Production cost management method

Abstract

The invention relates to a production cost management method. According to the method, the basic sub-cost proportion of each team is directly predicted according to the target work order information through the cost splitting model, manual setting of splitting causes is not needed, the efficiency of production cost management is improved, elastic cost distribution is introduced, and the distribution mode of the target elastic cost is determined according to the use condition of the elastic cost in the team history. The method improves the rationality of elastic cost distribution, can effectively adapt to the influence of factors such as a complex production environment and market fluctuation, and improves the accuracy of production cost management.

Description

Technical Field

[0001] The present invention is applicable to the field of cost management, and in particular relates to a production cost management method. Background Art

[0002] Currently, in the production cost management scenario, part of the production costs are still calculated to the management department rather than the cost center corresponding to each work team, thereby reducing the accuracy of the management side's statistics and simulation of production costs.

[0003] The existing method proposes to split the production cost into the cost center corresponding to each team according to the splitting driver when the production cost splitting driver is configured, which improves the refinement of production cost management. However, the production cost splitting drivers corresponding to various work order information may be different, and the management personnel need to manually configure or select the appropriate splitting driver, resulting in poor efficiency of production cost management.

[0004] In addition, due to factors such as market fluctuations and production environment, the budget allocated to the team may not match the resources it requires, which in turn leads to poor accuracy in production cost management.

[0005] Therefore, how to improve the efficiency and accuracy of production cost management has become an urgent problem to be solved. Summary of the invention

[0006] In view of this, an embodiment of the present invention provides a production cost management method to solve the problem.

[0007] A production cost management method is provided, the method comprising:

[0008] Obtain target work order information and several corresponding historical work order information, and determine the reference cost ratio according to the elastic cost ratios corresponding to each historical work order information;

[0009] Obtaining the overall cost corresponding to the target work order information, and determining a target basic cost and a target elastic cost according to the reference cost ratio and the overall cost;

[0010] Input the target work order information into the trained cost splitting model, and output the basic sub-cost ratios corresponding to the M teams;

[0011] Determine the target basic sub-costs corresponding to the M teams respectively according to the target basic cost and the ratio of the basic sub-costs corresponding to the M teams respectively;

[0012] For any team, obtain several historical elastic sub-costs corresponding to the team, and determine the cost fluctuation evaluation value, predicted elastic sub-cost and reference elastic sub-cost corresponding to the team according to each historical elastic sub-cost;

[0013] Sorting the M teams according to the cost fluctuation evaluation value to obtain a sorting result, and determining the target elastic sub-costs corresponding to the M teams respectively according to the target elastic cost, the sorting result, the predicted elastic sub-costs corresponding to the M teams respectively, and the reference elastic sub-costs;

[0014] For any team, the target basic sub-cost and the target elastic sub-cost corresponding to the team are added together, and the added result is used as the target sub-cost corresponding to the team.

[0015] Compared with the prior art, the present invention has the following beneficial effects:

[0016] The cost splitting model can be used to directly predict the basic sub-cost ratio of each team based on the target work order information. There is no need to manually set the splitting motivation, which improves the efficiency of production cost management. Flexible cost allocation is introduced to determine the target flexible cost allocation method based on the team's historical use of flexible costs, thereby improving the rationality of flexible cost allocation and being able to effectively adapt to the influence of complex production environments and market fluctuations, thereby improving the accuracy of production cost management. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the prior art description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative labor.

[0018] Figure 1 This is a schematic diagram of an application environment of a production cost management method provided by Embodiment 1 of the present invention;

[0019] Figure 2 It is a flowchart of a production cost management method provided in Embodiment 1 of the present invention; DETAILED DESCRIPTION

[0020] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0021] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0022] It should also be understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0023] As used in the present specification and the appended claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]", depending on the context.

[0024] In addition, in the description of the present specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0025] References to "one embodiment" or "some embodiments" etc. described in the specification of the present invention mean that one or more embodiments of the present invention include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0026] The embodiments of the present invention can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0027] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0028] It should be understood that the order of execution of the steps in the following embodiments does not imply a precedence of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0029] In order to illustrate the technical solution of the present invention, specific embodiments are provided below for illustration.

