Key link control system and method of distribution network materials based on artificial intelligence

Abstract

The present invention relates to the field of data processing technology, and in particular to a key link management and control system and method for distribution network materials based on artificial intelligence. The method includes the steps of: collecting data of each dimension at each sampling moment, obtaining each dimension historical data sequence corresponding to each sampling moment; based on each dimension historical data sequence, obtaining the degree of correlation between all two dimensional historical data sequences corresponding to each sampling moment and obtaining the comprehensive synergy index between all dimensional historical data sequences corresponding to each sampling moment, correcting the initial smoothing parameter according to the degree of correlation between all two dimensional historical data sequences corresponding to each sampling moment and the comprehensive synergy index between all dimensional historical data sequences, obtaining the corrected value of the smoothing parameter at each sampling moment, and predicting the value of each dimensional data at the next moment of each sampling moment according to the corrected value of the smoothing parameter at each sampling moment. The present invention makes the prediction result more accurate.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a distribution network material key link management and control system and method based on artificial intelligence. Background Art

[0002] In the power industry, distribution network material management is an indispensable part of ensuring the stable operation of the power grid. However, with the rapid growth of electricity demand and the increasing complexity of the supply chain, traditional manual material management methods have gradually exposed shortcomings such as poor real-time performance and inaccurate predictions. Especially when dealing with interdependent key links such as procurement, inventory, and distribution, traditional methods often find it difficult to capture the close coordination relationship between them, resulting in distorted prediction results when facing emergencies and unable to meet the needs of stable operation of the power grid.

[0003] The current publication number is CN109376924A. A method, device, equipment and readable storage medium for material demand forecasting. An exponential smoothing model is first established based on historical material demand data, and a prediction error analysis is performed on the exponential smoothing model. If the prediction error exceeds a preset condition, the historical material demand data is fitted to obtain multiple ARIMA models, from which the optimal historical material demand forecasting model is determined. Finally, the optimal historical material demand forecasting model is used to forecast the material demand of the forecast object.

[0004] When using the exponential smoothing method in the above algorithm to predict the data of various dimensions at the next sampling moment of distribution network material management, the close coordination relationship between key links such as procurement, inventory and distribution is ignored. For example, a decrease in inventory may directly lead to an increase in procurement and an increase in distribution frequency. That is, the exponential smoothing algorithm fails to capture this mutual influence, resulting in the prediction results deviating from reality. Secondly, emergencies in the distribution network such as natural disasters or equipment failures may cause a sudden increase in the amount of material demand data. If smoothing is performed according to fixed smoothing parameters, these sudden increases in data values ​​may distort the prediction results of the model and deviate from the true trend. Summary of the invention

[0005] In order to solve the problem that the exponential smoothing algorithm ignores the close coordination relationship between key links such as procurement, inventory and distribution in the distribution network, resulting in the prediction results deviating from reality, the present invention provides a key link management and control system and method for distribution network materials based on artificial intelligence.

[0006] In the first aspect, the present invention provides a method for controlling key links of distribution network materials based on artificial intelligence, which adopts the following technical solutions:

[0007] The key link control method of distribution network materials based on artificial intelligence includes the following steps:

[0008] Obtain the historical data sequence of each dimension corresponding to each sampling moment; obtain the correlation degree between any two historical data sequences of each dimension corresponding to each sampling moment, the correlation degree represents the trend characteristics of the same increase and decrease of the historical data sequences of the two dimensions; obtain the comprehensive synergy index between all historical data sequences of each dimension corresponding to each sampling moment, the comprehensive synergy index represents the synergy effect between the material management links; obtain the smoothing parameter correction value at each sampling moment:

[0009] , where represents the initial smoothing parameter value; Represents the mean of the absolute values ​​of the differences between the predicted values ​​and the actual values ​​of all dimensional data at the t-th sampling moment; as well as Represents the mean value of the correlation between all historical data sequences of any two dimensions corresponding to the t-th sampling time and the t+1-th sampling time; Represents the comprehensive synergy index between all dimensional historical data sequences corresponding to the t-th sampling moment; Represents the comprehensive synergy index between all dimensional historical data sequences corresponding to the t-th sampling moment; exp() represents an exponential function with a natural constant as the base; and the value of each dimensional data at the next sampling moment is predicted based on the smoothing parameter correction value.

