Material category demand decomposition method based on threshold analysis
By using a threshold-based method for decomposing material category requirements and revising procurement plans based on power engineering project forecasting models and implementation time periods, the problems of underreporting and over-procurement in power engineering material procurement were solved, thereby improving the accuracy and efficiency of procurement.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- BEIJING SGITG ACCENTURE INFORMATION TECH CO LTD
- Filing Date
- 2024-11-14
- Publication Date
- 2026-05-15
AI Technical Summary
The current procurement of materials for power engineering projects relies on subjective human decision-making, leading to underreporting of procurement, over-procurement, and instability in decision-making, which affects the cost-effectiveness and schedule of projects.
A threshold-based method for decomposing material category requirements is adopted. A standard material category matrix is obtained through a power engineering project prediction model. The difference matrix is then adjusted by combining the project implementation time period, and the procurement plan is adjusted by using threshold judgment.
It improved the accuracy of material procurement, reduced the timeliness deviation of the network model, optimized the procurement process, and reduced resource waste and inventory costs.
Smart Images
Figure CN122048221A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of power engineering material allocation technology, and more specifically to a method for decomposing material category requirements based on threshold analysis. Background Technology
[0002] In the field of power engineering, material procurement is a crucial link, directly affecting project cost control, schedule planning, and final construction quality. Traditional power engineering material procurement often relies on subjective human decision-making. While this approach allows for some judgment based on experience, it also has many shortcomings.
[0003] Due to the limitations of subjective human decision-making, procurement omissions frequently occur. In complex power engineering projects, a wide variety of materials with varying specifications are involved; even slight oversights can lead to the omission of critical materials, impacting the overall project schedule and quality. Furthermore, over-purchasing is another common problem arising from subjective human decision-making. Sometimes, to ensure sufficient supplies, procurement personnel may over-order certain materials, resulting not only in resource waste but also increased inventory costs and management complexity.
[0004] Human subjective decision-making is also influenced by various factors such as personal experience, knowledge level, and emotional state, leading to instability in procurement decisions. Different procurement personnel may have different judgments about the demand for the same material, and this difference further exacerbates the uncertainty and risk in the procurement process.
[0005] In summary, the procurement of power engineering materials currently relies heavily on subjective human decision-making. While this method is simple and easy to implement, it also has many drawbacks, such as underreporting of procurement, over-procurement, and instability in decision-making. These problems not only affect the cost-effectiveness of power engineering projects but may also adversely impact their smooth progress. Therefore, optimizing the procurement process for power engineering materials and improving its accuracy and efficiency has become an urgent issue to be addressed.
[0006] Existing technologies have developed network models for predicting material procurement plans. However, these models lack consideration for the impact of timeliness, leading to significant biases. Summary of the Invention
[0007] The purpose of this invention is to provide a method for decomposing material category requirements based on threshold analysis, which can improve the accuracy of material procurement quantity in the material procurement process.
[0008] To achieve the above objectives, embodiments of the present invention provide a method for decomposing material category requirements based on threshold analysis, including: Obtain the type of the currently submitted project and the corresponding material procurement plan; The project is input into a preset power engineering project prediction model to obtain the corresponding standard material category matrix; The material category requirements are determined based on the aforementioned material category procurement plan; The required material categories are placed into a preset material category table to update the material category table; The material category matrix is obtained by extracting valid data from the material category table based on the standard material category matrix. Obtain the expected implementation timeframe for the currently submitted project; Update the standard material category matrix according to the expected implementation period; Calculate the difference matrix between the material category matrix and the standard material category matrix; The material category procurement plan is revised based on the difference matrix.
[0009] Optionally, the power engineering project prediction model includes: The input layer is used to obtain the name, scale, keywords and location of the project, and combine them with a preset feature matrix of the name, scale, keywords and location to obtain combined feature input; The decision layer is used to perform feature iteration based on the combined feature input to obtain a one-dimensional feature sequence; The output layer contains multiple neurons, which are used to output each element in the standard material category matrix based on the one-dimensional feature sequence.
