Construction method and system of power distribution network project cost evaluation model based on project vector similarity

Abstract

The invention discloses a construction method and system of a modular power distribution network engineering similarity cost evaluation model based on engineering vectors, and belongs to the field of engineering cost in the power industry. Comprising the steps of 1, determining a list of materials used for power distribution network project construction; 2, determining a single power distribution network project construction material receiving list format; 3, defining a power distribution network project module list; step 4, initializing the corresponding relationship between the recorded modules and materials; 5, inputting the bill of material quantity of a single project, and filling in basic information of the project; 6, analyzing the actual bill of materials, and reversely deducing a module list; 7, dynamically adjusting a module-material relationship; 8, uploading and storing the adjusted module-material relationship to form a standardized template; and step 9, generating a module vector for each project and storing the module vector so as to facilitate subsequent analysis and similarity calculation. The method solves the problems that the number of modules is difficult to deduce reversely in the construction cost, and the module-material relationship and the engineering similarity are difficult to evaluate after adjustment.

Description

Technical Field

[0001] The present invention belongs to the field of engineering cost in the electric power industry, and relates to a method and system for constructing a distribution network engineering cost evaluation model based on engineering vector similarity, in particular to a method and system for constructing a modular distribution network engineering similarity cost evaluation model based on engineering vectors. Background Art

[0002] In the field of distribution network engineering cost, most projects adopt the quota cost method, which is a common cost control and budget preparation method. This method estimates the total cost of the entire project based on the national or industry standard quota (i.e. the pre-set standard cost of a single project or workload).

[0003] The quota cost of distribution network projects is usually based on national or local construction project cost quota standards. These standards include the predetermined prices and consumption of various materials, labor and machinery. By adopting a unified pricing basis, the quota cost aims to achieve standardization and rationalization of project budget preparation and improve the scientificity and accuracy of cost management.

[0004] In the current field of engineering cost, traditional cost analysis and budget preparation methods are still widely used, but they have the following three main problems:

[0005] 1. Low calculation efficiency and high technical requirements: The project cost still relies on traditional quotas for calculation. This method requires technical and economic personnel to have a deep understanding of the quota system and have a high level of cost technology and practical experience. Due to the complexity of the project and the cumbersome quota system, the compiler needs a lot of time and energy to enter and calculate the quota data one by one, resulting in low calculation efficiency and prone to human errors, which affects the accuracy of the cost.

[0006] 2. It is difficult to abstract materials into engineering modules: When using the method of associating quotas with bills of materials, although the technical requirements are relatively low, it is impossible to abstract the composition of each material into a clear engineering module. This method lacks the concept of modular costing, resulting in the costing process and results being not intuitive enough, and cannot be efficiently used in subsequent data analysis. It is difficult to form standardized modules for cost and resource allocation between projects, which complicates the analysis of engineering cost.

[0007] 3. It is difficult to determine the original engineering module after the BOM is adjusted: In the process of engineering cost estimation, a module-material correspondence relationship will be formed, and the BOM is obtained from the module BOM through the quantity relationship. In actual work, project managers often adjust the BOM according to engineering needs. These adjustments make the BOM different from the original module correspondence standard, making it difficult to directly compare the adjusted BOM with other projects. In actual engineering cost estimation, the initial data is the BOM, but the module BOM is used for subsequent data analysis, which will cause trouble for the cost personnel and affect the efficiency of project management and decision-making.

[0008] 4. It is difficult to measure project similarity: Using quotas or bills of materials to evaluate project similarity is too fragmented, making it difficult to highlight the key points of the project, making it difficult to effectively evaluate the similarity between different projects. Using modules for analysis can effectively solve this problem, abstracting the key parts of the project into modules, providing a clearer and more concise comparison dimension, and making the evaluation of project similarity more accurate.

[0009] Existing modular cost software systems can provide predefined relationships between materials and quotas, and can automatically generate quota lists based on input engineering data to calculate the cost of the entire project. Cost analysis based on modules and materials has the advantages of simplifying the budget preparation process and improving cost calculation efficiency. However, the shortcomings of the above modular cost software systems are: it is difficult to reverse the number of modules, the adjusted module-material relationship, and the difficulty in evaluating the similarity of projects. Summary of the invention

[0010] The purpose of the present invention is to address the problems in the above-mentioned prior art and to provide a method and system for constructing a distribution network engineering cost evaluation model based on engineering vector similarity. By constructing an engineering cost model based on module-material relationship adjustment and cosine similarity calculation, the problems of difficulty in inferring the number of modules, the adjusted module-material relationship and difficulty in evaluating engineering similarity in the existing engineering cost are solved, thereby ensuring the scientificity and standardization of project management and decision-making.

