090] The business analysis indicator model includes a target layer, a criterion layer and a factor layer.

[0091] When this implementation is actually applied, it can provide a basic framework for subsequent indicator confirmation and evaluation based on the target layer, criterion layer and factor layer.

[0092] Implementation method three, see Figure 2 , Figure 4 and Figure 5 This embodiment is described. This embodiment is an example of step S5 in the method for constructing a commercial analysis model for an integrated energy station described in the first embodiment. The step S5 is specifically as follows:

[0093] Step S51: using the improved analytic hierarchy process 1 to determine the weights of various indicators in the indicator evaluation model, and using the Bayesian optimization algorithm to optimize the weights;

[0094] Step S52: assigning the optimized weights to the indicator evaluation model, and then performing sensitivity analysis on the indicator evaluation model, and optimizing the indicator evaluation model according to the analysis results until a determined weight is obtained;

[0095] Step S53: Determine whether there is historical data;

[0096] Step S54: if not, directly assign the determined weights to the index evaluation model, and then use the Bayesian optimization algorithm to optimize the index evaluation model after the assigned indexes to obtain multiple judgment matrices;

[0097] Step S55: determining the optimal judgment matrix, and optimizing the index evaluation model again according to the optimal judgment matrix until the optimal index evaluation model is obtained, and then the optimal weight is obtained;

[0098] Step S56: If yes, the historical data is input into the business analysis template, and the evaluation model is used to score and obtain the forecast data;

[0099] Step S57: Calculate the variance of the predicted data and the real data to form a Bayesian optimization objective function, use the improved analytic hierarchy process 2 to determine the weight, and then use the Bayesian optimization objective function to optimize the weight;

[0100] Step S58: assigning the optimized weights to the indicator evaluation model, then performing sensitivity analysis on the indicator evaluation model, and optimizing the indicator evaluation model again according to the analysis results to obtain re-determined weights;

[0101] Step S59: assign the re-determined weights to the indicator evaluation model, and repeat steps S57-S58 until the optimal weights are obtained.

[0102] In practical application, if Figure 2 As shown,

[0103] Step S51: using the improved analytic hierarchy process 1 to determine the weights of various indicators in the indicator evaluation model, and using the Bayesian optimization algorithm to optimize the weights;

[0104] Specifically: Figure 4 As shown,

[0105] The improved analytic hierarchy process 1 is specifically as follows: the relative weight determination value in the analytic hierarchy process is improved to a range value, so as to improve the decision-making efficiency. The improved analytic hierarchy process 1 is used to determine the weights of each indicator in the standard evaluation model, and the Bayesian optimization algorithm is used to optimize the weights to ensure that the weight distribution is more accurate and reliable, and at the same time, it is not necessary to consider the problem of unqualified consistency ratio, thereby improving the modeling efficiency.

[0106] For example: First, determine the relative weight range: Based on the subjective judgment of the experts, generate a preliminary judgment matrix, in which the elements represent the relative weights between different indicators. As shown in the following table, the applicable range is [2,4], which can accommodate the uncertainty and subjectivity of the experts.

[0107] Basic Situation Customer Analysis Vehicle Analysis Competitive Analysis Macro Analysis Basic Situation 1 [6,8] [3,5] [2,5] [1,3] Customer Analysis 1 [1 / 3,1 / 2] [2,4] [1 / 4,1 / 3] Vehicle Analysis 1 [1 / 3,1 / 2] [1 / 6,1 / 4] Competitive Analysis 1 [1 / 6,1 / 5] Macro Analysis 1

[0108] Secondly, the Bayesian optimization algorithm is used to find the reasonable values ​​of each element in the judgment matrix with certain criteria as the objective function. This step can help optimize the judgment matrix to make it more consistent with the consistency requirements.

[0109] Then perform a consistency check: After each Bayesian optimization, a consistency check is performed to ensure that the consistency level of the judgment matrix is ​​within an acceptable range.

[0110] Final iterative optimization: If the consistency check does not meet the requirements, Bayesian optimization can be performed iteratively until a satisfactory consistency level is reached.

[0111] Step S52: assigning the optimized weights to the indicator evaluation model, and then performing sensitivity analysis on the indicator evaluation model, and optimizing the indicator evaluation model according to the analysis results until a determined weight is obtained;

[0112] Specifically:

[0113] In an iterative way, an initial judgment matrix is ​​first generated through Bayesian optimization, and then sensitivity analysis is performed to observe the changes of the model under different parameters or conditions. According to the results of the sensitivity analysis, the initial judgment matrix can be adjusted, and then Bayesian optimization can be performed again. This process can be iterated until a satisfactory result is achieved.