[0010] Optionally, the material category matrix is obtained by extracting valid data from the material category table based on the standard material category matrix, including: Project the boundaries of the standard material category matrix onto the material category matrix; Determine if there are non-zero values outside the projection area; If it is determined that there is a non-zero value outside the projection area, the projection area is augmented according to the location of the non-zero value, and the process returns to the step of determining whether there is a non-zero value outside the projection area. If it is determined that there are no non-zero values outside the projection area, the material category matrix is clipped according to the projection area.
[0011] Optionally, updating the standard material category matrix according to the expected implementation period includes: Determine the time period in which the expected implementation time falls; The standard material category matrix is updated according to the stated time period.
[0012] Optionally, the length of the time period is one of 5 days, 7 days, 10 days, 20 days or 1 month.
[0013] Optionally, updating the standard material category matrix according to the time period includes: The expected implementation time is broken down according to the time span of the time period to obtain multiple time periods; Update the standard material category matrix according to formula (1). (1) in, For the updated material category matrix, the first... The first category of supplies The value of each item For the material category matrix before the update, the first... The first category of supplies The value of each item The expected implementation time is defined by the number of time periods it spans. For the first time period The smoothing parameter value for each working day. For the first The number of working days occupied by the expected implementation time for each time period. The length of the time period is given.
[0014] Optionally, the procurement plan for the material categories is modified based on the difference matrix, including: For each element in the difference matrix, determine whether the element was added by an augmentation operation; If the element is determined to be added by an augmentation operation, determine whether the element is greater than or equal to a preset first threshold. If it is determined that the element is greater than or equal to the first threshold, the element is corrected to the first threshold. If it is determined that the element was not added by an augmentation operation, it is determined whether the element is greater than or equal to a preset second threshold. If the element is determined to be greater than or equal to the second threshold, the element is adjusted to the second threshold.
[0015] Through the above technical solution, the embodiments of the present invention provide a method for decomposing material category requirements based on threshold analysis. This method corrects the output value of the standard network model by introducing the actual implementation time period of the project, thereby reducing the bias of the network model that does not consider the time factor. Then, by combining the threshold for difference judgment, the accurate correction of the material category procurement plan is achieved.
[0016] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description section. Attached Figure Description
[0017] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart of a material category demand decomposition method based on threshold analysis according to an embodiment of the present invention; Figure 2 This is a structural block diagram of a power engineering project prediction model according to one embodiment of the present invention; Figure 3 This is a flowchart of a method for extracting valid data from a material category table based on a standard material category matrix, according to an embodiment of the present invention. Figure 4 This is a flowchart of a method for modifying a material category procurement plan based on a difference matrix according to an embodiment of the present invention. Detailed Implementation
[0018] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the scope of the present invention.
[0019] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application all comply with the relevant provisions of national laws and regulations. In the embodiments of this application, certain existing industry solutions such as software, components, and models may be mentioned. These should be considered exemplary, intended only to illustrate the feasibility of implementing the technical solution of this application, and do not imply that the applicant has already used or necessarily used such solutions.
[0020] like Figure 1 This is a flowchart of a material category demand decomposition method based on threshold analysis according to an embodiment of the present invention. Figure 1 In this method, the steps may include: In step S10, the type of the currently submitted project and the corresponding material category procurement plan are obtained; In step S11, the project is input into the preset power engineering project prediction model to obtain the corresponding standard material category matrix; In step S12, the material category requirements are determined according to the material category procurement plan; In step S13, the material category requirements are put into a preset material category table to update the material category table; In step S14, valid data is extracted from the material category table based on the standard material category matrix to obtain the material category matrix; In step S15, the expected implementation time period of the currently submitted project is obtained; In step S16, the standard material category matrix is updated according to the expected implementation period. In step S17, the difference matrix between the material category matrix and the standard material category matrix is calculated; In step S18, the material category procurement plan is revised based on the difference matrix.
[0021] In such Figure 1 In the method shown, step S10 can be used to specify the type of the currently submitted project and the corresponding material procurement plan. The project type can include, but is not limited to, the project name, location, project scale, number of personnel, and cost level. The corresponding material procurement plan can be the procurement quantity for each material category.
