Power grid engineering material insurance supply scheme evaluation method and device

Abstract

The invention provides a power grid engineering material insurance supply scheme evaluation method and device, and relates to the field of big data analysis. The method comprises the steps of obtaining material management data and engineering construction data in response to an evaluation operation for a power grid engineering material insurance supply scheme; constructing association features between the material management data and the engineering construction data through a data mining algorithm; acquiring key bottleneck points in the supply chain according to the association features based on mining task constraint rules; and inputting the key bottleneck point into the power grid engineering material insurance supply scheme evaluation model, and outputting a risk evaluation result. Through multi-dimensional data fusion, non-linear feature mining and dynamic adjustment of an optimization algorithm, the accuracy of power grid engineering material supply insurance scheme evaluation is improved, and the problem that when a traditional scheme is used for power grid engineering material supply insurance scheme evaluation, dynamic changes of a supply chain are not considered sufficiently, material demand fluctuation cannot be responded in real time, and the evaluation accuracy of the power grid engineering material supply insurance scheme evaluation is affected is solved. Therefore, the problem of low evaluation accuracy is solved.

Description

Technical Field

[0001] This application relates to the field of big data analysis, and particularly to a method and device for evaluating the supply guarantee plan of power grid project materials. Background Art

[0002] Ensuring the timely and high-quality supply of power grid project materials is the foundation for the safe production and orderly operation of power grid companies, which is crucial for the coordinated development and stable operation of the power grid. Power grid project construction involves a large number of key equipment and materials, such as transformers, conductors, cables, circuit breakers, etc. The timeliness and quality of their supply directly affect the project progress and power grid stability. Due to the complexity of power grid projects, the need for cross-regional dispatching, and the uncertainty of the material supply chain, establishing a scientific and accurate material supply guarantee plan evaluation mechanism is of great significance for ensuring the smooth progress of power grid projects.

[0003] When traditional solutions evaluate the supply guarantee plan of power grid project materials, they mostly rely on empirical judgment, historical statistical data analysis, manual review, and fixed threshold rule setting. For example, based on the historical performance of suppliers and the manually set risk levels, combined with a static evaluation method of project progress, to judge the risk level of material supply. However, due to insufficient consideration of the dynamic changes in the supply chain and the inability to respond to material demand fluctuations in real time, especially in the face of a complex supply chain environment, the evaluation results cannot conform to the actual supply chain situation. For example, sudden events such as the production capacity of suppliers and delays during transportation often cannot be reflected in the evaluation results in a timely manner, resulting in a sluggish or ineffective risk warning system. Therefore, there is a problem of low evaluation accuracy.

[0004] Therefore, there is an urgent need for a method and device for evaluating the supply guarantee plan of power grid project materials. Summary of the Invention

[0005] This application provides a method and device for evaluating the supply guarantee plan of power grid project materials, which solves the problem of low evaluation accuracy in the traditional solution for evaluating the supply guarantee plan of power grid project materials due to insufficient consideration of the dynamic changes in the supply chain and the inability to respond to material demand fluctuations in real time.

[0006] In the first aspect of this application, a method for evaluating the supply guarantee plan of power grid project materials is provided, including: in response to an evaluation operation for the supply guarantee plan of power grid project materials, obtaining material management data and project construction data; constructing an association feature between the material management data and the project construction data through a data mining algorithm; obtaining key bottleneck points in the supply chain based on the mining task constraint rules according to the association feature; inputting the key bottleneck points into the evaluation model of the supply guarantee plan of power grid project materials to output a risk evaluation result.

[0007] Optionally, construct the correlation features between the material management data and the engineering construction data through a data mining algorithm, including: performing preprocessing operations on the material management data and the engineering construction data respectively to obtain the preprocessed material management data and the preprocessed engineering construction data, where the preprocessing operations include data cleaning operations and normalization operations; constructing the correlation features based on the data mining algorithm according to the preprocessed material management data and the preprocessed engineering construction data.

[0008] Optionally, construct the correlation features between the material management data and the engineering construction data through a data mining algorithm, including: obtaining the change trends of the material management data and the engineering construction data based on a time series model; constructing the first correlation features between the material management data and the engineering construction data according to the change trends; obtaining the implicit relationships between the material management data and the engineering construction data through an association rule mining algorithm; constructing the second correlation features between the material management data and the engineering construction data according to the implicit relationships; and performing feature fusion on the first correlation features and the second correlation features through a feature fusion project to obtain the correlation features between the material management data and the engineering construction data.

[0009] Optionally, the feature fusion project includes the first type of feature fusion and the second type of feature fusion. Through the feature fusion project, performing feature fusion on the first correlation features and the second correlation features includes: performing weighted sum feature fusion on the first correlation features and the second correlation features based on the first type of feature fusion to obtain the first type of feature fusion result; performing product feature fusion on the first correlation features and the second correlation features based on the second type of feature fusion to obtain the second type of feature fusion result; and performing feature fusion based on the first type of feature fusion result and the second type of feature fusion result.

[0010] Optionally, obtain the key bottleneck points in the supply chain according to the correlation features based on the mining task constraint rules, including: obtaining the to-be-confirmed key bottleneck points in the supply chain according to the correlation features; determining whether the to-be-confirmed key bottleneck points meet the constraint conditions in the mining task constraint rules; and if the to-be-confirmed key bottleneck points do not meet the constraint conditions in the mining task constraint rules, taking the to-be-confirmed key bottleneck points as the key bottleneck points.

