Cost calculation method and device
By preprocessing and optimizing the calculation path of multi-source cost factor data, the accuracy and efficiency problems of traditional cost calculation methods when dealing with changes in complex dynamic data are solved, and efficient and accurate cost prediction is achieved.
Patent Information
- Application Number
- CN202510209309.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-25
- Publication Date
- 2025-07-04
AI Technical Summary
Traditional cost calculation methods are difficult to deal with complex and dynamic multi-source data changes in real time, and cannot identify the implicit and nonlinear relationships between data, resulting in a significant reduction in the accuracy and efficiency of cost calculations.
Preprocess the multi-source cost factor data, determine the key data, generate the calculation priority, generate the optimal cost calculation path according to the priority, calculate the predicted cost based on the historical and current data, and perform weighted summing.
Real-time response to complex dynamic multi-source data is realized, implicit and nonlinear relationships are identified, and the accuracy and efficiency of cost calculation are improved.
Smart Images
Figure CN120258852A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the technical field of cost calculation, and specifically relates to a cost calculation method and device. Background Art
[0002] With the rapid development of the global economy, the demand for cost calculation and control in scenarios such as enterprise project management, supply chain optimization, and financial decision-making is increasing.
[0003] However, traditional cost calculation methods usually rely on static models and rule-driven calculation methods, making it difficult to respond to complex and dynamic multi-source data changes in real time and identify implicit and non-linear relationships between data, resulting in a significant reduction in the accuracy and efficiency of cost calculation. Summary of the Invention
[0004] Embodiments of this application provide a cost calculation method and device to solve the technical problem that traditional cost calculation methods usually rely on static models and rule-driven calculation methods, making it difficult to respond to complex and dynamic multi-source data changes in real time and identify implicit and non-linear relationships between data, resulting in a significant reduction in the accuracy and efficiency of cost calculation.
[0005] In a first aspect, embodiments of this application provide a cost calculation method, including: Preprocess multi-source cost factor data to obtain preprocessed data; Based on the causal relationship between the preprocessed data and the correlation with historical preprocessed data, determine the key data in the preprocessed data; Generate a calculation priority for the corresponding cost factor based on the influence degree of the key data on cost calculation; Generate an optimal cost calculation path with the cost factor as the node in the order from high to low according to the calculation priority; Based on the historical data and current data of multiple nodes in the optimal cost calculation path, calculate the predicted cost of each node according to the optimal cost calculation path; Perform weighted summation on the predicted costs of each node to obtain the total predicted cost.
[0006] In one embodiment, the determining the key data in the preprocessed data based on the causal relationship between the preprocessed data and the correlation with historical preprocessed data includes: Based on the change synchronization between the preprocessed data and the proximity of the generation time points of the source data corresponding to the preprocessed data, determine whether there is a causal relationship between the preprocessed data; Determine whether there is a correlation between the preprocessed data and the historical preprocessed data based on the relationship between the correlation degree between the preprocessed data and the historical preprocessed data and the correlation degree threshold; Determine the preprocessed data with both the causal relationship and the correlation as key data.
[0007] In one embodiment, after obtaining the total prediction cost by weighted summation of the prediction costs of each node, it includes: Calculate the confidence level of the total prediction cost; When the confidence level is less than the confidence level threshold, identify the risks in the process of calculating the prediction cost of each node, and recalculate the total prediction cost based on the assessment of the risks.
[0008] In one embodiment, identifying the risks in the process of calculating the prediction cost of each node and recalculating the total prediction cost based on the assessment of the risks includes: Identify the risks of uncertain cost factors and cross-source data inconsistency in the process of calculating the prediction cost of each node; Evaluate the risk of the uncertain cost factors to obtain a first risk value; Evaluate the risk of cross-source data inconsistency to obtain a second risk value; Perform weighted summation on the first risk value and the second risk value to obtain a comprehensive risk value; When the comprehensive risk value is greater than or equal to the risk threshold, reduce the weight of the uncertain cost factors, correct the inconsistent cross-source data, and then return to the step of preprocessing the multi-source cost factor data to obtain preprocessed data until the total prediction cost is obtained again.
