A Classification Method for Construction Supply Chain
By scanning the QR code of the construction materials, obtaining supply information, constructing a membership equation and feature description set, solving the quality and safety problems caused by unclassified storage of construction materials, realizing the safety classification of materials and suitable warehouse matching, and ensuring the construction materials Quality and safety of engineering projects.
Patent Information
- Application Number
- CN202411288185.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-14
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-09-14
AI Technical Summary
The construction materials in the supply chain of construction projects are of various types and natures. Unclassified storage may cause moisture, deterioration, corrosion, pollution or safety accidents of the materials, affecting quality and safety.
By scanning the QR code image of the construction materials, obtaining supply information, constructing a member equation to generate a feature description set, determining the material classification results, and matching the appropriate warehouse for storage.
The safe classification and storage of construction materials is realized, the quality of materials and the safety of engineering projects is ensured, and the risk of passage blockage and accidents is avoided.
Smart Images

Figure CN118797068B_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the technical field of supply chain information processing, and in particular relates to a construction supply chain classification method. Background Art
[0002] A construction project is a complex and large system. Its supply chain covers the entire process from raw material procurement, processing and manufacturing, transportation and distribution to construction site use, involving a large number of construction materials. These construction materials are of various types and different in nature. Different types of construction materials have different storage requirements. For example, some materials need to be moisture-proof, sun-proof or avoid direct contact with other substances. If they are not stored in a classified manner, the materials may become damp, deteriorate, corrode or be contaminated, thus affecting their quality and performance. For another example, some construction materials (such as flammable and explosive items) require special safety measures for storage. If they are mixed with ordinary materials, safety accidents such as fire and explosion may occur. In addition, unclassified storage may also cause channel blockage and increase the risk of personal injury. Therefore, it is necessary to classify and store construction materials in the supply chain of construction projects to ensure safety. Summary of the invention
[0003] In order to solve the above problems, the present invention proposes a construction supply chain classification method.
[0004] The technical solution of the present invention is: a construction supply chain classification method comprises the following steps:
[0005] S1. Obtain supply information of each construction material by scanning the QR code image of each construction material in the supply chain of the construction project;
[0006] S2, construct a membership equation for each sentence of the supply information and generate a corresponding feature description set;
[0007] S3. Determine the classification result of the construction materials based on the feature description set corresponding to the supply information.
[0008] Furthermore, S2 includes the following sub-steps:
[0009] S21, calculating the membership equation of each sentence in the supply information of construction materials;
[0010] S22, traversing the membership equations of all sentences to determine the membership degree of each sentence;
[0011] S23. Determine a feature description set corresponding to the supply information based on the membership degrees of all sentences.
[0012] The beneficial effect of the above further scheme is: in the present invention, the supply information of construction materials includes the requirements of the construction materials for storage conditions, and also includes information such as the size of the construction materials, so the present invention needs to eliminate the redundancy of the supply information and select important information that can participate in the matching of classification results. Each sentence in the supply information of construction materials is traversed, and sentences that meet the characteristic conditions are selected according to the membership equation of each sentence to form a characteristic description set to represent the important data in the supply information.
[0013] Furthermore, in S21, the membership equation of the sentence F The expression is: ; In the formula, M Indicates the number of words in the sentence, IDF 1 represents the maximum inverse text frequency index of a word in a sentence, X 1 represents the word vector corresponding to the maximum inverse text frequency index in the sentence, IDF 2 represents the inverse text frequency index of the second-ranked sentence, X 2 represents the word vector corresponding to the second-ranked inverse text frequency index in the sentence. IDF M represents the minimum inverse text frequency index of a word in a sentence, X M Represents the word vector corresponding to the minimum inverse text frequency index in the sentence.
[0014] The beneficial effect of the above further scheme is: in the present invention, in the membership equation, the maximum inverse text frequency indexes corresponding to the words contained in the sentence are sorted from large to small, the word with the largest inverse text frequency index is used as the first term of the membership equation, and the word with the second largest inverse text frequency index is used as the second term of the membership equation, and so on, to form a membership equation that can reflect the importance distribution of all words in the sentence.
[0015] Further, S22 includes the following sub-steps:
[0016] S221, determining a membership matrix of the supply information according to the membership equation value of each sentence;
[0017] S222, transforming the membership matrix of the supply information to obtain a transformed membership matrix of the supply information;
[0018] S223. Determine the membership of each sentence according to the conversion membership matrix of the supply information.
