Communication operation project intelligent optimization distribution method

Abstract

The invention discloses a communication operation project intelligent optimization distribution method, which relates to the field of communication operation, solves the problem that the sales condition of a communication product cannot be predicted and purchased, and comprises the following steps: collecting historical purchase data and historical sales data of a communication product corresponding to a target enterprise, and processing the historical sales data; judging the rationality of the historical sales data after each store in the target enterprise completes noise reduction; analyzing the historical sales data and the historical purchase data of the multiple stores corresponding to the target enterprise to obtain predicted purchase quantities corresponding to the multiple stores; collecting the supply distance and the remaining goods between the plurality of suppliers and each store, supplying goods to each store, and generating a supply completion signal or an insufficient supply signal according to a supply result; and the display terminal receives the insufficient supply signal or the complete supply signal corresponding to each store to know that the state of the store is insufficient supply or sufficient supply, and the sales condition of the communication product is predicted and purchased.

Description

Technical Field

[0001] The present invention relates to the technical field of communication operation, and in particular to an intelligent optimization distribution method for communication operation projects. Background Art

[0002] Communication operating companies mainly refer to operators that provide communication services. These companies not only provide traditional voice call services, but also cover data services, SMS and MMS, broadband Internet, additional telephone functions, packages and billing, value-added services, and even TV services. In communication operating companies, product procurement optimization is crucial because the procurement of communication products involves a large amount of capital investment and supply chain management. By optimizing the distribution of communication products and the procurement process, companies can gain greater competitive advantages in the highly competitive communication market.

[0003] However, at the current stage, when optimizing the distribution of communication products, it is impossible to effectively estimate the sales of communication products in multiple stores, and thus it is impossible to purchase corresponding communication products based on the estimated sales, which affects the sales of communication products. To this end, the present invention proposes a method for intelligent optimization distribution of communication operation projects. Summary of the invention

[0004] The purpose of the present invention is to propose a method for intelligent optimization distribution of communication operation projects to solve the problem of being unable to predict and purchase the sales of communication products raised in the above-mentioned background technology.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions: A communication operation project intelligent optimization distribution method, comprising: Step S1, collecting historical purchase data and historical sales data of the target enterprise's corresponding communication products, processing the target enterprise's historical sales data, and removing noise data in the historical sales data; Step S2, judging the rationality of the historical sales data of each store in the target enterprise after noise reduction; Step S3, analyzing the historical sales data and historical purchase data of multiple stores corresponding to the target enterprise to obtain the predicted purchase volumes corresponding to the multiple stores; Step S4, collecting the supply distance and the remaining quantity between multiple suppliers and each store, supplying goods to each store, and generating a supply completion signal or a supply shortage signal according to the supply result; Step S5, the display terminal receives the shortage signal or the completion signal corresponding to each store, and learns whether the status of the corresponding store is shortage or sufficient supply. The user makes corresponding responses to the store corresponding to the shortage.

[0006] Furthermore, the historical purchasing data is the quarterly purchasing volume of multiple stores in the previous quarter, and the historical sales data is the quarterly total sales volume and quarterly daily sales volume of each store in the previous quarter.

[0007] Furthermore, the step S1 includes the following sub-steps: Step S11, obtain the historical sales data of the target enterprise's corresponding communication products, and obtain the quarterly daily sales volume RXL of the target enterprise's corresponding multiple stores in the previous quarter i , i is the date number, i=1, 2, ..., z, z is a positive integer; Step S12: for any store, the daily sales of the corresponding store in the previous quarter are added together and averaged to obtain the daily average sales RJX of the corresponding store in the previous quarter; Step S13, calculate the sales standard deviation BZC of the corresponding store in the previous quarter by using the formula, the specific formula is: ; Step S14, calculate the determination coefficient PD of the corresponding store every day in the previous quarter by formula i , the specific formula is: PD i =(RXL i -RJX) / BZC; Step S15: Similarly, perform steps S12 to S14 for all stores to obtain the determination coefficient of each store every day in the previous quarter; Step S16, for any store, if the determination coefficient is within the determination interval, the daily sales volume on the corresponding date is retained and recorded as the denoised daily sales volume; if the determination coefficient is outside the determination interval, the daily sales volume on the corresponding date is deemed to be noise data and the daily sales volume on the corresponding date is discarded.