[0022] Step S11 can be used to input the project into a preset power engineering project prediction model to obtain the corresponding standard material category matrix. The power engineering project prediction model can be a pre-trained network model structure. The specific structure of the network model can be of various forms known to those skilled in the art. In one example of the present invention, the power engineering project prediction model can include, for example... Figure 2 The diagram shows an input layer 01, a decision layer 02, and an output layer 03. The input layer 01 acquires the project's name, scale, keywords, and location, combining them with a pre-defined feature matrix to obtain a combined feature input. Since the input to this power engineering project prediction model consists of relatively simple features such as the project name, location, scale, number of personnel, and cost level, and the output is a standard material category matrix, the input layer 01 expands the features by combining them with a pre-defined feature matrix, making the standard material category matrix output by the output layer 03 more accurate. The decision layer 02 iterates based on the combined feature input to obtain a one-dimensional feature sequence. The output layer 03 can contain multiple neurons to output each element of the standard material category matrix based on the one-dimensional feature sequence.
[0023] Step S12 is used to determine the material category requirements based on the material category procurement plan. These requirements can be for each material category, with corresponding procurement quantities specified for different models. Since the keywords for the material categories in the subsequent material category table are preset standard phrases, to avoid errors caused by manual keyword input in the material category procurement plan, step S12 can also replace the nouns of the material categories in the procurement plan with nouns from the standard phrases using keyword matching before determining the material category requirements. Specifically, this replacement method can involve setting multiple keywords corresponding to the nouns in the standard phrases, and then searching for and matching these keywords in the material category procurement plan to complete the noun replacement.
[0024] Step S13 can be used to put the material category requirements into a preset material category table to update the material category table, thereby forming an initial material category matrix. Considering that the material category table includes many material categories, covering a much wider range than the material categories covered in the material category procurement plan, step S14 is needed to perform a truncation process. This involves trunculating the valid data from the material category table based on the standard material category matrix to obtain the material category matrix. Specifically, in one example of the present invention, step S14 may further include, for example... Figure 3 The steps shown are described in this. Figure 3 In this context, step S14 may further include the following steps: In step S20, the boundaries of the standard material category matrix are projected onto the material category matrix; In step S21, it is determined whether there is a non-zero value outside the projection area. A non-zero value indicates that the material category is included in the procurement plan; otherwise, it is not. In step S22, if it is determined that there are non-zero values outside the projection area, the projection area is augmented according to the location of the non-zero values, and the process returns to the step of determining whether there are non-zero values outside the projection area. In step S23, if it is determined that there are no non-zero values outside the projection area, the material category matrix is clipped according to the projection area.
[0025] Steps S15 and S16 are used to introduce the implementation time period, thereby completing the correction of the standard material category matrix. Specifically, in this embodiment, step S16 may involve first determining the time period in which the expected implementation time falls, and then updating the standard material category matrix according to the time period. This time period can be of various forms known to those skilled in the art. In one example of the present invention, the time period may be, for example, 5 days, 7 days, 10 days, 20 days, or 1 month. The specific method for updating the standard material category matrix can also be of various forms known to those skilled in the art. In one example of the present invention, the standard material category matrix may be updated according to the following formula (1). (1) in, For the updated material category matrix, the first The first category of supplies The value of each item The first item in the previous material category matrix The first category of supplies The value of each item The expected implementation time is calculated based on the number of time periods spanned. For the first time period The smoothing parameter value for each working day. For the first The number of working days that the expected implementation time will occupy for each time period. This represents the length of the time period.
[0026] Step S17 can be used to calculate the difference matrix between the material category matrix and the standard material category matrix. Specifically, the difference matrix can be obtained by subtracting the corresponding elements of the material category matrix and the standard material category matrix.
