Intelligent material management method and system

Abstract

The invention provides an intelligent material management method and system, and the method comprises the steps: determining a neighborhood segmentation coefficient set through an obtained to-be-stored bill of material data set, and segmenting the bill of material data set into a flat bill of material data field and a steep bill of material data field through the neighborhood segmentation coefficient set and a neighborhood segmentation decision value; determining a neighborhood discrete decision boundary according to the flat bill-of-material data field and a preset neighborhood discrete coefficient, and converting the flat bill-of-material data field into a flat bill-of-material data interference suppression sequence through the neighborhood discrete decision boundary; converting the steep bill-of-material data field into a steep bill-of-material data smooth sequence according to a spatial smoothing factor and a feature maintenance factor determined by the steep bill-of-material data field; and a plurality of noise-free bill of material data fields determined by the flat bill of material data interference suppression sequence and the steep bill of material data smoothing sequence are classified and stored, so that the storage efficiency of classified storage of the to-be-stored bill of material data is effectively improved.

Description

Technical Field

[0001] The present application relates to the technical field of engineering material data storage, and more specifically, to an intelligent material management method and system. Background Art

[0002] Engineering materials refer to materials used in various engineering projects, including those required in fields such as construction, roads, bridges, water conservancy projects, aerospace, etc. Engineering material bills of materials (BOMs) are usually included in the construction drawings and specifications of engineering projects. The BOMs detail the various materials, quantities, specifications, quality standards, and other information required for the project, facilitating procurement and construction by construction units.

[0003] The storage method for engineering material bill of materials data usually adopts a computerized information management system. Through database technology, detailed data such as the name, specifications, quantity, quality standards, and purpose of various engineering materials are structured and stored, such as SQL Server, MySQL, or Oracle. This achieves efficient data organization, rapid retrieval, and convenient updating. Users can perform data operations through a graphical interface or imperative language. In addition, with the development of Internet of Things technology, devices such as sensors and RFID are also widely used to monitor the inventory status and usage of materials in real time, making the management of bill of materials data more intelligent and refined, providing reliable data support and management convenience for engineering projects. However, the same data may appear in different system modules, resulting in data redundancy, making data updating and maintenance complicated and prone to inconsistency. In addition, engineering material bill of materials data often involves complex multi-level relationships, which affects data maintenance and query efficiency. When storing the bill of materials data to be stored in engineering projects, the redundancy of the bill of materials data to be stored leads to low storage efficiency when the bill of materials data to be stored is classified and stored. Summary of the Invention

[0004] The present application provides an intelligent material management method and system to solve the technical problem of low storage efficiency when classifying and storing bill of materials data.

[0005] To solve the above technical problems, this application adopts the following technical solutions:

[0006] In a first aspect, the present application provides an intelligent material management method, comprising the following steps:

[0007] Obtain the bill of materials to be stored in the project and obtain the bill of materials data set to be stored;

[0008] Determining a neighborhood segmentation coefficient set based on the bill of materials data set to be stored, and performing flat and steep neighborhood segmentation on the bill of materials data set to be stored based on the neighborhood segmentation coefficient set and the neighborhood segmentation decision value to obtain a flat bill of materials data domain and a steep bill of materials data domain;

[0009] Determining a neighborhood discrete decision boundary based on the flat BOM data domain and a preset neighborhood discrete coefficient, and converting the flat BOM data domain into a flat BOM data suppression sequence using the neighborhood discrete decision boundary;

[0010] Determining a spatial smoothing factor and a feature maintaining factor according to the steep BOM data domain, and converting the steep BOM data domain into a steep BOM data smoothing sequence by using the spatial smoothing factor and the feature maintaining factor;

[0011] A plurality of noise-free BOM data domains are determined by using the flat BOM data suppression sequence and the steep BOM data smoothing sequence, and each noise-free BOM data domain is then classified and stored.

[0012] In some embodiments, determining the neighborhood partition coefficient set using the bill of materials data set to be stored specifically includes:

[0013] Perform linear fitting on the stored bill of materials data set to obtain a bill of materials fitting curve;

[0014] The neighborhood segmentation coefficient corresponding to each BOM data in the BOM data set to be stored is determined by the BOM fitting curve, thereby obtaining a neighborhood segmentation coefficient set.

[0015] In some embodiments, performing flat and steep neighborhood segmentation on the to-be-stored BOM data set using the neighborhood segmentation coefficient set and the neighborhood segmentation decision value to obtain a flat BOM data domain and a steep BOM data domain specifically includes:

[0016] The BOM data whose neighborhood segmentation coefficient is greater than the neighborhood segmentation decision value in the BOM data set to be stored is used as steep BOM data, thereby obtaining a steep BOM data domain;

[0017] The BOM data whose neighborhood segmentation coefficient is less than the neighborhood segmentation decision value in the BOM data set to be stored is taken as the flat BOM data, thereby obtaining a flat BOM data domain.

[0018] In some embodiments, converting the flat BOM data domain into a flat BOM data suppression sequence is to, for each flat BOM data in the flat BOM data domain, remove the flat BOM data that is not within the neighborhood discrete decision boundary, thereby obtaining the flat BOM data suppression sequence.