[0114] This iterative approach helps to more comprehensively consider the stability and consistency of the model during the adjustment of the judgment matrix. In each round of iteration, the results of the sensitivity analysis can be observed to understand the performance of the model in different situations, and then targeted adjustments and optimizations can be made.

[0115] Such an iterative process helps to find a relatively stable and consistent judgment matrix in complex decision-making problems, thereby improving the reliability and accuracy of the decision-making model.

[0116] Step S53: Determine whether there is historical data;

[0117] Step S54: if not, directly assign the determined weights to the index evaluation model, and then use the Bayesian optimization algorithm to optimize the index evaluation model after the assigned indexes to obtain multiple judgment matrices;

[0118] Step S55: determining the optimal judgment matrix, and optimizing the index evaluation model again according to the optimal judgment matrix until the optimal index evaluation model is obtained, and then the optimal weight is obtained;

[0119] Specifically: Based on the actual situation and the interpretability of the indicator evaluation model, the optimal judgment matrix is ​​selected.

[0120] Step S56: If yes, the historical data is input into the business analysis template, and the evaluation model is used to score and obtain the forecast data;

[0121] Specifically: Figure 5 As shown,

[0122] The historical data are input into the business analysis template, and the evaluation model is used to score and output the forecast data. The evaluation model integrates fuzzy comprehensive evaluation, hierarchical analysis method, entropy method and other methods to form a comprehensive and powerful evaluation framework.

[0123] Step S57: Calculate the variance of the predicted data and the real data to form a Bayesian optimization objective function, use the improved analytic hierarchy process 2 to determine the weight, and then use the Bayesian optimization objective function to optimize the weight;

[0124] Specifically, by comparing historical business analysis case data as the true value, scoring the historical data as the predicted value, calculating the variance between the true value and the predicted value, forming the Bayesian optimization objective function, and performing Bayesian optimization to confirm the weights. This ensures that the weight distribution is more accurate and reliable, and also makes it more in line with the actual situation, improving the accuracy of the model and improving the efficiency of modeling.

[0125] Step S58: assigning the optimized weights to the indicator evaluation model, then performing sensitivity analysis on the indicator evaluation model, and optimizing the indicator evaluation model again according to the analysis results to obtain re-determined weights;

[0126] Specifically, the optimized weights are assigned to the indicator evaluation model, and then a sensitivity analysis is performed on the indicator evaluation model. The indicator evaluation model is optimized again according to the analysis results to obtain a re-determined weight;

[0127] Step S59: assign the re-determined weights to the indicator evaluation model, and repeat steps S57-S58 until the optimal weights are obtained.

[0128] Traditional analytic hierarchy process modeling converts expert experience into a scientific method, but it usually requires experts to determine the relative weights of the elements in the judgment matrix. Since the determined values ​​are subject to subjectivity, the modeling results are inaccurate and experts are required to judge the consistency requirements of the matrix multiple times, which in turn requires multiple iterations and increases the difficulty of modeling. This embodiment provides a method for constructing a commercial analysis model for an integrated energy station, which improves the determined value of the relative weight in the analytic hierarchy process to a range value, thereby improving decision-making efficiency, and combining the Bayesian optimization algorithm to continuously optimize the weights of each indicator in the indicator evaluation model, so that it is more in line with the actual situation, improve the accuracy of the model, and do not need to consider the problem of unqualified consistency ratios, thereby improving modeling efficiency. At the same time, based on historical data, an evaluation model is used for scoring, and the variance between the predicted data and the real data is used to form a Bayesian optimization objective function, and the weights are optimized again to improve the accuracy of the model.

[0129] Implementation 4: This implementation is to illustrate the evaluation model in step S56 of the method for constructing a commercial analysis model for an integrated energy station described in Implementation 3 by way of example;

[0130] The evaluation model includes fuzzy comprehensive evaluation, hierarchical analysis method and entropy method.

[0131] Implementation method 5: See Figure 6 This embodiment is described. This embodiment is an example of using an evaluation model to score in step S56 of a method for constructing a commercial analysis model for an integrated energy station described in Embodiment 4;

[0132] The specific steps of using the evaluation model for scoring are: scoring using subjective evaluation, objective evaluation, and a combination of subjective and objective evaluation.