[0011] Optionally, input the key bottleneck points into the evaluation model of the power grid project material supply guarantee plan and output the risk assessment result, including: inputting the key bottleneck points into the evaluation model of the power grid project material supply guarantee plan to calculate the risk score; determining whether the risk score is greater than the preset risk score threshold; if the risk score is greater than the preset risk score threshold, the output risk assessment result is that there is a risk in the power grid project material supply guarantee plan; if the risk score is less than or equal to the preset risk score threshold, the output risk assessment result is that there is no risk in the power grid project material supply guarantee plan.

[0012] Optionally, the method further includes: obtaining an improvement suggestion plan corresponding to the risk assessment result from a preset improvement suggestion database, where the preset improvement suggestion database is used to store the correspondence between the risk assessment result and the improvement suggestion plan; and sending the improvement suggestion plan to a preset terminal.

[0013] In a second aspect of the present application, there is provided an evaluation device for the power grid project material supply guarantee plan, including: an acquisition module, configured to obtain material management data in response to an evaluation operation on the power grid project material supply guarantee plan, where the material management data includes supplier information data, material specification data, material demand plan data, and historical performance data; the acquisition module is further configured to obtain project construction data, where the project construction data includes construction personnel and equipment data, construction progress data, and project information data; a processing module, configured to construct an association feature between the material management data and the project construction data through a data mining algorithm; the processing module is further configured to obtain key bottleneck points in the supply chain based on the association feature according to mining task constraint rules, where the mining task constraint rules include material supply time constraint rules, engineering material quality constraint rules, and supplier delivery capacity constraint rules; the processing module is further configured to input the key bottleneck points into a power grid project material supply guarantee plan evaluation model and output a risk assessment result.

[0014] In a third aspect of the present application, there is provided an electronic device, including a processor, a memory, a user interface, and a network interface, where the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is configured to execute the instructions stored in the memory so that the electronic device executes the method according to any one of the above.

[0015] In a fourth aspect of the present application, there is provided a computer-readable storage medium storing a computer program, and the computer program is executed by a processor to perform the method according to any one of the above.

[0016] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0017] 1. Obtain material management data and project construction data; construct an association feature between the material management data and the project construction data through a data mining algorithm; obtain key bottleneck points in the supply chain based on the mining task constraint rules and through the association feature; input the key bottleneck points into a power grid project material supply guarantee plan evaluation model, and output a risk assessment result through the power grid project material supply guarantee plan evaluation model, thereby improving the accuracy of the evaluation of the power grid project material supply guarantee plan through multi-dimensional data fusion, non-linear feature mining, and dynamic adjustment of the optimization algorithm, and improving the accuracy of the evaluation of the power grid project material supply guarantee plan.

[0018] 2. Obtain the change trends of material management data and engineering construction data through a time series model; construct the first association features between the material management data and the engineering construction data according to the change trends; obtain the implicit relationships between the material management data and the engineering construction data through an association rule mining algorithm; construct the second association features between the material management data and the engineering construction data according to the implicit relationships; through a feature fusion project, fuse the first association features and the second association features to obtain the association features between the material management data and the engineering construction data, thereby improving the dynamic adaptability and intelligent level of the evaluation of the engineering material supply guarantee plan, enhancing the ability to identify potential risks in the material supply chain, and improving the applicability and real-time response ability of the evaluation model to complex supply chain environments.

[0019] 3. Perform preprocessing operations on the material management data and the engineering construction data. The preprocessing operations include data cleaning operations and normalization operations. According to the data mining algorithm, construct association features through the preprocessed material management data and engineering construction data. Thus, through the preprocessing operations, improve the data quality, eliminate outliers, enhance the comparability between different data sources, optimize the stability of the model input, improve the accuracy of the association features, and provide more reliable data support for subsequent supply chain bottleneck identification and risk assessment. Description of the Drawings

[0020] Figure 1 is a schematic flowchart of a method for evaluating a power grid project material supply guarantee plan provided by an embodiment of the present application;

[0021] Figure 2 is a schematic block diagram of an apparatus for evaluating a power grid project material supply guarantee plan provided by an embodiment of the present application;

[0022] Figure 3 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

[0023] Description of the reference numerals: 21, acquisition module; 22, processing module; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. Detailed Embodiments

[0024] In order to enable those skilled in the art to better understand the technical solutions in this specification, the following will clearly and completely describe the technical solutions in the embodiments of this specification in conjunction with the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments.

[0025] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification of the present application, the singular forms "a", "an", "the", "above-mentioned", "said", "this" are also intended to include the plural forms, unless clearly indicated to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to and includes any or all possible combinations of one or more of the listed items.

[0026] Hereinafter, the terms "first" and "second" are only used for descriptive purposes and should not be construed as implying or suggesting relative importance or implicitly indicating the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present application, unless otherwise specified, the meaning of "a plurality" is two or more.

[0027] In order to enable those skilled in the art to better understand the technical solutions of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0028] Please refer to Figure 1 , which shows a schematic flowchart of a method for evaluating the power grid project material supply guarantee plan provided by the embodiments of the present application. The flowchart mainly includes the following steps: S101 to S105.

[0029] Step S101, in response to an evaluation operation for the power grid project material supply guarantee plan, obtain material management data.