[0019] In some embodiments, converting the steep BOM data domain into a steep BOM data smoothed sequence using the spatial smoothing factor and the feature preserving factor specifically includes:

[0020] Determine the BOM data filtering normal vector;

[0021] For each steep BOM data in the steep BOM data domain, the steep BOM data is converted into smooth steep BOM data by using the BOM data filtering normal vector, the spatial smoothing factor of the steep BOM data domain, and the feature maintenance factor of the steep BOM data domain, thereby obtaining a smoothed sequence of steep BOM data, wherein the smoothed steep BOM data is determined according to the following formula:

[0022]

[0023] Among them, β′ i represents the i-th smooth steep BOM data in the smooth sequence of steep BOM data, β i represents the i-th steep BOM data in the steep BOM data domain, n represents the BOM data filtering normal vector, m represents the total amount of data in the steep BOM data domain, β j represents the j-th steep BOM data in the steep BOM data domain, ω represents the spatial smoothing factor of the steep BOM data domain, Indicates the characteristic maintenance factor for steep BOM data domains.

[0024] In some embodiments, determining a plurality of noise-free BOM data domains using the flat BOM data suppression sequence and the steep BOM data smoothing sequence specifically includes:

[0025] Determining a noise-free BOM data set to be stored by using the flat BOM data suppression sequence and the steep BOM data smoothing sequence;

[0026] determining a spacing growth matrix for the noise-free bill of materials data set;

[0027] The noise-free bill of materials data set is decoupled by data domain according to the spacing growth matrix to obtain multiple noise-free bill of materials data domains.

[0028] In some embodiments, classifying and storing each noise-free bill of materials data field specifically includes:

[0029] Determine the inter-domain fuzzy factor for each noise-free BOM data domain;

[0030] The noise-free BOM data domain whose inter-domain fuzzy factor is smaller than the fuzzy decision value is used as the BOM data domain to be stored, thereby obtaining a plurality of BOM data domains to be stored;

[0031] Each BOM data field to be stored is classified and stored as a class.

[0032] In a second aspect, the present application provides an intelligent material management system, including a bill of materials data storage unit, wherein the bill of materials data storage unit includes:

[0033] The module for determining the data set of the bill of materials to be stored is used to obtain the bill of materials to be stored in the engineering project and obtain the data set of the bill of materials to be stored;

[0034] a bill of materials data domain segmentation module, configured to determine a neighborhood segmentation coefficient set based on the bill of materials data set to be stored, and perform flat and steep neighborhood segmentation on the bill of materials data set to be stored based on the neighborhood segmentation coefficient set and the neighborhood segmentation decision value to obtain a flat bill of materials data domain and a steep bill of materials data domain;

[0035] a flat BOM data suppression sequence determination module, configured to determine a neighborhood discrete decision boundary based on the flat BOM data domain and a preset neighborhood discrete coefficient, and convert the flat BOM data domain into a flat BOM data suppression sequence using the neighborhood discrete decision boundary;

[0036] a steep BOM data smoothing sequence determining module, configured to determine a spatial smoothing factor and a feature maintaining factor according to the steep BOM data domain, and convert the steep BOM data domain into a steep BOM data smoothing sequence using the spatial smoothing factor and the feature maintaining factor;

[0037] The BOM data classification and storage module is used to determine a plurality of noise-free BOM data domains through the flat BOM data suppression sequence and the steep BOM data smoothing sequence, and then classify and store each noise-free BOM data domain.

[0038] In a third aspect, the present application provides a computer device comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned intelligent material management method.

[0039] In a fourth aspect, the present application provides a computer-readable storage medium, in which instructions or codes are stored. When the instructions or codes are run on a computer, the computer implements the above-mentioned intelligent material management method when executing.

[0040] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects:

[0041] The present application provides an intelligent material management method and system, which obtains a bill of materials to be stored in an engineering project to obtain a bill of materials data set to be stored; determines a neighborhood segmentation coefficient set based on the bill of materials data set to be stored, and performs flat and steep neighborhood segmentation on the bill of materials data set to be stored based on the neighborhood segmentation coefficient set and the neighborhood segmentation decision value to obtain a flat bill of materials data domain and a steep bill of materials data domain; determines a neighborhood discrete decision boundary based on the flat bill of materials data domain and a preset neighborhood discrete coefficient, and converts the flat bill of materials data domain into a flat bill of materials data suppression sequence based on the neighborhood discrete decision boundary; determines a spatial smoothing factor and a feature maintenance factor based on the steep bill of materials data domain, and converts the steep bill of materials data domain into a steep bill of materials data smoothed sequence based on the spatial smoothing factor and the feature maintenance factor; determines multiple noise-free bill of materials data domains based on the flat bill of materials data suppression sequence and the steep bill of materials data smoothed sequence, and then classifies and stores each noise-free bill of materials data domain.