[0133] In practical application, if Figure 6 As shown in the figure, the evaluation model used for scoring includes subjective evaluation, objective evaluation and subjective and objective mixed methods; among them, for objective evaluation, the modeling method: the entropy method is used for modeling, which is suitable for comprehensive evaluation of multiple indicators and takes into account the relative importance of indicators. Evaluation method: For a single indicator, the following methods are used for evaluation:

[0134] 1. Control chart: used to monitor the stability of the process and display the trend of data through graphics. 2. Ratio: calculate the ratio between different variables and analyze the relative size relationship. 3. Trend: analyze the trend of data change and determine the development direction. 4. Information entropy: measure the uncertainty of information and can be used to evaluate the diversity and information content of indicators. 5. Variance: measure the degree of dispersion of data and evaluate the stability of data.

[0135] For subjective evaluation: Modeling method: Use the analytic hierarchy process to confirm the rights, build a judgment matrix through expert opinions, and accurately reflect the relative importance of each indicator. Evaluation method: Use the fuzzy comprehensive evaluation method to score, deal with uncertainty and ambiguity, and provide a scientific basis for subjective evaluation.

[0136] For the subjective and objective mixed method: adopt a mixed method, that is, a combination of any subjective and objective methods. Different objective evaluation methods can be selected and combined with subjective evaluation methods according to specific circumstances, making full use of objective data and expert experience. For simplicity, the model confirmation can adopt the average weight method, and the information in the form of judgment will be binarized during evaluation. The mixed evaluation can integrate the objective and subjective evaluation results through weight allocation to obtain a more comprehensive and reliable evaluation.

[0137] Implementation Method 6: See Figures 7 to 9 This embodiment is described. This embodiment provides an analysis method based on a business analysis model. The method is implemented based on the business analysis model. The business analysis model is obtained by using a method for constructing a business analysis model for a comprehensive energy station described in any one of Embodiments 1 to 5. The analysis method is:

[0138] Step S1: Collect Internet data, third-party interface data, field exploration data and data estimation results, and continuously accumulate and establish a scientific knowledge base;

[0139] Step S2: using a business analysis model to analyze the data in the scientific knowledge base to obtain analysis results;

[0140] Step S3: Incorporate the analysis results into a scientific knowledge base and repeat step 2 until the optimal analysis results are obtained.

[0141] In practical application, if Figure 7As shown, the business analysis method includes confirming the analysis template, data collection and data analysis; among them, confirming the analysis template: ensuring that the analysis process has a clear direction, this implementation method adopts a business analysis model. Data collection: using multi-faceted data sources, including Internet data collection, third-party interface data, on-site exploration and data estimation, and continuously accumulating and establishing a scientific knowledge base to obtain comprehensive and accurate information. Data analysis: using a business analysis model to conduct in-depth analysis of the collected data to gain insights into the business environment, market trends, etc.

[0142] Among them, Figure 8 As shown, the scientific knowledge base includes knowledge storage based on graph database and benchmarking and related analysis knowledge applications.

[0143] like Fig. 9 As shown, historical analysis cases, similar model comparative analysis data and expert opinions can be placed in a scientific knowledge base.

[0144] Implementation method 7: See Fig.10 This embodiment is described. This embodiment provides a business analysis method for an integrated energy station. The method is implemented based on a business analysis model and an analysis method based on a business analysis model described in Embodiment 6. The business analysis model is obtained by using a method for constructing a business analysis model for an integrated energy station described in any one of Embodiments 1 to 5. The analysis method is:

[0145] Step S1: Building a business analysis model;

[0146] Step S2: performing business analysis on the business analysis model, and incorporating the analysis results into a business analysis knowledge base;

[0147] Step S3: Incorporate other cases into the business analysis knowledge base, perform correlation analysis, incorporate the correlation analysis results into the business analysis knowledge base again, and repeat the business analysis according to the business analysis knowledge base until the optimal result is obtained.

[0148] In practical application, if Fig.10As shown, firstly, a business analysis model is established, wherein the business analysis model includes a business analysis indicator model and a business analysis template; the business analysis template includes a key indicator template and an indicator evaluation model; at the same time, the improved hierarchical analysis method, the Bayesian optimization algorithm and the sensitivity analysis are respectively used to continuously optimize the weights of various indicators in the indicator evaluation model, and the evaluation model formed by the fusion of fuzzy comprehensive evaluation, hierarchical analysis method and entropy method is used according to historical data to optimize the weights again, so as to solve the problem that the existing business analysis methods usually require experts to determine the relative weights of the elements in the judgment matrix, and the determination of the values ​​will be affected by subjectivity, resulting in inaccurate modeling results and the need for multiple iterations, which increases the difficulty of modeling.