[0030] Specifically, when a user initiates a request for evaluating the power grid project material supply guarantee plan, various types of data related to material management are automatically obtained, namely, material management data. The process of obtaining material management data involves collecting, integrating, and storing various information related to material supply from multiple data sources to support subsequent evaluation operations. Specifically, material management data includes, but is not limited to, supplier information data, material specification data, material demand plan data, and historical performance data, etc. Material management data can be obtained through various means. For example, supplier information data includes the basic information of suppliers, such as supplier name, contact person, contact information, creditworthiness, historical cooperation situation, etc., and is usually obtained through the cooperation platform with suppliers, contract management system, or API interface; material specification data includes the detailed description, model, specification, packaging standard, storage conditions, etc. of materials, and usually comes from the material management system or technical documents provided by suppliers; material demand plan data includes the types, quantities, delivery times, etc. of materials required for the project, and can be extracted through the engineering project management system or ERP system; historical performance data includes the performance of suppliers in past projects, such as whether the delivery is on time, whether the quality meets the requirements, whether the supply quantity meets the demand, etc. Historical performance data is usually stored in the project management platform, historical supply chain records, or contract execution system.

[0031] Step S102, obtain engineering construction data.

[0032] Specifically, the process of obtaining engineering construction data mainly involves collecting information related to project construction from different systems and data sources, namely, engineering construction data. Engineering construction data includes construction personnel and equipment data, construction progress data, and engineering project information data, etc. First, construction personnel and equipment data contains the situation of personnel and equipment resources required for each construction stage, such as the number, qualifications, and allocation of construction personnel, the type, number, usage status, and maintenance records of equipment, etc., and can usually be obtained through the human resource management system, equipment management system, or project site management system; construction progress data includes the execution situation of each construction task, specifically such as the start and end times, current progress, and estimated completion time of each construction stage. Construction progress data is usually provided by project management software (such as Primavera, MSProject, etc.) or on-site construction real-time monitoring system; engineering project information data includes the basic situation of the project: project name, project location, project budget, contract information, etc., and can usually be extracted from the project management platform, contract management system, or enterprise resource planning (ERP) system.

[0033] Step S103, construct the correlation features between material management data and engineering construction data through data mining algorithms.

[0034] Specifically, preprocessing operations are performed on the material management data and the project construction data respectively to obtain the preprocessed material management data and the preprocessed project construction data. The preprocessing operations include data cleaning operations and normalization operations. Based on data mining algorithms, correlation features are constructed according to the preprocessed material management data and the preprocessed project construction data. The preprocessing operation is an important link in the data mining process, aiming to improve the data quality and provide accurate basic data for the subsequent construction of correlation features. The preprocessing operation usually includes data cleaning and normalization operations, and the specific process is as follows: In the material management data and the project construction data, there may be some missing records or fields (such as missing supplier information, missing records of construction progress delays). It can be processed by filling, interpolation or deletion. For example, if the supply plan of some materials is missing, historical data or other relevant fields (such as the supply plan of similar materials) can be used for filling; or filling with the mean value, the previous value or the next value. Outliers in the data (such as too high or too low supplier performance rates, serious lags in construction progress, etc.) may affect the effectiveness of the subsequent model. Detect outliers by setting thresholds and select to delete, correct or replace these abnormal data according to the specific situation. Since the data sources are diverse, there may be duplicate records, such as: multiple records of the same supplier, multiple submissions of the same construction task, etc. Ensure the uniqueness of the data by checking for duplicates and deleting duplicate data. Ensure the consistency of the data formats such as material specifications, supply time, construction progress, etc. For example, unify the format of the time field (such as YYYY-MM-DD), and keep the material units consistent (such as kilograms, tons, etc.) to avoid data errors caused by inconsistent formats.

[0035] Specifically, the normalization operation is to convert data with different dimensions and scales into a unified standard range to avoid different features affecting the algorithm effect due to scale differences during model training. Common normalization methods include: linearly converting the data into the [0,1] interval, and making the data have a mean of 0 and a standard deviation of 1 by converting the data into a standard normal distribution. For features with skewed distributions (such as material demand, supply time, etc.), the data distribution can be smoothed by taking logarithms to reduce the influence of extreme values.

[0036] Exemplarily, during the preprocessing process, the material management data and the project construction data can also be appropriately transformed and fused according to needs for subsequent analysis. For example, the time field can be converted into periodic features, or the number of lag days can be calculated based on the construction progress data, and these transformed features can be combined with other data to form more effective correlation features.

[0037] In a possible implementation, step S103 further includes: obtaining the change trends of the material management data and the project construction data based on a time series model; constructing a first association feature between the material management data and the project construction data according to the change trends; obtaining the implicit relationship between the material management data and the project construction data through an association rule mining algorithm; constructing a second association feature between the material management data and the project construction data according to the implicit relationship; and performing feature fusion on the first association feature and the second association feature through a feature fusion project to obtain the association feature between the material management data and the project construction data.