[0009] In one embodiment, after obtaining the total prediction cost by weighted summation of the prediction costs of each node, it includes: Collect the feedback of the cost calculation user, and adjust the structure and generation method of the optimal cost calculation path based on the feedback; Add the structures and cost methods before and after the adjustment of the optimal cost calculation path to the knowledge base.
[0010] In one embodiment, after obtaining the total prediction cost by weighted summation of the prediction costs of each node, it includes: Based on the comparison between the total prediction cost and the historical total prediction cost, determine the defects of the first cost control strategy corresponding to the total prediction cost relative to the second cost control strategy corresponding to the historical total prediction cost; Optimize the strategy for the defects to generate a target cost control strategy.
[0011] In a second aspect, an embodiment of the present application provides a cost calculation device, including: A data preprocessing module, configured to: preprocess multi-source cost factor data to obtain preprocessed data; A key data determination module, configured to: determine key data in the preprocessed data based on the causal relationship between the preprocessed data and the correlation with historical preprocessed data; A priority generation module: configured to: generate a calculation priority for corresponding cost factors based on the influence degree of the key data on cost calculation; A calculation path generation module, configured to: generate an optimal cost calculation path with the cost factors as nodes in the order from high to low of the calculation priority; A node cost prediction module, configured to: calculate the predicted cost of each node according to the optimal cost calculation path based on the historical data and current data of multiple nodes in the optimal cost calculation path; A total cost prediction module, configured to: perform weighted summation on the predicted costs of each node to obtain a total predicted cost.
[0012] In a third aspect, an embodiment of the present application provides an electronic device, including a processor and a memory storing a computer program, and when the processor executes the program, the steps of the cost calculation method described in the first aspect are implemented.
[0013] In a fourth aspect, an embodiment of the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps of the cost calculation method described in the first aspect are implemented.
[0014] In a fifth aspect, an embodiment of the present application provides a non-transitory computer-readable storage medium, including a computer program, and when the computer program is executed by a processor, the steps of the cost calculation method described in the first aspect are implemented.
[0015] The cost calculation method and device provided by this application preprocess multi-source cost factor data to obtain preprocessed data. Based on the causal relationships between the preprocessed data and the correlation with historical preprocessed data, key data in the preprocessed data is determined. Based on the influence degree of the key data on cost calculation, the calculation priority of the corresponding cost factor is generated. An optimal cost calculation path with cost factors as nodes is generated in the order from high to low according to the calculation priority. Based on the historical data and current data of multiple nodes in the optimal cost calculation path, the predicted cost of each node is calculated according to the optimal cost calculation path, and the predicted costs of each node are weighted and summed to obtain the total predicted cost. This application first preprocesses multi-source data to enable better integration of data from different sources, and then fully explores the causal relationships between the preprocessed data and the correlation with historical preprocessed data to identify the implicit and non-linear relationships between the data, so as to accurately screen out the key data. Then, based on the key data, the calculation priority and the optimal cost calculation path are generated, so that the predicted cost of each node can be efficiently and accurately calculated according to the optimal cost calculation path, and then the total predicted cost can be obtained. In summary, this application can respond to complex and dynamic multi-source data changes in real time and identify the implicit and non-linear relationships between the data, thereby improving the accuracy and efficiency of cost calculation. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] In order to more clearly illustrate the technical solutions in this application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of this application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.
[0017] Figure 1 is one of the flow diagrams of the cost calculation method provided by the embodiments of this application; Figure 2 is the second flow diagram of the cost calculation method provided by the embodiments of this application; Figure 3 is the third flow diagram of the cost calculation method provided by the embodiments of this application; Figure 4 is the structural diagram of the cost calculation device provided by the embodiments of this application; Figure 5 is the structural diagram of the electronic device provided by the embodiments of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0018] To make the objectives, technical solutions, and advantages of the present application clearer, the technical solutions in the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Apparently, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.
