Method and device for predicting raw material cost in purchasing system, and storage medium

Abstract

The invention discloses a method and device for predicting the cost of raw materials in a purchasing system and a storage medium, and belongs to the technical field of raw material cost prediction, and the method comprises the steps: obtaining a plurality of historical costs of to-be-predicted raw materials in the purchasing system within a preset time period; determining a fluctuation ratio corresponding to each historical cost according to the plurality of historical costs; according to the fluctuation ratio, a preset peak clipping coefficient and a preset valley clipping coefficient, determining a maximum historical cost and a minimum historical cost in the plurality of historical costs; performing peak clipping processing and valley clipping processing on the maximum historical cost and the minimum historical cost in the plurality of historical costs to obtain a plurality of corrected historical costs; and determining the prediction cost of the to-be-predicted raw material according to the plurality of corrected historical costs. The historical cost of the to-be-predicted raw material can be corrected, interference caused by abnormal fluctuation of the historical cost of the raw material can be eliminated, and the accuracy of raw material cost prediction can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of raw material cost prediction, and in particular to a method, device and storage medium for predicting raw material costs in a procurement system. Background Art

[0002] Raw material cost information is mainly used in the procurement cost accounting system to reference the basic data of raw material cost items when calculating the procurement cost of outsourced parts. Currently, the raw material cost is manually collected by the corresponding raw material cost, and the subsequent quotation is predicted based on manual experience, and then the corresponding raw material cost information in the system is updated according to the prediction results. However, the manual collection time is relatively long, and the raw material cost information collected and maintained in the system has a lag, which cannot truly reflect the raw material cost in the current procurement cycle. In addition, when the raw material cost information undergoes periodic changes, it cannot be synchronized to the corresponding raw material cost maintenance personnel in a timely manner, resulting in inaccuracies in the maintained raw material cost information, and ultimately resulting in large deviations in the calculated procurement cost. Therefore, the prior art has the problem of low accuracy in raw material cost prediction. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide a method, device and storage medium for predicting raw material costs in a procurement system, so as to solve the problem of low accuracy in raw material cost prediction in the prior art.

[0004] In order to achieve the above-mentioned purpose, a first aspect of an embodiment of the present application provides a method for predicting raw material costs in a procurement system, the method comprising:

[0005] Obtain multiple historical costs of raw materials to be forecasted in the procurement system within a preset time period;

[0006] Determine the volatility ratio corresponding to each historical cost based on multiple historical costs;

[0007] Determine the maximum historical cost and the minimum historical cost among the multiple historical costs according to the fluctuation ratio, the preset peak-cutting coefficient and the preset valley-cutting coefficient;

[0008] Perform peak shaving processing and valley shaving processing on the maximum historical cost and the minimum historical cost among the multiple historical costs respectively, so as to obtain multiple corrected historical costs;

[0009] The forecast cost of the raw materials to be forecasted is determined based on the revised multiple historical costs.

[0010] In an embodiment of the present application, a volatility ratio corresponding to each historical cost is determined based on multiple historical costs, including: obtaining timestamp information of each historical cost; determining, based on the timestamp information and multiple historical costs, an average historical cost corresponding to the historical costs before the timestamp corresponding to each historical cost in the multiple historical costs; and determining the volatility ratio corresponding to each historical cost based on each historical cost and the average historical cost corresponding to each historical cost.

[0011] In an embodiment of the present application, the maximum historical cost and the minimum historical cost among multiple historical costs are determined based on the fluctuation ratio, the preset peak shaving coefficient and the preset valley cutting coefficient, including: comparing the fluctuation ratio corresponding to each historical cost among the multiple historical costs with the preset peak shaving coefficient and the preset valley cutting coefficient, respectively; determining the historical cost corresponding to the fluctuation ratio greater than the preset peak shaving coefficient as the maximum historical cost; and determining the historical cost corresponding to the fluctuation ratio less than the preset valley cutting coefficient as the maximum historical cost.

[0012] In an embodiment of the present application, the maximum historical cost and the minimum historical cost among multiple historical costs are subjected to peak shaving processing and valley shaving processing respectively to obtain multiple corrected historical costs, including: performing peak shaving processing on the maximum historical cost according to a preset peak shaving correction coefficient to obtain the corrected historical cost; and performing valley shaving processing on the minimum historical cost according to a preset valley shaving correction coefficient to obtain the corrected historical cost.