[0010] The innovation of the present invention lies in that, according to the close coordination relationship between various links in the distribution network material management process, the correlation degree between historical data sequences of different dimensions before each sampling moment and the comprehensive synergy index between historical data sequences of multiple dimensions are obtained, the initial smoothing parameters are corrected, and the smoothing parameter correction values ​​at each sampling moment are obtained. When the smoothing parameter correction values ​​at each sampling moment are used to predict the values ​​of the data of each dimension at the next moment of each sampling moment, the prediction results can be closer to actual needs and the accuracy of the prediction is improved; further, the correlation degree between historical data sequences of different dimensions before each sampling moment is obtained according to the same increase and decrease trend characteristics between the dimensional historical data sequences, which can reflect the connection between data of different dimensions; further, the comprehensive synergy index between historical data sequences of multiple dimensions at each sampling moment reflects the coordination relationship between various links in the distribution network material management process, which is convenient for the subsequent adaptive smoothing parameters according to the comprehensive synergy index.

[0011] Preferably, the step of obtaining the historical data sequences of each dimension corresponding to each sampling moment comprises the following steps:

[0012] Collect data of each dimension at each sampling moment, and sort each dimension data before the t-th sampling moment according to the order of sampling moments from small to large, to obtain the procurement dimension historical data sequence, procurement dimension historical data sequence, and distribution dimension historical data sequence corresponding to the t-th sampling moment.

[0013] Obtaining the historical data sequences of each dimension corresponding to each sampling moment facilitates the subsequent analysis of the closeness between various links in the distribution network material management process.

[0014] Preferably, the correlation degree between any two dimensional historical data sequences corresponding to each sampling moment is obtained, and the calculation formula is:

[0015] ;

[0016] In the formula, Represents the correlation between the historical data sequence of the ath dimension and the historical data sequence of the bth dimension corresponding to the tth sampling moment; Represents the number of data in the historical data sequence of the ath dimension corresponding to the tth sampling moment; and Represents the value of the i-th data in the historical data sequence of the a-th dimension and the value of the i-th data in the historical data sequence of the b-th dimension corresponding to the t-th sampling moment; as well as Represents the mean of all data in the historical data sequence of the a-th dimension corresponding to the t-th sampling moment and the mean of all data in the historical data sequence of the b-th dimension; || represents the absolute value symbol.

[0017] The greater the degree of correlation between two dimensional historical data series, the more they tend to increase and decrease together, which means that the different dimensions corresponding to the two dimensional historical data series are closely coordinated.

[0018] Preferably, the step of obtaining a comprehensive synergy index between all dimensional historical data sequences corresponding to each sampling moment includes:

[0019] Get the historical sales before each sampling moment;

[0020] ;

[0021] In the formula, Represents the comprehensive synergy index between all dimensional historical data sequences corresponding to the t-th sampling moment; Represents the historical sales before the tth sampling moment; Represents the number of delivery volume data in the historical data sequence of the delivery dimension corresponding to the t-th sampling moment; Represents the value of the kth delivery quantity data in the historical data sequence of the delivery dimension corresponding to the tth sampling moment; exp() represents an exponential function with a natural constant as the base.

[0022] The comprehensive synergy index can comprehensively reflect the synergy effect among various links of material management, making it easier to obtain the smoothing parameter correction value at the sampling moment based on the difference in the comprehensive synergy index between adjacent sampling moments.

[0023] Preferably, the historical sales before each sampling moment are obtained, and the calculation formula is:

[0024] ;

[0025] In the formula, Represents the historical sales before the tth sampling moment; Represents the value of the first inventory data in the inventory dimension historical data sequence corresponding to the t-th sampling moment; Represents the value of the last inventory data in the inventory dimension historical data sequence corresponding to the t-th sampling moment; Represents the number of purchase quantity data in the purchase dimension historical data sequence corresponding to the t-th sampling moment; Represents the value of the j-th purchase quantity data in the purchase dimension historical data sequence corresponding to the t-th sampling moment.

[0026] Preferably, the method for obtaining the predicted values ​​of all dimensional data at the sampling moment is:

[0027] Preset initial smoothing parameters , according to the initial smoothing parameter , use the exponential smoothing method to obtain the predicted value of each dimension data at the tth sampling time.

[0028] Preferably, predicting the value of each dimension data at the next sampling moment includes:

[0029] According to the corrected value of the smoothing parameter at the t-th sampling moment, the exponential smoothing method is used to obtain the predicted value of each dimension data at the t+1-th sampling moment.