[0042] In this application, firstly, the neighborhood splitting coefficient can be used to more accurately divide the bill of materials data set into two categories, flat and steep, thereby improving the accuracy of the bill of materials data classification, so that different bill of materials data processing methods can be used to improve the processing efficiency of the bill of materials data. Secondly, the discrete noise and irregular changes in the bill of materials data can be reduced through conversion, making the bill of materials data more accurate, helping to reduce the redundancy and complexity of the bill of materials data, thereby improving the classification and storage efficiency of the bill of materials data. Furthermore, the determined noise-free bill of materials data set does not contain noise and irregular changes, and the bill of materials data can be classified and stored more accurately, thereby improving the efficiency of the classification and storage of the bill of materials data. Then, through data domain decoupling, the bill of materials data can be classified more finely, improving the accuracy and classification accuracy of the bill of materials data. Finally, the noise-free bill of materials data domain to be stored is determined according to the inter-domain fuzzy factor, which improves the accuracy of the bill of materials data classification. By storing noise-free bill of materials data domains with different characteristics separately, the most suitable data storage structure and algorithm can be selected, effectively improving the storage efficiency when classifying and storing the bill of materials data to be stored. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0044] Figure 1 is an exemplary flow chart of an intelligent material management method according to some embodiments of the present application;

[0045] Figure 2 is a schematic diagram of exemplary hardware and / or software of a bill of materials data storage unit according to some embodiments of the present application;

[0046] Figure 3 It is a structural diagram of a computer device for implementing an intelligent material management method according to some embodiments of the present application. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0048] The present application provides an intelligent material management method and system, the core of which is to obtain a bill of materials to be stored in an engineering project to obtain a bill of materials data set to be stored; determine a neighborhood partitioning coefficient set based on the bill of materials data set to be stored, and perform flat and steep neighborhood partitioning on the bill of materials data set to be stored using the neighborhood partitioning coefficient set and the neighborhood partitioning decision value to obtain a flat bill of materials data domain and a steep bill of materials data domain; determine a neighborhood discrete decision boundary based on the flat bill of materials data domain and a preset neighborhood discrete coefficient, and convert the flat bill of materials data domain into a flat bill of materials data suppression sequence using the neighborhood discrete decision boundary; determine a spatial smoothing factor and a feature maintenance factor based on the steep bill of materials data domain, and convert the steep bill of materials data domain into a steep bill of materials data smoothed sequence using the spatial smoothing factor and the feature maintenance factor; determine multiple noise-free bill of materials data domains using the flat bill of materials data suppression sequence and the steep bill of materials data smoothed sequence, and then classify and store each noise-free bill of materials data domain, thereby effectively improving the storage efficiency when classifying and storing the bill of materials data to be stored.

[0049] In order to better understand the above technical solution, the following will be combined with the accompanying drawings and specific implementation methods to describe the above technical solution in detail. Figure 1 , which is an exemplary flow chart of an intelligent material management method according to some embodiments of the present application. The intelligent material management method 100 mainly includes the following steps:

[0050] In step 101, a bill of materials to be stored in a project is obtained to obtain a bill of materials data set to be stored.

[0051] In the specific implementation, first of all, it is necessary to clarify the scope, requirements and plan of the engineering project, understand the various engineering materials and items that need to be stored in the engineering project, including information data such as name, specifications, quantity, quality standards, and purpose. The bill of materials data to be stored can be collected through on-site surveys, engineering drawings, design documents, etc., and the information of various materials required for the project can be collected to obtain the bill of materials data set to be stored.

[0052] In step 102, a neighborhood partitioning coefficient set is determined based on the BOM data set to be stored, and a flat and steep neighborhood partitioning is performed on the BOM data set to be stored based on the neighborhood partitioning coefficient set and the neighborhood partitioning decision value to obtain a flat BOM data domain and a steep BOM data domain.

[0053] In some embodiments, the neighborhood partition coefficient set may be determined by using the bill of materials data set to be stored in the following manner:

[0054] Perform linear fitting on the stored bill of materials data set to obtain a bill of materials fitting curve;

[0055] The neighborhood segmentation coefficient corresponding to each BOM data in the BOM data set to be stored is determined by the BOM fitting curve, thereby obtaining a neighborhood segmentation coefficient set.

[0056] In specific implementation, the least squares method is used to perform linear fitting on the bill of materials data set to be stored to obtain a bill of materials fitting curve. The bill of materials fitting curve is used to determine the neighborhood segmentation coefficient corresponding to each bill of materials data in the bill of materials data set to be stored, and then the neighborhood segmentation coefficient set is obtained in the following manner, namely:

[0057] Determine the curvature of the bill of materials data set corresponding to the bill of materials fitting curve;

[0058] Determine the curvature of each BOM data in the BOM data set on the BOM fitting curve;

[0059] The neighborhood segmentation coefficient corresponding to each BOM data set is determined by the curvature corresponding to the BOM data set and the curvature corresponding to each BOM data, thereby obtaining a neighborhood segmentation coefficient set. In specific implementation, the neighborhood segmentation coefficient can be determined according to the following formula:

[0060]

[0061] Among them, s(x i) represents the neighborhood partition coefficient corresponding to the i-th BOM data, M represents the total amount of BOM data in the BOM dataset, x i Indicates the i-th bill of materials data in the bill of materials dataset, u i Indicates the curvature corresponding to the i-th bill of materials data, u m Represents the curvature corresponding to the mth BOM data, and u represents the curvature corresponding to the BOM data set. It should be noted that in this application, the neighborhood splitting coefficient represents the characteristic information content in the BOM data in the BOM data set, and is the splitting coefficient used to divide the characteristic information BOM data domain. The larger the neighborhood splitting coefficient, the richer the characteristic information content in the BOM data, and the smaller the neighborhood splitting coefficient, the less characteristic information content in the BOM data.