[0038] Specifically, a method of time series analysis is used to obtain the association feature between the material demand and the construction progress. The material demand and the construction progress usually present a certain time series relationship, and time series analysis can reveal the dynamic changes of this relationship, that is, through the time series model, obtain the change trends of the material management data and the project construction data: the time series analysis of the material management data can reveal the growth trend, volatility and periodic changes of the material demand; the time series analysis of the project construction data can reflect the change trends of the construction progress, personnel allocation, equipment scheduling, etc. in the time dimension. Extract the change trends, fluctuations, etc. of the material demand and the construction progress from the time series model, and analyze their change patterns over time. Calculate the first association feature according to the following formula:

[0039]

[0040] where F1 is the first association feature, F1(t) is the first association feature at the t-th moment, K is the upper limit of the time lag step, indicating the maximum time span considered. For example, if K = 3, the model will consider the relationship between the current moment and the data of the past 3 time steps, k is the time lag step, and β k , α, δ are all weight coefficients in the time series model, where β k represents the interaction effect weight of the material demand and the construction progress at the lag time k, α represents the interaction effect weight of the changes (i.e., increments) of the material demand and the construction progress, δ is used to represent the influence weight of the covariance between the material demand and the construction progress, and β k , α, δ can be learned through the model training process (such as regression analysis or optimization algorithm) to accurately model the influence of different time step lengths on the relationship between the material demand and the construction progress. f X is the time series model corresponding to the material management data, f Y is the time series model corresponding to the project construction data, and Δf X (t - k) represents the increment of the material demand quantity at the time step t - k (i.e., the difference between the current material demand and the demand quantity of the previous step), that is, the volatility of the material demand is captured through the change amount, and Δf Y(t - k) represents the increment of the construction progress at time step t - k (i.e., the difference between the current construction progress and the previous step's construction progress), which is used to describe the fluctuation of the construction progress. Cov(X(t - k), Y(t - k)) represents the covariance between the material demand and the construction progress. Covariance is used to measure the strength and direction of the relationship between two variables (in this case, the material demand and the construction progress). If the covariance is positive, it indicates a positive correlation between them (i.e., the material demand and the construction progress increase simultaneously); if the covariance is negative, it means their relationship may be negatively correlated (i.e., the construction progress decreases when the material demand increases). Covariance helps to quantify the dynamic relationship between the two.

[0041] By using the association rule mining algorithm, the implicit relationship between the material management data and the project construction data is obtained: The association rule mining algorithm (such as Apriori, FP - growth, etc.) is used to analyze the implicit relationship between the material management data and the project construction data. For example, the association rule between the change in material demand and the lag in construction progress is mined. The association rules obtained through the algorithm can reveal key dependencies, such as "During construction stage A, when the material demand is greater than 100, the construction progress may be delayed by X days". Calculate the second association feature according to the following formula:

[0042]

[0043] where F2 is the second association feature, N is the number of association rules, i is the index of the rule, θ i is the weight coefficient of the i - th association rule, r i is the i - th association rule. Association rule mining can reveal the dependency relationship between the material demand and the construction progress, usually in the form of "If the demand for a certain material reaches a specific value, the construction progress may be delayed". ε is the exponential coefficient of support, Support(r i ) ε represents the support of the i - th association rule. Support is an index used in association rule mining to measure the frequency of a rule appearing in the dataset, and it represents the proportion of records that satisfy the premise and conclusion of the rule among all transaction records. ∈ is the exponential coefficient of confidence, Confidence(r i ) ∈ represents the confidence of the i - th association rule. Confidence is a key index in association rule mining, which represents the probability that the conclusion holds when the premise condition is satisfied. γ is the exponential coefficient of lift, Lift(r i ) γ represents the lift of the i - th association rule. Lift represents the degree of independence between the premise and the conclusion of the rule; J is the number of feature functions, j is the index of the feature function, G j (ri ) represents the j-th feature function related to r i The feature function is additional information for each rule, such as the confidence level of the rule, importance score, or other factors related to material management and engineering construction.

[0044] In a possible implementation, the feature fusion project includes the first type of feature fusion and the second type of feature fusion; performing feature fusion on the first associated feature and the second associated feature through the feature fusion project includes: performing weighted sum feature fusion based on the first type of feature fusion according to the first associated feature and the second associated feature to obtain the first type of feature fusion result; performing product feature fusion based on the second type of feature fusion according to the first associated feature and the second associated feature to obtain the second type of feature fusion result; performing feature fusion based on the first type of feature fusion result and the second type of feature fusion result.

[0045] Specifically, afterwards, the first associated feature (trend based on the time series model) and the second associated feature (implied relationship based on association rule mining) can be feature-fused through at least two different fusion methods. The feature fusion methods include the first type of feature fusion and the second type of feature fusion. Among them, the first type of feature fusion combines the first associated feature and the second associated feature by means of weighted sum, focusing on the modeling of trends and periodic relationships, enhancing the model's ability to capture feature change trends and sensitivity to dynamic changes, thereby improving the capture accuracy of time series change patterns and implied laws; the second type of feature fusion can capture the mutual influence between the first associated feature and the second associated feature, as well as the contribution degree of this influence to the associated feature by considering the product relationship between the first associated feature and the second associated feature, so that the fused feature can better reflect the potential dependence relationship. Calculate the associated feature according to the following formula:

[0046]