[0011] In order to achieve the above object, the present invention is implemented by adopting the following technical solutions:

[0012] On the one hand, the present invention provides a method for constructing a distribution network engineering cost evaluation model based on engineering vector similarity, the method comprising the following steps:

[0013] Step 1: Determine the list of materials used in the construction of the distribution network project;

[0014] Step 2: Determine the material requisition form for the construction of a single distribution network project. Specifically, formulate a standardized material requisition form, which is used to record various materials and equipment actually used during the construction process;

[0015] Step 3: Define the module list of the distribution network project. Specifically, according to the engineering design and construction requirements, the distribution network project is decomposed into several smaller and manageable modules, and each module contains a certain amount of engineering and corresponding material requirements;

[0016] Step 4: Initialize the correspondence between the entered modules and materials to ensure that the mapping relationship between each module and the bill of materials is clear;

[0017] Step 5: Enter the BOM quantity of a single project and fill in the basic information of the project;

[0018] Step 6: Analyze the actual bill of materials and infer the module list;

[0019] Step 7: Based on the parsed module list and quantity, if the actual material demand of the project does not match the original module-material relationship, dynamically adjust the module-material relationship according to the actual situation to generate the adjusted module-material relationship of this project. The adjusted relationship will reflect the changes in the project manager or actual demand; the adjusted module-material relationship is the adjusted module-material matrix, which reflects the material consumption of each module in the current project and provides a more accurate cost basis;

[0020] Step 8: While retaining historical data, upload the adjusted module-material relationship to the cloud database for storage, gradually improve and enrich the database, and provide a more accurate and comprehensive standardized template for cost analysis of future projects; using this standardized template, the efficiency and accuracy of cost analysis can be further improved;

[0021] Step 9: Generate a module vector for each project, that is, use the parsed module list to convert the number of modules for each project into a module vector; and save the module vector of the project to the cloud database for subsequent analysis and similarity calculation.

[0022] Furthermore, in step 1, the material list is determined by collecting and compiling a list of all materials and equipment required in the entire distribution network construction process; the material list includes core equipment and auxiliary materials required for construction, and the core equipment includes but is not limited to cables, switches, and transformers; step 1 ensures that all materials are listed in a timely and accurate manner for effective budgeting.

[0023] Furthermore, in step 2, the format of the material requisition form includes key information, including but not limited to material name, specification, quantity, material requisition date, and material requisitioner.

[0024] Furthermore, in step 4, the initialization method is to initialize the module-material relationship matrix through pre-defined module-material relationships or by using historical data and the working experience of engineering technicians.

[0025] Furthermore, in step 5, before starting data analysis, the material quantity of a single project and basic information of the project are recorded in detail, and the basic information includes but is not limited to the project name, location and person in charge.

[0026] Furthermore, in step 6, the actual bill of materials of the project is matched with the module-material relationship matrix to infer the module list and its quantity; a reasonable mapping relationship is established between the adjusted actual material requirements and the module quantity to ensure that the module quantity required for the project is accurately derived;

[0027] The back-calculation is performed using the least square method or other mathematical methods.

[0028] Furthermore, in step 9, each module represents a dimension of the vector, and the modulus of the vector in this dimension is the number of modules in the project. This step ensures that the data can be continuously used for comparative analysis between projects and provide a reference for future projects.

[0029] On the other hand, the present invention provides a method for constructing a distribution network engineering cost evaluation model based on engineering vector similarity, which, in addition to the above steps 1 to 9, also includes:

[0030] Step 10: Calculate the similarity between multiple projects. Specifically, calculate the similarity between projects through cosine similarity to measure the similarity of module combinations between different projects and provide data basis for project management and resource allocation.

[0031] Furthermore, the method for calculating the similarity between the multiple items in step 10 includes:

[0032] Step 10-1, calculate cosine similarity

[0033] Using the cosine similarity formula between module vectors, the similarity between the current project and other past projects is calculated one by one; by calculating the cosine similarity of each pair of projects (the current project and some other project), the similarity between them is obtained and a similarity matrix is ​​established;

[0034] Step 10-2: Sorting and outputting similarity results

[0035] The calculated similarity matrix is ​​sorted from high to low according to the similarity, and the similarity ranking between the current project and other projects is output to help managers clarify the similarities between projects.

[0036] Furthermore, step 10-2 also includes downloading the settlement file. This step provides a download function to generate a settlement file containing similarity analysis results and adjusted module-material relationships, providing a complete reference file for project management, auditing and optimization.

[0037] Furthermore, the construction method of the present invention also includes:

[0038] Based on the adjusted module-material relationship and similarity analysis results, the final cost report is summarized and generated, recording in detail the project's cost structure, module relationship, and similarities between projects.

[0039] Furthermore, the construction method of the present invention also includes:

[0040] The total price of the distribution network project is calculated by summarizing the quota workload using the relationship between materials and project quantities, and summarizing all cost items to calculate the total budget of the entire distribution network project. The total budget includes but is not limited to material costs, labor costs, and other related expenses.