[0013] In an embodiment of the present application, the predicted cost of the raw materials to be predicted is determined based on multiple revised historical costs, including: obtaining timestamp information corresponding to the multiple revised historical costs; grouping the multiple revised historical costs according to the timestamp information to obtain multiple historical cost groups; determining the historical cost mean of each historical cost group; and performing weighted summation processing on the historical cost means corresponding to the multiple historical cost groups to obtain the predicted cost.

[0014] In the embodiment of the present application, the method further includes: updating a preset peak clipping coefficient and / or a preset valley clipping coefficient in response to a user input.

[0015] In an embodiment of the present application, the method also includes: obtaining the current system maintenance cost of the raw materials to be predicted in the procurement system; determining the cost deviation rate based on the predicted cost and the current system maintenance cost; and determining the target system maintenance cost of the raw materials to be predicted in the procurement system based on the cost deviation rate and the preset deviation rate.

[0016] In an embodiment of the present application, the target system maintenance cost of the raw materials to be predicted in the procurement system is determined based on the cost deviation rate and the preset deviation rate, including: comparing the cost deviation rate with the preset deviation rate; when the cost deviation rate is greater than or equal to the preset deviation rate, determining the predicted cost as the target system maintenance cost of the raw materials to be predicted; when the cost deviation rate is less than the preset deviation rate, determining the current system maintenance cost as the target system maintenance cost of the raw materials to be predicted.

[0017] A second aspect of an embodiment of the present application provides an apparatus for predicting the cost of raw materials in a procurement system, comprising: a memory configured to store instructions; and a processor configured to call instructions from the memory and to implement the above-mentioned method for predicting the cost of raw materials in a procurement system when executing the instructions.

[0018] A third aspect of an embodiment of the present application provides a machine-readable storage medium having instructions stored thereon, the instructions being used to enable a machine to execute the above-mentioned method for predicting the cost of raw materials in a procurement system.

[0019] The above technical scheme obtains multiple historical costs of the raw materials to be predicted in the procurement system within a preset time period, and then determines the fluctuation ratio corresponding to each historical cost based on the multiple historical costs, and then determines the maximum historical cost and the minimum historical cost among the multiple historical costs based on the fluctuation ratio, the preset peak-cutting coefficient, and the preset valley-cutting coefficient, and then performs peak-cutting and valley-cutting processing on the maximum historical cost and the minimum historical cost among the multiple historical costs, respectively, to obtain multiple corrected historical costs, and finally determines the predicted cost of the raw materials to be predicted based on the corrected multiple historical costs. The present application can correct the historical cost of the raw materials to be predicted, and predict the cost of the raw materials based on the corrected historical cost, which can eliminate the interference caused by abnormal fluctuations in the historical cost of the raw materials, and is conducive to improving the accuracy of the raw material cost prediction.

[0020] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present application, but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings:

[0022] Figure 1 A flowchart of a method for predicting raw material costs in a procurement system provided in an embodiment of the present application;

[0023] Figure 2A structural block diagram of a device for predicting raw material costs in a procurement system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0025] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back...), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0026] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0027] Figure 1 A flow chart of a method for predicting raw material costs in a procurement system provided in an embodiment of the present application. Figure 1 As shown, an embodiment of the present application provides a method for predicting raw material costs in a procurement system. The method is described by taking the application of the method to a processor as an example. The method may include the following steps.

[0028] Step S101, obtaining multiple historical costs of raw materials to be predicted in a procurement system within a preset time period.

[0029] In an embodiment of the present application, the cost of raw materials, i.e., the price of raw materials, may refer to the purchase price or selling price of raw materials. The procurement system may include a raw material database, which is used to store information about each raw material to be purchased, including the type and historical cost of the raw materials, etc. The raw material database of the procurement system may be docked with a third-party raw material network. According to the direct or indirect matching rules with the raw materials of the third-party raw material network, the procurement system may receive the daily cost of each raw material in the raw material database sent by the third-party raw material network, and store it in the raw material database. Therefore, the historical cost of each raw material is stored in the raw material database in units of days. In this way, by docking with a professional third-party raw material network, a raw material database that conforms to market conditions is formed, which is conducive to providing a data basis for raw material forecasting and improving the accuracy of forecasting results.

[0030] Specifically, when predicting the cost of any raw material to be predicted in the procurement system, including predicting the current or future cost of the raw material, the processor can obtain multiple historical costs of the raw material to be predicted stored in the raw material database of the procurement system within a preset time period. The preset time period can be pre-set according to actual needs. For example, the preset time period can be three months before the predicted date, and the multiple historical costs are the actual purchase costs of the raw material to be predicted in the daily market within the three months before the predicted date. In this way, the timeliness and accuracy of the raw material cost data in the raw material database are guaranteed.