[0047] where, F fusion is the associated feature, P is the number of times of performing the first type of feature fusion, μ p is the weight coefficient of the first type of feature fusion, and the weight coefficient of the first type of feature fusion is used to control the influence degree of the p-th feature (F1 p +F2 p ) on the associated feature, F1 p is the first associated feature of performing the p-th first type of feature fusion, F2 p is the second associated feature of performing the p-th first type of feature fusion, σ is the hyperparameter corresponding to the first type of feature fusion, Q is the number of times of performing the second type of feature fusion, ω q is the weight coefficient of the second type of feature fusion, and the weight coefficient of the second type of feature fusion is used to control the q-th feature F1 q ·F2q Degree of influence on associated features, F1 q The first associated feature for the q-th second type of feature fusion, F2 q The second associated feature for the q-th second type of feature fusion, τ is the hyperparameter corresponding to the second type of feature fusion, k1 and k2 are weighting coefficients, D is the number of dimensions of the non-linear relationship between the first associated feature and the second associated feature, F1 d Value of the first associated feature on the d-th non-linear relationship dimension, F2 d Value of the second associated feature on the d-th non-linear relationship dimension.

[0048] Step S104, obtaining the key bottleneck points in the supply chain according to the associated features based on the mining task constraint rules.

[0049] Specifically, set the mining task constraint rules according to the actual requirements of the power grid project material supply guarantee plan, and obtain the key bottleneck points in the supply chain through the associated features. The mining task constraint rules include material supply time constraint rules, engineering material quality constraint rules, and supplier delivery capacity constraint rules.

[0050] In a possible implementation manner, step S104 further includes: obtaining the to-be-confirmed key bottleneck points in the supply chain according to the associated features; determining whether the to-be-confirmed key bottleneck points meet the constraint conditions in the mining task constraint rules; if the to-be-confirmed key bottleneck points do not meet the constraint conditions in the mining task constraint rules, regarding the to-be-confirmed key bottleneck points as the key bottleneck points.

[0051] Specifically, the mining task constraint rules include but are not limited to: Material supply time constraint rule: It stipulates the maximum allowable time range for materials to be shipped from the supplier to the construction site. If the actual supply time of a certain material exceeds this threshold, it may lead to a lag in the construction progress and be identified as a potential bottleneck point; Engineering material quality constraint rule: It sets the quality standards that materials must meet during acceptance, such as strength, durability, dimensional error, etc. If there is a non-conforming situation higher than a certain proportion in the historical quality inspection records of a certain batch of materials, it may affect the project construction and be identified as a key bottleneck point; Supplier delivery capacity constraint rule: It evaluates the historical performance of suppliers, including on-time delivery rate, delivery qualification rate, etc. If a certain supplier has insufficient performance capacity in multiple time periods, the materials provided by it may become a key bottleneck point in the supply chain. On this basis, based on the first correlation feature and the second correlation feature, combined with historical data and real-time monitoring data, calculate the risk degree of each material supply node in the supply chain, and identify the key bottleneck points to be confirmed in the supply chain. The key bottleneck points to be confirmed may include some links with unstable material supply, links with higher supplier delivery risks, or links with serious mismatches between construction progress and material supply. For example, judge whether the material supply time exceeds the allowable range. If the actual arrival time of the material exceeds the maximum allowable time and the material is required for a key engineering link, then this supply chain node is confirmed as a key bottleneck point; judge whether the material quality meets the standards. If the detection qualification rate of a certain supply batch is lower than the set threshold and the material affects the construction progress, then this material supply chain node is confirmed as a key bottleneck point; judge whether the supplier's performance capacity is insufficient. If the performance success rate of the supplier within a certain past time window is lower than the set standard and the supplier is the core material supplier, then the supplier is confirmed as a key bottleneck point. If the key bottleneck point to be confirmed meets the constraint conditions in the mining task constraint rules, it indicates that it may not have a significant impact on the supply chain and is not treated as the final key bottleneck point; if the key bottleneck point to be confirmed does not meet at least one of the constraint conditions in the mining task constraint rules, it is marked as a key bottleneck point and enters the next risk assessment and optimization processing flow.

[0052] Step S105, input the key bottleneck point into the power grid project material supply guarantee plan evaluation model and output the risk assessment result.

[0053] Specifically, the power grid project material supply guarantee plan evaluation model is constructed by integrating multi-dimensional data analysis, machine learning model training, and supply chain simulation optimization, and the risk assessment result is output through the power grid project material supply guarantee plan evaluation model.

[0054] In a possible implementation, step S105 further includes: inputting the key bottleneck points into the evaluation model for the power grid project material supply guarantee plan to calculate the risk score; determining whether the risk score is greater than the preset risk score threshold; if the risk score is greater than the preset risk score threshold, the output risk assessment result is that there is a risk in the power grid project material supply guarantee plan; if the risk score is less than or equal to the preset risk score threshold, the output risk assessment result is that there is no risk in the power grid project material supply guarantee plan.