[0019] It should be noted that in the description of the embodiments of the present application, the terms "include", "comprise", or any other variation thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or device including a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or device. Without further limitation, an element defined by the phrase "including a..." does not exclude the presence of additional identical elements in the process, method, article, or device including the element. The orientation or positional relationship indicated by terms such as "upper", "lower", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation to the present application. Unless otherwise clearly specified and limited, the terms "mounted", "connected", and "coupled" shall be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the internal communication of two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.
[0020] The terms "first", "second", etc. in the present application are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of the same category, and do not limit the number of objects. For example, the first object may be one or multiple. In addition, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates an "or" relationship between the associated objects before and after.
[0021] Figure 1 is one of the flow diagrams of the cost calculation method provided by the embodiments of the present application. Referring to Figure 1 , the embodiments of the present application provide a cost calculation method, which may include: 101. Preprocess the multi-source cost factor data to obtain preprocessed data; 102. Determine the key data in the preprocessed data based on the causal relationships between the preprocessed data and the correlations with the historical preprocessed data; 103. Generate the calculation priorities for the corresponding cost factors based on the impact degrees of the key data on cost calculation; 104. Generate the optimal cost calculation path with cost factors as nodes in the order from the highest to the lowest calculation priority; 105. Calculate the predicted costs of each node according to the optimal cost calculation path based on the historical data and current data of multiple nodes in the optimal cost calculation path; 106. Perform weighted summation on the predicted costs of each node to obtain the total predicted cost.
[0022] In step 101, modern cost calculation needs to process data from different sources, including ERP systems, financial databases, market data platforms, supply chain management systems, etc. The data from these sources have different forms, which can include structured data such as financial statement data and cost accounting data, as well as unstructured data such as project reports and procurement contracts. Due to the different data types and data qualities of each data, problems such as data missing, conflicts, and heterogeneity are often involved in the fusion process. Therefore, it is necessary to preprocess them, which can specifically include removing duplicate data, filling in missing data, format conversion, outlier detection and correction, validity and integrity verification, etc., so as to ensure data quality and data consistency.
[0023] In step 102, since each key data has its corresponding cost factor, the screening of key data is the screening of key cost factors.
[0024] In step 103, cost factors can be divided into material costs, labor costs, logistics costs, operation costs, maintenance costs, etc. Each key data has its corresponding cost factor. For each cost factor, all its corresponding key data are screened out, the comprehensive impact degree of all key data on cost calculation is determined, and all the comprehensive impact degrees are sorted from large to small. Based on this sorting, the calculation priorities from high to low are set for the cost factors corresponding to each comprehensive impact degree in turn.
[0025] In step 104, the optimal cost calculation path is the order of cost factor calculation, that is, each cost factor is calculated in the order from the highest to the lowest calculation priority to ensure that the cost factors with high calculation priorities are calculated first.
[0026] In steps 105 to 106, since cost prediction and weighting are performed on each cost factor, the finally obtained total predicted cost covers cost factors at multiple levels and dimensions, thus having a high accuracy rate.
[0027] The cost calculation method provided in this embodiment preprocesses multi-source cost factor data to obtain preprocessed data. Based on the causal relationships between the preprocessed data and the correlation with historical preprocessed data, the key data in the preprocessed data is determined. Based on the degree of influence of the key data on cost calculation, the calculation priority of the corresponding cost factors is generated. An optimal cost calculation path with cost factors as nodes is generated in the order of decreasing calculation priority. Based on the historical data and current data of multiple nodes in the optimal cost calculation path, the predicted cost of each node is calculated according to the optimal cost calculation path, and the predicted costs of each node are weighted and summed to obtain the total predicted cost. In this embodiment, the multi-source data is first preprocessed to enable better fusion of data from different sources, and then the causal relationships between the preprocessed data and the correlation with historical preprocessed data are fully explored to identify the implicit and non-linear relationships between the data, so as to accurately screen out the key data. Then, based on the key data, the calculation priority and the optimal cost calculation path are generated, so that the predicted cost of each node can be efficiently and accurately calculated according to the optimal cost calculation path, and then the total predicted cost is obtained. In summary, this embodiment can respond to complex and dynamic multi-source data changes in real time and identify the implicit and non-linear relationships between the data, thereby improving the accuracy and efficiency of cost calculation.