[0062] It should be noted that the neighborhood segmentation coefficient can be used to more accurately determine the characteristics of the bill of materials data, which helps to subsequently classify the bill of materials data into two categories: flat and steep, thereby improving the accuracy of bill of materials data classification.

[0063] In some embodiments, the flat and steep neighborhood segmentation of the BOM data set to be stored is performed using the neighborhood segmentation coefficient set and the neighborhood segmentation decision value to obtain the flat BOM data domain and the steep BOM data domain in the following manner, namely:

[0064] The BOM data whose neighborhood segmentation coefficient is greater than the neighborhood segmentation decision value in the BOM data set to be stored is used as steep BOM data, thereby obtaining a steep BOM data domain;

[0065] The BOM data whose neighborhood segmentation coefficient is less than the neighborhood segmentation decision value in the BOM data set to be stored is taken as the flat BOM data, thereby obtaining a flat BOM data domain.

[0066] In specific implementation, the neighborhood segmentation decision value can be set based on historical segmentation experience and is not limited here.

[0067] It should be noted that after dividing the BOM data into a flat BOM data domain and a steep BOM data domain through the neighborhood splitting coefficient, different BOM data processing methods can be used to improve the processing efficiency of the BOM data, which helps to improve the classification and storage efficiency of the BOM data.

[0068] In step 103, a neighborhood discrete decision boundary is determined according to the flat BOM data domain and a preset neighborhood discrete coefficient, and the flat BOM data domain is converted into a flat BOM data suppression sequence using the neighborhood discrete decision boundary.

[0069] In some embodiments, the neighborhood discrete decision boundary may be determined based on the flat BOM data domain and a preset neighborhood discrete coefficient in the following manner, namely:

[0070] Determine the curvature corresponding to the flat BOM data domain;

[0071] Determine the neighborhood dispersion coefficient;

[0072] determining the curvature corresponding to each flat BOM data in the flat BOM data domain;

[0073] The neighborhood discrete decision bound of the flat BOM data domain is determined by the curvature corresponding to the flat BOM data domain, the neighborhood discrete coefficient, and the curvature corresponding to each flat BOM data. In specific implementation, the upper and lower bounds of the neighborhood discrete decision bound can be determined according to the following formula:

[0074]

[0075] Among them, Λ′ represents the upper bound of the neighborhood discrete decision boundary, Λ ′ represents the lower bound of the neighborhood discrete decision boundary, u r Indicates the curvature corresponding to the flat BOM data domain, M r represents the total amount of data in the flat BOM data domain, λ represents the neighborhood dispersion coefficient, Represents the curvature corresponding to the i-th flat BOM data in the flat BOM data domain. It should be noted that, in this application, the neighborhood discrete decision boundary of the flat BOM data domain is used to eliminate the decision interval of the flat BOM data in the flat BOM data domain, and the neighborhood discrete coefficient is a coefficient used to adjust the accuracy of the neighborhood discrete decision boundary. The neighborhood discrete coefficient can be obtained through historical experiments and will not be repeated here.

[0076] In some embodiments, converting the flat BOM data domain into a flat BOM data suppression sequence is to eliminate, for each flat BOM data in the flat BOM data domain, the flat BOM data that is not within the discrete decision boundary of the neighborhood, thereby obtaining the flat BOM data suppression sequence. In specific implementation, the mean of the curvatures corresponding to all flat BOM data in the flat BOM data domain is used as the curvature corresponding to the flat BOM data domain, and then the flat BOM data whose corresponding curvature is not within the discrete decision boundary of the neighborhood is used as discrete data, and the discrete data is eliminated to obtain the flat BOM data suppression sequence, thereby eliminating discrete noise and interfering flat BOM data in the flat BOM data domain, which helps to improve the processing efficiency of BOM data.

[0077] It should be noted that the neighborhood discrete decision boundary can reduce the discrete noise in the bill of materials data, making the bill of materials data more accurate, helping to improve data quality, reducing the redundancy and complexity of the bill of materials data, and thus improving the classification and storage efficiency of the bill of materials data.

[0078] In step 104, a spatial smoothing factor and a feature preserving factor are determined according to the steep BOM data domain, and the steep BOM data domain is converted into a steep BOM data smoothing sequence by using the spatial smoothing factor and the feature preserving factor.

[0079] In some embodiments, determining the spatial smoothing factor and the feature preservation factor based on the steep BOM data domain may be determined according to the following formula:

[0080]

[0081] where ω represents the spatial smoothing factor for the steep BOM data domain, Denotes the characteristic maintenance factor of the steep BOM data domain, β i represents the i-th steep BOM data in the steep BOM data domain, m represents the total amount of data in the steep BOM data domain, β j Represents the j-th steep BOM data in the steep BOM data domain, x, α1 and α2 all represent intermediate application variables and have no practical meaning. It should be noted that, in this application, the spatial smoothing factor is a factor used to control the degree of spatial smoothing of the smoothed sequence of steep BOM data, and the feature maintenance factor is a factor used to control the degree of feature maintenance of the smoothed sequence of steep BOM data.