[0041] Furthermore, the construction method of the present invention also includes:

[0042] Record the total price of the project to form a result file, and record the actual input quantity relationship, that is, the cost analysis of the entire project (i.e. the cost structure of the project) and the total budget are summarized into a detailed result file for project management and auditing. At the same time, record the actual material usage and engineering quantity data to provide reference and experience for subsequent calculation of similarity.

[0043] On the other hand, the present invention provides a system for constructing a distribution network engineering cost evaluation model based on engineering vector similarity, the system comprising:

[0044] The project construction material list determination module is used to determine the material list used in the distribution network project construction and encode all the materials and equipment used;

[0045] The material collection list confirmation module for a single distribution network project is used to record the various materials and equipment actually collected during the construction process;

[0046] A module for determining a module list of distribution network projects, which is used to decompose the distribution network project into a number of smaller and manageable modules according to the engineering design and construction requirements, and each module includes a certain amount of engineering work and corresponding material requirements;

[0047] The module for determining the correspondence between modules and materials is used to initialize the correspondence between the entered modules and materials, ensuring that the mapping relationship between each module and the bill of materials is clear;

[0048] The single project BOM quantity and project information entry module is used to enter the BOM quantity of a single project and fill in the basic project information;

[0049] The module list reverse deduction module is used to match the actual material list of the project with the module-material relationship matrix to reversely deduce the module list and its quantity; establish a reasonable mapping relationship between the adjusted actual material requirements and the module quantity to ensure accurate deduction of the module quantity required for the project;

[0050] The module-material relationship dynamic adjustment module is used to compare the parsed module list and quantity with the original module-material relationship, and dynamically adjust the module-material relationship according to the actual situation; the adjusted module-material relationship is the adjusted module-material matrix, which reflects the material consumption of each module in the current project and provides a more accurate cost basis;

[0051] The adjusted module-material relationship data update module is used to upload the adjusted module-material relationship to the cloud database for storage.

[0052] Furthermore, the construction system of the distribution network engineering cost evaluation model based on engineering vector similarity also includes:

[0053] The project module vector generation module is used to convert the number of modules of each project into a module vector; and save the module vector of the project to the cloud database for subsequent analysis and similarity calculation;

[0054] The similarity calculation module is used to calculate the similarity between multiple projects and provide data basis for project management and resource allocation.

[0055] Furthermore, the construction system of the distribution network engineering cost evaluation model based on engineering vector similarity also includes:

[0056] The cost summary module is used to summarize and generate the final cost report based on the adjusted module-material relationship and similarity analysis results, and record the cost composition of the project, module relationship and similarity between projects in detail;

[0057] The project total price summary calculation module is used to summarize the quota workload by using the relationship between materials and project quantities, and summarize all cost items to calculate the total budget of the entire distribution network project.

[0058] The result file formation module is used to record the total project price composition to form a result file and record the actual input quantity relationship, that is, to summarize the cost analysis and budget of the entire project into a detailed result file for project management and auditing; at the same time, it records the actual material usage and engineering quantity data to provide reference and experience for subsequent calculation of similarity.

[0059] Beneficial effects of the present invention:

[0060] Compared with the traditional software or Excel through a single quota entry method, the distribution network engineering cost assessment model of the present invention has obvious efficiency advantages and other advantages:

[0061] 1. Modular data simplification and analysis

[0062] The present invention uses a modular approach to perform data analysis, and reversely infers the bill of materials of the project cost into a module list, making data analysis more intuitive and simplifying the processing of project data. During the data analysis process, less important material data can be filtered out, and the focus can be directly on key modules. This method can significantly reduce the time and labor intensity of manually entering quota information one by one, and process a large amount of data in a short time, thereby improving the efficiency of cost assessment.

[0063] 2. Comparison of similarities between historical real projects

[0064] The present invention uses the participation data of past real projects, abstracts the current project into module vectors, and compares them with completed historical projects to quickly find the most similar projects. This method allows project managers to refer to the best practices of past projects, reduce risks, and provide more accurate estimates for new projects. At the same time, this modular analysis method can ensure the consistency of cross-project comparisons and maintain the standardization of evaluation and data processing.

[0065] 3. Dynamic adjustment and flexible adaptation

[0066] The present invention can timely adjust the relationship between modules and materials according to actual construction data, so that the cost model can accurately reflect the changes in actual conditions. This dynamic adjustment capability is more flexible and adaptable than the traditional fixed list cost method, which helps to reflect the cost structure of the actual project in real time and reduce valuation errors.

[0067] 4. Reduce human errors and improve accuracy

[0068] The present invention reduces the errors of manual information entry and improves the accuracy of data processing through modular design and standardized processes. In actual engineering, the consistency and accuracy of each data can be ensured through pre-defined module-material relationships, especially in multiple projects and stages. This consistency helps maintain cross-project comparison and analysis standards.