[0028] Figure 2 It is the second schematic flowchart of the cost calculation method provided by the embodiments of the present application. Refer to Figure 2 , in one embodiment, based on the causal relationships between the preprocessed data and the correlation with historical preprocessed data, determining the key data in the preprocessed data may include: 201. Determine whether there is a causal relationship between the preprocessed data based on the change synchronization between the preprocessed data and the proximity of the generation time points of the source data corresponding to the preprocessed data; 202. Determine whether there is a correlation between the preprocessed data and the historical preprocessed data based on the relationship between the correlation degree between the preprocessed data and the historical preprocessed data and the correlation degree threshold; 203. Determine the preprocessed data that simultaneously has the causal relationship and the correlation as the key data.
[0029] In step 201, when one of the two preprocessed data changes and the other preprocessed data also changes synchronously, it is determined that there may be a causal relationship in space between the two preprocessed data; when the time interval between the generation time points of the source data corresponding to one of the two preprocessed data and the source data corresponding to the other is within a preset range, it is determined that there may be a causal relationship in time between the two preprocessed data; and when there is a possibility of causal relationships in both space and time between the two preprocessed data, it can be determined that there is a causal relationship between the two preprocessed data.
[0030] In step 202, first calculate the correlation degree between a preprocessed data and its corresponding historical preprocessed data. When the correlation degree is greater than the correlation degree threshold, it can be determined that there is a correlation between the preprocessed data and its historical preprocessed data.
[0031] In step 203, when a preprocessed data has both a causal relationship with other preprocessed data and a correlation with its historical preprocessed data, it is considered that the dynamic change of the preprocessed data will affect other preprocessed data, and the preprocessed data can inherit the characteristics of the historical preprocessed data well. Thus, it can be determined that the preprocessed data is key data.
[0032] This embodiment uses the change synchronization and the proximity of the source data generation time points to accurately determine whether there is a causal relationship between the preprocessed data, and uses the relationship between the correlation degree and the correlation degree threshold to accurately determine whether there is a correlation between the preprocessed data and its historical preprocessed data. Thus, the preprocessed data that has both a causal relationship and a correlation can be determined as key data, realizing the accurate screening of key data.
[0033] Figure 3 is the third flowchart of the cost calculation method provided by the embodiment of the present application. Refer to Figure 3 , in one embodiment, after obtaining the total predicted cost by weighted summation of the predicted costs of each node, it may include: 301. Calculate the confidence level of the total predicted cost; 302. When the confidence level is less than the confidence level threshold, identify the risks of uncertain cost factors and cross-source data inconsistency risks in the process of calculating the predicted costs of each node; 303. Evaluate the risk of uncertain cost factors to obtain a first risk value; 304. Evaluate the risk of cross-source data inconsistency to obtain a second risk value; 305. Perform weighted summation on the first risk value and the second risk value to obtain a comprehensive risk value; 306. When the comprehensive risk value is greater than or equal to the risk threshold, reduce the weight of the uncertain cost factors, correct the inconsistent cross-source data, and then return to the step of preprocessing the multi-source cost factor data until the total predicted cost is obtained again.
[0034] In step 301, this confidence level is used to measure the calculation reliability of the total predicted cost.
