Distributed resource analysis method and device, equipment and medium

Abstract

The invention relates to a distributed resource analysis method and apparatus, a device and a medium. The method comprises the steps of obtaining quantitative data corresponding to a quantitative index of a to-be-analyzed distributed resource; the quantitative indexes comprise a plurality of indexes related to feedback resource values of the to-be-analyzed distributed resources; constructing a fuzzy relation matrix according to the membership degree between each quantization index and a preset quantization level; processing the quantized data according to a preset processing method to obtain a weight matrix corresponding to the quantized index; inputting the fuzzy relation matrix and the weight matrix into a preset analysis model, and obtaining a quantitative result of a feedback resource value of the to-be-analyzed distributed resource; the preset analysis model is obtained by training a sample quantification result and an actual quantification result of the sample distributed resources; the quantification result is used for representing grade information to which the feedback resource value of the to-be-analyzed distributed resource belongs. By adopting the method, the accuracy and the reliability of the comprehensive benefit evaluation result of the distributed resources can be improved.

Description

Technical Field

[0001] This application relates to the technical field of distributed resources, and in particular to a method, apparatus, device and medium for analyzing distributed resources. Background Technology

[0002] Distributed resources (such as distributed photovoltaic power generation and energy storage systems) are a sustainable energy source that can effectively alleviate energy supply pressure and reduce environmental pollution. However, the comprehensive benefit assessment of distributed resources involves multiple aspects. How to comprehensively, scientifically, and accurately assess the comprehensive benefits of distributed resources, i.e., how to provide feedback on resource value, is one of the important issues in the current energy field.

[0003] Traditional methods typically begin by defining the various indicators and their quantified values ​​used to evaluate the overall benefits of distributed resources. Then, based on expert experience, each indicator is assigned a corresponding weight. Finally, a weighted summation method is used to calculate the overall benefit score, which is then used to comprehensively evaluate each indicator. However, the evaluation results obtained using this traditional method for assessing the overall benefits of distributed resources are not accurate enough. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, equipment, and medium for analyzing distributed resources to address the aforementioned technical problems, thereby improving the accuracy and reliability of the comprehensive benefit assessment results of distributed resources.

[0005] Firstly, this application provides a method for analyzing distributed resources, the method comprising:

[0006] Obtain the quantitative data corresponding to the quantitative indicators of the distributed resource to be analyzed; the quantitative indicators include multiple indicators related to the feedback resource value of the distributed resource to be analyzed;

[0007] Based on the membership degree between each quantitative indicator and the preset quantitative level, a fuzzy relationship matrix is ​​constructed;

[0008] The quantitative data is processed according to a preset processing method to obtain the weight matrix corresponding to the quantitative indicators;

[0009] The fuzzy relation matrix and weight matrix are input into the preset analysis model to obtain the quantification results of the feedback resource value of the distributed resource to be analyzed. The preset analysis model is trained using the sample quantification results and actual quantification results of the sample distributed resources. The quantification results are used to characterize the level information of the feedback resource value of the distributed resource to be analyzed.

[0010] In one embodiment, a fuzzy relation matrix is ​​constructed based on the membership degree between each quantification index and a preset quantification level, including:

[0011] Obtain the type of each quantitative indicator, and determine the corresponding membership function based on the type of the quantitative indicator;

[0012] Based on the membership function, determine the membership vector between the quantitative index and the preset quantitative level;

[0013] By integrating the membership vectors corresponding to each quantitative indicator, a fuzzy relation matrix is ​​obtained.

[0014] In one embodiment, the quantized data is processed according to a preset processing method to obtain a weight matrix corresponding to the quantized index, including:

[0015] Construct a judgment matrix based on the relative importance of each quantitative indicator;

[0016] The values ​​of each element in the judgment matrix are processed using the analytic hierarchy process to obtain the first judgment matrix corresponding to each quantitative indicator.

[0017] Construct a data matrix based on the quantified data;

[0018] The values ​​of each element in the data matrix are processed using the entropy weight method to obtain the second judgment matrix corresponding to each quantitative indicator;

[0019] The weight matrix is ​​determined based on the first and second judgment matrices.

[0020] In one embodiment, the first judgment matrix corresponding to each quantitative indicator is determined based on the values ​​of each element in the judgment matrix, including:

[0021] The judgment matrix is ​​normalized to obtain the processed judgment matrix;

[0022] Based on the processed judgment matrix, the first judgment matrix is ​​determined.

[0023] In one embodiment, determining the first judgment matrix based on the processed judgment matrix includes:

[0024] Perform a consistency check on the processed judgment matrix;

[0025] If the processed judgment matrix meets the consistency requirements, the first judgment matrix is ​​determined based on the values ​​of each element in the processed judgment matrix.

[0026] If the processed judgment matrix does not meet the consistency requirements, the processed judgment matrix is ​​updated, and the first judgment matrix is ​​determined based on the values ​​of each element in the updated judgment matrix.

[0027] In one embodiment, determining the second judgment matrix corresponding to each quantitative indicator based on the values ​​of each element in the data matrix further includes:

[0028] The data matrix is ​​forward-oriented to obtain the forward-oriented data matrix;

[0029] Calculate the information entropy based on the normalized data matrix;

[0030] Determine the second judgment matrix based on information entropy.

[0031] In one embodiment, determining the weight matrix based on the first judgment matrix and the second judgment matrix includes:

[0032] Construct a weight set based on the first and second judgment matrices;

[0033] The weight matrix is ​​determined based on the weight set.

[0034] Secondly, this application also provides a distributed resource analysis apparatus, the apparatus comprising:

[0035] The quantitative data acquisition module is used to acquire the quantitative data corresponding to the quantitative indicators of the distributed resource to be analyzed; the quantitative indicators include multiple indicators related to the feedback resource value of the distributed resource to be analyzed.

[0036] The relation matrix construction module is used to construct a fuzzy relation matrix based on the membership degree between each quantitative indicator and the preset quantitative level.

[0037] The weight matrix acquisition module is used to process the quantitative data according to a preset processing method and obtain the weight matrix corresponding to the quantitative index.

[0038] The quantization result determination module is used to input the fuzzy relation matrix and weight matrix into the preset analysis model to obtain the quantization result of the feedback resource value of the distributed resource to be analyzed; the preset analysis model is trained using the sample quantization result and the actual quantization result of the sample distributed resource; the quantization result is used to characterize the level information to which the feedback resource value of the distributed resource to be analyzed belongs.

