Method and device for providing enterprise resource demand reference information in supply chain business, equipment, storage medium and program product

Abstract

The invention relates to a method and device for providing enterprise resource demand reference information in supply chain business, equipment, a storage medium and a program product, and relates to the technical field of resource management and data analysis. The method can improve the prediction accuracy of the enterprise resource demand. The method comprises the following steps: respectively carrying out deep processing on a preprocessed historical resource demand data set of an enterprise according to months and product categories through a normal distribution algorithm to obtain normal distribution characteristics of historical resource demand data subsets corresponding to the product categories in each month; according to a Pearson's correlation coefficient between each potential influence factor and the resource demand, determining a key influence factor of the enterprise resource demand, and according to the normal distribution characteristics and the key influence factor, constructing a multiple linear regression model; and obtaining prediction data of the key influence factors in the to-be-predicted time period, performing prediction through the multiple linear regression model according to the prediction data, and obtaining a resource demand value of the enterprise in each month in the to-be-predicted time period.

Description

Technical Field

[0001] This application relates to the field of resource management and data analysis technology, and in particular to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for providing reference information on enterprise resource needs in supply chain operations. Background Technology

[0002] With the development of computer technology and data analysis theory, methods for forecasting resource demand using a single algorithm have emerged. Among these, resource demand forecasting based on time series analysis is more widely used. Time series analysis predicts future resource demand by modeling the trend, seasonality, and periodicity characteristics of historical resource data.

[0003] However, resource demand forecasting methods based on time series analysis have significant drawbacks. On the one hand, this method relies solely on the temporal relationship of historical resource data, neglecting numerous external factors influencing resource demand in the market, such as market competition, policy and regulatory changes, and shifts in consumer preferences. When the market environment fluctuates significantly, the forecast results deviate considerably from actual demand. On the other hand, time series analysis is highly sensitive to outliers in the data. Once an abnormal resource data is generated due to a sudden event, it will severely interfere with the stability of the model and the accuracy of the forecast. Both of these aspects contribute to the problem of low forecast accuracy in this method. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for providing reference information on enterprise resource needs in supply chain operations, in order to address the aforementioned technical problems.

[0005] Firstly, this application provides a method for providing reference information on enterprise resource requirements in supply chain operations, including:

[0006] Obtain the enterprise's historical resource demand dataset, delete duplicate data in the historical resource demand dataset, and fill in the missing data in the historical resource demand dataset to obtain a preprocessed historical resource demand dataset.

[0007] The preprocessed historical resource demand dataset is processed by month and product category using a normal distribution algorithm to obtain the normal distribution characteristics of the historical resource demand data subsets corresponding to each product category in each month.

[0008] Based on the Pearson correlation coefficient between each potential influencing factor and resource demand, the key influencing factors of enterprise resource demand are determined, and a multiple linear regression model is constructed based on the normal distribution characteristics and the key influencing factors.

[0009] Obtain the predicted data of the key influencing factors within the predicted time period, and make predictions based on the predicted data using the multiple linear regression model to obtain the resource demand value of the enterprise for each month within the predicted time period, and display the enterprise resource demand reference information containing the resource demand value.

[0010] In one embodiment, determining the key influencing factors of enterprise resource demand based on the Pearson correlation coefficient between each potential influencing factor and resource demand includes:

[0011] Based on the Pearson correlation coefficient, candidate influencing factors are selected from the potential influencing factors; principal component analysis is performed on the candidate influencing factors to calculate the cumulative variance contribution rate of the principal components, and the original factors to be retained are determined based on the cumulative variance contribution rate; the original factors are input into a multiple linear regression model using stepwise regression, and the multiple linear regression model determines the key influencing factors based on the significance of the original factors.

[0012] In one embodiment, constructing a multiple linear regression model based on the normal distribution characteristics and the key influencing factors includes:

[0013] Using the resource demand data corresponding to the normal distribution characteristics as the dependent variable and the key influencing factors as the independent variables, an initial multiple linear regression model is constructed; based on the objective function of the initial multiple linear regression model, the estimated values ​​of the regression coefficients are obtained; the initial multiple linear regression model is trained based on the estimated values ​​of the regression coefficients to obtain the multiple linear regression model.