[0055] Specifically, input the identified key bottleneck points into the evaluation model for the power grid project material supply guarantee plan. This model has integrated multi-dimensional information such as material management data, project construction data, supply chain historical data, and correlation feature analysis results, and is based on machine learning models, supply chain simulation optimization technologies, and dynamic evaluation methods, capable of quantitatively analyzing the supply risks of power grid project materials. After inputting the key bottleneck points, this model will comprehensively consider factors such as their influence degree in historical data, importance on the critical path in the supply chain, supplier performance capabilities, and the changing trend of material supply time, and calculate the risk score. The risk score can be calculated through the following formula:

[0056]

[0057] where Score is the risk score, L is the number of dimensions of the fused features, α` l is the risk weight coefficient, representing the importance of the fused features in the l-th dimension, F fusion l is the fused feature in the l-th dimension, β` is the non-linear exponential parameter, used to adjust the influence of the fused feature F fusion on the final risk score. If β`>1, the influence of the feature is amplified, otherwise it is weakened. This parameter is usually set by experimental tuning or through machine learning methods. S is the number of task constraint violation situations, Violatioon s is the s-th constraint violation situation. The setting method of Violation is as follows: if there is a violation, this value is set to 1, otherwise it is set to 0; or it can be set in the way of the proportion of the degree of violation. Im(Violation s ) is the influence factor of the constraint violation, representing the contribution degree of the s-th constraint violation situation to the risk score. The severity of different violation situations is different, so weighting can be carried out through the influence factor. γ` is the Lagrangian optimization adjustment parameter, H is the number of feature dimensions involved in Lagrangian constraint optimization, F fusion h$F_h$ is the fused feature on the $h$-th feature dimension, and $Lagrange(h)$ is the Lagrangian optimization factor for the $h$-th feature dimension, representing the parameter used for constraint adjustment during the risk assessment optimization process. This parameter is typically used for constrained optimization in optimization problems. For example, during the risk score calculation process, if the risk caused by a certain feature exceeds the expectation, the Lagrangian optimization method can be used to dynamically adjust its impact, making the final score more in line with the actual supply chain situation. If the risk score is greater than the preset risk score threshold, the risk assessment result output by the power grid project material supply guarantee plan evaluation model is that there is a risk in the power grid project material supply guarantee plan; if the risk score is less than or equal to the preset risk score threshold, the risk assessment result output by the power grid project material supply guarantee plan evaluation model is that there is no risk in the power grid project material supply guarantee plan.

[0058] In a possible implementation manner, step S105 further includes: obtaining the improvement suggestion plan corresponding to the risk assessment result from the preset improvement suggestion database, where the preset improvement suggestion database is used to store the correspondence between the risk assessment result and the improvement suggestion plan; and sending the improvement suggestion plan to the preset terminal.

[0059] Specifically, after obtaining the risk assessment result, according to the evaluated risk level, retrieve the improvement suggestion plan that matches the risk assessment result from the preset improvement suggestion database. The preset improvement suggestion database has pre-stored the mapping relationship between different risk score ranges and corresponding improvement strategies, including material supply optimization plans, supplier adjustment suggestions, logistics scheduling optimization, inventory replenishment strategies, construction schedule adjustment, etc.; if the risk score is relatively high, the database may return high-priority response plans such as "replace the supplier", "increase safety inventory", or "adjust the construction plan", and if the risk score is relatively low, it may suggest "monitor the supply chain status" or "optimize the transportation route" to reduce potential risks; after matching the appropriate improvement suggestion plan, encapsulate it into executable task information, and send the improvement plan to the preset terminal (such as the terminal device corresponding to the user) through the API interface, message push system, or project management platform, including mobile applications, enterprise management systems, or intelligent supply chain management platforms, enabling users to obtain real-time risk analysis results and optimization suggestions, thereby facilitating quick decision-making and execution, and improving the execution efficiency of the power grid project material supply guarantee plan and the stability of supply chain management.

[0060] By adopting the above method, this application obtains material management data and engineering construction data; constructs the correlation features between the material management data and the engineering construction data through a data mining algorithm; obtains the key bottleneck points in the supply chain based on the mining task constraint rules according to the correlation features; inputs the key bottleneck points into the power grid project material supply guarantee plan evaluation model, and outputs the risk evaluation result through the power grid project material supply guarantee plan evaluation model, thereby improving the accuracy of the power grid project material supply guarantee plan evaluation through multi-dimensional data fusion, non-linear feature mining, and dynamic adjustment of the optimization algorithm.

[0061] Please refer to Figure 2 , which shows a module schematic diagram of a power grid project material supply guarantee plan evaluation device provided by an embodiment of this application. The device includes an acquisition module 21 and a processing module 22, where,

[0062] The acquisition module 21 is configured to obtain material management data in response to an evaluation operation on the power grid project material supply guarantee plan. The material management data includes supplier information data, material specification data, material demand plan data, and historical performance data;

[0063] The acquisition module 21 is further configured to obtain engineering construction data, and the engineering construction data includes construction personnel and equipment data, construction progress data, and engineering project information data.

[0064] The processing module 22 is configured to construct the correlation features between the material management data and the engineering construction data through a data mining algorithm;

[0065] The processing module 22 is further configured to obtain the key bottleneck points in the supply chain based on the mining task constraint rules according to the correlation features. The mining task constraint rules include material supply time constraint rules, engineering material quality constraint rules, and supplier delivery capacity constraint rules;

[0066] The processing module 22 is further configured to input the key bottleneck points into the power grid project material supply guarantee plan evaluation model and output the risk evaluation result.

[0067] In a possible implementation manner, the processing module 22 is configured to construct the correlation features between the material management data and the engineering construction data through a data mining algorithm, specifically including: respectively performing preprocessing operations on the material management data and the engineering construction data to obtain the preprocessed material management data and the preprocessed engineering construction data. The preprocessing operations include data cleaning operations and normalization operations; constructing the correlation features based on the data mining algorithm according to the preprocessed material management data and the preprocessed engineering construction data.