[0149] Then, business analysis is performed and the analysis template is confirmed. The constructed business analysis model or other business analysis models can be used. Data collection includes network data, third-party interface data, field exploration data and data estimation results. Business analysis is performed based on the data collected using the confirmed analysis template.

[0150] Finally, the analysis results are incorporated into the business analysis knowledge base. Other cases can also be incorporated into the business analysis knowledge base. For example, the methods of other related and similar cases in actual work are introduced into the design of the business analysis knowledge base, and the business analysis indicator model, business analysis template, case and the content of the case itself are established. And conduct correlation analysis to establish the correlation between the indicator model, business analysis template and case, so that the connection between each element is clearer. By analyzing the map, you can better understand the dependence and influence between them. At the same time, carry out knowledge inheritance and reduce knowledge loss. Manage the case content to ensure that each case has a clear description, including key indicators, templates used, lessons learned from success or failure, etc.

[0151] Embodiment 8: This embodiment provides a system for building a business analysis model for an integrated energy station, the system comprising:

[0152] A storage device for establishing a business analysis indicator model;

[0153] A storage device for splitting key indicators according to business scenarios based on the business analysis indicator model to form a key indicator template;

[0154] A storage device for establishing an indicator evaluation model based on a key indicator template and a quantitative evaluation method;

[0155] A storage device for constructing a business analysis template based on a key indicator template and an indicator evaluation model;

[0156] A storage device for determining the weights of various indicators in the indicator evaluation model and optimizing the weights to obtain the optimal weights;

[0157] A storage device for assigning the optimal weight to an indicator evaluation model to form a business analysis model.

[0158] Implementation method nine. This implementation method provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for constructing a business analysis model for an integrated energy station as described in any one of implementation methods one to five, the analysis method based on a business analysis model as described in implementation method six, or the business analysis method for an integrated energy station as described in implementation method seven is executed.

[0159] Embodiment 10. This embodiment provides a computer device including a memory and a processor, wherein the memory stores a computer program. When the processor runs the computer program stored in the memory, the processor executes a method for constructing a business analysis model for an integrated energy station as described in any one of embodiments 1 to 5, or an analysis method based on a business analysis model as described in embodiment 6, or a business analysis method for an integrated energy station as described in embodiment 7.

[0160] Implementation Method 11: See Fig.11 This embodiment is to illustrate the commercial analysis method of a comprehensive energy station described in Embodiment 6.

[0161] First, determine the analysis template: divide the gas station business analysis into 5 analysis templates according to geographical location. The specific classifications are as follows: urban station, highway station, service area station, tourist area station, and suburban combined station.

[0162] The five business analysis templates are mainly divided into general analysis and personalized analysis. According to different dimensions, professional analysis templates suitable for the characteristics of each environment are formed, such as Fig.11 shown.

[0163] Then data collection: use the Internet and third-party application data collection, and on-site exploration collection respectively.

[0164] The Internet and third-party application data collection uses the Internet professional application interface to obtain data. For image data, software is required for image recognition, such as using Baidu PaddlePaddle OCR to recognize text and tables, and manually confirming the data. For curve graphs, use OpenCV tools to extract curves and then convert them into data. For other scattered information, it is entered manually.

[0165] On-site exploration and collection, assisted by intelligent technology, such as using OpenCV video processing technology to identify vehicles and count.

[0166] Finally, data analysis: Data extraction and analysis uses technical methods such as data location, data distribution, data trend, data aggregation, and data combination to mine data and quantitatively describe and evaluate various factors in business analysis.

[0167] Model analysis uses statistical analysis and machine learning algorithms and techniques to conduct correlation analysis, causal analysis, predictive analysis, benchmarking analysis, importance analysis, and optimization analysis on various indicators and factors, and finally conducts a comprehensive evaluation based on the hierarchical analysis method and fuzzy comprehensive evaluation method.

[0168] The above description is only an embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may be subject to various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention shall be included in the scope of the claims of the present invention.

Claims

1. A method for constructing a commercial analysis model for an integrated energy station, characterized in that: The method is: S1: Establish a business analysis indicator model; S2: Based on the business analysis indicator model, key indicators are split according to business scenarios to form a key indicator template; S3: Establish an indicator evaluation model based on the key indicator template and quantitative evaluation method; S4: Build a business analysis template based on the key indicator template and indicator evaluation model; S5: Determine the weight of each indicator in the indicator evaluation model, and optimize the weight to obtain the optimal weight; S6: assigning the optimal weight to the indicator evaluation model to form a business analysis model.