[0039] Thirdly, this application also provides a computer device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0040] Obtain the quantitative data corresponding to the quantitative indicators of the distributed resource to be analyzed; the quantitative indicators include multiple indicators related to the feedback resource value of the distributed resource to be analyzed;

[0041] Based on the membership degree between each quantitative indicator and the preset quantitative level, a fuzzy relationship matrix is ​​constructed;

[0042] The quantitative data is processed according to a preset processing method to obtain the weight matrix corresponding to the quantitative indicators;

[0043] The fuzzy relation matrix and weight matrix are input into the preset analysis model to obtain the quantification results of the feedback resource value of the distributed resource to be analyzed. The preset analysis model is trained using the sample quantification results and actual quantification results of the sample distributed resources. The quantification results are used to characterize the level information of the feedback resource value of the distributed resource to be analyzed.

[0044] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0045] Obtain the quantitative data corresponding to the quantitative indicators of the distributed resource to be analyzed; the quantitative indicators include multiple indicators related to the feedback resource value of the distributed resource to be analyzed;

[0046] Based on the membership degree between each quantitative indicator and the preset quantitative level, a fuzzy relationship matrix is ​​constructed;

[0047] The quantitative data is processed according to a preset processing method to obtain the weight matrix corresponding to the quantitative indicators;

[0048] The fuzzy relation matrix and weight matrix are input into the preset analysis model to obtain the quantification results of the feedback resource value of the distributed resource to be analyzed. The preset analysis model is trained using the sample quantification results and actual quantification results of the sample distributed resources. The quantification results are used to characterize the level information of the feedback resource value of the distributed resource to be analyzed.

[0049] Fifthly, this application also provides a computer program product comprising a computer program that, when executed by a processor, performs the following steps:

[0050] Obtain the quantitative data corresponding to the quantitative indicators of the distributed resource to be analyzed; the quantitative indicators include multiple indicators related to the feedback resource value of the distributed resource to be analyzed;

[0051] Based on the membership degree between each quantitative indicator and the preset quantitative level, a fuzzy relationship matrix is ​​constructed;

[0052] The quantitative data is processed according to a preset processing method to obtain the weight matrix corresponding to the quantitative indicators;

[0053] The fuzzy relation matrix and weight matrix are input into the preset analysis model to obtain the quantification results of the feedback resource value of the distributed resource to be analyzed. The preset analysis model is trained using the sample quantification results and actual quantification results of the sample distributed resources. The quantification results are used to characterize the level information of the feedback resource value of the distributed resource to be analyzed.

[0054] The aforementioned distributed resource analysis method, apparatus, equipment, and medium first acquire the quantitative data corresponding to the quantitative indicators of the distributed resource to be analyzed, in order to comprehensively and objectively understand the actual performance of the distributed resource in various aspects. Then, based on the membership degree between each quantitative indicator and the preset quantitative level, a fuzzy relation matrix is ​​constructed to better handle the fuzziness and uncertainty in the evaluation of distributed resources, thereby making the final quantitative result more consistent with the actual situation. Next, the quantitative data is processed according to a preset processing method to obtain the weight matrix corresponding to the quantitative indicators, highlighting the role of important indicators and making the final quantitative result more reasonable and scientific. Finally, the fuzzy relation matrix and weight matrix are input into a preset analysis model to obtain the quantitative result of the feedback resource value of the distributed resource to be analyzed. Since the preset analysis model is trained with sample data, it can learn the intrinsic relationship between the quantitative indicators of the distributed resource and the feedback resource value. Therefore, by inputting the fuzzy relation matrix and weight matrix into the model, the predictive ability of the model can be utilized to quickly and accurately obtain the quantitative result of the feedback resource value of the distributed resource to be analyzed, providing strong support for decision-making. Attached Figure Description

[0055] Figure 1 An application environment diagram for the distributed resource analysis method provided in some embodiments of this application;

[0056] Figure 2 A flowchart illustrating a distributed resource analysis method provided in some embodiments of this application;

[0057] Figure 3 A flowchart for obtaining a fuzzy relation matrix provided in some embodiments of this application;

[0058] Figure 4 A flowchart for determining the weight matrix provided in some embodiments of this application;

[0059] Figure 5 A flowchart for determining the first judgment matrix provided in some embodiments of this application;

[0060] Figure 6 A flowchart for determining the first judgment matrix provided in other embodiments of this application;

[0061] Figure 7 A flowchart for determining the second judgment matrix provided in some embodiments of this application;

[0062] Figure 8 A flowchart for determining the weight matrix provided in other embodiments of this application;

[0063] Figure 9 A structural block diagram of a distributed resource analysis apparatus provided in some embodiments of this application;

[0064] Figure 10 This is an internal structural diagram of a computer device provided in some embodiments of this application. Detailed Implementation

[0065] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0066] The distributed resource analysis method provided in this application embodiment can be applied to, for example, Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104, or it can be located on a cloud or other network server. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, and tablets. Terminal 102 can load the distributed resource analysis method of this application to accurately analyze the quantification results of the feedback resource values ​​of distributed resources. Server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0067] In one embodiment, such as Figure 2 As shown, this method is applied to Figure 1 Taking a terminal as an example, it can be understood that this method can also be applied to a server, and to a system that includes both a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0068] Step 202: Obtain the quantitative data corresponding to the quantitative indicators of the distributed resource to be analyzed.

[0069] The distributed resources to be analyzed are comprehensive energy utilization systems distributed at the user end, encompassing various energy forms, such as renewable energy power generation equipment like solar and wind power, as well as energy storage devices and small gas turbines. Quantitative indicators include multiple metrics related to the feedback resource values ​​of the distributed resources to be analyzed. These quantitative indicators are specific metrics used to measure the performance of the distributed resources in various aspects. For example, economic aspects include investment costs, operating costs, and revenue; environmental aspects include carbon emissions and pollutant reductions; and social aspects include user satisfaction and employment contributions. Quantitative data are the specific numerical values ​​corresponding to the quantitative indicators, obtained through actual measurement, statistics, or calculation. For example, for the quantitative indicator "power generation," the quantitative data could be the actual amount of electricity generated by the distributed resources within a certain time period.

[0070] Specifically, the quantitative indicators in this embodiment include economic benefit indicators, environmental benefit indicators, social benefit indicators, and technical benefit indicators. Economic benefit indicators further include sub-indicators for investment cost, revenue, return on investment, and cost savings. Investment cost sub-indicators include initial equipment investment (such as the purchase cost of distributed photovoltaic power generation equipment and energy storage systems), installation costs (including equipment installation, commissioning, and wiring costs), and operation and maintenance costs (costs for daily equipment maintenance, repair, and replacement of parts). Revenue sub-indicators include electricity sales revenue (revenue from selling electricity generated from distributed resources to the grid or users), energy-saving benefits (electricity costs saved by reducing electricity purchases from the grid), and subsidy benefits (subsidies for distributed resources, such as renewable energy subsidies and tax incentives). Return on investment sub-indicators include rate of return (measuring the ratio of investment income to investment cost), net present value (investment income considering the time value of money), and internal rate of return (reflecting the project's potential rate of return). Cost savings sub-indicators include electricity cost savings (reducing the cost of purchasing electricity from the grid through distributed resource generation) and delaying grid upgrade costs (distributed resources reduce the load pressure on the grid, delaying grid upgrade costs).