[0069] 5. Dealing with project changes and uncertainties

[0070] The present invention can flexibly adapt to changes in projects and actual environments, ensuring that the evaluation model can be updated in a timely manner. Compared with the traditional fixed list cost method, the present invention can provide more personalized and customized evaluation results under different construction environments and conditions, making the project cost evaluation more accurate and truly reflecting the real needs and costs of the project. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below.The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application.

[0072] Figure 1 It is a functional architecture diagram of a method for constructing a distribution network engineering cost evaluation model based on engineering vector similarity of the present invention;

[0073] Figure 2 It is a flow chart of a method for constructing a distribution network engineering cost evaluation model based on engineering vector similarity described in Example 1 of the present invention;

[0074] Figure 3 It is a flow chart of a method for constructing a distribution network engineering cost evaluation model based on engineering vector similarity described in Example 2 of the present invention;

[0075] Figure 4 It is a flow chart of a method for constructing a distribution network engineering cost evaluation model based on engineering vector similarity described in Embodiment 3 of the present invention;

[0076] Figure 5 It is a flow chart of a method for constructing a distribution network engineering cost evaluation model based on engineering vector similarity described in Embodiment 4 of the present invention;

[0077] Figure 6 It is a schematic diagram of a system for constructing a distribution network engineering cost assessment model based on engineering vector similarity as described in Example 5 of the present invention. DETAILED DESCRIPTION

[0078] The following embodiments of the technical solution of the present application are described in detail in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application, and are therefore only used as examples, and cannot be used to limit the scope of protection of the present application.

[0079] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the term "including" and any variations thereof in the specification and claims of this application and the above-mentioned figure descriptions are intended to cover non-exclusive inclusions.

[0080] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two (including two), unless otherwise clearly and specifically defined.

[0081] The present invention provides a method and system for constructing a distribution network engineering cost evaluation model based on engineering vector similarity, Figure 1 This is the functional architecture diagram of the present invention. By constructing an engineering cost model based on module-material relationship adjustment and cosine similarity calculation, the problems of difficulty in inferring the number of modules, the adjusted module-material relationship and the difficulty in evaluating engineering similarity in the existing engineering cost are solved.

[0082] The advantages of the present invention are:

[0083] 1. Reverse infer the module list based on the bill of materials: Provide a reverse inferring mechanism based on the module-material relationship adjustment, and accurately deduce the composition and specific quantity relationship of each module under this project according to the adjusted bill of materials.

[0084] 2. Generate adjusted module-material relationship: Calculate and generate the module-material relationship specific to this project so that material adjustments can be accurately mapped to specific modules, providing intuitive data for project cost analysis.

[0085] 3. Measure project similarity: By representing each project as a vector of the number of modules and using cosine similarity to measure the similarity between different projects, a quantitative basis is provided for project decision making. When measuring similarity, it is necessary to consider the situation where the projects are still similar when they are scaled proportionally.

[0086] 4. Improve efficiency and accuracy: With the help of automated adjustment and analysis methods, the technical threshold for technical and economic personnel is lowered, and the efficiency and accuracy of engineering cost are significantly improved.

[0087] Embodiment 1: This embodiment 1 discloses the establishment process of the module of the present invention.

[0088] Refer to the attached Figure 2 The present invention provides a method for constructing a distribution network engineering cost evaluation model based on engineering vector similarity, the method comprising the following steps:

[0089] Step 1: Determine the list of materials used in the construction of the distribution network project;

[0090] In this step, the material list is determined by collecting and compiling a list of all materials and equipment required in the entire distribution network construction process; the material list includes core equipment and auxiliary materials required for construction, and the core equipment includes but is not limited to cables, switches, and transformers; the step 1 ensures that all materials are listed in a timely and accurate manner for effective budgeting.

[0091] Step 2: Determine the format of the material requisition form for the construction of a single distribution network project. Specifically, formulate a standardized material requisition form, which is used to record the various materials and equipment actually collected during the construction process; the format of the material requisition form includes key information, including but not limited to the material name, specification, quantity, material collection date, and material collection person.

[0092] Step 3: Define the module list of the distribution network project. Specifically, according to the engineering design and construction requirements, the distribution network project is decomposed into several smaller and manageable modules, and each module contains a certain amount of engineering and corresponding material requirements.

[0093] Step 4: Initialize the correspondence between the entered modules and materials to ensure that the mapping relationship between each module and the bill of materials is clear; the initialization method is to initialize the module-material relationship matrix through pre-defined module-material relationships or by using historical data and the work experience of engineering and technical personnel.

[0094] Step 5. Enter the bill of materials quantity of a single project and fill in the basic information of the project. Before starting data analysis, record the material quantity of a single project and the basic information of the project in detail. The basic information includes but is not limited to the project name, location and person in charge.