[0068] In a possible implementation, the processing module 22 is used to construct the correlation features between the material management data and the engineering construction data through a data mining algorithm, specifically including: obtaining the change trends of the material management data and the engineering construction data based on a time series model; constructing the first correlation features between the material management data and the engineering construction data according to the change trends; obtaining the implicit relationship between the material management data and the engineering construction data through an association rule mining algorithm; constructing the second correlation features between the material management data and the engineering construction data according to the implicit relationship; and performing feature fusion on the first correlation features and the second correlation features through a feature fusion project to obtain the correlation features between the material management data and the engineering construction data.

[0069] In a possible implementation, the feature fusion project includes the first type of feature fusion and the second type of feature fusion. The processing module 22 is used to perform feature fusion on the first correlation features and the second correlation features through the feature fusion project, specifically including: performing weighted sum feature fusion on the first correlation features and the second correlation features based on the first type of feature fusion to obtain the first type of feature fusion result; performing product feature fusion on the first correlation features and the second correlation features based on the second type of feature fusion to obtain the second type of feature fusion result; and performing feature fusion based on the first type of feature fusion result and the second type of feature fusion result.

[0070] In a possible implementation, the processing module 22 is used to obtain the key bottleneck points in the supply chain based on the mining task constraint rules according to the correlation features, specifically including: obtaining the to-be-confirmed key bottleneck points in the supply chain according to the correlation features; determining whether the to-be-confirmed key bottleneck points meet the constraint conditions in the mining task constraint rules; and if the to-be-confirmed key bottleneck points do not meet the constraint conditions in the mining task constraint rules, using the to-be-confirmed key bottleneck points as the key bottleneck points.

[0071] In a possible implementation, the processing module 22 is used to input the key bottleneck points into the power grid project material supply guarantee plan evaluation model and output a risk assessment result, specifically including: inputting the key bottleneck points into the power grid project material supply guarantee plan evaluation model to calculate a risk score; determining whether the risk score is greater than a preset risk score threshold; if the risk score is greater than the preset risk score threshold, the output risk assessment result is that there is a risk in the power grid project material supply guarantee plan; if the risk score is less than or equal to the preset risk score threshold, the output risk assessment result is that there is no risk in the power grid project material supply guarantee plan.

[0072] In a possible implementation, the power grid project material supply guarantee plan evaluation device further includes an improvement module. The improvement module is used to obtain an improvement suggestion plan corresponding to the risk assessment result in a preset improvement suggestion database, and the preset improvement suggestion database is used to store the correspondence between the risk assessment result and the improvement suggestion plan; and sending the improvement suggestion plan to a preset terminal.

[0073] By adopting the above device, through multi-dimensional data fusion, non-linear feature mining and dynamic adjustment of optimization algorithms, the accuracy of the evaluation of the power grid project material supply guarantee plan is improved, and the problem of low accuracy of the evaluation existing in the traditional plan when evaluating the power grid project material supply guarantee plan is solved, because the dynamic changes of the supply chain are insufficiently considered and the material demand fluctuations cannot be responded to in real time.

[0074] It should be noted that when the device provided in the above embodiment realizes its functions, only the division of the above functional modules is used for illustration. In actual application, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0075] This application also provides an electronic device. Refer to Figure 3 , Figure 3 which is a schematic structural diagram of an electronic device provided in an embodiment of this application. The electronic device may include: at least one processor 301, at least one communication bus 302, a user interface 303, at least one network interface 304, and a memory 305.

[0076] Among them, the communication bus 302 is used to realize the connection and communication between these components.

[0077] Among them, the user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may further include a standard wired interface and a wireless interface.

[0078] Among them, the network interface 304 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0079] Among them, the processor 301 may include one or more processing cores. The processor 301 connects various parts within the entire server through various interfaces and lines, and executes various functions of the server and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 305, and by calling the data stored in the memory 305. Optionally, the processor 301 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 301 may integrate a combination of one or more of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU mainly processes the operating system, user interface, application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301 and may be implemented separately by a single chip.

[0080] Among them, the memory 305 may include random access memory (RAM) and may also include read-only memory. Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 305 may include a program storage area and a data storage area. Among them, the program storage area may store instructions for implementing the operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above method embodiments, etc.; the data storage area may store the data involved in the above method embodiments. Optionally, the memory 305 may further be at least one storage device located far from the aforementioned processor 301. Refer to Figure 3 , the memory 305, as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for evaluating the supply guarantee plan for power grid engineering materials.

[0081] In Figure 3In the electronic device shown, the user interface 303 is mainly used to provide an interface for the user to input data and obtain the data input by the user; the processor 301 can be used to call the grid project material supply guarantee scheme evaluation application program stored in the memory 305. When executed by one or more processors 301, the electronic device is caused to execute one or more of the methods as described in the foregoing embodiments. It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited by the described action sequence, because according to this application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0082] This application also provides a computer-readable storage medium storing instructions. When executed by one or more processors, the electronic device is caused to execute one or more of the methods as described in the foregoing embodiments.

[0083] In the foregoing embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0084] In several implementation manners provided by this application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some service interfaces. The indirect couplings or communication connections of the devices or units can be in electrical or other forms.

[0085] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0086] In addition, in each embodiment of this application, the functional units can be integrated in one processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0087] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of various embodiments of this application. And the aforementioned memory includes: various media such as USB flash drives, mobile hard disks, magnetic disks, or optical discs that can store program codes.