[0071] Environmental benefit indicators include sub-indicators for carbon emission reduction, pollutant emission reduction, resource utilization, and ecological benefits. Carbon emission reduction sub-indicators include carbon emission reduction (reduction in carbon dioxide emissions from distributed renewable energy power generation replacing traditional fossil fuel power generation) and carbon credit income (carbon credit income obtained through the carbon trading market). Pollutant emission reduction sub-indicators include reductions in sulfide emissions (such as sulfur dioxide), nitrogen oxide emissions, and particulate matter emissions. Resource utilization sub-indicators include renewable energy utilization rate (the proportion of renewable energy used in distributed resources) and land use efficiency (the efficiency of land use for distributed resource construction). Ecological benefit sub-indicators include impacts on ecosystems (such as impacts on biodiversity) and water conservation (such as reduced water consumption during the operation of distributed resources).

[0072] The social benefit indicators include sub-indicators for energy security and independence, economic development, social welfare, and community participation. The energy security and independence sub-indicators include energy self-sufficiency rate (the proportion of local electricity demand met by distributed resource generation) and power supply reliability (the contribution of distributed resources to grid stability). The economic development sub-indicators include job creation (the number of jobs created during the construction and operation of distributed resources) and the development of related industries (such as the development of industries related to new energy equipment manufacturing, installation, and maintenance). The social welfare sub-indicators include improvement in energy poverty (the improvement of energy supply to low-income families or remote areas by distributed resources) and improved quality of life (such as reducing the impact of environmental pollution on residents' health). The community participation sub-indicators include community acceptance (residents' acceptance of distributed resource projects) and community sharing economy (such as the shared use model of distributed resources).

[0073] Technical benefit indicators include sub-indicators for grid support and optimization, technological innovation, system flexibility, and technological reliability. Grid support and optimization sub-indicators include peak shaving and valley filling capacity (the contribution of distributed resources to grid load balance), reduction of grid losses (distributed resources generating and consuming electricity locally, reducing power transmission losses), and improved power supply reliability (the ability of distributed resources as backup power). Technological innovation sub-indicators include the application of new technologies (such as energy storage technology and smart grid technology) and technological demonstration effects (the demonstration effect of distributed resource projects on other regions). System flexibility sub-indicators include the adjustability of distributed resources (such as the charging and discharging capacity of energy storage systems) and adaptability to the grid (the ability of distributed resources to adapt to grid operating conditions). Technological reliability sub-indicators include equipment failure rate (the failure frequency of distributed resource equipment) and system availability (the proportion of uptime of distributed resource systems).

[0074] For example, suppose we obtain the sub-indicators involved in a certain distributed resource and the collected quantitative data as shown in Table 1:

[0075]

[0076] Table 1

[0077] Step 204: Construct a fuzzy relation matrix based on the membership degree between each quantitative indicator and the preset quantitative level.

[0078] The preset quantitative level is a pre-defined grading standard used to classify and evaluate quantitative indicators. In this embodiment, the preset quantitative levels include "Excellent," "Good," "Average," "Qualified," and "Poor." Membership degree indicates the degree to which a quantitative indicator belongs to a preset quantitative level, typically ranging from [0, 1]. For example, the "carbon emissions" indicator of a distributed resource, after evaluation, has a membership degree of 0.8 belonging to the "Excellent" level, meaning there is an 80% probability that the indicator belongs to the "Excellent" level.

[0079] The fuzzy relation matrix is ​​a matrix constructed based on the membership degrees between each quantitative indicator and a preset quantitative level. It is used to describe the fuzzy relationship between the quantitative indicator and the preset quantitative level. The elements in the matrix represent the membership degree of each quantitative indicator to each preset quantitative level.

[0080] Optionally, the membership degree between each quantitative indicator and the preset quantitative level can be arranged in the form that the rows represent the indicators and the columns represent the preset quantitative levels to obtain a fuzzy relation matrix.

[0081] For example, the obtained fuzzy relation matrix is... For example, the first row represents the membership degree of the initial investment (economic benefits) to each preset quantitative level (excellent, good, medium, qualified, and poor), the second row represents the membership degree of carbon dioxide emission reduction (environmental benefits) to each preset quantitative level, and the third and fourth rows represent the assumed membership degrees of social benefits and technical benefits, respectively.

[0082] Step 206: Process the quantitative data according to the preset processing method to obtain the weight matrix corresponding to the quantitative index.

[0083] The preset processing method is a pre-determined method for calculating the weights of quantitative indicators. Common methods include expert scoring and the analytic hierarchy process (AHP). These methods can assign corresponding weights to quantitative indicators based on their importance. The weight matrix is ​​a matrix composed of the weights of each quantitative indicator, reflecting the importance of each quantitative indicator in the comprehensive evaluation. The elements in the weight matrix represent the weight value of each quantitative indicator.

[0084] Optionally, a weight matrix corresponding to the quantitative index can be obtained based on the analytic hierarchy process or the entropy weight method.

[0085] Step 208: Input the fuzzy relation matrix and weight matrix into the preset analysis model to obtain the quantitative results of the feedback resource value of the distributed resource to be analyzed.

[0086] The pre-defined analysis model is trained using the sample quantification results and actual quantification results of the distributed resources. It is used to analyze and predict the feedback resource value of the distributed resources. This model can learn the patterns and characteristics in the sample data, thereby accurately evaluating the distributed resources to be analyzed. The feedback resource value is a comprehensive value obtained by considering the performance of the distributed resources under analysis across multiple quantification indicators. It reflects the overall status of the distributed resources. For example, the comprehensive benefit value of the distributed resources obtained by comprehensively evaluating multiple quantification indicators in economic, environmental, and social aspects is the feedback resource value.

[0087] The feedback resource value of the distributed resource to be analyzed is the comprehensive benefit of the distributed resource to be analyzed. The quantification result is the output of the preset analysis model and is used to characterize the level information of the feedback resource value of the distributed resource to be analyzed. For example, the quantification result can indicate that the comprehensive benefit of a distributed resource belongs to the "excellent" level or the "good" level.