[0030] A production cost management method provided in the first embodiment of the present invention can be applied in the following aspects: Figure 1 The Enterprise Resource Planning (ERP) system in the application environment, among which the Production Management System (PMS), marketing system, etc. can communicate with the data middle platform, and the data middle platform communicates with the enterprise resource planning system. The production management system can be used for enterprise production process management and optimization. The data middle platform can be used to collect, store, integrate, process and analyze multi-source heterogeneous data inside and outside the enterprise, providing enterprises with unified data services and data application capabilities. The enterprise resource planning system can include financial management, production management, supply chain management, resource management and other functions.

[0031] See also Figure 2 , is a flow chart of a production cost management method provided by Embodiment 1 of the present invention. The above production cost management method can be applied to Figure 1 The enterprise resource planning system in the production management system receives the target work order information, overall cost and other information provided by the production management system, and determines the historical work order information and elastic cost ratio corresponding to the target work order information from the database. The enterprise resource planning system is deployed with a trained cost splitting model. Figure 2 As shown, the production cost management method may include the following steps:

[0032] Step S201 , obtaining target work order information and several pieces of historical work order information corresponding thereto, and determining a reference cost ratio according to elastic cost ratios corresponding to each piece of historical work order information.

[0033] Among them, the target work order information may refer to the work order information that currently needs to be cost managed. The work order information may include information such as equipment, work content, work team, planned construction period, number of operations, and related teams. The historical work order information may refer to the work order information that has been cost managed. The elastic cost ratio may refer to the ratio of the elastic cost corresponding to the historical work order information to the overall historical cost. The reference cost ratio may refer to the ratio of the elastic cost corresponding to the target work order information to the overall cost.

[0034] Specifically, the correspondence between historical work order information and target work order information can be determined by similarity calculation. The specific means of similarity calculation can be cosine similarity, Euclidean distance, etc. It should be noted that both historical work order information and target work order information need to be represented in the form of word vectors or encoding vectors to facilitate similarity calculation.

[0035] Optionally, a reference cost ratio is determined according to elastic cost ratios corresponding to each historical work order information, including:

[0036] Calculate the mean of each elastic cost ratio and use the mean calculation result as the reference cost ratio.

[0037] Among them, several historical work order information corresponding to the target work order information should be similar to the job-related content contained in the target work order information. Therefore, the average of the elastic cost ratios corresponding to each historical work order information can be used as the reference cost ratio of the target work order information.

[0038] Step S202, obtaining the overall cost corresponding to the target work order information, and determining the target basic cost and the target flexible cost according to the reference cost ratio and the overall cost.

[0039] Among them, the overall cost can refer to the total cost corresponding to the target work order information, the target basic cost can refer to the cost allocated according to the job content, and the target elastic cost can be used to adapt to scenarios such as market fluctuations and complex production environments. The sum of the target basic cost and the target elastic cost is the overall cost.

[0040] Optionally, based on the reference cost ratio and the overall cost, a target base cost and a target flexible cost are determined, including:

[0041] Multiply the reference cost ratio and the overall cost to obtain a multiplication result, and use the multiplication result as the target elastic cost;

[0042] Subtract the overall cost from the target elastic cost, and use the result as the target basic cost.

[0043] Among them, since the reference cost ratio can represent the ratio of the elastic cost corresponding to the target work order information to the overall cost, the result of multiplying the reference cost ratio and the overall cost is taken as the target elastic cost.

[0044] In this embodiment, the overall cost is divided into two parts: a target basic cost and a target flexible cost, and the two parts are allocated separately. Therefore, the sum of the target basic cost and the target flexible cost is the overall cost, that is, the result of subtracting the overall cost from the target flexible cost is the target basic cost.

[0045] Step S203: input the target work order information into the trained cost splitting model, and output the basic sub-cost ratios corresponding to the M teams.

[0046] Among them, the trained cost splitting model can be used to determine the basic sub-cost ratio allocated to each team according to the input work order information, and the sum of the basic sub-cost ratios corresponding to the M teams is 1.