[0014] In one embodiment, the step of performing deep processing on the preprocessed historical resource demand dataset by month and product category using a normal distribution algorithm to obtain the normal distribution characteristics of the historical resource demand data subsets corresponding to each product category in each month includes:

[0015] Based on the preprocessed historical resource demand dataset, the mean and variance of the historical resource demand data subset are calculated using the maximum likelihood estimation method with the normal distribution algorithm; based on the mean and the variance, the normal distribution characteristics of the historical resource demand data subset are determined.

[0016] In one embodiment, the method further includes:

[0017] Based on the 3σ principle of normal distribution, abnormal data in the subset of historical resource demand data are identified; the abnormal data are corrected using a locally weighted linear regression method, and the normal distribution characteristics are updated based on the corrected abnormal data to obtain the updated normal distribution characteristics.

[0018] The step of constructing a multiple linear regression model based on the normal distribution characteristics and the key influencing factors includes: constructing a multiple linear regression model based on the updated normal distribution characteristics and the key influencing factors.

[0019] In one embodiment, the method further includes:

[0020] Obtain the newly generated resource demand dataset from the enterprise, and retrain the multiple linear regression model based on the resource demand dataset to adjust the regression coefficients, thereby obtaining an updated multiple linear regression model; the updated multiple linear regression model is used to replace the original multiple linear regression model.

[0021] Secondly, this application also provides an apparatus for providing reference information on enterprise resource requirements in supply chain operations, comprising:

[0022] The data acquisition module is used to acquire the enterprise's historical resource demand dataset, delete duplicate data in the historical resource demand dataset, and fill in the missing data in the historical resource demand dataset to obtain a preprocessed historical resource demand dataset.

[0023] The data processing module is used to perform in-depth processing on the preprocessed historical resource demand dataset by month and product category using a normal distribution algorithm, so as to obtain the normal distribution characteristics of the historical resource demand data subset corresponding to each product category in each month;

[0024] The model building module is used to determine the key influencing factors of enterprise resource demand based on the Pearson correlation coefficient between each potential influencing factor and the resource demand, and to construct a multiple linear regression model based on the normal distribution characteristics and the key influencing factors.

[0025] The demand forecasting module is used to acquire forecast data of the key influencing factors within the forecast period, and to make predictions based on the forecast data using the multiple linear regression model to obtain the resource demand value of the enterprise for each month within the forecast period, and to display enterprise resource demand reference information containing the resource demand value.

[0026] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0027] A preprocessed historical resource demand dataset is obtained by acquiring the enterprise's historical resource demand dataset, deleting duplicate data and filling in missing data. The preprocessed dataset is then subjected to in-depth processing by month and product category using a normal distribution algorithm to obtain the normal distribution characteristics of the historical resource demand subsets corresponding to each product category in each month. Based on the Pearson correlation coefficient between each potential influencing factor and resource demand, key influencing factors of the enterprise's resource demand are identified. A multiple linear regression model is constructed based on the normal distribution characteristics and the key influencing factors. Predicted data of the key influencing factors for the period to be predicted is obtained. Based on the predicted data, the multiple linear regression model is used to predict the enterprise's resource demand value for each month within the period to be predicted, and reference information on the enterprise's resource demand containing these values ​​is displayed.

[0028] 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:

[0029] A preprocessed historical resource demand dataset is obtained by acquiring the enterprise's historical resource demand dataset, deleting duplicate data and filling in missing data. The preprocessed dataset is then subjected to in-depth processing by month and product category using a normal distribution algorithm to obtain the normal distribution characteristics of the historical resource demand subsets corresponding to each product category in each month. Based on the Pearson correlation coefficient between each potential influencing factor and resource demand, key influencing factors of the enterprise's resource demand are identified. A multiple linear regression model is constructed based on the normal distribution characteristics and the key influencing factors. Predicted data of the key influencing factors for the period to be predicted is obtained. Based on the predicted data, the multiple linear regression model is used to predict the enterprise's resource demand value for each month within the period to be predicted, and reference information on the enterprise's resource demand containing these values ​​is displayed.

[0030] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0031] A preprocessed historical resource demand dataset is obtained by acquiring the enterprise's historical resource demand dataset, deleting duplicate data and filling in missing data. The preprocessed dataset is then subjected to in-depth processing by month and product category using a normal distribution algorithm to obtain the normal distribution characteristics of the historical resource demand subsets corresponding to each product category in each month. Based on the Pearson correlation coefficient between each potential influencing factor and resource demand, key influencing factors of the enterprise's resource demand are identified. A multiple linear regression model is constructed based on the normal distribution characteristics and the key influencing factors. Predicted data of the key influencing factors for the period to be predicted is obtained. Based on the predicted data, the multiple linear regression model is used to predict the enterprise's resource demand value for each month within the period to be predicted, and reference information on the enterprise's resource demand containing these values ​​is displayed.