[0088] Optionally, the preset analysis model can be a time-series learning model, such as a Long Short-Term Memory Network (LSTM). In this way, the sample quantization results and actual quantization results of the sample distributed resources can be used for training, and the feedback resource values ​​of the distributed resources can be accurately analyzed and predicted to obtain the prediction results of the feedback resource values ​​of the distributed resources at the current time or within a period including the current time.

[0089] The aforementioned distributed resource analysis method first obtains the quantitative data corresponding to the quantitative indicators of the distributed resource to be analyzed, in order to comprehensively and objectively understand the actual performance of the distributed resource in various aspects. Then, based on the membership degree between each quantitative indicator and the preset quantitative level, a fuzzy relation matrix is ​​constructed to better handle the fuzziness and uncertainty in the evaluation of distributed resources, thus making the final quantitative result more consistent with reality. Next, the quantitative data is processed according to a preset processing method to obtain the weight matrix corresponding to the quantitative indicators, highlighting the role of important indicators and making the final quantitative result more reasonable and scientific. Finally, the fuzzy relation matrix and weight matrix are input into a preset analysis model to obtain the quantitative result of the feedback resource value of the distributed resource to be analyzed. Since the preset analysis model has been trained with sample data, it can learn the intrinsic relationship between the quantitative indicators of the distributed resource and the feedback resource value. Therefore, by inputting the fuzzy relation matrix and weight matrix into the model, the predictive power of the model can be utilized to quickly and accurately obtain the quantitative result of the feedback resource value of the distributed resource to be analyzed, providing strong support for decision-making.

[0090] In one possible embodiment, after obtaining the quantitative data corresponding to the quantitative indicators of the distributed resources to be analyzed, the quantitative data needs to be cleaned first to remove noise, missing values, and duplicate data. For missing values, interpolation, mean imputation, and other methods are used. For noisy data, filtering techniques are used for smoothing, and then the data is normalized to convert the data to the same scale. For numerical data, Z-score standardization with a mean of 0 and a standard deviation of 1 or min-max normalization is performed.

[0091] The Z-score standardization formula is: , For the raw quantitative data, The mean of the data. This represents the standard deviation of the data.

[0092] For categorical data, encoding is performed. Encoding methods include one-hot encoding and label encoding. One-hot encoding converts categorical variables into a set of binary variables, with each category corresponding to a feature column. Label encoding maps each category to an integer. Specifically, different quantization methods are selected based on the type of data to be quantized.

[0093] For example, taking the data in Table 1 above as an example, for the missing value in "Initial Investment", this embodiment preferably uses the mean imputation method. First, calculate the mean of the "Initial Investment" data as (200+250+180+300) / 4=2.325 million yuan, and fill the missing value with 2.325 million yuan. Assuming that the 400,000 yuan in the "Annual Operating Cost" data may be noisy data (outlier), this embodiment preferably uses a simple moving average filtering technique for smoothing. Calculate the moving average (assuming the window size is 3). The moving average of the first three data is (30+35+28) / 3=310,000 yuan, and the moving average of the second to fourth data is (35+28+40) / 3=343,300 yuan. Then, replace 400,000 yuan with 343,300 yuan.

[0094] Taking "carbon dioxide emission reduction" as an example, we calculate its mean and standard deviation. The mean is (500+550+480+600+520) / 5 = 530 tons / year, and the standard deviation is 41.95. Then, we use the Z-score standardization formula to standardize each data point. For example... .

[0095] For numerical data, taking "annual operating costs" as an example, calculate its minimum value. maximum value Using the minimum-maximum normalization formula Normalize each data point; for example, normalizing 30 results in 0.29.

[0096] For example, when using unique thermal coding for energy type data, assuming there are three categories of energy types: solar, wind, and hydro, the coded data would be as follows: solar energy is 100, wind energy is 010, and hydro is 001.

[0097] In one embodiment, such as Figure 3 As shown, a fuzzy relation matrix is ​​constructed based on the membership degrees between each quantitative indicator and the preset quantitative level, including:

[0098] Step 302: Obtain the type of each quantitative indicator and determine the corresponding membership function based on the type of the quantitative indicator.

[0099] The quantitative indicators can be categorized into fluctuation-type and stable-type. Since different types of quantitative indicators have different characteristics and variation patterns, using a single membership function without considering the indicator type may lead to inaccurate membership calculations, thus affecting the quality of the fuzzy relation matrix and the final evaluation results. Therefore, it is necessary to select an appropriate membership function based on the type of quantitative indicator to accurately describe the relationship between the quantitative indicator and the preset quantitative level. This allows for more reasonable membership calculations, ensuring that the subsequently constructed fuzzy relation matrix better reflects the actual situation.

[0100] Optionally, for volatility indicators, an improved S-shaped membership function is used; for stability indicators, an improved Gaussian mixture membership function is used.

[0101] Specifically, for volatility indicators, the improved S-shaped membership function is used as follows:

[0102] ;

[0103] In the formula, It is the membership degree obtained based on the quantitative data corresponding to the volatility indicator; parameters , and Adjust dynamically based on data distribution. , and These are the lower quartile and upper quartile of the data, respectively.

[0104] For stable indices, an improved Gaussian mixture membership function is used:

[0105] ;

[0106] In the formula, It is the membership degree obtained based on the quantitative data corresponding to the stable index; and The weighting coefficients and , and With two center points, and This is the standard deviation parameter.

[0107] Step 304: Determine the membership vector between the quantitative index and the preset quantitative level based on the membership function.

[0108] The membership function describes the degree to which an element belongs to a preset quantization level. The membership vector is a vector composed of the membership values ​​of the quantization index belonging to each preset quantization level. Assuming there are n preset quantization levels, for a given quantization index, its membership vector is an n-dimensional vector, where each element represents the membership degree of the quantization index to each preset quantization level.

[0109] Optionally, the membership degree between the quantitative index and each preset quantitative level can be calculated first based on the membership function, and then the membership degree vector between the quantitative index and the preset quantitative level can be obtained based on each membership degree.

[0110] For example, continuing with the quantitative data in Table 1 above, "initial investment" and "annual operating cost" are economic benefit indicators, which can be considered as volatile indicators, and the improved S-shaped membership function is used; "carbon dioxide emission reduction" can be considered as a stable indicator, and the improved Gaussian mixed membership function is used.

[0111] First, determine the lower quartile of the "initial investment" data (200, 250, 180, 300, 232.5). Upper quartiles as well as It can be known that , ,but The improved S-shaped membership function is then:

[0112] ;

[0113] For the "initial investment" data, the first data point will be used. For example, the membership vector of the product under each preset quantitative level (excellent, good, medium, qualified, poor) is (0,0,0,1,0).