[0095] Step 6: Analyze the actual bill of materials and infer the module list; match the actual bill of materials of the project with the module-material relationship matrix to infer the module list and its quantity; establish a reasonable mapping relationship between the adjusted actual material requirements and the module quantity to ensure accurate derivation of the module quantity required for the project;

[0096] Use the least squares method or other mathematical methods for reverse deduction.

[0097] The reverse calculation of the number of modules in the present invention is similar to the problem of solving a one-variable multi-time equation. However, the equation may have no solution because the project manager may modify the number when the module is converted into materials. Therefore, the current problem is more in line with the problem of data fitting and regression analysis. The least squares method is a more common solution to this problem. The specific steps are as follows:

[0098] Step A: Define the mathematical model to be fitted. Same as the above “Step 4: Initialize the correspondence between the entered modules and materials”. The mathematical model is expressed as in is a list vector of materials used in a project, M is the correspondence matrix between modules and materials, the rows in the matrix represent different modules, the columns represent different materials, and M in the matrix ij represents the contribution of the i-th module to the j-th material, A vector of lists of modules in a project.

[0099] Step B: Build a demand vector, which is a list of materials for a specific project.

[0100] Step C: define a residual vector. The residual function is used to calculate the difference between the mapping from modules to materials and the actual material demand under a given module quantity forecast. In the present invention, the residual vector is:

[0101] Step D: Least squares method is used to solve the problem. The goal of the least squares method is to minimize the sum of squares of the residuals, that is, to minimize the function

[0102] The method to minimize the function is to calculate relatively The derivative of is 0, that is This can be solved

[0103] A similar solution is linear programming, and their core difference lies in the nature of the objectives and constraints. Linear programming focuses on optimizing linear objectives under given linear constraints, while the least squares method focuses on finding the best model parameters by minimizing errors. Since the number of modules in the present invention is relatively small, the linear programming method is not suitable for solving.

[0104] Step 7: Based on the parsed module list and quantity, if the actual material demand of the project does not match the original module-material relationship, dynamically adjust the module-material relationship according to the actual situation to generate the adjusted module-material relationship of this project. The adjusted relationship will reflect the changes in the project manager or actual demand; the adjusted module-material relationship is the adjusted module-material matrix, which reflects the material consumption of each module in the current project and provides a more accurate cost basis;

[0105] Step 8. While retaining historical data, upload the adjusted module-material relationship to the cloud database for storage, gradually improve and enrich the database, and provide a more accurate and comprehensive template for cost analysis of future projects; using standardized templates can further improve the efficiency and accuracy of cost analysis.

[0106] Step 9: Generate a module vector for each project, that is, use the parsed module list to convert the number of modules in each project into a module vector; and save the module vector of the project to the cloud database for subsequent analysis and similarity calculation; each module represents a dimension of the vector, and the modulus of the vector in this dimension is the number of modules in the project. This step ensures that the data can be continuously used for comparative analysis between projects and provide reference for future projects.

[0107] The above-mentioned Example 1 shows that the method of the present invention predefines the relationship between materials and modules and represents them through a matrix by parsing a given bill of materials, thereby realizing the reverse deduction of the project cost, and using the bill of materials to reversely deduce the list of modules and their quantities. This process can accurately reflect the quantity of materials required for each module in the current project, and generate an adjusted module-material relationship according to the actual situation of the project. In the reverse deduction process, the mapping relationship between modules and materials is kept consistent, and it is ensured that the adjusted material consumption is consistent with the actual demand.

[0108] Example 2

[0109] Refer to the attached Figure 3 The present invention also provides a method for constructing a distribution network engineering cost evaluation model based on engineering vector similarity, which, in addition to the above steps 1 to 9, also includes:

[0110] Step 10: Calculate the similarity between multiple projects. Specifically, calculate the similarity between projects through cosine similarity to measure the similarity of module combinations between different projects and provide data basis for project management and resource allocation.

[0111] Furthermore, the method for calculating the similarity between the multiple items in step 10 includes:

[0112] Step 10-1, calculate cosine similarity

[0113] Using the cosine similarity formula between module vectors, the similarity between the current project and other past projects is calculated one by one; by calculating the cosine similarity of each pair of projects (the current project and some other project), the similarity between them is obtained and a similarity matrix is ​​established;

[0114] Step 10-2: Sorting and outputting similarity results

[0115] The calculated similarity matrix is ​​sorted from high to low according to the similarity, and the similarity ranking between the current project and other projects is output to help managers clarify the similarities between projects.