[0035] In step 302, when the confidence level is less than the confidence threshold, it indicates that the calculation of the total predicted cost is not reliable, and the risks in the calculation process need to be avoided to improve the calculation reliability. In this embodiment, the risks of uncertain cost factors and inconsistent cross-source data in the process of calculating the predicted cost of each node are mainly identified.
[0036] In step 303, the risk of uncertain cost factors is the risk caused by cost factors with strong volatility. For example, when market fluctuations and policy changes occur frequently, it will cause drastic fluctuations in the material costs vulnerable to this impact. Then the cost factor of material costs will cause the risk of uncertain cost factors. At this time, the risk can be simulated and the cost fluctuation range that the risk may cause can be predicted, and then the first risk value can be determined according to this fluctuation range.
[0037] In step 304, that is, for the same data from different sources, compare its format, value, etc. for consistency, and determine the second risk value based on the size of the difference.
[0038] In step 305, the two risk values are weighted and summed to balance the impact of the two risks on the calculation.
[0039] In steps 305 to 306, when the comprehensive risk value is greater than or equal to the risk threshold, it indicates that at least one of the two risks has an impact on the calculation that cannot be ignored. For safety reasons, both risks are processed simultaneously, that is, by reducing the weight of the uncertain cost factors and correcting the inconsistent cross-source data, the simultaneous avoidance of the two risks is realized, and then the total predicted cost is recalculated to improve its confidence level.
[0040] Furthermore, risk thresholds can also be set for the first risk value and the second risk value respectively. When any of the first risk value, the second risk value, or the comprehensive risk value is greater than or equal to the corresponding risk threshold, an automatic alarm is triggered to prompt relevant personnel to take corresponding measures in a timely manner.
[0041] Furthermore, for the risk assessment, a risk assessment report can also be generated and presented in the form of charts, texts, or other customized forms, and it supports being exported in formats such as PDF and Excel.
[0042] When the total predicted cost calculation in this embodiment is unreliable, the risks of uncertain cost factors and cross-source data inconsistency are evaluated and weighted to obtain a comprehensive risk value that balances the two risks. Furthermore, when the comprehensive risk value is relatively large, it is determined that the processing time has arrived, so as to simultaneously avoid and process the two risks, and improve the reliability of the recalculated total predicted cost.
[0043] In one embodiment, after weighted summation of the predicted costs of each node to obtain the total predicted cost, it may include: Collect feedback from the cost calculation user, adjust the structure and generation method of the optimal cost calculation path based on the feedback, and add the structures and cost methods before and after the adjustment of the optimal cost calculation path to the knowledge base.
[0044] This embodiment combines the feedback of the cost calculation user to automatically adjust the structure and generation method of the optimal cost calculation path, ensuring flexibility in the cost calculation process, thereby gradually improving the adaptability and calculation accuracy for complex cost scenarios to meet user expectations. At the same time, adding the structures and cost methods before and after each adjustment to the knowledge base can achieve real-time update of the knowledge base, provide richer data support for subsequent cost calculations, and form a continuously optimized closed-loop process.
[0045] In one embodiment, after weighted summation of the predicted costs of each node to obtain the total predicted cost, it may include: Based on the comparison between the total predicted cost and the historical total predicted cost, determine the deficiencies of the first cost control strategy corresponding to the total predicted cost relative to the second cost control strategy corresponding to the historical total predicted cost, optimize the deficiencies in the strategy, and generate a target cost control strategy.
[0046] This embodiment can generate an optimized suggestion plan for the deficiencies of the cost control strategy. The plan can also be presented in the form of charts, texts, or other customized forms, and supports export to formats such as PDF and Excel, intuitively presenting the key cost factors affecting the total predicted cost, providing a clear cost optimization path, and giving data-driven decision support, such as how to reduce the impact of key cost factors and what alternative solutions can be selected, etc., to help users quickly identify high-risk cost factors and take effective countermeasures.