[0032] The aforementioned method, apparatus, computer equipment, computer-readable storage medium, and computer program product for providing reference information on enterprise resource demand in supply chain operations firstly perform in-depth processing on the preprocessed historical resource demand dataset by month and product category using a normal distribution algorithm. This yields the normal distribution characteristics of the historical resource demand data subsets corresponding to each product category in each month, clearly presenting the data's fluctuation patterns and central tendency. Then, based on the Pearson correlation coefficient between each potential influencing factor and resource demand, the key influencing factors of enterprise resource demand are determined. A multiple linear regression model is then constructed based on the normal distribution characteristics and the key influencing factors, thereby achieving quantitative analysis of resource demand volatility and significantly improving prediction accuracy compared to traditional methods. Finally, the predicted data of key influencing factors within the predicted time period are obtained. Based on the predicted data, the multiple linear regression model is used to predict the enterprise's resource demand value for each month within the predicted time period, thus achieving accurate prediction of enterprise resource demand for each month within the predicted time period. This overcomes the shortcomings of traditional technologies in processing complex data and comprehensively considering the influence of multiple factors, providing a scientific and reliable basis for enterprise resource decision-making. Attached Figure Description

[0033] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0034] Figure 1 This is an application environment diagram of a method for providing reference information on enterprise resource requirements in supply chain operations, as shown in one embodiment.

[0035] Figure 2 This is a flowchart illustrating a method for providing reference information on enterprise resource requirements in a supply chain operation, as shown in one embodiment.

[0036] Figure 3 This is a flowchart illustrating the steps for determining key influencing factors in one embodiment.

[0037] Figure 4 A flowchart illustrating a method for providing reference information on enterprise resource requirements in a supply chain business, as shown in a specific embodiment;

[0038] Figure 5 A structural block diagram of an apparatus for providing reference information on enterprise resource requirements in a supply chain operation, as shown in one embodiment;

[0039] Figure 6 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0040] 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.

[0041] The method for providing reference information on enterprise resource requirements in supply chain operations provided in this application embodiment can be applied to, for example... Figure 1 The application environment shown illustrates this. In this environment, the terminal can communicate with the server via a network. The data storage system can store the data that the server needs to process. The data storage system can be integrated onto the server or located on the cloud or other network servers. In situations such as... Figure 1 In the application environment shown, the terminal can be, but is not limited to, various personal computers, laptops, smartphones, and tablets. The server can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0042] In one embodiment, such as Figure 2 As shown, a method is provided for providing reference information on enterprise resource requirements in supply chain operations. This method can be applied to... Figure 1 In the terminal, the method may include the following steps:

[0043] Step S201: Obtain the enterprise's historical resource demand dataset, delete duplicate data in the historical resource demand dataset, and fill in the missing data in the historical resource demand dataset to obtain the preprocessed historical resource demand dataset.

[0044] Specifically, the terminal obtains at least three years of historical resource demand data from enterprises. Data dimensions include, but are not limited to, the target of resource framework agreements, the completion amount at each framework agreement time point, resource time (accurate to the month), resource quantity, product category, supplier information, market price fluctuation data (such as raw material price index), and macroeconomic indicators (regional GDP growth rate, inflation rate, electricity consumption), etc. Using data cleaning tools, the raw data is processed according to the following rules: duplicate data is detected and deleted using a hash algorithm; data with logical errors (such as negative resource quantities) is marked and corrected; for missing data, if the missing percentage is less than 5%, a multiple imputation method is used. Taking missing resource quantities as an example, based on historical data with similar product categories and resource times, the average resource quantity of similar data points is calculated using the K-nearest neighbor classification algorithm for imputation; if the missing percentage exceeds 5%, the original documents are manually checked or relevant business personnel are contacted to supplement the data.

[0045] Furthermore, data quality was improved and error rate was reduced through cleaning and interpolation techniques, providing a reliable foundation for subsequent modeling.