[0030] It is more accurate to use the smoothing parameter correction value at the t-th sampling moment to predict the value of each dimensional data at the t+1-th sampling moment.

[0031] In the second aspect, the present invention provides a key link management and control system for distribution network materials based on artificial intelligence, which adopts the following technical solutions:

[0032] The key link management and control system of distribution network materials based on artificial intelligence includes: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the key link management and control method of distribution network materials based on artificial intelligence is implemented.

[0033] By adopting the above technical solution, the above-mentioned artificial intelligence-based key link management and control method of distribution network materials is generated into a computer program and stored in a memory to be loaded and executed by a processor, so that a terminal device is made according to the memory and the processor for easy use.

[0034] The present invention has the following technical effects: the present invention first obtains the correlation between historical data sequences of different dimensions before each sampling moment and the comprehensive synergy index between historical data sequences of multiple dimensions according to the close coordination relationship between various links in the material management process of the distribution network, corrects the initial smoothing parameters, and obtains the corrected values ​​of the smoothing parameters at each sampling moment. When the corrected values ​​of the smoothing parameters at each sampling moment are used to predict the values ​​of the data of each dimension at the next moment of each sampling moment, the prediction results can be closer to actual needs and the accuracy of the prediction is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0036] Figure 1 It is a flow chart of the method in the key link control method of distribution network materials based on artificial intelligence in an embodiment of the present invention. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0038] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0039] The embodiment of the present invention discloses a method for controlling key links of distribution network materials based on artificial intelligence, referring to Figure 1 , comprising steps S1 to S3:

[0040] S1: Collect data of each dimension at each sampling moment.

[0041] In the embodiment of the present invention, every other day is a sampling moment, and each time, the three dimensional data types, namely, purchase quantity data, inventory quantity data, and delivery quantity data, are collected in sequence from the database of the distribution network material management system, and the collection is carried out for a total of 100 days; it should be noted that each sampling moment contains three dimensional data, namely, purchase quantity data, inventory quantity data, and delivery quantity data.

[0042] S2: Obtain each dimensional historical data sequence corresponding to each sampling moment, and based on each dimensional historical data sequence, obtain the degree of correlation between all two dimensional historical data sequences corresponding to each sampling moment, and obtain the comprehensive synergy index between all dimensional historical data sequences corresponding to each sampling moment.

[0043] It should be noted that the traditional exponential smoothing algorithm is based on a fixed smoothing parameter and predicts future values ​​by weighted averaging historical data. However, when using the traditional exponential smoothing algorithm to predict data values, the close coordination relationship between key links such as procurement, inventory, and distribution is ignored. For example, a decrease in inventory may directly lead to an increase in procurement and an increase in distribution frequency, but the traditional exponential smoothing algorithm fails to capture this mutual influence, resulting in the prediction results deviating from reality. Secondly, in the distribution network, emergencies such as natural disasters or equipment failures may cause a sudden increase in the amount of material demand data. If only the exponential smoothing algorithm is used for smoothing based on a fixed smoothing parameter, these sudden increases in data values ​​may distort the prediction results of the model and deviate from the true trend. Therefore, the present invention considers the degree of correlation between historical data sequences of different dimensions before any sampling moment and the comprehensive synergy index between historical data sequences of multiple dimensions to correct the smoothing parameters, and obtains the corrected value of the smoothing parameter at the sampling moment. When the corrected value of the smoothing parameter at the sampling moment is used to predict the value of each dimensional data at the next moment of the sampling moment, the prediction result can be closer to the actual demand and the accuracy of the prediction can be improved.

[0044] Step S2 includes steps S20-S21, which are specifically as follows:

[0045] S20: Obtain each dimensional historical data sequence corresponding to each sampling moment, and based on each dimensional historical data sequence, obtain the degree of correlation between any two dimensional historical data sequences corresponding to each sampling moment.

[0046] It should be noted that in the material management of distribution networks, data of different dimensions (such as purchase volume, inventory volume, delivery volume, etc.) are usually not isolated, and there may be direct or indirect connections between them, that is, the change in data of one dimension and the change in data of another dimension show an obvious trend of increasing or decreasing together. Therefore, the present invention takes the t-th sampling moment as an example, and each dimensional historical data sequence corresponding to the t-th sampling moment, and then obtains the correlation degree between all two dimensional historical data sequences corresponding to the t-th sampling moment according to the feature that the changes between data of different dimensions show an obvious trend of increasing or decreasing together.