[0047] Next, the cost calculation device provided by the embodiments of the present application will be described. The cost calculation device described below can be mutually corresponding and referenced to the cost calculation method described above.
[0048] Figure 4 It is a schematic structural diagram of the cost calculation device provided by the embodiments of the present application. Refer to Figure 4 In this application, an embodiment provides a cost calculation device, which may include: The data preprocessing module 401 is configured to: preprocess the multi-source cost factor data to obtain preprocessed data; The key data determination module 402 is configured to: determine the key data in the preprocessed data based on the causal relationship between the preprocessed data and the correlation with the historical preprocessed data; The priority generation module 403 is configured to: generate the calculation priority of the corresponding cost factor based on the influence degree of the key data on the cost calculation; The calculation path generation module 404 is configured to: generate an optimal cost calculation path with the cost factor as the node in the order from high to low of the calculation priority; The node cost prediction module 405 is configured to: calculate the predicted cost of each node according to the optimal cost calculation path based on the historical data and the current data of multiple nodes in the optimal cost calculation path; The total cost prediction module 406 is configured to: perform weighted summation on the predicted costs of each node to obtain the total predicted cost.
[0049] The cost calculation device provided in this embodiment preprocesses the multi-source cost factor data to obtain preprocessed data, determines the key data in the preprocessed data based on the causal relationship between the preprocessed data and the correlation with the historical preprocessed data, generates the calculation priority of the corresponding cost factor based on the influence degree of the key data on the cost calculation, generates an optimal cost calculation path with the cost factor as the node in the order from high to low of the calculation priority, calculates the predicted cost of each node according to the optimal cost calculation path based on the historical data and the current data of multiple nodes in the optimal cost calculation path, and performs weighted summation on the predicted costs of each node to obtain the total predicted cost. In this embodiment, the multi-source data is preprocessed first to enable better fusion of data from different sources, and then the causal relationship between the preprocessed data and the correlation with the historical preprocessed data are fully explored to realize the identification of the implicit relationship and non-linear relationship between the data, so as to accurately screen out the key data, and then generate the calculation priority and the optimal cost calculation path based on the key data, so that the predicted cost of each node can be calculated efficiently and accurately according to the optimal cost calculation path, and then the total predicted cost can be obtained. In summary, this embodiment can respond to complex and dynamic multi-source data changes in real time, and identify the implicit relationship and non-linear relationship between the data, thereby improving the accuracy and efficiency of cost calculation.
[0050] In one embodiment, the key data determination module 402 is specifically configured to: Determine whether there is a causal relationship between the preprocessed data based on the change synchronization between the preprocessed data and the proximity of the generation time points of the source data corresponding to the preprocessed data; Determine whether there is a correlation between the preprocessed data and the historical preprocessed data based on the relationship between the correlation degree between the preprocessed data and the historical preprocessed data and the correlation degree threshold; Determine the preprocessed data with both the causal relationship and the correlation as key data.
[0051] In one embodiment, it further includes a risk processing module (not shown in the figure), which is used for: Calculate the confidence level of the total predicted cost; When the confidence level is less than the confidence level threshold, identify the risks in the process of calculating the predicted cost for each node, and recalculate the total predicted cost based on the assessment of the risks.
[0052] In one embodiment, the risk processing module is specifically used for: Identify the risks of uncertain cost factors and cross-source data inconsistency in the process of calculating the predicted cost for each node; Evaluate the risk of the uncertain cost factors to obtain a first risk value; Evaluate the risk of the cross-source data inconsistency to obtain a second risk value; Perform a weighted sum of the first risk value and the second risk value to obtain a comprehensive risk value; When the comprehensive risk value is greater than or equal to the risk threshold, reduce the weight of the uncertain cost factors, correct the inconsistent cross-source data, and then return to the step of preprocessing the multi-source cost factor data to obtain preprocessed data until the total predicted cost is obtained again.