[0082] In some embodiments, the steep BOM data domain is converted into a steep BOM data smoothed sequence by using the spatial smoothing factor and the feature maintaining factor in the following manner, namely:

[0083] Determine the BOM data filtering normal vector;

[0084] For each steep BOM data in the steep BOM data domain, the steep BOM data is converted into smooth steep BOM data by using the BOM data filtering normal vector, the spatial smoothing factor of the steep BOM data domain, and the feature maintenance factor of the steep BOM data domain, thereby obtaining a smoothed sequence of steep BOM data. In a specific implementation, the smoothed steep BOM data can be determined according to the following formula:

[0085]

[0086] Among them, β′ irepresents the i-th smooth steep BOM data in the smooth sequence of steep BOM data, β i represents the i-th steep BOM data in the steep BOM data domain, n represents the BOM data filtering normal vector, m represents the total amount of data in the steep BOM data domain, β j represents the j-th steep BOM data in the steep BOM data domain, ω represents the spatial smoothing factor of the steep BOM data domain, Represents the feature maintenance factor of the steep BOM data domain. It should be noted that, in this application, the BOM data filtering normal vector is the normal vector that controls the filtering translation direction when filtering out noise in the steep BOM data domain.

[0087] In specific implementation, the filtering normal vector of the bill of materials data is determined by plane fitting. A normal equation can be constructed at a point in the steep bill of materials data domain. The normal equation is usually expressed as the distance from the point to the plane. The least squares method or other fitting methods can be used to fit the parameters in the normal equation to obtain the filtering normal vector of the bill of materials data. The steep bill of materials data in the steep bill of materials data domain is smoothed by normal translation, which helps to improve the processing efficiency of the bill of materials data. In actual implementation.

[0088] It should be noted that conversion can reduce irregular changes in BOM data, make BOM data more accurate, simplify the complexity of subsequent BOM data processing, improve the efficiency of BOM data processing, and thus improve the classification and storage efficiency of BOM data.

[0089] In step 105 , a plurality of noise-free BOM data domains are determined by using the flat BOM data suppression sequence and the steep BOM data smoothing sequence, and each noise-free BOM data domain is then classified and stored.

[0090] In some embodiments, the following method may be used to determine multiple noise-free BOM data domains using the flat BOM data suppression sequence and the steep BOM data smoothing sequence:

[0091] Determining a noise-free BOM data set to be stored by using the flat BOM data suppression sequence and the steep BOM data smoothing sequence;

[0092] determining a spacing growth matrix for the noise-free bill of materials data set;

[0093] The noise-free bill of materials data set is decoupled by data domain according to the spacing growth matrix to obtain multiple noise-free bill of materials data domains.

[0094] In specific implementation, the flat BOM data suppression sequence and the steep BOM data smooth sequence can be coupled to obtain a noise-free BOM data set to be stored, that is, the flat BOM data suppression sequence and the steep BOM data smooth sequence are merged together to obtain a noise-free BOM data set to be stored, and the noise and interference data in the noise-free BOM data set to be stored have been removed. It should be noted that the noise-free BOM data set is more compact than the original data, does not contain noise and irregular changes, reduces data redundancy and complexity, and can classify and store BOM data more accurately, thereby improving the efficiency of classification and storage of BOM data.

[0095] It should be noted that, in the present application, the spacing growth matrix is ​​a spacing growth matrix containing the data point distances between all noise-free BOM data, and the spacing growth matrix represents the differences between all noise-free BOM data in the noise-free BOM data set. In specific implementation, the data point distances between all noise-free BOM data in the noise-free BOM data set to be stored are determined. The Euclidean distance between all noise-free BOM data can be determined by the Euclidean measurement method, so that the Euclidean distance between all noise-free BOM data is used as the data point distance between all noise-free BOM data. A matrix is ​​constructed by the data point distances between all noise-free BOM data, that is, the growth matrix of the data point distances between all noise-free BOM data. The rows and columns of the spacing growth matrix respectively represent the noise-free BOM data in the noise-free BOM data set, and the elements in the spacing growth matrix represent the Euclidean distances between the corresponding noise-free BOM data.

[0096] In some embodiments, the noise-free BOM data set is decoupled according to the spacing growth matrix to obtain multiple noise-free BOM data domains in the following manner:

[0097] Determine the local BOM data density of all noise-free BOM data using a spacing growth matrix;

[0098] determining a plurality of noise-free BOM data domain centers according to local BOM data densities of all noise-free BOM data;

[0099] All noise-free BOM data are decoupled according to multiple noise-free BOM data domain centers to obtain multiple noise-free BOM data domains.

[0100] In specific implementation, the number of noise-free BOM data around a noise-free BOM data can be obtained by using the spacing growth matrix and setting the data point spacing, and then the local BOM data density of the noise-free BOM data can be obtained. The above steps can be repeated to obtain the local BOM data density of all noise-free BOM data. The top k noise-free BOM data with the largest local BOM data density are used as the centers of the noise-free BOM data domain. In actual implementation, the value of k can be determined based on historical experience and the requirements of the engineering project. It will not be repeated here. All noise-free BOM data in the noise-free BOM data set are divided by the obtained k noise-free BOM data domain centers, thereby determining multiple independent noise-free BOM data domains, i.e., the decoupling process. The noise-free BOM data in each noise-free BOM data domain have high similarity. It should be noted that through data domain decoupling, multiple independent noise-free BOM data domains are obtained, which can more finely classify BOM data and improve the precision and accuracy of BOM data. When storing in categories, appropriate data structures and storage methods can be selected according to the characteristics of each noise-free BOM data domain, thereby improving storage efficiency.