[0046] The resource framework agreement is a crucial document in enterprise resource management, establishing a foundation for long-term cooperation between buyers and sellers. Resource framework agreements are typically signed with suppliers on a time-specific basis, and generally require 80% to 120% fulfillment, but rarely exceeding 150%.

[0047] Step S202: The preprocessed historical resource demand dataset is processed by month and product category using a normal distribution algorithm to obtain the normal distribution characteristics of the historical resource demand data subsets corresponding to each product category in each month.

[0048] Specifically, the terminal uses a normal distribution algorithm to perform in-depth processing on the preprocessed historical resource demand dataset by month and product category. By calculating the mean and variance of the data for each month, its probability distribution characteristics are determined, and abnormal fluctuations in the data are effectively handled, clearly presenting the fluctuation patterns and central trends of the data.

[0049] Step S203: Based on the Pearson correlation coefficient between each potential influencing factor and resource demand, determine the key influencing factors of enterprise resource demand, and construct a multiple linear regression model based on the normal distribution characteristics and key influencing factors.

[0050] Specifically, the terminal comprehensively analyzes the diverse potential factors affecting enterprise resource demand, covering macroeconomic indicators, seasonal factors, product life cycle, and competitor strategies, and uses methods such as correlation analysis to screen key influencing factors. Based on this, a multiple linear regression model is constructed using the processed historical resource demand dataset as the dependent variable and the key influencing factors as independent variables. The regression coefficients are determined using optimization algorithms such as the least squares method, and an accurate linear relationship between resource demand and diverse influencing factors is established.

[0051] Step S204: Obtain the forecast data of key influencing factors within the forecast period, and make predictions based on the forecast data using a multiple linear regression model to obtain the enterprise's resource demand value for each month within the forecast period, and display the enterprise's resource demand reference information containing the resource demand value.

[0052] Specifically, for each month within the forecast period, the terminal collects actual or forecast data on key influencing factors for that period. For example, it obtains forecast data on market price fluctuations for the next three months from market research institutions and determines promotional activities based on the company's marketing plan. This data is then fed into a pre-constructed multiple linear regression model to calculate the company's predicted resource needs for each month within the forecast period, and displays reference information on the company's resource needs, including these values.

[0053] It should be noted that, in addition to the multiple linear regression model, other time series forecasting models, such as the mean regression model, can also be used to predict resource demand.

[0054] In this embodiment, the preprocessed historical resource demand dataset is first processed by month and product category using a normal distribution algorithm. This yields the normal distribution characteristics of the historical resource demand subsets for each product category in each month, clearly revealing the data's fluctuation patterns and central tendency. Then, based on the Pearson correlation coefficient between potential influencing factors and resource demand, key influencing factors of enterprise resource demand are identified. A multiple linear regression model is then constructed based on the normal distribution characteristics and key influencing factors, enabling quantitative analysis of resource demand volatility and significantly improving prediction accuracy compared to traditional methods. Finally, predicted data of key influencing factors for the forecast period are obtained. Using the multiple linear regression model, the resource demand value for each month within the forecast period is predicted, achieving accurate prediction of enterprise resource demand for each month. This overcomes the shortcomings of traditional technologies in processing complex data and comprehensively considering the influence of multiple factors, providing a scientific and reliable basis for enterprise resource decision-making.

[0055] In one embodiment, such as Figure 3As shown, in step S203 above, determining the key influencing factors of enterprise resource demand based on the Pearson correlation coefficient between each potential influencing factor and resource demand may include the following steps:

[0056] Step S301: Based on the Pearson correlation coefficient, candidate influencing factors are selected from the potential influencing factors.

[0057] Step S302: Perform principal component analysis on the candidate influencing factors, calculate the cumulative variance contribution rate of the principal components, and determine the original factors to be retained based on the cumulative variance contribution rate.

[0058] Step S303: Input the original factors into the multiple linear regression model using the stepwise regression method. The multiple linear regression model then determines the key influencing factors based on the significance of the original factors.