[0008] Furthermore, the step S2 includes the following sub-steps: Step S21, adding up the retained daily sales to obtain the total noise reduction sales of the corresponding store; Step S22, compare the noise reduction total sales with the actual quarterly total sales of the corresponding store. If the value of the noise reduction total sales divided by the quarterly total sales is less than the comparison threshold, it is determined that the historical sales data of the corresponding store that has completed noise reduction is too different from the original data, and the historical purchase volume of the corresponding store is used as the purchase volume for the next quarter. Step S23: If the value of the total noise reduction sales divided by the quarterly total sales is greater than or equal to the comparison threshold, the subsequent steps are executed.

[0009] Furthermore, the step S3 includes the following sub-steps: Step S31, obtaining the historical sales data of any store after noise reduction, obtaining the denoised daily sales of the corresponding store, and determining the stability of the historical sales data of the corresponding store after noise reduction; Step S32: if the historical sales data of the corresponding store after denoising is not stable, then perform differential processing on the historical sales data, specifically subtracting the denoised daily sales of adjacent dates to obtain the first-order differential data of the corresponding store and execute subsequent steps; if the historical sales data is stable, execute step S35; Step S33, substitute the first-order difference data into step S31, and judge the stability of the first-order difference data. If the first-order difference data is not stable, perform difference processing on the first-order difference data to obtain second-order difference data; if the first-order difference data is stable, execute step S35; Step S34, repeat step S33 until the n-order difference data is stable.

[0010] Furthermore, the step S3 also includes the following sub-steps: Step S35, substitute the stable historical sales data or n-order difference data into the sales forecasting model, obtain the predicted sales volume of the corresponding store every day in the future according to the sales forecasting model, and then calculate the predicted monthly sales volume of the corresponding store in the next month; Step S36, adding the predicted monthly sales to the quarterly total sales of the corresponding store to obtain the predicted total sales of the store; Step S37, obtaining the quarterly purchase volume of the corresponding store, and comparing the quarterly purchase volume with the predicted total sales volume. If the quarterly purchase volume is greater than the predicted total sales volume, it is determined that the corresponding store has an inventory overflow of communication products and no purchase is required; If the quarterly purchase volume is less than or equal to the predicted total sales volume, it is determined that the communication products of the corresponding store need to be purchased, and the predicted purchase volume is obtained by subtracting the quarterly purchase volume from the predicted total sales volume.

[0011] Furthermore, the stability determination process is specifically as follows: Step S311, construct a stationary regression equation and estimate the stationary coefficient P i The value of , the stationary regression equation is specifically: QUR i =P i ×Q i-1 +α+β; where QZR i is the denoised daily sales volume on date i, QZR i-1 is the daily sales volume on the day before date i; α is the intercept, and β is the error term; Step S312: Calculate the stable detection value PWJ between the corresponding adjacent dates by formula i , the specific formula is: PWJ i=|P i -1| / BZP; where BZP is the standard stability coefficient; Step S313, if the stability detection value is greater than or equal to the stability detection threshold, the corresponding historical sales data is determined to be unstable; if the stability detection value is less than the stability detection threshold, the corresponding historical sales data is determined to be stable.

[0012] Further, the desired step S4 includes the following sub-steps: Step S41, obtaining the supply distance between multiple suppliers and each store; Step S42, arranging different stores in descending order according to predicted purchase volume; Step S43, calculating the supply preference values ​​between all stores and suppliers in order; Step S44, compare the supply preference value corresponding to the supplier with the supply preference threshold. If the supply preference value is less than or equal to the supply preference threshold, the corresponding supplier is discarded; if the supply preference value is greater than the supply preference threshold, the corresponding supplier is recorded as a supplier to be selected.