[0047] In an embodiment of the present invention, each dimension data before the t-th sampling moment is sorted in order from small to large according to the sampling moments, so as to obtain each dimension historical data sequence corresponding to the t-th sampling moment, that is, the procurement dimension historical data sequence, the procurement dimension historical data sequence and the distribution dimension historical data sequence corresponding to the t-th sampling moment.

[0048] Get the correlation between the historical data sequence of the ath dimension and the historical data sequence of the bth dimension corresponding to the tth sampling moment:

[0049] ;

[0050] In the formula, Represents the correlation between the historical data sequence of the ath dimension and the historical data sequence of the bth dimension corresponding to the tth sampling moment; Represents the number of data in the historical data sequence of the ath dimension corresponding to the tth sampling moment; Represents the value of the i-th data in the a-th dimension historical data sequence corresponding to the t-th sampling moment; Represents the mean of all data in the historical data sequence of the ath dimension corresponding to the tth sampling moment; Represents the value of the i-th data in the b-th dimension historical data sequence corresponding to the t-th sampling moment; Represents the mean of all data in the b-th dimension historical data sequence corresponding to the t-th sampling moment; The larger the value is, the stronger the linear relationship between the historical data sequence of the a-th dimension and the historical data sequence of the b-th dimension corresponding to the t-th sampling moment is, that is, the data changes of the historical data sequence of the a-th dimension and the historical data sequence of the b-th dimension show a trend of increasing and decreasing at the same time. At this time, the correlation between the historical data sequence of the a-th dimension and the historical data sequence of the b-th dimension corresponding to the t-th sampling moment is greater.

[0051] S21: Obtain the comprehensive synergy index between all dimensional historical data sequences corresponding to each sampling moment.

[0052] It should be noted that the management and control of key links of distribution network materials aims to optimize existing management strategies and predict future demand by evaluating the efficiency of historical material management, that is, whether the various links of material management are coordinated. First of all, it is crucial to understand the actual consumption of materials. This can be achieved by analyzing the differences between the initial inventory, final inventory and purchase volume at the tth sampling moment to obtain the historical sales volume before the tth sampling moment. The larger the value, the higher the inventory turnover rate of historical data, which can intuitively measure the efficiency of inventory management; however, whether the various links of material management are coordinated also needs to be combined with the matching degree between the distribution link and the sales link to avoid inventory backlogs or material shortages. Therefore, the comprehensive synergy index between the historical data sequences of all dimensions corresponding to each sampling moment is quantified by combining the two. The value of this indicator can fully reflect the synergy effect between the various links of material management. The larger the value, the better the synergy effect.

[0053] In this embodiment of the present invention, the historical sales before the t-th sampling moment is obtained:

[0054] ;

[0055] In the formula, Represents the historical sales before the tth sampling moment; Represents the value of the first inventory data in the inventory dimension historical data sequence corresponding to the t-th sampling moment; Represents the value of the last inventory data in the inventory dimension historical data sequence corresponding to the t-th sampling moment; Represents the number of purchase quantity data in the purchase dimension historical data sequence corresponding to the t-th sampling moment; Represents the value of the j-th purchase quantity data in the purchase dimension historical data sequence corresponding to the t-th sampling moment; It represents the historical sales before the t-th sampling moment. The larger the value, the larger the value of the initial inventory plus the daily purchase volume minus the final inventory, which means that more inventory was sold during the period of the historical data series of each dimension corresponding to the t-th sampling moment, indicating that the inventory turnover rate is high.

[0056] Get the comprehensive synergy index between all dimensional historical data sequences corresponding to the t-th sampling moment:

[0057] ;

[0058] In the formula, Represents the comprehensive synergy index between all dimensional historical data sequences corresponding to the t-th sampling moment; Represents the historical sales before the tth sampling moment; Represents the number of delivery volume data in the historical data sequence of the delivery dimension corresponding to the t-th sampling moment; Represents the value of the kth delivery quantity data in the delivery dimension historical data sequence corresponding to the tth sampling moment; It represents the difference between the historical sales volume and the sum of the distribution volume before the t-th sampling moment. The smaller the value, the higher the match between the distribution link and the sales link. When the match between the distribution link and the sales link is higher and the inventory turnover rate is high, it means that the comprehensive synergy index between the historical data sequences of each dimension corresponding to the t-th sampling moment is higher.