[0031] Step S102: determining the fluctuation ratio corresponding to each historical cost according to a plurality of historical costs.

[0032] Specifically, considering that the historical cost of raw materials may have abnormal fluctuations, in order to prevent the abnormal fluctuations in the cost of raw materials from affecting the accuracy of the prediction results, the processor can determine the fluctuation ratio corresponding to each historical cost based on multiple historical costs, that is, the daily fluctuation ratio of the cost of raw materials. The fluctuation ratio can be used to indicate the fluctuation of the raw material cost on the calculation day in a certain period of time.

[0033] Step S103, determining a maximum historical cost and a minimum historical cost among a plurality of historical costs according to the fluctuation ratio, the preset peak shaving coefficient and the preset valley shaving coefficient.

[0034] It can be understood that the preset peak shaving coefficient is a preset value used to determine whether the historical cost of a certain day is a maximum historical cost, and the preset valley shaving coefficient is a preset value used to determine whether the historical cost of a certain day is a minimum historical cost. It can be understood that the preset peak shaving coefficient and the preset valley shaving coefficient are both preset parameters of the procurement system, which are set by the technical staff of the business department based on test data or historical experience. The maximum historical cost refers to a larger value caused by abnormal fluctuations, and the minimum historical cost is a smaller value caused by abnormal fluctuations. Specifically, according to the fluctuation ratio corresponding to each historical cost, combined with the preset peak shaving coefficient and the preset valley shaving coefficient, it can be determined whether each historical cost is a maximum historical cost or a minimum historical cost, thereby determining the maximum historical cost and the minimum historical cost among multiple historical costs. In this way, the abnormal data of fluctuations can be screened out to eliminate the impact of abnormal data on the prediction results.

[0035] Step S104 , performing peak shaving processing and valley shaving processing on the maximum historical cost and the minimum historical cost among the multiple historical costs, respectively, to obtain multiple corrected historical costs.

[0036] It can be understood that in order to eliminate the influence of abnormal data on the prediction results of the raw materials to be predicted, the processor can perform peak and valley shaving processing on the maximum historical cost and the minimum historical cost in the multiple historical costs, respectively, to obtain multiple corrected historical costs. In one example, the processor can directly complete the peak and valley shaving processing of multiple historical costs by eliminating the maximum historical cost and the minimum historical cost, so as to obtain multiple corrected historical costs. In this way, it is conducive to eliminating the influence of abnormal data on the prediction results, thereby improving the accuracy of the prediction results.

[0037] Step S105, determining the forecast cost of the raw material to be forecasted according to the corrected multiple historical costs.

[0038] In one example, the revised multiple historical costs can be input into the cost forecasting model, and the predicted cost of the raw materials to be forecasted can be obtained through the processing of the cost forecasting model; wherein the cost forecasting model can be constructed based on a deep learning algorithm by collecting a large amount of cost data of the raw materials to be forecasted. In this way, the cost of the raw materials to be forecasted can be forecasted based on the revised multiple historical costs, which can improve the accuracy of the forecast results.

[0039] The above technical scheme obtains multiple historical costs of the raw materials to be predicted in the procurement system within a preset time period, and then determines the fluctuation ratio corresponding to each historical cost based on the multiple historical costs, and then determines the maximum historical cost and the minimum historical cost among the multiple historical costs based on the fluctuation ratio, the preset peak-cutting coefficient, and the preset valley-cutting coefficient, and then performs peak-cutting and valley-cutting processing on the maximum historical cost and the minimum historical cost among the multiple historical costs, respectively, to obtain multiple corrected historical costs, and finally determines the predicted cost of the raw materials to be predicted based on the corrected multiple historical costs. The present application can correct the historical cost of the raw materials to be predicted, and predict the cost of the raw materials based on the corrected historical cost, which can eliminate the interference caused by abnormal fluctuations in the historical cost of the raw materials, and is conducive to improving the accuracy of the raw material cost prediction.

[0040] In an embodiment of the present application, determining the volatility ratio corresponding to each historical cost based on multiple historical costs may include: obtaining timestamp information of each historical cost; determining, based on the timestamp information and the multiple historical costs, an average historical cost corresponding to the historical costs before the timestamp corresponding to each historical cost in the multiple historical costs; and determining the volatility ratio corresponding to each historical cost based on each historical cost and the average historical cost corresponding to each historical cost.