[0027] Step S18 can be used to revise the material category procurement plan based on the difference matrix. However, considering that the material categories outside the standard material category matrix included in the material category procurement plan and the material categories in the standard material category matrix need to adopt different reference standards, in one example of the present invention, step S18 may further include, for example... Figure 4 The steps shown are described in this. Figure 4 In this process, step S18 may further include the following methods: In step S30, for each element in the difference matrix, it is determined whether the element was added by an augmentation operation; In step S31, if the element is determined to be added by an augmentation operation, it is determined whether the element is greater than or equal to a preset first threshold. In step S32, if an element is determined to be greater than or equal to a first threshold, the element is adjusted to the first threshold. Otherwise, the original element value can be retained. In step S33, if it is determined that the element was not added by an augmentation operation, it is determined whether the element is greater than or equal to a preset second threshold. In step S34, if an element is determined to be greater than or equal to the second threshold, the element is adjusted to the second threshold. Otherwise, the original element value can be retained.
[0028] Through the above technical solution, the embodiments of the present invention provide a method for decomposing material category requirements based on threshold analysis. This method corrects the output value of the standard network model by introducing the actual implementation time period of the project, thereby reducing the deviation of the network model that does not consider the time factor. Then, by combining the threshold for difference judgment, the accurate correction of the material procurement plan is achieved.
[0029] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0030] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0031] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0032] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0033] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0034] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.
[0035] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, 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 technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.
[0036] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.
[0037] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.
Claims
1. A method for decomposing material category requirements based on threshold analysis, characterized in that, include: Obtain the type of the currently submitted project and the corresponding material procurement plan; The project is input into a preset power engineering project prediction model to obtain the corresponding standard material category matrix; The material category requirements are determined based on the aforementioned material category procurement plan; The required material categories are placed into a preset material category table to update the material category table; The material category matrix is obtained by extracting valid data from the material category table based on the standard material category matrix. Obtain the expected implementation timeframe for the currently submitted project; Update the standard material category matrix according to the expected implementation period; Calculate the difference matrix between the material category matrix and the standard material category matrix; The material category procurement plan is revised based on the difference matrix.
2. The method according to claim 1, characterized in that, The power engineering project prediction model includes: The input layer is used to obtain the name, scale, keywords and location of the project, and combine them with a preset feature matrix of the name, scale, keywords and location to obtain combined feature input; The decision layer is used to perform feature iteration based on the combined feature input to obtain a one-dimensional feature sequence; The output layer contains multiple neurons, which are used to output each element in the standard material category matrix based on the one-dimensional feature sequence.
3. The method according to claim 1, characterized in that, Based on the standard material category matrix, valid data is extracted from the material category table to obtain the material category matrix, including: Project the boundaries of the standard material category matrix onto the material category matrix; Determine if there are non-zero values outside the projection area; If it is determined that there is a non-zero value outside the projection area, the projection area is augmented according to the location of the non-zero value, and the process returns to the step of determining whether there is a non-zero value outside the projection area. If it is determined that there are no non-zero values outside the projection area, the material category matrix is clipped according to the projection area.
4. The method according to claim 1, characterized in that, The standard material category matrix is updated according to the expected implementation period, including: Determine the time period in which the expected implementation time falls; The standard material category matrix is updated according to the stated time period.
5. The method according to claim 4, characterized in that, The length of the time period is one of 5 days, 7 days, 10 days, 20 days, or 1 month.
6. The method according to claim 4, characterized in that, Update the standard material category matrix according to the time period, including: The expected implementation time is broken down according to the time span of the time period to obtain multiple time periods; Update the standard material category matrix according to formula (1). ，（1） in, For the updated material category matrix, the first... The first category of supplies The value of each item For the material category matrix before the update, the first... The first category of supplies The value of each item The expected implementation time is defined by the number of time periods it spans. For the first time period The smoothing parameter value for each working day. For the first The number of working days occupied by the expected implementation time for each time period. The length of the time period is given.
7. The method according to claim 3, characterized in that, The material category procurement plan is revised based on the difference matrix, including: For each element in the difference matrix, determine whether the element was added by an augmentation operation; If the element is determined to be added by an augmentation operation, determine whether the element is greater than or equal to a preset first threshold. If it is determined that the element is greater than or equal to the first threshold, the element is corrected to the first threshold. If it is determined that the element was not added by an augmentation operation, it is determined whether the element is greater than or equal to a preset second threshold. If the element is determined to be greater than or equal to the second threshold, the element is adjusted to the second threshold.