[0013] Furthermore, the step S4 further includes the following sub-steps: Step S45, selecting the supplier with the largest supply preference value as the selected supplier, comparing the remaining quantity of the selected supplier with the predicted purchase quantity of the corresponding store, and if the remaining quantity is greater than or equal to the predicted purchase quantity, supplying the corresponding store with the communication products of the predicted purchase quantity; Step S46: If the remaining quantity is less than the predicted purchase quantity, all the remaining quantity of the corresponding selected supplier is supplied to the corresponding store, and the predicted purchase quantity of the current store is changed to the difference between the predicted purchase quantity in the previous step and the remaining quantity of the corresponding selected supplier; Step S47, record the supplier with the second largest supply preference value as the selected supplier, update the predicted purchase quantity according to the difference between the predicted purchase quantity and the corresponding remaining quantity of the selected supplier, and repeat steps S44-S45 until the corresponding store purchases the communication products of the number corresponding to the predicted purchase quantity or there are no remaining suppliers to be selected; when the corresponding store purchases the communication products of the number corresponding to the predicted purchase quantity, generate a supply completion signal and send it to the display terminal; when there are no remaining suppliers to be selected, generate a supply shortage signal and send it to the display terminal; Step S48, repeating steps S43 to S46 for all stores to obtain insufficient supply signals or complete supply signals for the corresponding stores.

[0014] Furthermore, the calculation process of the supply optimization value is as follows: Step S431, for any store, the supply distance between it and multiple suppliers is recorded as GHJm, where m is the number of different suppliers; Step S432, obtaining the sales prices of corresponding communication products from different suppliers and recording them as XSJm; Step S433, calculating the supply optimization value GYXm between the corresponding store and multiple suppliers through a formula; GYXm=e / (XSJm×A1+GHJm×A2);wherein, e is a natural constant, and A1 and A2 are proportional coefficients with fixed values.

[0015] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are: The present invention first collects the historical purchase data and historical sales data of the communication products of the target enterprise, processes the historical sales data of the target enterprise, and removes the noise data in the historical sales data; then determines the rationality of the historical sales data of each store in the target enterprise after noise reduction; then analyzes the historical sales data and historical purchase data of multiple stores corresponding to the target enterprise, and obtains the predicted purchase quantities corresponding to the multiple stores; then collects the supply distances and the remaining quantities of goods between multiple suppliers and each store, supplies each store, and generates a supply completion signal or an insufficient supply signal according to the supply result; finally, uses a display terminal to receive the insufficient supply signal or the supply completion signal corresponding to each store, and learns whether the status of the corresponding store is insufficient supply or sufficient supply, and the user makes a corresponding response to the store corresponding to the insufficient supply, and the present invention realizes the prediction and purchase of the sales situation of communication products. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0017] Figure 1 is a flow chart of the method of the present invention; Figure 2 It is a schematic diagram of the process of denoising the historical sales data in the present invention; Figure 3 A schematic diagram of a process for calculating the predicted purchase quantities corresponding to multiple stores in the present invention; Figure 4 It is a schematic diagram of the structure of the computer device in the present invention. DETAILED DESCRIPTION