[0114] The improved Gaussian mixture membership function, taking "carbon dioxide emission reduction" as an example, assumes the weighting coefficients... , center point center point Standard deviation parameter , The improved Gaussian mixture function is then... For the data on "carbon dioxide emission reduction", For example, its membership vector at each preset quantization level is calculated as (0.7, 0.2, 0.1, 0, 0).

[0115] In addition, to facilitate subsequent calculations, the membership degrees obtained above can be normalized. For example, taking the membership vector (0.7, 0.2, 0.1, 0, 0) as an example, after normalizing each membership degree, the final membership vector is still (0.7, 0.2, 0.1, 0, 0).

[0116] Step 306: Merge the membership vectors corresponding to each quantitative indicator to obtain the fuzzy relation matrix.

[0117] The fuzzy relation matrix is ​​a matrix used to describe the fuzzy relationships between multiple quantification indicators and various preset quantification levels. Assuming there are m quantification indicators and n preset quantification levels, the final result will be a fuzzy relation matrix of form m*n.

[0118] For example, assuming that "initial investment" and "carbon dioxide emission reduction" represent economic benefits and environmental benefits respectively, and that social and technological benefits are temporarily assumed to be uniformly distributed (here, we simply assume they are uniformly distributed), we construct a fuzzy relation matrix. The first row represents the membership degree of "initial investment" (economic benefits) to each evaluation level, the second row represents the membership degree of "carbon dioxide emission reduction" (environmental benefits) to each evaluation level, and the third and fourth rows represent the assumed membership degrees of social and technical benefits.

[0119] In this embodiment, selecting an appropriate membership function to calculate the membership vector based on the type of quantification index helps ensure the accuracy of the subsequently obtained fuzzy relation matrix, thereby improving the accuracy and reliability of the final quantification result of the distributed resource feedback resource value.

[0120] In one embodiment, such as Figure 4 As shown, the quantitative data is processed according to a preset processing method to obtain the weight matrix corresponding to the quantitative indicators, including:

[0121] Step 402: Construct a judgment matrix based on the relative importance of each quantitative indicator.

[0122] The judgment matrix is ​​a matrix constructed based on the relative importance of two quantitative indicators. In other words, the elements in the judgment matrix can represent the comparison results of the relative importance between different quantitative indicators.

[0123] Optionally, based on a preset scaling table and expert evaluation experience, the relative importance between two quantifications can be determined, and an n*n matrix can be constructed based on the relative importance, where n is the number of quantification indicators, i.e., the judgment matrix.

[0124] Specifically, the scaling table is shown in Table 2:

[0125]

[0126] Table 2

[0127] For example, suppose that based on expert evaluation experience, the relative importance of the aforementioned four quantitative indicators is assessed, resulting in a judgment matrix. .

[0128] Step 404: Process the values ​​of each element in the judgment matrix based on the analytic hierarchy process to obtain the first judgment matrix corresponding to each quantitative indicator.

[0129] The first judgment matrix is ​​derived from a judgment matrix constructed based on the relative importance of each quantitative indicator. The first judgment matrix reflects the relative importance relationships of each quantitative indicator as determined subjectively, based on expert experience and understanding.

[0130] Optionally, based on methods such as the Analytic Hierarchy Process (AHP), eigenvectors can be calculated from the judgment matrix, and after normalization, the weights of each quantitative indicator can be obtained, thereby further obtaining the first judgment matrix.

[0131] Step 406: Construct a data matrix based on the quantified data.

[0132] The data matrix contains the actual quantitative data of each quantitative indicator, reflecting the performance of each quantitative indicator in actual situations.

[0133] It is understandable that the actual quantitative data of each quantitative indicator is organized into a data matrix. This matrix contains the specific performance data of each quantitative indicator in actual operation. The actual quantitative data reflects the objective situation of distributed resources in various aspects. Constructing a data matrix provides basic data for analyzing the importance of each quantitative indicator from the perspective of objective data.

[0134] For example, a data matrix ,in, For the first The first quantitative indicator The indicator values ​​of each evaluation object; This is the number of objects to be evaluated; It refers to the quantity of quantitative indicators. Regarding the positive correlation of economic indicators: For positive indices within a range: .in, The elements are those after the indicator has been positively oriented. This represents the optimal point for the intermediate index.

[0135] Step 408: Process the values ​​of each element in the data matrix based on the entropy weight method to obtain the second judgment matrix corresponding to each quantitative indicator.

[0136] The second judgment matrix is ​​derived from a data matrix constructed based on the quantitative data. The second judgment matrix reflects the relative importance of each quantitative indicator in the actual data from an objective data perspective.

[0137] Optionally, the data matrix can be processed using the entropy weighting method to calculate statistical measures such as the coefficient of variation of each indicator data, thereby determining the weight of each quantitative indicator based on the data performance.

[0138] Understandably, when determining the second judgment matrix, the fluctuations and dispersion of each quantitative indicator in the actual data were taken into account, reflecting the relative importance of each indicator from the perspective of objective data, thus avoiding the one-sidedness that may be caused by subjective judgment.

[0139] Step 410: Determine the weight matrix based on the first judgment matrix and the second judgment matrix.

[0140] Optionally, the weight matrix can be determined by fusing elements from the first and second judgment matrices.

[0141] Understandably, determining the weight matrix based on the first and second judgment matrices can combine subjective judgments and objective data, allowing the weight matrix to reflect both the experience and knowledge of experts and the characteristics of actual data. This results in more reasonable and accurate quantitative indicator weights, improving the reliability of subsequent comprehensive evaluations of distributed resources.

[0142] In this embodiment, the weight matrix is ​​determined by using a first judgment matrix obtained based on subjective analysis and a second judgment matrix obtained based on actual data. This avoids the problems of excessive subjectivity that may result from relying solely on subjective judgment and the potential neglect of important factors when relying solely on objective data. Furthermore, by integrating subjective and objective information, the accuracy of the weight matrix is ​​improved, thereby enhancing the accuracy of the evaluation of distributed resource feedback resource values.

[0143] In one embodiment, such as Figure 5 As shown, based on the values ​​of each element in the judgment matrix, the first judgment matrix corresponding to each quantitative indicator is determined, including:

[0144] Step 502: Normalize the judgment matrix to obtain the processed judgment matrix.

[0145] Understandably, the judgment matrix is ​​constructed based on the relative importance of various quantitative indicators, and the values ​​of the elements in the matrix reflect the proportional importance of pairwise comparisons of different indicators. However, since the value ranges and scales of different indicators may differ when comparing them, directly using the original judgment matrix to calculate weights may be affected by differences in numerical magnitude, leading to inaccurate results. Normalization, on the other hand, adjusts the elements in the judgment matrix according to certain rules, bringing them to a uniform scale and eliminating the influence of differences in the units and numerical values ​​of the original data.