[0101] In some embodiments, each noise-free bill of materials data field may be classified and stored in the following manner:

[0102] Determine the inter-domain fuzzy factor for each noise-free BOM data domain;

[0103] The noise-free BOM data domain in which the inter-domain fuzzy factor is smaller than the fuzzy decision value is used as the BOM data domain to be stored, thereby obtaining a plurality of BOM data domains to be stored;

[0104] Each BOM data field to be stored is classified and stored as a class.

[0105] In specific implementation, different noise-free bill of materials data domains to be stored can adopt different storage structures and storage strategies to be stored in the engineering material database to complete the storage of engineering material bill of materials data in engineering projects. It should be noted that the inter-domain fuzzy factor is less than the fuzzy decision value, which indicates that the noise-free bill of materials data in the noise-free bill of materials data domain have high similarity and low category fuzziness.

[0106] In some embodiments, the inter-domain fuzzy factor of each noise-free BOM data domain may be determined in the following manner:

[0107] For each noise-free BOM data domain, determining the total amount of noise-free BOM data in the noise-free BOM data domain;

[0108] Obtaining the noise-free BOM data domain center of the noise-free BOM data domain;

[0109] Determine the inner accumulation coefficient of the noise-free BOM data domain;

[0110] The inter-domain fuzzy factor of the noise-free BOM data domain is determined by the total amount of noise-free BOM data in the noise-free BOM data domain, the center of the noise-free BOM data domain of the noise-free BOM data domain, and the inner accumulation coefficient of the noise-free BOM data domain. Then, the inter-domain fuzzy factor of each noise-free BOM data domain is determined. In specific implementation, the inter-domain fuzzy factor can be determined according to the following formula:

[0111]

[0112] Where μ(k) represents the inter-domain fuzzy factor of the k-th noise-free BOM data domain, T represents the total amount of noise-free BOM data in the k-th noise-free BOM data domain, and y t represents the t-th noise-free BOM data in the k-th noise-free BOM data domain, R k represents the center of the noise-free BOM data domain of the k-th noise-free BOM data domain, Ω k Represents the inner clustering coefficient of the kth noise-free BOM data domain. It should be noted that, in this application, the inter-domain fuzzy factor represents the degree of dispersion of the noise-free BOM data in the noise-free BOM data domain. The larger the inter-domain fuzzy factor, the greater the dispersion of the noise-free BOM data in the noise-free BOM data domain, and the greater the possibility that the noise-free BOM data domain is a fuzzy BOM data domain. The smaller the inter-domain fuzzy factor, the smaller the dispersion of the noise-free BOM data in the noise-free BOM data domain. The inner clustering coefficient represents the degree of approach of all noise-free BOM data in the noise-free BOM data domain to the center of the noise-free BOM data domain. The larger the inner clustering coefficient, the closer all noise-free BOM data are to the center of the noise-free BOM data domain.

[0113] In specific implementation, the global distribution information in the noise-free BOM data domain can be described by the inter-domain fuzzy factor. For each noise-free BOM data domain, the mean distance between all noise-free BOM data in the noise-free BOM data domain and the center of the noise-free BOM data domain can be used as the inner clustering coefficient of the noise-free BOM data domain. The mean distance can be determined by the spacing growth matrix.

[0114] It should be noted that the noise-free bill of materials data domain to be stored is determined according to the inter-domain fuzzy factor, and a noise-free bill of materials data domain to be stored is used as a noise-free bill of materials data class to be stored, so that the bill of materials data in each class are more similar, which improves the accuracy of bill of materials data classification. By storing noise-free bill of materials data domains with different characteristics separately, the most suitable data storage structure and algorithm can be selected to optimize the classification storage efficiency.

[0115] In this application, firstly, the neighborhood splitting coefficient can be used to more accurately divide the bill of materials data set into two categories, flat and steep, thereby improving the accuracy of the bill of materials data classification, so that different bill of materials data processing methods can be used to improve the processing efficiency of the bill of materials data. Secondly, the discrete noise and irregular changes in the bill of materials data can be reduced through conversion, making the bill of materials data more accurate, helping to reduce the redundancy and complexity of the bill of materials data, thereby improving the classification and storage efficiency of the bill of materials data. Furthermore, the determined noise-free bill of materials data set does not contain noise and irregular changes, and the bill of materials data can be classified and stored more accurately, thereby improving the efficiency of the classification and storage of the bill of materials data. Then, through data domain decoupling, the bill of materials data can be classified more finely, improving the accuracy and classification accuracy of the bill of materials data. Finally, the noise-free bill of materials data domain to be stored is determined according to the inter-domain fuzzy factor, which improves the accuracy of the bill of materials data classification. By storing noise-free bill of materials data domains with different characteristics separately, the most suitable data storage structure and algorithm can be selected, effectively improving the storage efficiency when classifying and storing the bill of materials data to be stored.