[0047] Optionally, the cost splitting model training process includes:

[0048] Obtain reference work order information and reference basic sub-cost ratios corresponding to M teams;

[0049] The reference work order information is used as the training input data, and the reference proportion vector formed by the reference basic sub-cost proportions corresponding to the M teams is used as the label data;

[0050] Input the training input data into the cost splitting model, and output the predicted proportion vector formed by the predicted basic sub-cost proportions corresponding to the M teams;

[0051] The training loss is calculated based on the reference scale vector, the predicted scale vector and the preset loss function;

[0052] According to the training loss, the parameters of the cost splitting model are updated until the training loss converges to obtain a trained cost splitting model.

[0053] Among them, multiple reference work order information and their corresponding label data can be obtained to train the cost splitting model. The reference work order information can refer to the work order information that has been cost allocated, and the reference basic sub-cost ratio can refer to the ratio of the basic sub-cost allocated to the corresponding team to the reference cost corresponding to the reference work order information.

[0054] Specifically, the loss function can adopt the mean square error loss function. Furthermore, the implementer can add a constraint function. The constraint function is specifically the mean square error loss calculation of the sum of each element in the prediction proportion vector and 1 to ensure that the sum of the predicted sub-cost proportions corresponding to the M teams is 1.

[0055] Step S204, determining the target basic sub-costs corresponding to the M teams respectively according to the target basic cost and the proportions of the basic sub-costs corresponding to the M teams respectively.

[0056] The target basic sub-cost may refer to the basic sub-cost allocated to the corresponding team.

[0057] Optionally, according to the target basic cost and the proportion of the basic sub-costs corresponding to the M teams, the target basic sub-costs corresponding to the M teams are determined, including:

[0058] For any team, multiply the basic sub-cost ratio corresponding to the team and the target basic cost, and use the multiplication result as the target basic sub-cost of the corresponding team;

[0059] Traverse the M teams and obtain the target basic sub-costs corresponding to the M teams respectively.

[0060] Among them, the sum of the target basic sub-costs corresponding to the M teams is equal to the target basic cost.

[0061] Step S205, for any team, obtain several historical elastic sub-costs corresponding to the team, and determine the cost fluctuation evaluation value, predicted elastic sub-cost and reference elastic sub-cost of the corresponding team according to each historical elastic sub-cost.

[0062] Among them, the historical elastic sub-cost may refer to the elastic sub-cost consumed by the corresponding team under other historical work order information, rather than the allocated elastic sub-cost. It should be noted that the historical elastic sub-cost should be the elastic sub-cost corresponding to the most recent work order information of the corresponding team.

[0063] The cost fluctuation evaluation value can be used to measure the fluctuation of the historical elastic sub-cost usage of the corresponding team. The predicted elastic sub-cost can refer to the elastic sub-cost predicted based on the historical elastic sub-cost. The reference elastic sub-cost can refer to the threshold of the elastic sub-cost that the corresponding team needs to use.

[0064] Optionally, according to each historical elastic sub-cost, the cost fluctuation evaluation value, predicted elastic sub-cost and reference elastic sub-cost of the corresponding team are determined, including:

[0065] Calculate the variance based on each historical elastic sub-cost, and use the variance calculation result as the cost fluctuation evaluation value of the corresponding team;

[0066] The minimum value among all historical elastic sub-costs is used as the reference elastic sub-cost of the corresponding team;

[0067] Input each historical elastic sub-cost into the trained time series forecasting model and output the predicted elastic sub-cost of the corresponding team.

[0068] Among them, the trained time series prediction model can adopt a long short-term memory neural network model, a time domain convolutional network model, etc., and each historical elastic sub-cost is sorted in chronological order and then input into the trained time series prediction model.

[0069] Step S206, sorting the M teams according to the cost fluctuation evaluation value to obtain a sorting result, and determining the target elastic sub-costs corresponding to the M teams according to the target elastic cost, the sorting result, the predicted elastic sub-costs corresponding to the M teams, and the reference elastic sub-costs.

[0070] Among them, the sorting is carried out in ascending order, and the target elastic sub-cost can refer to the elastic sub-cost allocated to the corresponding team.

[0071] Optionally, according to the target elastic cost, the sorting result, the predicted elastic sub-costs corresponding to the M shifts, and the reference elastic sub-costs, the target elastic sub-costs corresponding to the M shifts are determined, including:

[0072] Set allocation status for each of the M teams. The allocation status corresponding to each of the M teams is initially unallocated, and the target elastic cost is used as the intermediate cost.