[0053] In one embodiment, it further includes a feedback adjustment module (not shown in the figure), which is used for: Collect the feedback from the cost calculation user, and adjust the structure and generation method of the optimal cost calculation path based on the feedback; Add the structures and cost methods before and after the adjustment of the optimal cost calculation path to the knowledge base.
[0054] In one embodiment, it further includes a strategy optimization module (not shown in the figure), which is used for: Based on the comparison between the total predicted cost and the historical total predicted cost, determine the defects of the first cost control strategy corresponding to the total predicted cost relative to the second cost control strategy corresponding to the historical total predicted cost; Optimize the strategy for the defects to generate a target cost control strategy.
[0055] Figure 5 It is a schematic structural diagram of the electronic device provided by the embodiment of the present application, as Figure 5As shown in the figure, the electronic device may include: a processor 510, a communication interface 520, a memory 530, and a communication bus 540. Among them, the processor 510, the communication interface 520, and the memory 530 complete communication with each other through the communication bus 540. The processor 510 may call a computer program in the memory 530 to execute the steps of the cost calculation method, for example, including: Preprocess the multi-source cost factor data to obtain preprocessed data; Based on the causal relationship between the preprocessed data and the correlation with the historical preprocessed data, determine the key data in the preprocessed data; Generate the calculation priority of the corresponding cost factor based on the influence degree of the key data on the cost calculation; Generate an optimal cost calculation path with the cost factor as the node in the order from high to low according to the calculation priority; Based on the historical data and current data of multiple nodes in the optimal cost calculation path, calculate the predicted cost of each node according to the optimal cost calculation path; Perform weighted summation on the predicted costs of each node to obtain the total predicted cost.
[0056] In addition, when the logical instructions in the above-mentioned memory 530 are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.
[0057] On the other hand, the embodiment of the present application also provides a computer program product. The computer program product includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the steps of the cost calculation method provided in the above-mentioned various embodiments, for example, including: Preprocess the multi-source cost factor data to obtain preprocessed data; Determine the key data in the preprocessed data based on the causal relationships between the preprocessed data and the correlations with the historical preprocessed data; Generate the calculation priorities of the corresponding cost factors based on the influence degree of the key data on cost calculation; Generate an optimal cost calculation path with the cost factors as nodes in the order from high to low according to the calculation priorities; Based on the historical data and current data of multiple nodes in the optimal cost calculation path, calculate the predicted costs of each node according to the optimal cost calculation path; Perform weighted summation on the predicted costs of each node to obtain the total predicted cost.
[0058] On the other hand, an embodiment of the present application further provides a non-transitory computer-readable storage medium, on which a computer program is stored, and the computer program is used to enable a processor to execute the steps of the cost calculation method provided in the above embodiments, for example, including: Preprocess the multi-source cost factor data to obtain preprocessed data; Determine the key data in the preprocessed data based on the causal relationships between the preprocessed data and the correlations with the historical preprocessed data; Generate the calculation priorities of the corresponding cost factors based on the influence degree of the key data on cost calculation; Generate an optimal cost calculation path with the cost factors as nodes in the order from high to low according to the calculation priorities; Based on the historical data and current data of multiple nodes in the optimal cost calculation path, calculate the predicted costs of each node according to the optimal cost calculation path; Perform weighted summation on the predicted costs of each node to obtain the total predicted cost.
[0059] The non-transitory computer-readable storage medium may be any available medium or data storage device accessible by the processor, including but not limited to magnetic memories (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical memories (such as CDs, DVDs, BDs, HVDs, etc.), and semiconductor memories (such as ROMs, EPROMs, EEPROMs, non-volatile memories (NAND FLASH), solid state drives (SSDs)), etc.
[0060] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without creative labor.
[0061] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing 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.
[0062] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of each embodiment of the present application.