[0059] Specifically, the terminal employs a combination of principal component analysis and stepwise regression to identify key influencing factors of resource demand. First, correlation analysis is used to calculate the Pearson correlation coefficient between each potential influencing factor and resource demand. Factors with an absolute Pearson correlation coefficient greater than 0.3 are selected as candidate influencing factors. The set of candidate influencing factors is assumed to be F={f1,f2,……fm}, including various influencing factors such as market price volatility index f1 and promotional activity participation f2. Then, principal component analysis is performed on the candidate influencing factors, transforming multiple correlated factors into a few uncorrelated principal components. Each principal component is a linear combination of the original factors. The cumulative variance contribution rate of the principal components is calculated. When the cumulative variance contribution rate reaches 85% or higher, the number of principal components to be retained and the corresponding original factors are determined. Then, using the stepwise regression method, the original factors that were retained were sequentially introduced into the multiple linear regression model. The significance of the factors was judged according to the AIC (Akaike information criterion) or BIC (Bayesian information criterion), and insignificant factors were eliminated to finally determine the set of key influencing factors of resource demand.

[0060] In one embodiment, step S203 above, constructing a multiple linear regression model based on normal distribution characteristics and key influencing factors, may include the following steps:

[0061] Using resource demand data corresponding to normal distribution characteristics as the dependent variable and key influencing factors as independent variables, an initial multiple linear regression model is constructed; based on the objective function of the initial multiple linear regression model, the estimated values ​​of the regression coefficients are obtained; based on the estimated values ​​of the regression coefficients, the initial multiple linear regression model is trained to obtain the multiple linear regression model.

[0062] Specifically, the terminal uses the monthly resource demand data processed by the normal distribution algorithm as the dependent variable y, and the factors in the selected set of key influencing factors as independent variables x1, x2, ..., x. k Construct the initial multiple linear regression model:

[0063] y = β0 + β1x1 + β2x2 + … + β k x k +

[0064] Where β0 is the intercept term, β1, β2, ..., β k For regression coefficients, For random error term, It follows a normal distribution with mean μ = 0 and variance σ = 2.

[0065] The regression coefficients are solved using the least squares method. The objective function of the initial multiple linear regression model is: By taking the partial derivatives of the objective function and setting them equal to 0, we obtain the normal equation system. Solving this system yields estimates of the regression coefficients. The initial multiple linear regression model was trained based on the estimated regression coefficients to obtain the final multiple linear regression model. Simultaneously, the coefficient of determination was calculated. Adjusted coefficient of determination In addition, indicators such as the test statistic F are used to test the goodness of fit and significance of the model to ensure its reliability.

[0066] In one embodiment, step S202 above, which involves performing deep processing on the preprocessed historical resource demand dataset by month and product category using a normal distribution algorithm to obtain the normal distribution characteristics of the historical resource demand data subsets corresponding to each product category in each month, may include the following steps:

[0067] Based on the preprocessed historical resource demand dataset, the mean and variance of the historical resource demand data subset are calculated using the maximum likelihood estimation method with a normal distribution algorithm; based on the mean and variance, the normal distribution characteristics of the historical resource demand data subset are determined.

[0068] Specifically, the terminal groups the preprocessed historical resource demand dataset by month, and then processes the resource demand data sequence for each month. (where i represents the year and j represents the month), assuming it follows a normal distribution. The parameters characteristic of the normal distribution are calculated using the maximum likelihood estimation method:

[0069]

[0070] Taking a certain type of product resource data from January 2021 as an example, assuming there are 30 resource records in that month, the resource quantities are as follows: The mean is calculated using the above formula. and variance This allows us to determine the normal distribution characteristics of resource demand data for this type of product in January 2021.

[0071] It should be noted that this application assumes that the quantity of resources follows a normal distribution. However, in reality, if the data exhibits non-normal characteristics such as a skewed distribution, other probability distribution models can be used instead. For example, for products with long-tailed demand, log-normal and gamma distributions can be used. These distribution models can better fit data with special distribution characteristics, improving the model's interpretability and predictive accuracy.

[0072] In one embodiment, the method of this application further includes the following steps:

[0073] Based on the 3σ principle of normal distribution, outlier data in the subset of historical resource demand data is identified; local weighted linear regression is used to correct the outlier data, and the normal distribution characteristics are updated based on the corrected outlier data to obtain the updated normal distribution characteristics.

[0074] In step S202 above, constructing a multiple linear regression model based on the normal distribution characteristics and key influencing factors may include the following steps:

[0075] Based on the updated normal distribution characteristics and key influencing factors, a multiple linear regression model is constructed.