[0059] S3: According to the correlation between all two-dimensional historical data sequences corresponding to each sampling moment and the comprehensive synergy index between all dimensional historical data sequences, the initial smoothing parameters are corrected to obtain the corrected values ​​of the smoothing parameters at each sampling moment, and the values ​​of the data of each dimension at the next moment of each sampling moment are predicted according to the corrected values ​​of the smoothing parameters at each sampling moment.

[0060] Step S3 includes steps S30 and S31, which are specifically as follows:

[0061] S30: Obtain the smoothing parameter correction value at each sampling moment.

[0062] It should be noted that when predicting future trends based on historical data, especially when facing a sudden increase in material demand caused by an emergency, the traditional fixed smoothing parameter method is often difficult to deal with effectively, which may lead to distortion of the prediction results. In this case, it is necessary to increase the weight of new data and reduce the weight of old data. Therefore, the smoothing parameter is increased to make the response to new data more sensitive and the prediction of the next data more accurate. The comprehensive synergy index between all dimensional historical data sequences corresponding to the known sampling moment and the correlation between any two dimensional historical data sequences reflect whether the various links of material management are coordinated. Therefore, in order to optimize the prediction accuracy, combined with the difference in the comprehensive synergy index between all dimensional historical data sequences corresponding to the t-th sampling moment and the t+1-th sampling moment and the correlation between all two dimensional historical data sequences, the smoothing parameter of the t-th sampling moment is adaptively adjusted to obtain the smoothing parameter correction value of the t-th sampling moment. The prediction of the values ​​of the dimensional data at the t+1 sampling moment is more accurate. The larger the difference, the lower the coordination between the various links of material management. At this time, it means that the smoothing parameter needs to be increased when smoothing the dimensional data at the t+1-th sampling moment.

[0063] In the embodiment of the present invention, the initial smoothing parameter is preset , according to the initial smoothing parameter , use the exponential smoothing method to obtain the predicted value of each dimension data at the tth sampling time.

[0064] Get the corrected value of the smoothing parameter at the tth sampling moment:

[0065] ;

[0066] In the formula, Represents the smoothing parameter correction value at the tth sampling moment; represents the initial smoothing parameter value; Represents the mean of the difference between the actual value and the predicted value of all dimension data at the tth sampling moment; Represents the mean value of the correlation between all historical data sequences of any two dimensions corresponding to the t-th sampling moment; Represents the comprehensive synergy index between all dimensional historical data sequences corresponding to the t-th sampling moment; Represents the mean value of the correlation between all historical data sequences of any two dimensions corresponding to the t+1th sampling time; Represents the comprehensive synergy index between all dimensional historical data sequences corresponding to the t-th sampling moment; The larger the value, the larger the prediction error, and the smoothing parameter needs to be adjusted; The larger the value is, the lower the correlation between all two-dimensional historical data sequences corresponding to the t-th sampling time to the t+1-th sampling time and the comprehensive synergy index between all dimensional historical data sequences is. This means that the smoothing parameter needs to be increased when smoothing the dimensional data at the t+1-th sampling time.

[0067] S31: predicting the value of each dimensional data at the next moment of each sampling moment according to the smoothing parameter correction value at each sampling moment.

[0068] In the embodiment of the present invention, the exponential smoothing method is used according to the smoothing parameter correction value at the t-th sampling moment to obtain the predicted value of each dimensional data at the t+1-th sampling moment.

[0069] According to the method for obtaining the comprehensive synergy index between all dimensional historical data sequences corresponding to the t-th sampling time and the predicted value of each dimensional data at the t+1-th sampling time, the comprehensive synergy index between all dimensional historical data sequences corresponding to the t+2-th sampling time is obtained, which is recorded as ,like The value is less than the warning coefficient When the warning is issued, relevant personnel will be notified to adjust the distribution network material links to improve resource utilization; preset warning coefficient In other embodiments, the implementer may preset the value of the warning coefficient according to the specific implementation situation.

[0070] The present invention first obtains the correlation between historical data sequences of different dimensions before each sampling moment and the comprehensive synergy index between historical data sequences of multiple dimensions according to the close coordination relationship between various links in the material management process of the distribution network, corrects the initial smoothing parameters, and obtains the corrected values ​​of the smoothing parameters at each sampling moment. When the corrected values ​​of the smoothing parameters at each sampling moment are used to predict the values ​​of the data of each dimension at the next moment of each sampling moment, the prediction results can be closer to actual needs and the accuracy of the prediction can be improved.