[0116] Assuming that 292 modules are constructed, each project can be understood as a vector in a 292-dimensional space according to the number of project modules. For example, if project A consists of 1 first module and 2 second modules, then project A can be represented as A = (1, 2, 0..... 0), and project B consists of 2 second modules and 1 third module, that is, B = (0, 2, 1, 0... 0). The cosine similarity of the two is:

[0117]

[0118] There is a practical benefit in using vector cosine similarity in this way. Since many distribution network projects are proportionally scaled up between projects, for example, Project A is to replace one transformer and install 1 km of cable, and Project B is to replace two transformers and install 2 km of cable. These two projects are proportionally scaled up projects and have strong reference value. In the above algorithm, the angle between these two projects in the vector space is 0, the cosine value is 1, and the similarity is 100%. Using cosine similarity can effectively count.

[0119] Furthermore, step 10-2 also includes downloading the settlement file. This step provides a download function to generate a settlement file containing similarity analysis results and adjusted module-material relationships, providing a complete reference file for project management, auditing and optimization.

[0120] The above embodiments show that the method of the present invention abstracts the number of modules of each project into a vector and uses cosine similarity to calculate the similarity between different projects. This process can effectively quantify the similarity between different projects and provide data basis for project management and optimization. Using the pre-parsed module list, each project is represented as a module vector, and the vector dimension is unified to ensure consistency. The cosine similarity between project vectors is calculated to measure the similarity between different projects in order to better manage projects and allocate resources. Through the ranking and analysis of similarity, project optimization suggestions and management strategies are provided.

[0121] Example 3

[0122] Refer to the attached Figure 4 , based on Example 2, the present invention further includes:

[0123] Based on the adjusted module-material relationship and similarity analysis results, the final cost report is summarized and generated, recording in detail the cost composition of the project, module relationship and similarity between projects;

[0124] The total price of the distribution network project is calculated by summarizing the quota workload using the relationship between materials and project quantities, and summarizing all cost items to calculate the total budget of the entire distribution network project. The total budget includes but is not limited to material costs, labor costs, and other related expenses.

[0125] Example 4

[0126] Refer to the attached Figure 5 On the basis of Example 3, the present invention further comprises:

[0127] Record the total price of the project to form a result file, and record the actual input quantity relationship, that is, summarize the cost analysis and budget of the entire project into a detailed result file for project management and auditing. At the same time, record the actual material usage and engineering quantity data to provide reference and experience for subsequent calculation similarity.

[0128] Example 5

[0129] Refer to the attached Figure 6 The present invention provides a system for constructing a distribution network engineering cost evaluation model based on engineering vector similarity, the system comprising:

[0130] The project construction material list determination module is used to determine the material list used in the distribution network project construction and encode all the materials and equipment used;

[0131] The material collection list confirmation module for a single distribution network project is used to record the various materials and equipment actually collected during the construction process;

[0132] A module for determining a module list of distribution network projects, which is used to decompose the distribution network project into a number of smaller and manageable modules according to the engineering design and construction requirements, and each module includes a certain amount of engineering work and corresponding material requirements;

[0133] The module for determining the correspondence between modules and materials is used to initialize the correspondence between the entered modules and materials, ensuring that the mapping relationship between each module and the bill of materials is clear;

[0134] The single project BOM quantity and project information entry module is used to enter the BOM quantity of a single project and fill in the basic project information;

[0135] The module list reverse deduction module is used to match the actual material list of the project with the module-material relationship matrix to reversely deduce the module list and its quantity; establish a reasonable mapping relationship between the adjusted actual material requirements and the module quantity to ensure accurate deduction of the module quantity required for the project;

[0136] The module-material relationship dynamic adjustment module is used to compare the parsed module list and quantity with the original module-material relationship, and dynamically adjust the module-material relationship according to the actual situation; the adjusted module-material relationship is the adjusted module-material matrix, which reflects the material consumption of each module in the current project and provides a more accurate cost basis;

[0137] The adjusted module-material relationship data update module is used to upload the adjusted module-material relationship to the cloud database for storage.

[0138] Furthermore, the construction system of the distribution network engineering cost evaluation model based on engineering vector similarity also includes:

[0139] The project module vector generation module is used to convert the number of modules of each project into a module vector; and save the module vector of the project to the cloud database for subsequent analysis and similarity calculation;

[0140] The similarity calculation module is used to calculate the similarity between multiple projects and provide data basis for project management and resource allocation.

[0141] Furthermore, the construction system of the distribution network engineering cost evaluation model based on engineering vector similarity also includes:

[0142] The cost summary module is used to summarize and generate the final cost report based on the adjusted module-material relationship and similarity analysis results, and record the cost composition of the project, module relationship and similarity between projects in detail;

[0143] The project total price summary calculation module is used to summarize the quota workload by using the relationship between materials and project quantities, and summarize all cost items to calculate the total budget of the entire distribution network project.

[0144] The result file formation module is used to record the total project price composition to form a result file and record the actual input quantity relationship, that is, to summarize the cost analysis and budget of the entire project into a detailed result file for project management and auditing; at the same time, it records the actual material usage and engineering quantity data to provide reference and experience for subsequent calculation of similarity.