[0018] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] Example 1: Please refer to Figure 1-Figure 3As shown, the technical solution provided by the present invention is: a method for intelligent optimization distribution of communication operation projects, which is applied to the scenario of communication operation enterprises purchasing communication products. The method is specifically as follows: Step S1, collecting historical purchase data and historical sales data of the target enterprise's corresponding communication products, processing the target enterprise's historical sales data, and removing noise data in the historical sales data; The historical purchase data specifically refers to the quarterly purchase volume of multiple stores in the previous quarter, and the historical sales data refers to the quarterly total sales volume and quarterly daily sales volume of each store in the previous quarter; The step S1 includes the following sub-steps: Step S11, obtain the historical sales data of the target enterprise's corresponding communication products, and obtain the quarterly daily sales volume RXL of the target enterprise's corresponding multiple stores in the previous quarter i , i is the date number, i=1, 2, ..., z, z is a positive integer; Step S12: for any store, the daily sales of the corresponding store in the previous quarter are added together and averaged to obtain the daily average sales RJX of the corresponding store in the previous quarter; Step S13, calculate the sales standard deviation BZC of the corresponding store in the previous quarter by using the formula, the specific formula is: ; Step S14, calculate the determination coefficient PD of the corresponding store every day in the previous quarter by formula i , the specific formula is: PD i =(RXL i -RJX) / BZC; Specifically, the determination coefficient is used to determine whether the quarterly daily sales volume is noise data; Step S15: Similarly, perform steps S12 to S14 for all stores to obtain the determination coefficient of each store every day in the previous quarter; Step S16: for any store, if the determination coefficient is within the determination interval, the daily sales volume on the corresponding date is retained and recorded as the denoised daily sales volume; if the determination coefficient is outside the determination interval, the daily sales volume on the corresponding date is deemed to be noise data and the daily sales volume on the corresponding date is discarded; It should be noted that the determination interval is an interval symmetrical about the origin, that is, the left endpoint and the right endpoint of the determination interval are opposite numbers to each other, and the preferred determination interval is [-3, 3]; Step S2, judging the rationality of the historical sales data of each store in the target enterprise after noise reduction; The step S2 includes the following sub-steps: Step S21, adding up the retained daily sales to obtain the total noise reduction sales of the corresponding store; Step S22, compare the noise reduction total sales with the actual quarterly total sales of the corresponding store. If the value of the noise reduction total sales divided by the quarterly total sales is less than the comparison threshold, it is determined that the historical sales data of the corresponding store that has completed noise reduction is too different from the original data, and the historical purchase volume of the corresponding store is used as the purchase volume for the next quarter. Step S23, if the value of the total noise reduction sales divided by the quarterly total sales is greater than or equal to the comparison threshold, then execute the subsequent steps; Step S3, analyzing the historical sales data and historical purchase data of multiple stores corresponding to the target enterprise to obtain the predicted purchase volumes corresponding to the multiple stores; The step S3 includes the following sub-steps: Step S31, obtaining the historical sales data of any store after noise reduction, obtaining the denoised daily sales of the corresponding store, and determining the stability of the historical sales data of the corresponding store after noise reduction; The stability determination process is specifically as follows: Step S311, construct a stationary regression equation and estimate the stationary coefficient P i The value of , the stationary regression equation is specifically: QUR i =P i ×Q i-1 +α+β; where QZR i is the denoised daily sales volume on date i, QZR i-1 is the daily sales volume on the day before date i; α is the intercept, and β is the error term; Step S312: Calculate the stable detection value PWJ between the corresponding adjacent dates by formula i , the specific formula is: PWJ i =|P i -1| / BZP; where BZP is the standard stability coefficient; Step S313: if the stability detection value is greater than or equal to the stability detection threshold, the corresponding historical sales data is considered to be unstable; if the stability detection value is less than the stability detection threshold, the corresponding historical sales data is considered to be stable; wherein the preferred value of the stability detection threshold is 0.05; Step S32: if the historical sales data of the corresponding store after denoising is not stable, then perform differential processing on the historical sales data, specifically subtracting the denoised daily sales of adjacent dates to obtain the first-order differential data of the corresponding store and execute subsequent steps; if the historical sales data is stable, execute step S35; Step S33, substitute the first-order difference data into step S31, and judge the stability of the first-order difference data. If the first-order difference data is not stable, perform difference processing on the first-order difference data