[0073] The team that is in the unassigned state and ranked first in the sorting results is used as the team to be assigned;

[0074] Add up the reference elastic sub-costs corresponding to the M-1 teams except the team to be assigned, and use the added result as the temporary reserved cost;

[0075] Subtract the intermediate cost from the temporary reserved cost to obtain the temporary allocated cost;

[0076] If the predicted elastic sub-cost corresponding to the to-be-assigned team is greater than the temporary allocation cost, and the temporary allocation cost is greater than the reference elastic sub-cost corresponding to the to-be-assigned team, the temporary allocation cost is used as the target elastic sub-cost corresponding to the to-be-assigned team;

[0077] If the predicted elastic sub-cost corresponding to the to-be-assigned team is greater than the temporary allocation cost, and the temporary allocation cost is less than the reference elastic sub-cost corresponding to the to-be-assigned team, the reference elastic sub-cost is used as the target elastic sub-cost corresponding to the to-be-assigned team;

[0078] If the predicted elastic sub-cost corresponding to the to-be-assigned team is less than the temporary allocation cost, the predicted elastic sub-cost is used as the target elastic sub-cost corresponding to the to-be-assigned team;

[0079] Subtract the intermediate cost from the target elastic sub-cost corresponding to the shift to be assigned, and update the intermediate cost with the subtraction result;

[0080] Set the allocation status of the team to be allocated to the allocated status;

[0081] Return to the step of setting the unassigned and top-ranked shift in the sorting result as the shift to be assigned, and then set the assignment status of the shift to be assigned to the assigned status, until the assignment statuses of all shifts are assigned, and obtain the target elastic sub-costs corresponding to the M shifts.

[0082] The allocation status may include an unallocated status and an allocated status.

[0083] Specifically, if the predicted elastic sub-cost corresponding to the to-be-assigned team is greater than the temporary allocation cost, it means that if the predicted elastic sub-cost required by the to-be-assigned team is met at this time, the reference elastic sub-costs of other teams may not be met, thereby reducing the rationality of the elastic sub-cost allocation. Therefore, the larger value of the temporary allocation cost and the reference elastic sub-cost corresponding to the to-be-assigned team is used as the target elastic sub-cost.

[0084] Step S207: for any team, add the target basic sub-cost and the target elastic sub-cost corresponding to the team, and use the added result as the target sub-cost of the corresponding team.

[0085] The target sub-cost may refer to the cost allocated to the corresponding team from the overall cost.

[0086] In this embodiment, the basic sub-cost ratio of each team is directly predicted based on the target work order information through the cost splitting model, without the need to manually set the splitting motivation, thereby improving the efficiency of production cost management, introducing flexible cost allocation, and determining the target flexible cost allocation method based on the team's historical use of flexible costs. This improves the rationality of flexible cost allocation and can effectively adapt to the influence of factors such as complex production environments and market fluctuations, thereby improving the accuracy of production cost management.

[0087] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0088] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0089] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such 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 invention, and should be included in the protection scope of the present invention.

Claims

1. A production cost management method, characterized in that: The production cost management method comprises: Obtain target work order information and several corresponding historical work order information, and determine the reference cost ratio according to the elastic cost ratios corresponding to each historical work order information; Obtaining the overall cost corresponding to the target work order information, and determining a target basic cost and a target elastic cost according to the reference cost ratio and the overall cost; Input the target work order information into the trained cost splitting model, and output the basic sub-cost ratios corresponding to the M teams; Determine the target basic sub-costs corresponding to the M teams respectively according to the target basic cost and the ratio of the basic sub-costs corresponding to the M teams respectively; For any team, obtain several historical elastic sub-costs corresponding to the team, and determine the cost fluctuation evaluation value, predicted elastic sub-cost and reference elastic sub-cost corresponding to the team according to each historical elastic sub-cost; Sorting the M teams according to the cost fluctuation evaluation value to obtain a sorting result, and determining the target elastic sub-costs corresponding to the M teams respectively according to the target elastic cost, the sorting result, the predicted elastic sub-costs corresponding to the M teams respectively, and the reference elastic sub-costs; For any team, the target basic sub-cost and the target elastic sub-cost corresponding to the team are added together, and the added result is used as the target sub-cost corresponding to the team.