Claims
1. A costing method, characterized in that, Including: Preprocess multi-source cost factor data to obtain preprocessed data; Based on the causal relationships between the preprocessed data and the correlation with historical preprocessed data, determine the key data in the preprocessed data; Generate the calculation priority of the corresponding cost factor based on the influence degree of the key data on cost calculation; Generate an optimal cost calculation path with the cost factors as nodes in the order from high to low according to the calculation priority; Based on the historical data and current data of multiple nodes in the optimal cost calculation path, calculate the predicted cost of each node according to the optimal cost calculation path; Perform weighted summation on the predicted costs of each node to obtain the total predicted cost.
2. The cost calculation method according to claim 1, wherein The step of determining the key data in the preprocessed data based on the causal relationships between the preprocessed data and the correlation with historical preprocessed data includes: Based on the change synchronization between the preprocessed data and the proximity of the generation time points of the source data corresponding to the preprocessed data, determine whether there is a causal relationship between the preprocessed data; Based on the relationship between the correlation degree between the preprocessed data and historical preprocessed data and the correlation degree threshold, determine whether there is a correlation between the preprocessed data and the historical preprocessed data; Determine the preprocessed data that simultaneously has the causal relationship and the correlation as the key data.
3. The cost calculation method according to claim 1, wherein After performing weighted summation on the predicted costs of each node to obtain the total predicted cost, it includes: Calculate the confidence level of the total predicted cost; When the confidence level is less than the confidence level threshold, identify the risks in the process of calculating the predicted cost of each node, and recalculate the total predicted cost based on the assessment of the risks.
4. The costing method according to claim 3, characterized in that The step of identifying the risks in the process of calculating the predicted cost of each node and recalculating the total predicted cost based on the assessment of the risks includes: Identify the risks of uncertain cost factors and cross-source data inconsistency in the process of calculating the predicted cost of each node; Evaluate the risk of uncertain cost factors to obtain a first risk value; Evaluate the risk of cross-source data inconsistency to obtain a second risk value; Perform weighted summation on the first risk value and the second risk value to obtain a comprehensive risk value; When the comprehensive risk value is greater than or equal to the risk threshold, reduce the weight of the uncertain cost factors, correct the inconsistent cross-source data, and then return to the step of preprocessing the multi-source cost factor data to obtain preprocessed data until the total predicted cost is obtained again.
5. The costing method according to claim 1, wherein After performing weighted summation on the predicted costs of each node to obtain the total predicted cost, it includes: Collect the feedback of the cost calculation user, and adjust the structure and generation method of the optimal cost calculation path based on the feedback; Add the structures and cost methods before and after the adjustment of the optimal cost calculation path to the knowledge base.
6. The costing method according to claim 1, characterized in that, After performing weighted summation on the predicted costs of each node to obtain the total predicted cost, it includes: Based on the comparison between the total predicted cost and the historical total predicted cost, determine the deficiencies of the first cost control strategy corresponding to the total predicted cost relative to the second cost control strategy corresponding to the historical total predicted cost; Optimize the strategy for the deficiencies to generate a target cost control strategy.
7. A cost calculation device, characterized in that, Including: A data preprocessing module for preprocessing multi-source cost factor data to obtain preprocessed data; A key data determination module for determining the key data in the preprocessed data based on the causal relationship between the preprocessed data and the correlation with the historical preprocessed data; A priority generation module for generating the calculation priority of the corresponding cost factors based on the influence degree of the key data on the cost calculation; A calculation path generation module for generating an optimal cost calculation path with the cost factors as nodes in the order from high to low of the calculation priority; A node cost prediction module for calculating the predicted cost of each node according to the optimal cost calculation path based on the historical data and current data of multiple nodes in the optimal cost calculation path; A total cost prediction module for performing weighted summation on the predicted costs of each node to obtain the total predicted cost.
8. An electronic device, comprising a processor and a memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the cost calculation method according to any one of claims 1 to 6.
9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the cost calculation method according to any one of claims 1 to 6.
10. A non-transitory computer-readable storage medium, having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the cost calculation method according to any one of claims 1 to 6.