to obtain second-order difference data; if the first-order difference data is stable, execute step S35; Step S34, repeating step S33 until the n-order difference data is stable; Step S35, substitute the stable historical sales data or n-order difference data into the sales forecasting model, obtain the predicted sales volume of the corresponding store every day in the future according to the sales forecasting model, and then calculate the predicted monthly sales volume of the corresponding store in the next month; The sales forecasting model is obtained by training with the prior art, and the sales forecasting model can be obtained by training with an ARIMA model, or a random forest model, or a neural network model; the present invention is preferably an ARIMA model; Step S36, adding the predicted monthly sales to the quarterly total sales of the corresponding store to obtain the predicted total sales of the store; Step S37, obtaining the quarterly purchase volume of the corresponding store, and comparing the quarterly purchase volume with the predicted total sales volume. If the quarterly purchase volume is greater than the predicted total sales volume, it is determined that the corresponding store has an inventory overflow of communication products and no purchase is required; If the quarterly purchase volume is less than or equal to the predicted total sales volume, it is determined that the corresponding store needs to purchase communication products, and the predicted purchase volume is obtained by subtracting the quarterly purchase volume from the predicted total sales volume; Step S4, collecting the supply distance and the remaining quantity between multiple suppliers and each store, supplying goods to each store, and generating a supply completion signal or a supply shortage signal according to the supply result; wherein the supply distance refers to the actual transportation distance between the supplier and the store; The step S4 includes the following sub-steps: Step S41, obtaining the supply distance between multiple suppliers and each store; Step S42, arranging different stores in descending order according to predicted purchase volume; Step S43, calculating the supply preference values ​​between all stores and suppliers in order; The calculation process of the supply optimization value is as follows: Step S431, for any store, the supply distance between it and multiple suppliers is recorded as GHJm, where m is the number of different suppliers; Step S432, obtaining the sales prices of corresponding communication products from different suppliers and recording them as XSJm; Step S433, calculating the supply optimization value GYXm between the corresponding store and multiple suppliers through a formula; GYXm=e / (XSJm×A1+GHJm×A2); where e is a natural constant, and A1 and A2 are fixed proportional coefficients; Step S44, compare the supply preference value corresponding to the supplier with the supply preference threshold. If the supply preference value is less than or equal to the supply preference threshold, the corresponding supplier is discarded; if the supply preference value is greater than the supply preference threshold, the corresponding supplier is recorded as a supplier to be selected; Step S45, selecting the supplier with the largest supply preference value as the selected supplier, comparing the remaining quantity of the selected supplier with the predicted purchase quantity of the corresponding store, and if the remaining quantity is greater than or equal to the predicted purchase quantity, supplying the corresponding store with the communication products of the predicted purchase quantity; Step S46: If the remaining quantity is less than the predicted purchase quantity, all the remaining quantity of the corresponding selected supplier is supplied to the corresponding store, and the predicted purchase quantity of the current store is changed to the difference between the predicted purchase quantity in the previous step and the remaining quantity of the corresponding selected supplier; Step S47, record the candidate supplier with the second largest supply preference value as the selected supplier, update the predicted purchase quantity according to the difference between the predicted purchase quantity and the corresponding remaining quantity of the selected supplier, and repeat the process described in steps S44-S45 until the corresponding store purchases the communication products corresponding to the predicted purchase quantity or there are no remaining candidates; When the corresponding store purchases the communication products corresponding to the predicted purchase volume, a supply completion signal is generated and sent to the display terminal; when there are no remaining suppliers to be selected, a supply shortage signal is generated and sent to the display terminal; Step S48, repeating steps S43 to S46 for all stores to obtain a shortage signal or a completion signal of the corresponding store; Step S5, the display terminal receives the shortage signal or the completion signal corresponding to each store, and learns whether the corresponding store is shortage or sufficient, and the user takes corresponding measures for the store corresponding to the shortage; For example, corresponding communication products are taken from stores with overflowing inventory to achieve replenishment; In this application, if corresponding calculation formulas appear, the above calculation formulas are all dimensionless and take their numerical calculations. The weight coefficients, proportional coefficients and other coefficients in the formulas are set to a result value obtained by quantifying each parameter. The size of the weight coefficient and the proportional coefficient can be determined as long as it does not affect the proportional relationship between the parameter and the result value.