[0076] Specifically, the terminal identifies and marks outliers in the monthly data (i.e., values ​​falling within the normal distribution's 3σ principle) based on the 3σ principle. , For data outside the specified range, outliers are not directly deleted. Instead, locally weighted linear regression (LWLR) is used to correct them, preventing data loss from affecting the distribution characteristics. The normal distribution characteristics are then updated based on the corrected outliers, resulting in the updated normal distribution characteristics. Finally, a multiple linear regression model is constructed based on the updated normal distribution characteristics and key influencing factors.

[0077] This embodiment enables quantitative analysis of resource demand volatility, significantly improving prediction accuracy compared to traditional methods, and exhibiting stronger robustness, especially when dealing with abnormal data.

[0078] In one embodiment, the method of this application further includes the following steps:

[0079] Obtain the newly generated resource demand dataset from the enterprise, retrain the multiple linear regression model based on the resource demand dataset to adjust the regression coefficients, and obtain the updated multiple linear regression model; the updated multiple linear regression model is used to replace the original multiple linear regression model.

[0080] Specifically, a monthly data update mechanism is established. At the end of each month, newly generated resource demand datasets from the enterprise are incorporated into the historical dataset, and the normal distribution algorithm processing steps are re-executed to update the mean and variance of the monthly resource demand data. Simultaneously, the newly generated resource demand dataset is used to retrain the multiple linear regression model, adjusting the regression coefficients to ensure the model can reflect market changes promptly. When major market events occur (such as significant adjustments to industry policies or sudden natural disasters), an emergency data processing procedure is initiated, with manual intervention to analyze the impact of the event on resource demand and adjust model parameters to ensure the accuracy of the prediction results.

[0081] The dynamic adjustment mechanism implemented in this model enables it to quickly adapt to market changes, providing a significant advantage in responding to emergencies and seasonal fluctuations, and enhancing the flexibility of the enterprise's supply chain.

[0082] In one embodiment, such as Figure 4 As shown, a method for providing reference information on enterprise resource requirements in supply chain operations is provided in a specific embodiment, which specifically includes the following steps:

[0083] Step S401: Obtain the enterprise's historical resource demand dataset, delete duplicate data in the historical resource demand dataset, and fill in the missing data in the historical resource demand dataset to obtain the preprocessed historical resource demand dataset.

[0084] Step S402: Based on the preprocessed historical resource demand dataset, the mean and variance of the historical resource demand data subset are calculated using the maximum likelihood estimation method with a normal distribution algorithm; based on the mean and variance, the normal distribution characteristics of the historical resource demand data subset are determined.

[0085] Step S403: Based on the Pearson correlation coefficient between each potential influencing factor and the procurement demand, candidate influencing factors are selected from each potential influencing factor; principal component analysis is performed on the candidate influencing factors to calculate the cumulative variance contribution rate of the principal components, and the original factors to be retained are determined based on the cumulative variance contribution rate; the original factors are input into the multiple linear regression model through stepwise regression, and the multiple linear regression model determines the key influencing factors based on the significance of the original factors.

[0086] Step S404: Using the resource demand data corresponding to the normal distribution characteristics as the dependent variable and the key influencing factors as the independent variables, construct an initial multiple linear regression model; obtain the estimated values ​​of the regression coefficients based on the objective function of the initial multiple linear regression model; train the initial multiple linear regression model based on the estimated values ​​of the regression coefficients to obtain the multiple linear regression model.

[0087] Step S405: Obtain the forecast data of key influencing factors within the forecast period, and make predictions based on the forecast data using a multiple linear regression model to obtain the enterprise's resource demand value for each month within the forecast period, and display the enterprise's resource demand reference information containing the resource demand value.

[0088] The beneficial effects of the above embodiments are as follows:

[0089] 1) Data preprocessing effect: Data quality was improved and error rate was reduced through cleaning and imputation techniques, providing a reliable foundation for subsequent modeling.

[0090] 2) Normal distribution modeling effect: It realizes the quantitative analysis of resource demand fluctuations, significantly improves the prediction accuracy compared with traditional methods, and shows stronger robustness, especially when dealing with abnormal data.

[0091] 3) Effect of dynamic adjustment mechanism: It enables the model to adapt quickly to market changes, has a significant advantage in dealing with emergencies and seasonal fluctuations, and improves the flexibility of the enterprise's supply chain.

[0092] 4) Comprehensive business value: It directly brings economic benefits such as reduced inventory costs and controlled stockout rates, while improving supply chain collaboration efficiency and scientific decision-making, forming a complete closed loop from data processing to business optimization.