[0041] It can be understood that each historical cost is associated with a timestamp information, which is used to determine the date corresponding to each historical cost. The embodiment of the present application can determine the volatility ratio corresponding to each historical cost based on each historical cost and the historical cost average corresponding to each historical cost. The historical cost average corresponding to the historical cost refers to the average of multiple historical costs before the timestamp of the historical cost. For example, for the historical cost of a certain day, its historical cost average is the average of the historical costs of each day in the month before that day.

[0042] In an example, the historical cost average corresponding to the historical cost can also be the historical cost average of a period of time before and after the timestamp of the historical cost. For example, for the historical cost of a certain day, the historical cost average is the average of the historical costs of the fifteen days before and after the day.

[0043] Furthermore, the volatility ratio of the historical cost on the day can be determined based on the historical cost and the corresponding average. In one example, the volatility ratio can be calculated as the ratio of the difference between the historical cost and the historical cost average to the historical cost. In another example, the volatility ratio can be the ratio of the historical cost to the historical cost average. In this way, the volatility of the historical cost can be quantified, providing a basis for judgment for the subsequent revision of the historical cost.

[0044] In an embodiment of the present application, determining the maximum historical cost and the minimum historical cost among multiple historical costs based on the fluctuation ratio, the preset peak shaving coefficient and the preset valley cutting coefficient can include: comparing the fluctuation ratio corresponding to each historical cost among the multiple historical costs with the preset peak shaving coefficient and the preset valley cutting coefficient, respectively; determining the historical cost corresponding to the fluctuation ratio greater than the preset peak shaving coefficient as the maximum historical cost; and determining the historical cost corresponding to the fluctuation ratio less than the preset valley cutting coefficient as the maximum historical cost.

[0045] It can be understood that the preset peak-cutting coefficient is a preset value used to determine whether the historical cost of a certain day is a maximum historical cost, and the preset valley-cutting coefficient is a preset value used to determine whether the historical cost of a certain day is a minimum historical cost. It can be understood that the preset peak-cutting coefficient and the preset valley-cutting coefficient are both preset parameters of the procurement system, which are set by the technical staff of the business department based on test data or historical experience. Among them, the preset peak-cutting coefficient is greater than the preset valley-cutting coefficient.

[0046] Specifically, the processor can determine the historical cost whose corresponding fluctuation ratio is greater than the preset peak-cutting coefficient as the maximum historical cost, and determine the historical cost whose corresponding fluctuation ratio is less than the preset valley-cutting coefficient as the minimum historical cost, both of which are abnormal fluctuation data. For the historical cost whose fluctuation ratio is less than or equal to the preset peak-cutting coefficient and greater than or equal to the preset valley-cutting coefficient, it is determined to be normal data, and no peak-cutting or valley-cutting processing is required. In this way, the abnormal fluctuation data in the historical cost can be quickly determined through the fluctuation ratio and the preset peak-cutting coefficient and the preset valley-cutting coefficient, which is convenient for subsequent processing.

[0047] In an embodiment of the present application, the maximum historical cost and the minimum historical cost among multiple historical costs are subjected to peak shaving processing and valley shaving processing respectively to obtain multiple corrected historical costs, which may include: performing peak shaving processing on the maximum historical cost according to a preset peak shaving correction coefficient to obtain the corrected historical cost; and performing valley shaving processing on the minimum historical cost according to a preset valley shaving correction coefficient to obtain the corrected historical cost.

[0048] Specifically, a preset peak shaving correction coefficient and a preset valley shaving correction coefficient are pre-set in the procurement system. Among them, the preset peak shaving correction coefficient is used to perform peak shaving processing on the maximum historical cost to obtain the corrected historical cost; the preset valley shaving correction coefficient is used to perform valley shaving processing on the minimum historical cost to obtain the corrected historical cost. It can be understood that the preset peak shaving correction coefficient corresponds to the preset peak shaving coefficient, and the preset valley shaving correction coefficient corresponds to the preset valley shaving coefficient, and both are system preset parameters set by technical personnel based on experiments or experience. In this way, by performing peak shaving and valley shaving processing on the maximum historical cost and the minimum historical cost in multiple historical costs respectively, the correction of abnormal data can be achieved, thereby ensuring the accuracy of the data.