[0020] Embodiment 2: Figure 4The structural diagram of a computer device is illustrated, and the computer device may include: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus. The processor may call the logic instructions in the memory to execute a communication operation project intelligent optimization distribution method, which includes: collecting the historical purchase data and historical sales data of the communication products corresponding to the target enterprise, processing the historical sales data of the target enterprise, and removing the noise data in the historical sales data; judging the rationality of the historical sales data of each store in the target enterprise after noise reduction; analyzing the historical sales data and historical purchase data of multiple stores corresponding to the target enterprise, and obtaining the predicted purchase volume corresponding to the multiple stores; collecting the supply distance and the remaining quantity of goods between multiple suppliers and each store, supplying each store, and generating a supply completion signal or a supply shortage signal according to the supply result; the display terminal receives the supply shortage signal or the supply completion signal corresponding to each store, and learns that the status of the corresponding store is insufficient supply or sufficient supply, and the user makes corresponding responses to the store corresponding to the insufficient supply.

[0021] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0022] On the other hand, the present application also provides a computer program product, which includes a computer program stored on a computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute a communication operation project intelligent optimization distribution method provided by the above methods, the method including: collecting historical procurement data and historical sales data corresponding to the target enterprise's communication products, processing the historical sales data of the target enterprise, and removing noise data in the historical sales data; judging the rationality of the historical sales data of each store in the target enterprise after noise reduction; analyzing the historical sales data and historical procurement data of multiple stores corresponding to the target enterprise to obtain the predicted procurement volume corresponding to the multiple stores; collecting the supply distance and the remaining goods between multiple suppliers and each store, supplying each store, and generating a supply completion signal or an insufficient supply signal based on the supply result; the display terminal receives the insufficient supply signal or the supply completion signal corresponding to each store, and learns that the status of the corresponding store is insufficient supply or sufficient supply, and the user makes corresponding responses to the store corresponding to the insufficient supply.

[0023] On the other hand, the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the above-mentioned intelligent optimization distribution method for communication operation projects, the method comprising: collecting historical procurement data and historical sales data corresponding to the communication products of the target enterprise, processing the historical sales data of the target enterprise, and removing noise data in the historical sales data; judging the rationality of the historical sales data of each store in the target enterprise after noise reduction; analyzing the historical sales data and historical procurement data of multiple stores corresponding to the target enterprise, and obtaining the predicted procurement quantities corresponding to the multiple stores; collecting the supply distance and the remaining goods between multiple suppliers and each store, supplying each store, and generating a supply completion signal or an insufficient supply signal based on the supply result; the display terminal receives the insufficient supply signal or the supply completion signal corresponding to each store, and learns that the status of the corresponding store is insufficient supply or sufficient supply, and the user makes corresponding responses to the store corresponding to the insufficient supply.

[0024] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0025] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0026] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for intelligent optimization distribution of communication operation projects, characterized in that: Methods include: Step S1, collecting historical purchase data and historical sales data of the target enterprise's corresponding communication products, processing the target enterprise's historical sales data, and removing noise data in the historical sales data; Step S2, judging the rationality of the historical sales data of each store in the target enterprise after noise reduction; Step S3, analyzing the historical sales data and historical purchase data of multiple stores corresponding to the target enterprise to obtain the predicted purchase volumes corresponding to the multiple stores; Step S4, collecting the supply distance and the remaining quantity between multiple suppliers and each store, supplying goods to each store, and generating a supply completion signal or a supply shortage signal according to the supply result; Step S5, the display terminal receives the shortage signal or the completion signal corresponding to each store, and learns whether the status of the corresponding store is shortage or sufficient supply. The user makes corresponding responses to the store corresponding to the shortage.