[0145] In summary, the present invention can achieve the following objectives:

[0146] 1. Module deduction and adjustment: Through the pre-defined module-material relationship matrix, the quantity and allocation method of each module can be deduced from the actual material list provided by the project; and the module-material relationship matrix specific to this project is generated based on the adjusted module quantity, making the cost analysis process more intuitive and accurate.

[0147] 2. Similarity calculation: Use the number of modules to construct a project vector, and by calculating the cosine similarity between different projects, provide quantitative similarity analysis and solve the problem of proportional scaling; this analysis provides data basis for project cost decision-making, helps managers formulate project optimization strategies, and is used to measure the similarity and resource utilization between multiple projects.

[0148] 3. Efficiency and standardization: By automatically inferring the calculation process of module-material relationship and similarity analysis, the existing complex cost management process is simplified, manual intervention is reduced, and the efficiency and accuracy of cost calculation are improved; at the same time, the predefined module relationship table is used to ensure data consistency and standardization.

[0149] 4. Development trend of cost management technology: Combined with modern engineering cost management concepts, complex module reverse deduction, adjustment and similarity calculation are transformed into a set of standardized and reusable engineering cost solutions; with the help of data collection and algorithm analysis, project managers can efficiently obtain key indicator data and provide technical support for the intelligent and automated development of engineering cost management.

[0150] The present invention has proven its high practicability in practice, and can effectively meet user needs and significantly improve work efficiency. In order to verify the feasibility and effect of the present invention, it not only relies on theoretical analysis and simulation experiments, but also verifies the model by applying it to actual distribution network engineering projects. Specifically, after actual use by distribution network engineering technical personnel, the present invention has come to the conclusion that it can be widely used in actual projects. Furthermore, it has been tested in more than 40 actual distribution network engineering projects, which cover distribution network projects of various types and sizes. The test results show that the evaluation model is not only feasible, but can also find the most similar past projects, which can effectively improve the accuracy and efficiency of project evaluation.

[0151] Other technical features of this system are similar to those of the corresponding method and will not be described in detail here.

[0152] The embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of complete hardware embodiments, complete software embodiments or embodiments in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0153] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1A device that provides the functions specified in a block or multiple blocks.

[0154] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0155] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0156] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0157] Obviously, those skilled in the art can make various changes and modifications to the embodiments of the present invention without departing from the spirit and scope of the embodiments of the present invention. Thus, if these modifications and variations of the embodiments of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for constructing a distribution network engineering cost evaluation model based on engineering vector similarity, characterized in that: The method comprises the following steps: Step 1: Determine the list of materials used in the construction of the distribution network project; Step 2: Determine the material requisition form for the construction of a single distribution network project. Specifically, formulate a standardized material requisition form, which is used to record various materials and equipment actually used during the construction process; Step 3: Define the module list of the distribution network project. Specifically, according to the engineering design and construction requirements, the distribution network project is decomposed into several smaller and manageable modules, and each module contains a certain amount of engineering and corresponding material requirements; Step 4: Initialize the correspondence between the entered modules and materials to ensure that the mapping relationship between each module and the bill of materials is clear; Step 5: Enter the BOM quantity of a single project and fill in the basic information of the project; Step 6: Analyze the actual bill of materials and infer the module list; Step 7: Based on the parsed module list and quantity, if the actual material demand of the project does not match the original module-material relationship, dynamically adjust the module-material relationship according to the actual situation to generate the adjusted module-material relationship of this project. The adjusted relationship will reflect the changes of the project manager or actual demand; the adjusted module-material relationship is the adjusted module-material matrix; Step 8: While retaining historical data, upload the adjusted module-material relationship to the cloud database for storage, gradually improve and enrich the database, and provide a standardized template for cost analysis of future projects; Step 9: Generate a module vector for each project, that is, use the parsed module list to convert the number of modules for each project into a module vector; and save the module vector of the project to the cloud database.

2. The method for constructing a distribution network engineering cost evaluation model based on engineering vector similarity according to claim 1 is characterized in that: In step 5, before starting data analysis, the material quantity of a single project and basic information of the project are recorded in detail, and the basic information at least includes the project name, location and person in charge.

3. The method for constructing a distribution network engineering cost evaluation model based on engineering vector similarity according to claim 1 is characterized in that: In step 6, the actual bill of materials of the project is matched with the module-material relationship matrix to infer the module list and its quantity; a reasonable mapping relationship is established between the adjusted actual material requirements and the module quantity to ensure that the number of modules required for the project is accurately derived; The back-calculation is performed using the least square method or other mathematical methods.

4. The method for constructing a distribution network engineering cost evaluation model based on engineering vector similarity according to claim 1 is characterized in that: In step 9, each module represents a dimension of the vector, and the modulus of the vector in this dimension is the number of modules in the project.