[0146] Optionally, you can first calculate the sum of the elements in each column of the judgment matrix based on each element in the judgment matrix, then divide each element by the sum of the elements in its column to obtain the processed elements, and then update the judgment matrix based on the processed elements to obtain the processed judgment matrix.

[0147] Specifically, the elements in the judgment matrix A can be normalized using the following formula:

[0148] ;

[0149] In the formula, To determine the first element in the matrix Line number The elements after normalization of column elements; To determine the first element in matrix A The elements of the column.

[0150] For example, after normalizing the judgment matrix A according to the above normalization formula, the processed judgment matrix is ​​obtained. .

[0151] Step 504: Determine the first judgment matrix based on the processed judgment matrix.

[0152] The first judgment matrix is ​​a weight matrix composed of the weights corresponding to each quantitative indicator obtained based on the above-mentioned analytic hierarchy process. Each element in the first judgment matrix reflects the proportion of the corresponding quantitative indicator in the comprehensive evaluation of the distributed resource feedback resource value. The larger the weight, the greater the influence of the quantitative indicator on the final evaluation result.

[0153] Optionally, the mean of each row of the processed judgment matrix can be used as the weight element in the first judgment matrix.

[0154] Understandably, the processed judgment matrix has eliminated the influence of dimensions and numerical scales. Determining the first judgment matrix based on this eliminates the influence of these dimensions and scales, allowing for a more accurate reflection of the relative importance of each quantitative indicator in the comprehensive evaluation. The elements in the first judgment matrix represent the weight of each quantitative indicator in the evaluation of distributed resource feedback resource value, serving as key parameters for subsequent comprehensive evaluation.

[0155] For example, using the judgment matrix after the above processing... For example, the first judgment matrix obtained is, i.e., the first weight vector. .

[0156] In this embodiment, the judgment matrix is ​​first normalized to eliminate unreasonable influences from the data. Then, based on the processed judgment matrix, the first judgment matrix is ​​determined. This avoids excessive influence of subjective factors on weight allocation, enabling the weights of each quantitative indicator to objectively and accurately reflect their importance in the comprehensive evaluation, thereby improving the scientificity and credibility of the evaluation results.

[0157] In one embodiment, such as Figure 6 As shown, based on the processed judgment matrix, the first judgment matrix is ​​determined, including:

[0158] Step 602: Perform a consistency check on the processed judgment matrix.

[0159] Consistency checking is the process of verifying whether the judgment matrix satisfies logical consistency. For example, if indicator A is more important than indicator B, and indicator B is more important than indicator C, then indicator A should be more important than indicator C, and this relationship of importance should also be transitive. Consistency checking is the process of verifying whether the judgment matrix satisfies this logical consistency relationship.

[0160] Alternatively, it can be determined using the consistency index (CI) and the random consistency ratio (CR).

[0161] Step 604: If the processed judgment matrix meets the consistency requirements, determine the first judgment matrix based on the values ​​of each element in the processed judgment matrix.

[0162] Understandably, when the judgment matrix passes the consistency check, it indicates that the judgments on the relative importance of its elements have good logic and consistency. Calculating the first judgment matrix based on this matrix then ensures that the weight values ​​accurately reflect the actual importance of each quantitative indicator.

[0163] Optionally, the first judgment matrix can be determined based on the method in step 504, which will not be repeated here.

[0164] Step 606: If the processed judgment matrix does not meet the consistency requirements, update the processed judgment matrix and determine the first judgment matrix based on the values ​​of each element in the updated judgment matrix.

[0165] Understandably, when the judgment matrix fails to meet the consistency requirements, it indicates a problem with the original judgment, which needs to be corrected. By updating the judgment matrix to meet the consistency requirements, an accurate first judgment matrix can be obtained.

[0166] Optionally, one or more abnormal elements in the judgment matrix can be updated to obtain a new judgment matrix. Then, the elements of the new judgment matrix can be normalized according to the method in step 502 to obtain the updated judgment matrix.

[0167] In this embodiment, the judgment matrix that does not meet the requirements is updated by consistency check and verification, which ensures the rationality and consistency of the judgment matrix, thereby improving the accuracy of the calculation of the first judgment matrix and making the resource value evaluation results of distributed resources more reliable.

[0168] In one embodiment, consistency verification of the processed judgment matrix can be performed first according to the formula. Calculate the maximum eigenvalue, and then determine the consistency verification value of the processed judgment matrix based on the maximum eigenvalue, the number of quantification indicators, and the preset verification formula.

[0169] Specifically, first according to the formula Calculate the consistency index of the processed judgment matrix, where, As a consistency indicator, To quantify the number of indicators, the judgment matrix after the above processing is... The consistency index value is 0.041; then according to the formula The consistency check value of the processed judgment matrix is ​​calculated as follows: Where, This is the consistency check value of the processed judgment matrix, which is also the random consistency ratio. This is a mapping table between consistency index values ​​and the number of quantitative indicators, showing the corresponding consistency index value found for a specific number of quantitative indicators. Table 3 illustrates this mapping.

[0170]

[0171] Table 3

[0172] As shown in Table 3, when n=4, Then the calculation yields In other words, the processed judgment matrix meets the consistency check.

[0173] In one embodiment, such as Figure 7 As shown, based on the values ​​of each element in the data matrix, the second judgment matrix corresponding to each quantitative indicator is determined, which also includes:

[0174] Step 702: Perform forward transformation on the data matrix to obtain the forward-transformed data matrix.

[0175] Understandably, different quantitative indicators may have different properties in actual quantitative data. Some indicators are benefit-oriented, meaning the higher the value, the better, such as power generation and revenue; some are cost-oriented, meaning the lower the value, the better, such as construction costs and operating costs; and some are range-oriented, where the value is optimal within a specific range. Forward processing is the process of unifying different types of quantitative indicators into benefit-oriented indicators.

[0176] Optionally, for cost-based indicators, a mathematical transformation (such as taking the reciprocal) can be used to convert them into a form where a larger value indicates better performance. For interval-based indicators, a specific calculation method can be used to convert them into benefit-based indicators. The purpose of this is to standardize data processing and facilitate comprehensive analysis and comparison.

[0177] For example, the elements in the data matrix are first standardized to convert indicators of different magnitudes into the same magnitude, as shown in the following formula:

[0178] ;

[0179] In the formula, These are the standardized data matrix elements; The elements are those after the indicator has been positively oriented. The minimum value among the elements after the index has been positively oriented; It represents the maximum value among the elements after the index has been positively oriented.