2. According to claim 1, a method for intelligent optimization distribution of communication operation projects is characterized in that: The historical purchasing data is the quarterly purchasing volume of multiple stores in the previous quarter, and the historical sales data is the quarterly total sales volume and quarterly daily sales volume of each store in the previous quarter.

3. A communication operation project intelligent optimization distribution method according to claim 2, characterized in that: The step S1 includes the following sub-steps: Step S11, obtain the historical sales data of the target enterprise's corresponding communication products, and obtain the quarterly daily sales volume RXL of the target enterprise's corresponding multiple stores in the previous quarter i , i is the date number, i=1, 2, ..., z, z is a positive integer; Step S12: for any store, the daily sales of the corresponding store in the previous quarter are added together and averaged to obtain the daily average sales RJX of the corresponding store in the previous quarter; Step S13, calculate the sales standard deviation BZC of the corresponding store in the previous quarter by using the formula, the specific formula is: ； Step S14, calculate the determination coefficient PD of the corresponding store every day in the previous quarter by formula i , the specific formula is: PD i =(RXL i -RJX) / BZC; Step S15: Similarly, perform steps S12 to S14 for all stores to obtain the determination coefficient of each store every day in the previous quarter; Step S16, for any store, if the determination coefficient is within the determination interval, the daily sales volume on the corresponding date is retained and recorded as the denoised daily sales volume; if the determination coefficient is outside the determination interval, the daily sales volume on the corresponding date is deemed to be noise data and the daily sales volume on the corresponding date is discarded.

4. A method for intelligent optimization distribution of communication operation projects according to claim 3, characterized in that: The step S2 includes the following sub-steps: Step S21, adding up the retained daily sales to obtain the total noise reduction sales of the corresponding store; Step S22, compare the noise reduction total sales with the actual quarterly total sales of the corresponding store. If the value of the noise reduction total sales divided by the quarterly total sales is less than the comparison threshold, it is determined that the historical sales data of the corresponding store that has completed noise reduction is too different from the original data, and the historical purchase volume of the corresponding store is used as the purchase volume for the next quarter. Step S23: If the value of the total noise reduction sales divided by the quarterly total sales is greater than or equal to the comparison threshold, the subsequent steps are executed.

5. A method for intelligent optimization distribution of communication operation projects according to claim 4, characterized in that: The step S3 includes the following sub-steps: Step S31, obtaining the historical sales data of any store after noise reduction, obtaining the denoised daily sales of the corresponding store, and determining the stability of the historical sales data of the corresponding store after noise reduction; Step S32: if the historical sales data of the corresponding store after denoising is not stable, then perform differential processing on the historical sales data, specifically subtracting the denoised daily sales of adjacent dates to obtain the first-order differential data of the corresponding store and execute subsequent steps; if the historical sales data is stable, execute step S35; Step S33, substitute the first-order difference data into step S31, and judge the stability of the first-order difference data. If the first-order difference data is not stable, perform difference processing on the first-order difference data to obtain second-order difference data; if the first-order difference data is stable, execute step S35; Step S34, repeat step S33 until the n-order difference data is stable.

6. A method for intelligent optimization distribution of communication operation projects according to claim 5, characterized in that: The step S3 also includes the following sub-steps: Step S35, substitute the stable historical sales data or n-order difference data into the sales forecasting model, obtain the predicted sales volume of the corresponding store every day in the future according to the sales forecasting model, and then calculate the predicted monthly sales volume of the corresponding store in the next month; Step S36, adding the predicted monthly sales to the quarterly total sales of the corresponding store to obtain the predicted total sales of the store; Step S37, obtaining the quarterly purchase volume of the corresponding store, and comparing the quarterly purchase volume with the predicted total sales volume. If the quarterly purchase volume is greater than the predicted total sales volume, it is determined that the corresponding store has an inventory overflow of communication products and no purchase is required; If the quarterly purchase volume is less than or equal to the predicted total sales volume, it is determined that the communication products of the corresponding store need to be purchased, and the predicted purchase volume is obtained by subtracting the quarterly purchase volume from the predicted total sales volume.