[0116] In addition, in another aspect of the present application, in some embodiments, the present application provides an intelligent material management system, the system includes a material list data storage unit, reference Figure 2 , which is a schematic diagram of exemplary hardware and / or software of a bill of materials data storage unit according to some embodiments of the present application. The bill of materials data storage unit 200 includes: a bill of materials data set determination module 201 to be stored, a bill of materials data domain segmentation module 202, a flat bill of materials data suppression sequence determination module 203, a steep bill of materials data smoothing sequence determination module 204, and a bill of materials data classification storage module 205, which are described as follows:

[0117] The module 201 for determining a bill of materials data set to be stored is mainly used to obtain a bill of materials to be stored in a project and obtain a bill of materials data set to be stored.

[0118] The BOM data domain segmentation module 202 in this application is mainly used to determine a neighborhood segmentation coefficient set based on the BOM data set to be stored, and perform flat and steep neighborhood segmentation on the BOM data set to be stored using the neighborhood segmentation coefficient set and the neighborhood segmentation decision value to obtain a flat BOM data domain and a steep BOM data domain;

[0119] The flat BOM data suppression sequence determination module 203 in the present application is mainly used to determine a neighborhood discrete decision boundary based on the flat BOM data domain and a preset neighborhood discrete coefficient, and convert the flat BOM data domain into a flat BOM data suppression sequence using the neighborhood discrete decision boundary;

[0120] A steep BOM data smoothing sequence determining module 204 is used in the present application to determine a spatial smoothing factor and a feature maintenance factor based on the steep BOM data domain, and convert the steep BOM data domain into a steep BOM data smoothing sequence using the spatial smoothing factor and the feature maintenance factor.

[0121] The bill of materials data classification storage module 205 in this application is mainly used to determine multiple noise-free bill of materials data domains through the flat bill of materials data suppression sequence and the steep bill of materials data smoothing sequence, and then classify and store each noise-free bill of materials data domain.

[0122] The above describes in detail the examples of the intelligent material management method and related equipment provided by the embodiments of the present application. It can be understood that the corresponding device includes a hardware structure and / or software module corresponding to the execution of each function in order to realize the above functions. Those skilled in the art should easily appreciate that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0123] In some embodiments, the present application also provides a computer device, which includes a memory and a processor, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned intelligent material management method.

[0124] In some embodiments, reference Figure 3 , the dotted line in the figure indicates that the unit or module is optional. The figure is a structural diagram of a computer device according to an intelligent material management method provided by an embodiment of the present application. The intelligent material management method in the above embodiment can be Figure 3The computer device 300 is implemented as shown, and the computer device 300 includes at least one processor 301, a memory 302 and at least one communication unit 305. The computer device 300 can be a terminal device, a server or a chip.

[0125] The processor 301 may be a general-purpose processor or a dedicated processor. For example, the processor 301 may be a central processing unit (CPU), which may be used to control the computer device 300, execute software programs, and process data from the software programs. The computer device 300 may also include a communication unit 305 for inputting (receiving) and outputting (transmitting) signals.

[0126] For example, the computer device 300 may be a chip, the communication unit 305 may be an input and / or output circuit of the chip, or the communication unit 305 may be a communication interface of the chip, and the chip may be a component of a terminal device, a network device, or other device.

[0127] For another example, the computer device 300 may be a terminal device or a server, and the communication unit 305 may be a transceiver of the terminal device or the server, or the communication unit 305 may be a transceiver circuit of the terminal device or the server.

[0128] The computer device 300 may include one or more memories 302, on which a program 304 is stored. The program 304 can be executed by the processor 301 to generate instructions 303, so that the processor 301 executes the method described in the above method embodiment according to the instructions 303. Optionally, the memory 302 may also store data (such as a target audit model). Optionally, the processor 301 may also read data stored in the memory 302. The data may be stored at the same storage address as the program 304, or the data may be stored at a different storage address from the program 304.

[0129] The processor 301 and the memory 302 may be provided separately or integrated together, for example, integrated on a system on chip (SOC) of a terminal device.

[0130] It should be understood that each step of the above method embodiment can be completed by a hardware-based logic circuit or software-based instructions in the processor 301. The processor 301 can be a central processing unit, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, such as discrete gates, transistor logic devices, or discrete hardware components.

[0131] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0132] For example, in some embodiments, the present application also provides a computer-readable storage medium, in which instructions or codes are stored. When the instructions or codes are run on a computer, the computer implements the above-mentioned intelligent material management method when executing.

[0133] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional 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 application.

[0134] Obviously, those skilled in the art may make various changes and modifications to the present application without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present application fall within the scope of the claims and their equivalents, the present application is intended to include such modifications and variations.

Claims

1. An intelligent material management method, characterized in that: The steps include: Obtain the bill of materials to be stored in the project and obtain the bill of materials data set to be stored; Determining a neighborhood segmentation coefficient set based on the bill of materials data set to be stored, and performing flat and steep neighborhood segmentation on the bill of materials data set to be stored based on the neighborhood segmentation coefficient set and the neighborhood segmentation decision value to obtain a flat bill of materials data domain and a steep bill of materials data domain; Determining a neighborhood discrete decision boundary based on the flat BOM data domain and a preset neighborhood discrete coefficient, and converting the flat BOM data domain into a flat BOM data suppression sequence using the neighborhood discrete decision boundary; Determining a spatial smoothing factor and a feature maintaining factor according to the steep BOM data domain, and converting the steep BOM data domain into a steep BOM data smoothing sequence by using the spatial smoothing factor and the feature maintaining factor; A plurality of noise-free BOM data domains are determined by using the flat BOM data suppression sequence and the steep BOM data smoothing sequence, and each noise-free BOM data domain is then classified and stored.