[0180] Step 704: Calculate the information entropy based on the forward-directed data matrix.

[0181] Information entropy is used to measure the degree of uncertainty or disorder in data. In the context of a data matrix, information entropy can be used to reflect the amount of information contained in each quantitative indicator. For a quantitative indicator, the greater the difference in its data among various samples, the more information the indicator contains, and the smaller its information entropy; conversely, the smaller the difference in data, the greater the information entropy. In other words, the lower the information entropy of a quantitative indicator, the greater the dispersion of its data, indicating that the indicator has a stronger ability to distinguish different samples, which also means that the indicator may be more important in comprehensive evaluation.

[0182] Understandably, by calculating the information entropy of each quantitative indicator, the amount of information contained in each indicator can be measured, thereby providing an objective basis for determining the importance of each quantitative indicator.

[0183] Optionally, the information entropy can be calculated using the following formula:

[0184] ;

[0185] ;

[0186] In the formula, Information entropy; The weights of each quantitative indicator.

[0187] Step 706: Determine the second judgment matrix based on the information entropy.

[0188] The second judgment matrix is ​​a weight matrix or weight vector obtained based on the entropy weighting method. This second judgment matrix reflects the weights of each quantitative indicator determined based on the characteristics of the data itself. It provides objective weight information for subsequently determining the final weight matrix by comprehensively considering subjective and objective factors, making the determination of weights more scientific and reasonable.

[0189] Optionally, the second judgment matrix can be obtained according to the following formula:

[0190] ;

[0191] In the formula, For the first The weights corresponding to each quantitative indicator.

[0192] For example, suppose the second judgment matrix, i.e. the second weight vector, is finally obtained through the entropy weight method. .

[0193] In this embodiment, the data matrix is ​​first forward-oriented, and then the information entropy is calculated based on the forward-oriented data matrix. The second judgment matrix is ​​determined based on the information entropy, which helps to improve the accuracy of the final weight matrix, thereby improving the accuracy of the evaluation of the resource value feedback of distributed resources.

[0194] In one embodiment, such as Figure 8 As shown, the weight matrix is ​​determined based on the first judgment matrix and the second judgment matrix, including:

[0195] Step 802: Construct a weight set based on the first judgment matrix and the second judgment matrix.

[0196] The weight set is a collection that integrates the information contained in the first and second judgment matrices. The first judgment matrix is ​​a weight correlation matrix for each quantitative indicator, determined based on the relative importance of each indicator (subjective level, based on expert judgment). The second judgment matrix is ​​a weight correlation matrix for each quantitative indicator obtained based on quantitative data (objective level, calculated through data information entropy, etc.). The weight set summarizes these two different sources and types of weight information, forming a collection that includes both subjective and objective weight information, providing a comprehensive data foundation for the final determination of the weight matrix.

[0197] Step 804: Determine the weight matrix based on the weight set.

[0198] The weight matrix is ​​the final matrix used to characterize the importance of each quantitative indicator.

[0199] For example, the first judgment matrix, i.e. the first weight vector, is obtained first by the above-mentioned analytic hierarchy process. The second judgment matrix obtained by the entropy weight method, i.e., the second weight vector Construct a weight set .

[0200] Then solve the system of linear equations: After solving this system of equations, for and Then, normalization was performed to obtain... and Then, according to the formula... Obtain the combined vector .

[0201] Specifically, based on the first and second weight vectors, the system of equations obtained is as follows: Solve the system of equations again to obtain... , The final combined vector, i.e., the weight matrix, is: .

[0202] This embodiment uses the above method, which can avoid the problems of excessive subjectivity that may result from relying solely on subjective judgment and the potential neglect of important factors when relying solely on objective data, thereby improving the accuracy of resource value evaluation for distributed resources.

[0203] Furthermore, when training a pre-defined analytical model using the sample quantization results from distributed sample resources and the actual quantization results, the sample quantization results used are obtained based on the weight matrix and the fuzzy relation matrix. Specifically, this includes the following steps:

[0204] (1) Perform fuzzy synthesis operation on the weight matrix and the fuzzy relation matrix to obtain the comprehensive evaluation result vector. The commonly used synthesis model is the weighted average model.

[0205] (2) Defuzzification: The comprehensive evaluation result vector is defuzzified to obtain the specific evaluation result. Commonly used methods include the maximum membership method and the weighted average method, among which:

[0206] Maximum membership method: Select the evaluation level with the highest membership degree as the final evaluation result;

[0207] Weighted average method: Calculate the weighted average and convert it into a specific numerical value or level.

[0208] (3) Results analysis and decision-making: Based on the results of fuzzy comprehensive evaluation, analyze the comprehensive benefits of distributed resource projects to provide decision support for project planning, investment and operation.

[0209] Optionally, a weighted average model can be used for fuzzy synthesis, that is, the weight matrix is ​​multiplied by the fuzzy relation matrix to obtain the comprehensive evaluation result vector.

[0210] For example, assuming the comprehensive evaluation result vector B=(0.202,0.321,0.355,0.165,0.101), it can be seen that the value with the largest membership degree is 0.355, and its corresponding quantification level is "medium". Therefore, according to the maximum membership degree method, the final quantification result of the feedback resource value of the distributed resource to be analyzed is "medium", that is, the corresponding sample quantification result is "medium".

[0211] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0212] Based on the same inventive concept, this application also provides a distributed resource analysis apparatus for implementing the distributed resource analysis method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations of one or more distributed resource analysis apparatus embodiments provided below can be found in the limitations of the distributed resource analysis method described above, and will not be repeated here.

[0213] In one embodiment, such as Figure 9 As shown, a distributed resource analysis device is provided, including: a quantization data acquisition module 902, a relationship matrix construction module 904, a weight matrix acquisition module 906, and a quantization result determination module 908, wherein:

[0214] The quantitative data acquisition module 902 is used to acquire the quantitative data corresponding to the quantitative indicators of the distributed resource to be analyzed; the quantitative indicators include multiple indicators related to the feedback resource value of the distributed resource to be analyzed.

[0215] The relation matrix construction module 904 is used to construct a fuzzy relation matrix based on the membership degree between each quantitative indicator and the preset quantitative level.

[0216] The weight matrix acquisition module 906 is used to process the quantitative data according to a preset processing method to obtain the weight matrix corresponding to the quantitative index.

[0217] The quantization result determination module 908 is used to input the fuzzy relation matrix and weight matrix into the preset analysis model to obtain the quantization result of the feedback resource value of the distributed resource to be analyzed; the preset analysis model is trained using the sample quantization result and the actual quantization result of the sample distributed resource; the quantization result is used to characterize the level information to which the feedback resource value of the distributed resource to be analyzed belongs.