[0088] The foregoing are only exemplary embodiments disclosed in this application and should not be used to limit the scope of the disclosure of this application. That is, any equivalent changes and modifications made in accordance with the teachings of this application disclosure still fall within the scope covered by this application disclosure. Those skilled in the art will readily think of other implementation schemes of this application disclosure after considering the specification and practice.

[0089] This application aims to cover any variations, uses, or adaptive changes of this application disclosure, and these variations, uses, or adaptive changes follow the general principles of this application disclosure and include common general knowledge or conventional technical means in the technical field not recorded in this application disclosure.

Claims

1. A method for evaluating a power grid engineering material supply guarantee scheme, characterized in that: include: In response to an evaluation operation on a material supply guarantee plan for a power grid project, obtaining material management data, the material management data including supplier information data, material specification data, material demand plan data, and historical contract performance data; Acquiring engineering construction data, wherein the engineering construction data includes construction personnel and equipment data, construction progress data, and engineering project information data; Constructing the correlation features between the material management data and the engineering construction data through a data mining algorithm; Acquire key bottlenecks in the supply chain based on the associated features based on mining task constraint rules, wherein the mining task constraint rules include material supply time constraint rules, engineering material quality constraint rules, and supplier delivery capacity constraint rules; The key bottleneck points are input into the evaluation model of the power grid engineering material supply plan, and the risk assessment results are output.

2. The method according to claim 1, characterized in that The constructing of the association features between the material management data and the engineering construction data by using a data mining algorithm includes: Preprocessing the material management data and the engineering construction data respectively to obtain preprocessed material management data and preprocessed engineering construction data, wherein the preprocessing operation includes a data cleaning operation and a normalization operation; Based on the data mining algorithm, the associated features are constructed according to the preprocessed material management data and the preprocessed engineering construction data.

3. The method according to claim 1, characterized in that The constructing of the association features between the material management data and the engineering construction data by using a data mining algorithm includes: Acquire the change trends of the material management data and the engineering construction data based on a time series model; Constructing a first correlation feature between the material management data and the engineering construction data according to the change trend; Obtaining the implicit relationship between the material management data and the engineering construction data through an association rule mining algorithm; Constructing a second association feature between the material management data and the engineering construction data according to the implicit relationship; The first associated feature and the second associated feature are fused through a feature fusion project to obtain the associated feature between the material management data and the engineering construction data.

4. The method according to claim 3, characterized in that The feature fusion project includes first-class feature fusion and second-class feature fusion; The step of fusing the first associated feature and the second associated feature through a feature fusion project includes: Based on the first type of feature fusion, weighted feature fusion is performed according to the first associated feature and the second associated feature to obtain a first type of feature fusion result; Based on the second type of feature fusion, a product feature fusion is performed according to the first associated feature and the second associated feature to obtain a second type of feature fusion result; Feature fusion is performed based on the first-category feature fusion result and the second-category feature fusion result.

5. The method according to claim 1, characterized in that The step of obtaining key bottlenecks in the supply chain based on the associated features based on mining task constraint rules includes: Acquire the key bottleneck points to be confirmed in the supply chain according to the correlation characteristics; Determine whether the key bottleneck point to be confirmed meets the constraint conditions in the mining task constraint rules; If the key bottleneck point to be confirmed does not satisfy the constraint conditions in the mining task constraint rules, the key bottleneck point to be confirmed is used as the key bottleneck point.

6. The method according to claim 1, characterized in that The key bottleneck points are input into the power grid engineering material supply guarantee scheme evaluation model, and the risk assessment results are output, including: Input the key bottleneck points into the power grid engineering material supply guarantee scheme evaluation model to calculate the risk score; Determining whether the risk score is greater than a preset risk score threshold; If the risk score is greater than the preset risk score threshold, the output risk assessment result is that the power grid project material supply guarantee plan has risks; If the risk score is less than or equal to the preset risk score threshold, the output risk assessment result is that there is no risk in the power grid project material supply plan.

7. The method according to claim 6, characterized in that The method further comprises: Obtaining an improvement suggestion scheme corresponding to the risk assessment result from a preset improvement suggestion database, wherein the preset improvement suggestion database is used to store a correspondence between the risk assessment result and the improvement suggestion scheme; The improvement suggestion is sent to a preset terminal.

8. A device for evaluating a material supply plan for a power grid project, characterized in that: include: An acquisition module, for acquiring material management data in response to an evaluation operation on a material supply guarantee plan for a power grid project, wherein the material management data includes supplier information data, material specification data, material demand plan data, and historical contract performance data; The acquisition module is also used to acquire engineering construction data, which includes construction personnel and equipment data, construction progress data, and engineering project information data; A processing module, used for constructing the correlation features between the material management data and the engineering construction data through a data mining algorithm; The processing module is further used to obtain key bottlenecks in the supply chain according to the associated features based on mining task constraint rules, wherein the mining task constraint rules include material supply time constraint rules, engineering material quality constraint rules, and supplier delivery capacity constraint rules; The processing module is also used to input the key bottleneck point into the power grid engineering material supply guarantee plan evaluation model and output the risk assessment result.

9. An electronic device, characterized in that: It includes a processor, a communication bus, a user interface, a network interface and a memory, wherein the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is performed.

Images