2. The method according to claim 1, wherein Determining the neighborhood partition coefficient set using the bill of materials data set to be stored specifically includes: Perform linear fitting on the stored bill of materials data set to obtain a bill of materials fitting curve; The neighborhood segmentation coefficient corresponding to each BOM data in the BOM data set to be stored is determined by the BOM fitting curve, thereby obtaining a neighborhood segmentation coefficient set.

3. The method according to claim 1, wherein The flat and steep neighborhood segmentation is performed on the bill of materials data set to be stored using the neighborhood segmentation coefficient set and the neighborhood segmentation decision value to obtain a flat bill of materials data domain and a steep bill of materials data domain. Specifically, the flat and steep neighborhood segmentation is performed on the bill of materials data set to be stored. The BOM data whose neighborhood segmentation coefficient is greater than the neighborhood segmentation decision value in the BOM data set to be stored is used as steep BOM data, thereby obtaining a steep BOM data domain; The BOM data whose neighborhood segmentation coefficient is less than the neighborhood segmentation decision value in the BOM data set to be stored is taken as the flat BOM data, thereby obtaining a flat BOM data domain.

4. The method according to claim 1, wherein Converting the flat BOM data domain into a flat BOM data suppression sequence is to, for each flat BOM data in the flat BOM data domain, remove the flat BOM data that is not in the neighborhood discrete decision boundary, thereby obtaining the flat BOM data suppression sequence.

5. The method according to claim 1, wherein Converting the steep BOM data domain into a steep BOM data smoothing sequence by using the spatial smoothing factor and the feature maintaining factor specifically includes: Determine the BOM data filtering normal vector; For each steep BOM data in the steep BOM data domain, the steep BOM data is converted into smooth steep BOM data by using the BOM data filtering normal vector, the spatial smoothing factor of the steep BOM data domain, and the feature maintenance factor of the steep BOM data domain, thereby obtaining a smoothed sequence of steep BOM data, wherein the smoothed steep BOM data is determined according to the following formula: Among them, β′ i represents the i-th smooth steep BOM data in the smooth sequence of steep BOM data, β i represents the i-th steep BOM data in the steep BOM data domain, n represents the BOM data filtering normal vector, m represents the total amount of data in the steep BOM data domain, β j represents the j-th steep BOM data in the steep BOM data domain, ω represents the spatial smoothing factor of the steep BOM data domain, Indicates the characteristic maintenance factor for steep BOM data domains.

6. The method according to claim 1, wherein Determining a plurality of noise-free BOM data domains by using the flat BOM data suppression sequence and the steep BOM data smoothing sequence specifically includes: Determining a noise-free BOM data set to be stored by using the flat BOM data suppression sequence and the steep BOM data smoothing sequence; determining a spacing growth matrix for the noise-free bill of materials data set; The noise-free bill of materials data set is decoupled by data domain according to the spacing growth matrix to obtain multiple noise-free bill of materials data domains.

7. The method according to claim 1, wherein Classification and storage of each noise-free bill of materials data field specifically include: Determine the inter-domain fuzzy factor for each noise-free BOM data domain; The noise-free BOM data domain whose inter-domain fuzzy factor is smaller than the fuzzy decision value is used as the BOM data domain to be stored, thereby obtaining a plurality of BOM data domains to be stored; Each BOM data field to be stored is classified and stored as a class.

8. An intelligent material management system, characterized in that: A bill of materials data storage unit is included, and the bill of materials data storage unit includes: The module for determining the data set of the bill of materials to be stored is used to obtain the bill of materials to be stored in the engineering project and obtain the data set of the bill of materials to be stored; a bill of materials data domain segmentation module, configured to determine a neighborhood segmentation coefficient set based on the bill of materials data set to be stored, and perform flat and steep neighborhood segmentation on the bill of materials data set to be stored based on the neighborhood segmentation coefficient set and the neighborhood segmentation decision value to obtain a flat bill of materials data domain and a steep bill of materials data domain; a flat BOM data suppression sequence determination module, configured to determine a neighborhood discrete decision boundary based on the flat BOM data domain and a preset neighborhood discrete coefficient, and convert the flat BOM data domain into a flat BOM data suppression sequence using the neighborhood discrete decision boundary; a steep BOM data smoothing sequence determining module, configured to determine a spatial smoothing factor and a feature maintaining factor according to the steep BOM data domain, and convert the steep BOM data domain into a steep BOM data smoothing sequence using the spatial smoothing factor and the feature maintaining factor; The BOM data classification and storage module is used to determine a plurality of noise-free BOM data domains through the flat BOM data suppression sequence and the steep BOM data smoothing sequence, and then classify and store each noise-free BOM data domain.

9. A computer device, characterized in that: The computer device includes a memory and a processor, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the intelligent material management method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing instructions or codes, which, when executed on a computer, enable the computer to implement the intelligent material management method according to any one of claims 1 to 7.

Images