[0093] 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.

[0094] Based on the same inventive concept, this application also provides an apparatus for providing reference information on enterprise resource requirements in a supply chain business, which is used to implement the method described above for providing reference information on enterprise resource requirements in a supply chain business. The solution provided by this apparatus is similar to the solution described in the above method. Therefore, the specific limitations in one or more apparatus embodiments for providing reference information on enterprise resource requirements in a supply chain business provided below can be found in the limitations of the method for providing reference information on enterprise resource requirements in a supply chain business described above, and will not be repeated here.

[0095] In one exemplary embodiment, such as Figure 5 As shown, an apparatus is provided for providing reference information on enterprise resource requirements in supply chain operations. The apparatus may include:

[0096] The data acquisition module 501 is used to acquire the enterprise's historical resource demand dataset, delete duplicate data in the historical resource demand dataset, and fill in the missing data in the historical resource demand dataset to obtain a preprocessed historical resource demand dataset.

[0097] Data processing module 502 is used to perform in-depth processing on the preprocessed historical resource demand dataset by month and product category using a normal distribution algorithm, so as to obtain the normal distribution characteristics of the historical resource demand data subset corresponding to each product category in each month;

[0098] Model building module 503 is used to determine the key influencing factors of enterprise resource demand based on the Pearson correlation coefficient between each potential influencing factor and resource demand, and to build a multiple linear regression model based on the normal distribution characteristics and key influencing factors.

[0099] The demand forecasting module 504 is used to obtain forecast data of key influencing factors within the forecast period. Based on the forecast data, it uses a multiple linear regression model to make predictions and obtain the enterprise's resource demand values ​​for each month within the forecast period. It also displays reference information on the enterprise's resource demand, including the resource demand values.

[0100] In one embodiment, the model building module 503 is further configured to screen candidate influencing factors from among potential influencing factors based on the Pearson correlation coefficient; perform principal component analysis on the candidate influencing factors, calculate the cumulative variance contribution rate of the principal components, determine the original factors to be retained based on the cumulative variance contribution rate; input the original factors into the multiple linear regression model through stepwise regression, and determine the key influencing factors based on the significance of the original factors by the multiple linear regression model.

[0101] In one embodiment, the model building module 503 is further configured to construct an initial multiple linear regression model using resource demand data corresponding to normal distribution characteristics as the dependent variable and key influencing factors as independent variables; obtain estimated values ​​of regression coefficients based on the objective function of the initial multiple linear regression model; and train the initial multiple linear regression model based on the estimated values ​​of regression coefficients to obtain a multiple linear regression model.

[0102] In one embodiment, the data processing module 502 is further configured to calculate the mean and variance of a subset of historical resource demand data using the maximum likelihood estimation method with a normal distribution algorithm based on the preprocessed historical resource demand dataset; and determine the normal distribution characteristics of the subset of historical resource demand data based on the mean and variance.

[0103] In one embodiment, the device may further include: an anomaly correction module, used to identify anomalous data in a subset of historical resource demand data according to the 3σ principle of normal distribution; to correct the anomalous data using a locally weighted linear regression method, and to update the normal distribution characteristics based on the corrected anomalous data to obtain updated normal distribution characteristics; and a model building module 503, used to build a multiple linear regression model based on the updated normal distribution characteristics and key influencing factors.

[0104] In one embodiment, the apparatus may further include: a model update module, configured to acquire a newly generated resource demand dataset in the enterprise, retrain the multiple linear regression model based on the resource demand dataset to adjust the regression coefficients, and obtain an updated multiple linear regression model; the updated multiple linear regression model is used to replace the original multiple linear regression model.

[0105] The modules in the aforementioned device that provides reference information on enterprise resource requirements in supply chain operations 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.

[0106] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 6As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. 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 in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When executed by the processor, the computer program implements a method for providing reference information on enterprise resource requirements in supply chain operations. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0107] Those skilled in the art will understand that Figure 6 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.

[0108] In one embodiment, a computer device is also 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 method embodiments.

[0109] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0110] 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.

[0111] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0112] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory 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, artificial intelligence (AI) processors, etc., and are not limited to these.

[0113] 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 application.