5. A method for constructing a distribution network engineering cost evaluation model based on engineering vector similarity, the method comprising steps 1 to 9 as described in claim 1, characterized in that: Also includes: Step 10: Calculate the similarity between multiple projects. Specifically, calculate the similarity between projects through cosine similarity to measure the similarity of module combinations between different projects and provide data basis for project management and resource allocation.

6. The method for constructing a distribution network engineering cost evaluation model based on engineering vector similarity according to claim 5 is characterized in that: The method for calculating the similarity between the multiple items in step 10 includes: Step 10-1, calculate cosine similarity Using the cosine similarity formula between module vectors, the similarity between the current project and other past projects is calculated one by one; by calculating the cosine similarity of each pair of projects, the similarity between them is obtained and a similarity matrix is ​​established; Step 10-2: Sorting and outputting similarity results The calculated similarity matrix is ​​sorted from high to low according to the similarity, and the similarity ranking between the current project and other projects is output to help managers clarify the similarities between projects.

7. The method for constructing a distribution network engineering cost evaluation model based on engineering vector similarity according to claim 6 is characterized in that: Step 10-2 also includes downloading the settlement file. This step provides a download function to generate a settlement file containing the similarity analysis results and the adjusted module-material relationship, providing a complete reference file for project management, auditing and optimization.

8. The method for constructing a distribution network engineering cost evaluation model based on engineering vector similarity according to claim 7 is characterized in that: Also includes: Based on the adjusted module-material relationship and similarity analysis results, the final cost report is summarized and generated, recording in detail the project's cost structure, module relationship, and similarities between projects.

9. The method for constructing a distribution network engineering cost evaluation model based on engineering vector similarity according to claim 8 is characterized in that: Also includes: The total price of the distribution network project is calculated by summarizing the quota workload using the relationship between materials and project quantities, and summarizing all cost items to calculate the total budget of the entire distribution network project. The total budget includes at least material costs, labor costs, and other related expenses.

10. The method for constructing a distribution network engineering cost evaluation model based on engineering vector similarity according to claim 9 is characterized in that: Also includes: The total project price composition is recorded to form a result file, and the actual input quantity relationship is recorded, that is, the cost analysis and total budget of the entire project are summarized into a detailed result file for project management and auditing; at the same time, the actual material usage and engineering quantity data are recorded to provide reference and experience for subsequent calculation of similarity.

11. A system for constructing a distribution network engineering cost evaluation model based on engineering vector similarity, characterized in that: The system includes: The project construction material list determination module is used to determine the material list used in the distribution network project construction and encode all the materials and equipment used; The material collection list confirmation module for a single distribution network project is used to record the various materials and equipment actually collected during the construction process; A module for determining a module list of distribution network projects, which is used to decompose the distribution network project into a number of smaller and manageable modules according to the engineering design and construction requirements, and each module includes a certain amount of engineering work and corresponding material requirements; The module for determining the correspondence between modules and materials is used to initialize the correspondence between the entered modules and materials, ensuring that the mapping relationship between each module and the bill of materials is clear; The single project BOM quantity and project information entry module is used to enter the BOM quantity of a single project and fill in the basic project information; The module list reverse deduction module is used to match the actual material list of the project with the module-material relationship matrix to reversely deduce the module list and its quantity; establish a reasonable mapping relationship between the adjusted actual material requirements and the module quantity to ensure accurate deduction of the module quantity required for the project; The module-material relationship dynamic adjustment module is used to compare the parsed module list and quantity with the original module-material relationship, and dynamically adjust the module-material relationship according to the actual situation; the adjusted module-material relationship is the adjusted module-material matrix, which reflects the material consumption of each module in the current project and provides a more accurate cost basis; The adjusted module-material relationship data update module is used to upload the adjusted module-material relationship to the cloud database for storage.

12. The system for constructing a distribution network engineering cost evaluation model based on engineering vector similarity according to claim 11, characterized in that: Also includes: The project module vector generation module is used to convert the number of modules of each project into a module vector; and save the module vector of the project to the cloud database for subsequent analysis and similarity calculation; The similarity calculation module is used to calculate the similarity between multiple projects and provide data basis for project management and resource allocation.

13. The system for constructing a distribution network engineering cost evaluation model based on engineering vector similarity according to claim 12, characterized in that: Also includes: The cost summary module is used to summarize and generate the final cost report based on the adjusted module-material relationship and similarity analysis results, and record the cost composition of the project, module relationship and similarity between projects in detail; The project total price summary calculation module is used to summarize the quota workload by using the relationship between materials and project quantities, and summarize all cost items to calculate the total budget of the entire distribution network project. The result file formation module is used to record the total project price composition to form a result file and record the actual input quantity relationship, that is, to summarize the cost analysis and budget of the entire project into a detailed result file for project management and auditing; at the same time, it records the actual material usage and engineering quantity data to provide reference and experience for subsequent calculation of similarity.

Images