[0071] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0072] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory, a dynamic random access memory, a static random access memory, an enhanced dynamic random access memory, a high bandwidth memory, a hybrid storage cube, etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of the device or accessible or connectable to the device.

[0073] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0074] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for controlling key links of distribution network materials based on artificial intelligence, characterized in that: Includes steps: Obtain the historical data series of each dimension corresponding to each sampling time; obtain the correlation between any two historical data series of each dimension corresponding to each sampling time, and the calculation formula is: ; In the formula, Represents the correlation between the historical data sequence of the ath dimension and the historical data sequence of the bth dimension corresponding to the tth sampling moment; Represents the number of data in the historical data sequence of the ath dimension corresponding to the tth sampling moment; and Represents the value of the i-th data in the historical data sequence of the a-th dimension and the value of the i-th data in the historical data sequence of the b-th dimension corresponding to the t-th sampling moment; as well as represents the mean of all data in the historical data sequence of the a-th dimension and the mean of all data in the historical data sequence of the b-th dimension corresponding to the t-th sampling moment; || represents the absolute value symbol, and the correlation degree represents the trend characteristics of the same increase and decrease of the historical data sequences of the two dimensions; Obtain the comprehensive synergy index between all dimensional historical data series corresponding to each sampling moment, including: obtaining the historical sales before each sampling moment; ; In the formula, Represents the comprehensive synergy index between all dimensional historical data sequences corresponding to the t-th sampling moment; Represents the historical sales before the tth sampling moment; Represents the number of delivery volume data in the historical data sequence of the delivery dimension corresponding to the t-th sampling moment; Represents the value of the kth distribution volume data in the distribution dimension historical data sequence corresponding to the tth sampling moment; exp() represents an exponential function with a natural constant as the base, and the comprehensive synergy index represents the synergy effect between material management links; obtain the smoothing parameter correction value at each sampling moment: , where represents the initial smoothing parameter value; Represents the mean of the absolute values ​​of the differences between the predicted values ​​and the actual values ​​of all dimensional data at the t-th sampling moment; as well as Represents the mean value of the correlation between all historical data sequences of any two dimensions corresponding to the t-th sampling time and the t+1-th sampling time; Represents the comprehensive synergy index between all dimensional historical data sequences corresponding to the t-th sampling moment; Represents the comprehensive synergy index between all dimensional historical data sequences corresponding to the t-th sampling moment; exp() represents an exponential function with a natural constant as the base; and the value of each dimensional data at the next sampling moment is predicted based on the smoothing parameter correction value.

2. The method for controlling key links of distribution network materials based on artificial intelligence according to claim 1 is characterized in that: The method of obtaining the historical data sequences of each dimension corresponding to each sampling moment comprises the following steps: Collect data of each dimension at each sampling moment, sort each dimension data before the t-th sampling moment according to the order of the sampling moments from small to large, and obtain the purchase quantity data, inventory quantity data and distribution quantity data corresponding to the t-th sampling moment.

3. The method for controlling key links of distribution network materials based on artificial intelligence according to claim 1 is characterized in that: The calculation formula for obtaining the historical sales before each sampling moment is: ； In the formula, Represents the historical sales before the tth sampling moment; Represents the value of the first inventory data in the inventory dimension historical data sequence corresponding to the t-th sampling moment; Represents the value of the last inventory data in the inventory dimension historical data sequence corresponding to the t-th sampling moment; Represents the number of purchase quantity data in the purchase dimension historical data sequence corresponding to the t-th sampling moment; Represents the value of the j-th purchase quantity data in the purchase dimension historical data sequence corresponding to the t-th sampling moment.

4. The method for controlling key links of distribution network materials based on artificial intelligence according to claim 1 is characterized in that: The method for obtaining the predicted values ​​of all dimensional data at the sampling time is: Preset initial smoothing parameters , according to the initial smoothing parameter , use the exponential smoothing method to obtain the predicted value of each dimension data at the tth sampling time.

5. The method for controlling key links of distribution network materials based on artificial intelligence according to claim 1 is characterized in that: The predicting of the value of each dimension data at the next sampling moment includes: According to the corrected value of the smoothing parameter at the t-th sampling moment, the exponential smoothing method is used to obtain the predicted value of each dimension data at the t+1-th sampling moment.

6. The key link management and control system of distribution network materials based on artificial intelligence is characterized by: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the method for controlling key links of distribution network materials based on artificial intelligence according to any one of claims 1 to 5 is implemented.

Images