[0114] 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 providing reference information on enterprise resource requirements in supply chain operations, characterized in that, The method includes: Obtain the enterprise's historical resource demand dataset, delete duplicate data in the historical resource demand dataset, and fill in the missing data in the historical resource demand dataset to obtain a preprocessed historical resource demand dataset. The preprocessed historical resource demand dataset is processed by month and product category using a normal distribution algorithm to obtain the normal distribution characteristics of the historical resource demand data subsets corresponding to each product category in each month. Based on the Pearson correlation coefficient between each potential influencing factor and resource demand, the key influencing factors of enterprise resource demand are determined, and a multiple linear regression model is constructed based on the normal distribution characteristics and the key influencing factors. Obtain the predicted data of the key influencing factors within the predicted time period, and make predictions based on the predicted data using the multiple linear regression model to obtain the resource demand value of the enterprise for each month within the predicted time period, and display the enterprise resource demand reference information containing the resource demand value.

2. The method according to claim 1, characterized in that, The key influencing factors of enterprise resource demand are determined based on the Pearson correlation coefficient between each potential influencing factor and resource demand, including: Based on the Pearson correlation coefficient, candidate influencing factors are selected from each of the potential influencing factors; Principal component analysis is performed on the candidate influencing factors to calculate the cumulative variance contribution rate of the principal components, and the original factors to be retained are determined based on the cumulative variance contribution rate. The original factors are input into a multiple linear regression model using stepwise regression, and the multiple linear regression model determines the key influencing factors based on the significance of the original factors.

3. The method according to claim 1, characterized in that, The construction of a multiple linear regression model based on the normal distribution characteristics and the key influencing factors includes: Using the resource demand data corresponding to the normal distribution characteristics as the dependent variable and the key influencing factors as the independent variables, an initial multiple linear regression model is constructed. Based on the objective function of the initial multiple linear regression model, the estimated values ​​of the regression coefficients are obtained; The initial multiple linear regression model is trained based on the estimated values ​​of the regression coefficients to obtain the multiple linear regression model.

4. The method according to claim 1, characterized in that, The preprocessed historical resource demand dataset is processed using a normal distribution algorithm by month and product category to obtain the normal distribution characteristics of the historical resource demand data subsets corresponding to each product category in each month, including: Based on the preprocessed historical resource demand dataset, the mean and variance of the historical resource demand data subset are calculated using the maximum likelihood estimation method with the normal distribution algorithm. Based on the mean and the variance, the normal distribution characteristics of the historical resource demand data subset are determined.

5. The method according to claim 4, characterized in that, The method further includes: Based on the 3σ principle of normal distribution, abnormal data in the subset of historical resource demand data are identified; The outlier data is corrected using a locally weighted linear regression method, and the normal distribution characteristics are updated based on the corrected outlier data to obtain the updated normal distribution characteristics. The construction of a multiple linear regression model based on the normal distribution characteristics and the key influencing factors includes: Based on the updated normal distribution characteristics and the key influencing factors, a multiple linear regression model is constructed.

6. The method according to claim 3, characterized in that, The method further includes: Obtain the newly generated resource demand dataset from the enterprise, and retrain the multiple linear regression model based on the resource demand dataset to adjust the regression coefficients, thereby obtaining an updated multiple linear regression model; the updated multiple linear regression model is used to replace the original multiple linear regression model.

7. An apparatus for providing reference information on enterprise resource requirements in supply chain operations, characterized in that, The device includes: The data acquisition module is used to acquire the enterprise's historical resource demand dataset, delete duplicate data in the historical resource demand dataset, and fill in the missing data in the historical resource demand dataset to obtain a preprocessed historical resource demand dataset. The data processing module is used to perform in-depth processing on the preprocessed historical resource demand dataset by month and product category using a normal distribution algorithm, so as to obtain the normal distribution characteristics of the historical resource demand data subset corresponding to each product category in each month; The model building module is used to determine the key influencing factors of enterprise resource demand based on the Pearson correlation coefficient between each potential influencing factor and the resource demand, and to construct a multiple linear regression model based on the normal distribution characteristics and the key influencing factors. The demand forecasting module is used to acquire forecast data of the key influencing factors within the forecast period, and to make predictions based on the forecast data using the multiple linear regression model to obtain the resource demand value of the enterprise for each month within the forecast period, and to display enterprise resource demand reference information containing the resource demand value.

8. 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 6.

9. 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 6.

10. A computer program product, comprising a computer program, 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 6.

Images