2. A method for constructing a commercial analysis model for an integrated energy station according to claim 1, characterized in that: The business analysis indicator model in S1 includes the target layer, the criterion layer and the factor layer.

3. The method for constructing a commercial analysis model for an integrated energy station according to claim 1, characterized in that: S5 is as follows: S51: using the improved analytic hierarchy process 1 to determine the weights of various indicators in the indicator evaluation model, and using the Bayesian optimization algorithm to optimize the weights; S52: assigning the optimized weights to the indicator evaluation model, and then performing sensitivity analysis on the indicator evaluation model, and optimizing the indicator evaluation model according to the analysis results until a determined weight is obtained; S53: Determine whether there is historical data; S54, if not, directly assign the determined weights to the indicator evaluation model, and then use the Bayesian optimization algorithm to optimize the indicator evaluation model after the assigned indicators to obtain multiple judgment matrices; S55: determining an optimal judgment matrix, and optimizing the index evaluation model again according to the optimal judgment matrix until an optimal index evaluation model is obtained, and then an optimal weight is obtained; S56: If yes, the historical data is input into the business analysis template, and the evaluation model is used to score and obtain the forecast data; S57: Calculate the variance of the predicted data and the real data to form a Bayesian optimization objective function, use the improved analytic hierarchy process 2 to determine the weight, and then use the Bayesian optimization objective function to optimize the weight; S58: assigning the optimized weights to the indicator evaluation model, and then performing sensitivity analysis on the indicator evaluation model, optimizing the indicator evaluation model again according to the analysis results, and obtaining re-determined weights; S59: assign the re-determined weight to the indicator evaluation model, and repeat steps S57-S58 until the optimal weight is obtained.

4. A method for constructing a commercial analysis model for an integrated energy station according to claim 3, characterized in that: The evaluation models in S56 include fuzzy comprehensive evaluation, hierarchical analysis method and entropy method.

5. A method for constructing a commercial analysis model for an integrated energy station according to claim 4, characterized in that: The specific steps of using the evaluation model for scoring in S56 are: scoring using subjective evaluation, objective evaluation, and a combination of subjective and objective evaluation.

6. The analysis method for implementing the integrated energy station business analysis model according to any one of claims 1 to 5, characterized in that: The method is: S1: Collect Internet data, third-party interface data, field exploration data and data estimation results, and continuously accumulate and establish a scientific knowledge base; S2: Use business analysis models to analyze data in the scientific knowledge base and obtain analysis results; S3: Incorporate the analysis results into a scientific knowledge base and repeat step 2 until the optimal analysis results are obtained.

7. A commercial analysis method for an integrated energy station, characterized in that: The analysis method is implemented based on the business analysis model described in any one of claims 1 to 5 and the analysis method described in claim 6, and the analysis method is: S1: Build business analysis model; S2: Perform business analysis on the business analysis model, and incorporate the analysis results into a business analysis knowledge base; S3: Incorporate other cases into the business analysis knowledge base, perform correlation analysis, incorporate the correlation analysis results into the business analysis knowledge base again, and repeat the business analysis according to the business analysis knowledge base until the optimal result is obtained.

8. A system for constructing a business analysis model for an integrated energy station, characterized in that: The system comprises: A storage device for establishing a business analysis indicator model; A storage device for splitting key indicators according to business scenarios based on the business analysis indicator model to form a key indicator template; A storage device for establishing an indicator evaluation model based on a key indicator template and a quantitative evaluation method; A storage device for constructing a business analysis template based on a key indicator template and an indicator evaluation model; A storage device for determining the weights of various indicators in the indicator evaluation model and optimizing the weights to obtain the optimal weights; A storage device for assigning the optimal weight to an indicator evaluation model to form a business analysis model.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, executes a method for constructing a commercial analysis model for an integrated energy station as described in any one of claims 1 to 5, an analysis method based on a commercial analysis model as described in claim 6, or a commercial analysis method for an integrated energy station as described in claim 7.

10. A computer device, characterized in that: The device includes a memory and a processor, wherein a computer program is stored in the memory. When the processor runs the computer program stored in the memory, the processor executes a method for constructing a commercial analysis model for an integrated energy station as described in any one of claims 1 to 5, an analysis method based on a commercial analysis model as described in claim 6, or a commercial analysis method for an integrated energy station as described in claim 7.

Images