[0049] In an embodiment of the present application, determining the predicted cost of the raw materials to be predicted based on the revised multiple historical costs can include: obtaining timestamp information corresponding to the revised multiple historical costs; grouping the revised multiple historical costs according to the timestamp information to obtain multiple historical cost groups; determining the historical cost mean of each historical cost group; and performing weighted summation processing on the historical cost means corresponding to the multiple historical cost groups to obtain the predicted cost.

[0050] It can be understood that each historical cost is associated with a timestamp information, which is used to determine the date corresponding to each historical cost. Therefore, the corrected multiple historical costs can be grouped according to the timestamp information to obtain multiple historical cost groups. In one example, the historical costs with timestamps of the same year and month can be grouped together. Further, the historical cost mean of each historical cost group is determined, and then the weighted sum of the multiple historical cost means is performed to obtain the predicted cost of the raw materials to be predicted. Among them, the weighting coefficient of each historical cost mean can be a preset value. For example, the historical cost mean of the previous three months can be taken for prediction, and then the previous three months correspond to different weighting coefficients, which are customized or adjusted by the user according to the system operation conditions. In this way, it is conducive to obtaining better prediction results.

[0051] In the embodiment of the present application, the method may further include: updating a preset peak clipping coefficient and / or a preset valley clipping coefficient in response to a user input.

[0052] It is understandable that the user adjusts the preset peak shaving coefficient and the preset valley shaving coefficient according to the system operation situation, and the procurement system can receive the updated peak shaving coefficient and / or valley shaving coefficient input by the user, thereby updating the peak shaving coefficient and / or valley shaving coefficient currently configured in the system according to the updated peak shaving coefficient and / or valley shaving coefficient input by the user. This is conducive to further improving the accuracy of the prediction results.

[0053] In an embodiment of the present application, the method may also include: obtaining the current system maintenance cost of the raw materials to be predicted in the procurement system; determining the cost deviation rate based on the predicted cost and the current system maintenance cost; and determining the target system maintenance cost of the raw materials to be predicted in the procurement system based on the cost deviation rate and the preset deviation rate.

[0054] It can be understood that the target system maintenance cost refers to the cost of the raw materials to be predicted that should be maintained in the current system. Specifically, after determining the predicted cost of the raw materials to be predicted, the processor can obtain the current system maintenance cost of the raw materials to be predicted in the procurement system and determine the cost deviation rate. In one example, the cost deviation rate can be the absolute value of the difference between the current system maintenance cost and the predicted cost. In another example, the cost deviation rate can be the ratio of the current system maintenance cost to the predicted cost. Furthermore, based on the cost deviation rate and the preset deviation rate, the deviation of the current system maintenance cost of the raw materials to be predicted in the procurement system can be determined, and then the target system maintenance cost can be determined.

[0055] In an embodiment of the present application, determining the target system maintenance cost of the raw materials to be predicted in the procurement system based on the cost deviation rate and the preset deviation rate can include: comparing the cost deviation rate with the preset deviation rate; when the cost deviation rate is greater than or equal to the preset deviation rate, determining the predicted cost as the target system maintenance cost of the raw materials to be predicted; when the cost deviation rate is less than the preset deviation rate, determining the current system maintenance cost as the target system maintenance cost of the raw materials to be predicted.

[0056] It can be understood that the preset deviation rate is a threshold for determining the deviation of the current system maintenance cost of the raw materials to be predicted. Specifically, if the calculated cost deviation rate is greater than or equal to the preset deviation rate, it means that the current system maintenance cost of the raw materials to be predicted in the procurement system has a large deviation and needs to be updated to the predicted cost to prevent data errors in the later stage. If the calculated cost deviation rate is greater than or equal to the preset deviation rate, it means that the current system maintenance cost of the raw materials to be predicted in the procurement system has a small deviation and has little impact on subsequent purchases. At this time, the system can maintain the current system maintenance cost of the raw materials to be predicted to save processing flow.

[0057] In an embodiment of the present application, when the cost deviation rate is greater than or equal to the preset deviation rate, that is, the target system maintenance cost is the predicted cost, the procurement system can issue a prompt to update the cost of the raw materials to be predicted, so that the technical salesperson can promptly update the cost of the raw materials to be predicted maintained in the system to ensure the accuracy of subsequent procurement data.

[0058] Figure 2 This is a structural block diagram of a device for predicting raw material costs in a procurement system provided in an embodiment of the present application. Figure 2 As shown, the embodiment of the present application also provides a device for predicting the cost of raw materials in a procurement system, and the device may include:

[0059] The memory 410 is configured to store instructions.