2. The production cost management method according to claim 1, characterized in that: Determining the reference cost ratio according to the elastic cost ratios corresponding to each historical work order information includes: The average of each elastic cost ratio is calculated, and the average calculation result is used as the reference cost ratio.

3. The production cost management method according to claim 1, characterized in that: The determining of the target basic cost and the target flexible cost according to the reference cost ratio and the overall cost includes: Multiplying the reference cost ratio and the overall cost to obtain a multiplication result, and using the multiplication result as the target elastic cost; The overall cost and the target elastic cost are subtracted from each other, and the subtraction result is used as the target basic cost.

4. The production cost management method according to claim 1, characterized in that: The training process of the cost splitting model includes: Obtain reference work order information and reference basic sub-cost ratios corresponding to the M teams; The reference work order information is used as training input data, and the reference proportion vector formed by the reference basic sub-cost proportions corresponding to the M teams is used as label data; Input the training input data into the cost splitting model, and output a predicted proportion vector formed by the predicted basic sub-cost proportions corresponding to the M teams respectively; Calculating a training loss according to the reference scale vector, the predicted scale vector and a preset loss function; According to the training loss, the parameters of the cost splitting model are updated until the training loss converges to obtain the trained cost splitting model.

5. The production cost management method according to claim 1, characterized in that: The determining the target basic sub-costs corresponding to the M teams respectively according to the target basic cost and the proportions of the basic sub-costs corresponding to the M teams respectively includes: For any team, multiply the basic sub-cost ratio corresponding to the team by the target basic cost, and use the multiplication result as the target basic sub-cost corresponding to the team; The M teams are traversed to obtain the target basic sub-costs respectively corresponding to the M teams.

6. The production cost management method according to claim 1, characterized in that: Determining the cost fluctuation evaluation value, predicted elastic sub-cost and reference elastic sub-cost corresponding to the team according to each historical elastic sub-cost includes: Calculate the variance based on each historical elastic sub-cost, and use the variance calculation result as the cost fluctuation evaluation value corresponding to the team; The minimum value among the historical elastic sub-costs is used as the reference elastic sub-cost corresponding to the team; Each historical elastic sub-cost is input into the trained time series forecasting model, and the predicted elastic sub-cost corresponding to the team is output.

7. The production cost management method according to any one of claims 1 to 6, characterized in that: Determining the target elastic sub-costs corresponding to the M shifts respectively according to the target elastic cost, the ranking result, the predicted elastic sub-costs corresponding to the M shifts respectively, and the reference elastic sub-costs, including: Setting allocation states for the M teams respectively, wherein the allocation states corresponding to the M teams are initially unallocated, and the target elastic cost is used as the intermediate cost; The team in the sorting result that is in the unassigned state and ranked the highest is used as the team to be assigned; Add the reference elastic sub-costs corresponding to the M-1 teams except the team to be assigned, and use the added result as the temporary reserved cost; Subtracting the intermediate cost from the temporary reserved cost to obtain a temporary allocated cost; If the predicted elastic sub-cost corresponding to the to-be-assigned team is greater than the temporary allocation cost, and the temporary allocation cost is greater than the reference elastic sub-cost corresponding to the to-be-assigned team, the temporary allocation cost is used as the target elastic sub-cost corresponding to the to-be-assigned team; If the predicted elastic sub-cost corresponding to the to-be-assigned team is greater than the temporary allocation cost, and the temporary allocation cost is less than the reference elastic sub-cost corresponding to the to-be-assigned team, the reference elastic sub-cost is used as the target elastic sub-cost corresponding to the to-be-assigned team; If the predicted elastic sub-cost corresponding to the to-be-assigned team is less than the temporary allocation cost, the predicted elastic sub-cost is used as the target elastic sub-cost corresponding to the to-be-assigned team; Subtract the intermediate cost from the target elastic sub-cost corresponding to the to-be-assigned shift, and update the intermediate cost with the subtraction result; Setting the allocation status corresponding to the to-be-allocated team to the allocated status; Return to the step of setting the unassigned team with the highest ranking in the sorting result as the team to be assigned to the step of setting the assignment status corresponding to the team to be assigned to the assigned status, until the assignment statuses corresponding to all teams are assigned, thereby obtaining the target elastic sub-costs corresponding to the M teams.

Images