[0218] In one embodiment, the relation matrix construction module 904 is further configured to: obtain the type of each quantitative indicator, and determine the corresponding membership function based on the type of the quantitative indicator; determine the membership vector between the quantitative indicator and the preset quantitative level according to the membership function; and fuse the membership vectors corresponding to each quantitative indicator to obtain a fuzzy relation matrix.

[0219] In one embodiment, the weight matrix acquisition module 906 is further configured to: construct a judgment matrix based on the relative importance of each quantitative indicator; process the values ​​of each element in the judgment matrix based on the analytic hierarchy process to obtain a first judgment matrix corresponding to each quantitative indicator; construct a data matrix based on the quantitative data; process the values ​​of each element in the data matrix based on the entropy weight method to obtain a second judgment matrix corresponding to each quantitative indicator; and determine the weight matrix based on the first judgment matrix and the second judgment matrix.

[0220] In one embodiment, the weight matrix acquisition module 906 is further configured to: normalize the judgment matrix to obtain the processed judgment matrix; and determine the first judgment matrix based on the processed judgment matrix.

[0221] In one embodiment, the weight matrix acquisition module 906 is further configured to: perform consistency verification on the processed judgment matrix; if the processed judgment matrix meets the consistency requirements, determine a first judgment matrix based on the values ​​of each element in the processed judgment matrix; if the processed judgment matrix does not meet the consistency requirements, update the processed judgment matrix, and determine the first judgment matrix based on the values ​​of each element in the updated judgment matrix.

[0222] In one embodiment, the weight matrix acquisition module 906 is further configured to: perform forward processing on the data matrix to obtain a forwarded data matrix; calculate the information entropy based on the forwarded data matrix; and determine the second judgment matrix based on the information entropy.

[0223] In one embodiment, the weight matrix acquisition module 906 is further configured to: construct a weight set based on the first judgment matrix and the second judgment matrix; and determine the weight matrix based on the weight set.

[0224] Each module in the aforementioned distributed resource analysis device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0225] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 10As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a distributed resource analysis method. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0226] Those skilled in the art will understand that Figure 10 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0227] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0228] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0229] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0230] It should be noted that the quantitative data and related data of the distributed resources to be analyzed involved in this application (including but not limited to data used for analysis, stored data, and displayed data) are all information and data authorized by the user or fully authorized by all parties.

[0231] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0232] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0233] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for analyzing distributed resources, characterized in that, The method includes: Obtain the quantitative data corresponding to the quantitative indicators of the distributed resource to be analyzed; the quantitative indicators include multiple indicators related to the feedback resource value of the distributed resource to be analyzed; Based on the membership degree between each of the quantitative indicators and the preset quantitative level, a fuzzy relationship matrix is ​​constructed; The quantified data is processed according to a preset processing method to obtain the weight matrix corresponding to the quantified index; The fuzzy relation matrix and the weight matrix are input into a preset analysis model to obtain the quantification result of the feedback resource value of the distributed resource to be analyzed; the preset analysis model is trained using the sample quantification result and the actual quantification result of the sample distributed resource; the quantification result is used to characterize the level information to which the feedback resource value of the distributed resource to be analyzed belongs.

2. The method according to claim 1, characterized in that, The step of constructing a fuzzy relationship matrix based on the membership degree between each of the quantification indicators and the preset quantification level includes: Obtain the type of each quantitative indicator, and determine the corresponding membership function based on the type of the quantitative indicator; Based on the membership function, determine the membership vector between the quantification index and the preset quantification level; The fuzzy relation matrix is ​​obtained by fusing the membership vectors corresponding to each of the quantitative indicators.

3. The method according to claim 1, characterized in that, The step of processing the quantized data according to a preset processing method to obtain the weight matrix corresponding to the quantized index includes: Construct a judgment matrix based on the relative importance of each of the quantitative indicators; The values ​​of each element in the judgment matrix are processed using the analytic hierarchy process to obtain the first judgment matrix corresponding to each of the quantitative indicators. Based on the quantified data, construct a data matrix; The values ​​of each element in the data matrix are processed using the entropy weighting method to obtain the second judgment matrix corresponding to each of the quantitative indicators. The weight matrix is ​​determined based on the first judgment matrix and the second judgment matrix.

4. The method according to claim 3, characterized in that, The step of determining the first judgment matrix corresponding to each of the quantitative indicators based on the values ​​of each element in the judgment matrix includes: The judgment matrix is ​​normalized to obtain the processed judgment matrix; Based on the processed judgment matrix, the first judgment matrix is ​​determined.

5. The method according to claim 4, characterized in that, Determining the first judgment matrix based on the processed judgment matrix includes: Perform a consistency check on the processed judgment matrix; If the processed judgment matrix meets the consistency requirements, the first judgment matrix is ​​determined based on the values ​​of each element in the processed judgment matrix. If the processed judgment matrix does not meet the consistency requirements, the processed judgment matrix is ​​updated, and the first judgment matrix is ​​determined based on the values ​​of each element in the updated judgment matrix.

6. The method according to claim 3, characterized in that, The step of determining the second judgment matrix corresponding to each quantitative indicator based on the value of each element in the data matrix further includes: The data matrix is ​​forward-oriented to obtain a forward-oriented data matrix; Based on the positiveized data matrix, calculate the information entropy; The second judgment matrix is ​​determined based on the information entropy.

7. The method according to claim 3, characterized in that, Determining the weight matrix based on the first judgment matrix and the second judgment matrix includes: Construct a weight set based on the first judgment matrix and the second judgment matrix; The weight matrix is ​​determined based on the weight set.

8. A distributed resource analysis device, characterized in that, The device includes: The quantitative data acquisition module is used to acquire quantitative data corresponding to the quantitative indicators of the distributed resource to be analyzed; the quantitative indicators include multiple indicators related to the feedback resource value of the distributed resource to be analyzed. The relation matrix construction module is used to construct a fuzzy relation matrix based on the membership degree between each of the quantitative indicators and the preset quantitative level; The weight matrix acquisition module is used to process the quantized data according to a preset processing method to obtain the weight matrix corresponding to the quantized index. The quantization result determination module is used to input the fuzzy relation matrix and the weight matrix into a preset analysis model to obtain the quantization result of the feedback resource value of the distributed resource to be analyzed; the preset analysis model is trained using the sample quantization result and the actual quantization result of the sample distributed resource; the quantization result is used to characterize the level information to which the feedback resource value of the distributed resource to be analyzed belongs.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images