7. A method for intelligent optimization distribution of communication operation projects according to claim 5, characterized in that: The stability determination process is specifically as follows: Step S311, construct a stationary regression equation and estimate the stationary coefficient P i The value of , the stationary regression equation is specifically: QUR i =P i ×Q i-1 +α+β; where QZR i is the denoised daily sales volume on date i, QZR i-1 is the daily sales volume on the day before date i; α is the intercept, and β is the error term; Step S312: Calculate the stable detection value PWJ between the corresponding adjacent dates by formula i , the specific formula is: PWJ i =|P i -1| / BZP; where BZP is the standard stability coefficient; Step S313, if the stability detection value is greater than or equal to the stability detection threshold, the corresponding historical sales data is determined to be unstable; if the stability detection value is less than the stability detection threshold, the corresponding historical sales data is determined to be stable.

8. The method for intelligent optimization distribution of communication operation projects according to claim 1, characterized in that: The step S4 includes the following sub-steps: Step S41, obtaining the supply distance between multiple suppliers and each store; Step S42, arranging different stores in descending order according to predicted purchase volume; Step S43, calculating the supply preference values ​​between all stores and suppliers in order; Step S44, compare the supply preference value corresponding to the supplier with the supply preference threshold. If the supply preference value is less than or equal to the supply preference threshold, the corresponding supplier is discarded; if the supply preference value is greater than the supply preference threshold, the corresponding supplier is recorded as a supplier to be selected.

9. A method for intelligent optimization distribution of communication operation projects according to claim 8, characterized in that: The step S4 also includes the following sub-steps: Step S45, selecting the supplier with the largest supply preference value as the selected supplier, comparing the remaining quantity of the selected supplier with the predicted purchase quantity of the corresponding store, and if the remaining quantity is greater than or equal to the predicted purchase quantity, supplying the corresponding store with the communication products of the predicted purchase quantity; Step S46: If the remaining quantity is less than the predicted purchase quantity, all the remaining quantity of the corresponding selected supplier is supplied to the corresponding store, and the predicted purchase quantity of the current store is changed to the difference between the predicted purchase quantity in the previous step and the remaining quantity of the corresponding selected supplier; Step S47, record the supplier with the second largest supply preference value as the selected supplier, update the predicted purchase quantity according to the difference between the predicted purchase quantity and the corresponding remaining quantity of the selected supplier, and repeat steps S44-S45 until the corresponding store purchases the communication products of the number corresponding to the predicted purchase quantity or there are no remaining suppliers to be selected; when the corresponding store purchases the communication products of the number corresponding to the predicted purchase quantity, generate a supply completion signal and send it to the display terminal; when there are no remaining suppliers to be selected, generate a supply shortage signal and send it to the display terminal; Step S48, repeating steps S43 to S46 for all stores to obtain insufficient supply signals or complete supply signals for the corresponding stores.

10. A method for intelligent optimization distribution of communication operation projects according to claim 8, characterized in that: The calculation process of the supply optimization value is as follows: Step S431, for any store, the supply distance between it and multiple suppliers is recorded as GHJm, where m is the number of different suppliers; Step S432, obtaining the sales prices of corresponding communication products from different suppliers and recording them as XSJm; Step S433, calculating the supply optimization value GYXm between the corresponding store and multiple suppliers through a formula; GYXm=e / (XSJm×A1+GHJm×A2);wherein, e is a natural constant, and A1 and A2 are proportional coefficients with fixed values.

Images