[0060] The processor 420 is configured to call instructions from the memory 410 and implement the above-mentioned method for predicting the cost of raw materials in a procurement system when executing the instructions.

[0061] An embodiment of the present application also provides a machine-readable storage medium having instructions stored thereon, the instructions being used to enable a machine to execute the above-mentioned method for predicting the cost of raw materials in a procurement system.

[0062] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0063] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0064] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0065] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0066] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0067] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0068] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0069] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0070] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for predicting raw material costs in a procurement system, characterized in that: The method comprises: Obtain multiple historical costs of raw materials to be forecasted in the procurement system within a preset time period; Determining, according to the multiple historical costs, a fluctuation ratio corresponding to each of the historical costs; Determine a maximum historical cost and a minimum historical cost among the multiple historical costs according to the fluctuation ratio, the preset peak cutting coefficient and the preset valley cutting coefficient; Performing peak shaving processing and valley shaving processing on the maximum historical cost and the minimum historical cost among the multiple historical costs, respectively, to obtain multiple corrected historical costs; The forecast cost of the raw material to be forecasted is determined according to the revised multiple historical costs.

2. The method according to claim 1, characterized in that The determining, according to the plurality of historical costs, the fluctuation ratio corresponding to each of the historical costs comprises: Obtaining timestamp information of each of the historical costs; Determine, according to the timestamp information and the multiple historical costs, an average of the historical costs corresponding to the historical costs before the timestamp corresponding to each of the multiple historical costs; The fluctuation ratio corresponding to each of the historical costs is determined based on the historical costs and the historical cost averages corresponding to each of the historical costs.

3. The method according to claim 1, characterized in that The determining of the maximum historical cost and the minimum historical cost among the multiple historical costs according to the fluctuation ratio, the preset peak cutting coefficient and the preset valley cutting coefficient includes: Compare the fluctuation ratio corresponding to each of the multiple historical costs with the preset peak-cutting coefficient and the preset valley-cutting coefficient respectively; Determine the historical cost corresponding to the fluctuation ratio greater than the preset peak shaving coefficient as the maximum historical cost; The historical cost corresponding to the fluctuation ratio less than the preset valley cutting coefficient is determined as the maximum historical cost.

4. The method according to claim 1, characterized in that: The peak shaving process and valley shaving process are respectively performed on the maximum historical cost and the minimum historical cost in the multiple historical costs to obtain the corrected multiple historical costs, including: Performing peak shaving processing on the maximum historical cost according to a preset peak shaving correction coefficient to obtain a corrected historical cost; and The minimum historical cost is subjected to valley cutting processing according to a preset valley cutting correction coefficient to obtain a corrected historical cost.

5. The method according to claim 1, characterized in that The step of determining the forecast cost of the raw material to be forecasted according to the corrected multiple historical costs includes: Obtaining timestamp information corresponding to the corrected multiple historical costs; grouping the corrected multiple historical costs according to the timestamp information to obtain multiple historical cost groups; determining a mean historical cost for each of the historical cost groups; The weighted summation process is performed on the historical cost means corresponding to the multiple historical cost groups to obtain the predicted cost.

6. The method according to claim 1, characterized in that The method further comprises: In response to a user input, the preset peak clipping coefficient and / or the preset valley clipping coefficient is updated.

7. The method according to claim 1, characterized in that The method further comprises: Obtaining the current system maintenance cost of the raw materials to be predicted in the procurement system; determining a cost deviation rate based on the predicted cost and the current system maintenance cost; The target system maintenance cost of the raw materials to be predicted in the procurement system is determined according to the cost deviation rate and the preset deviation rate.

8. The method according to claim 7, characterized in that The step of determining the target system maintenance cost of the raw materials to be predicted in the procurement system according to the cost deviation rate and the preset deviation rate includes: comparing the cost deviation rate with a preset deviation rate; When the cost deviation rate is greater than or equal to the preset deviation rate, the predicted cost is determined as the target system maintenance cost of the raw material to be predicted; When the cost deviation rate is less than the preset deviation rate, the current system maintenance cost is determined as the target system maintenance cost of the raw material to be predicted.

9. A device for predicting raw material costs in a procurement system, characterized in that: include: a memory configured to store instructions; as well as A processor is configured to call the instructions from the memory and implement the method for predicting raw material costs in a procurement system according to any one of claims 1 to 8 when executing the instructions.

10. A machine-readable storage medium, characterized in that: The machine-readable storage medium stores instructions for causing a machine to execute the method for predicting raw material costs in a procurement system according to any one of claims 1 to 8.

Images