[0019] Furthermore, in S221, the membership matrix of the supply information D The expression is: ; In the formula, F 1 represents the membership equation value of the first sentence in the supply information, min1 represents the value of the minimum term of the membership equation of the first sentence, max 1 represents the value of the maximum term of the membership equation of the first sentence, F 2 represents the membership equation value of the second sentence in the supply information, min 2 represents the value of the minimum term of the membership equation of the second sentence, max 2 represents the value of the maximum term of the membership equation of the second sentence, F n Indicates the supply information n The membership equation value of the sentence, min n Indicates n The value of the minimum term of the membership equation of the sentence, max n Indicates n The value of the maximum term of the membership equation of the sentence, F N Indicates the supply information N The membership equation value of the sentence, min N Indicates N The value of the minimum term of the membership equation of the sentence, max N Indicates N The value of the maximum term of the membership equation of the sentence.
[0020] The beneficial effect of the above further scheme is: in the present invention, the membership equation contains multiple items, each item can be substituted into the corresponding word vector and the inverse text frequency index value of the word for calculation, and the corresponding value of each item is obtained, and the final membership degree is determined based on the maximum and minimum terms of the membership equation.
[0021] Further, in S222, the conversion membership matrix i The calculation formula for the row element value is: ; In the formula, d i represents the first i The values of the elements of the row at the same position in the membership matrix, c represents a constant, N The number of sentences representing supply information, Indicates a round-up operation.
[0022] The number of rows of the conversion membership matrix is the same as that of the membership matrix. The elements of each row in the membership matrix are processed to obtain the conversion membership matrix.
[0023] Furthermore, the membership of the sentence e The calculation formula is: ; In the formula, Erepresents the transition membership matrix of supply information, Represents the membership equation value of the sentence.
[0024] Furthermore, in S23, the sentences whose membership degree satisfies the characteristic condition are taken as the characteristic description set, wherein the expression of the characteristic condition is: ; In the formula, N The number of sentences representing supply information, e n Indicates n The membership degree of a sentence.
[0025] Furthermore, S3 includes the following sub-steps:
[0026] S31. Obtain storage information of storage warehouses included in the construction project;
[0027] S32. Calculate the similarity between the feature description set and the storage information of each storage warehouse, and use the storage warehouse with the highest similarity as the classification result of the construction materials.
[0028] The storage information of each storage warehouse contains the storage conditions of the warehouse, so when matching with the supply information, the storage warehouse with the highest text similarity is the most suitable. For example, if the supply information requires construction materials to be stored in a flame retardant manner, a warehouse with flame retardant function needs to be matched for the construction materials.
[0029] The beneficial effects of the present invention are as follows: the present invention extracts features from the supply information of construction materials involved in the supply chain to obtain a feature description set, pairs the feature description set with the storage information of the storage warehouse, matches appropriate warehouses for the construction materials, and completes classification; the present invention is based on the fact that the storage characteristics of construction materials are different, and reasonable separate storage can not only ensure the quality of the construction materials, but also ensure the safety of the construction project. BRIEF DESCRIPTION OF THE DRAWINGS
[0030] Figure 1 Flowchart of the classification method for the construction supply chain. DETAILED DESCRIPTION
[0031] The embodiments of the present invention will be further described below in conjunction with the accompanying drawings.
[0032] like Figure 1 As shown, the present invention provides a construction supply chain classification method, comprising the following steps:
[0033] S1. Obtain supply information of each construction material by scanning the QR code image of each construction material in the supply chain of the construction project;
[0034] S2, construct a membership equation for each sentence of the supply information and generate a corresponding feature description set;
[0035] S3. Determine the classification result of the construction materials based on the feature description set corresponding to the supply information.
[0036] In this embodiment of the present invention, S2 includes the following sub-steps:
[0037] S21, calculating the membership equation of each sentence in the supply information of construction materials;
[0038] S22, traversing the membership equations of all sentences to determine the membership degree of each sentence;
[0039] S23. Determine a feature description set corresponding to the supply information based on the membership degrees of all sentences.
[0040] In the present invention, the supply information of construction materials includes the requirements of the construction materials for storage conditions, and also includes information such as the size of the construction materials. Therefore, the present invention needs to eliminate the redundancy of the supply information and select the important information that can be used for classification result matching. Each sentence in the supply information of construction materials is traversed, and sentences that meet the characteristic conditions are selected according to the membership equation of each sentence to form a characteristic description set to represent the important data in the supply information.
[0041] In the embodiment of the present invention, in S21, the membership equation of the sentence F The expression is: ; In the formula, M Indicates the number of words in the sentence, IDF 1 represents the maximum inverse text frequency index of a word in a sentence, X 1 represents the word vector corresponding to the maximum inverse text frequency index in the sentence, IDF 2 represents the inverse text frequency index of the second-ranked sentence, X 2 represents the word vector corresponding to the second-ranked inverse text frequency index in the sentence. IDF M represents the minimum inverse text frequency index of a word in a sentence, X M Represents the word vector corresponding to the minimum inverse text frequency index in the sentence.
[0042] In the present invention, in the membership equation, the maximum inverse text frequency indexes corresponding to the words contained in the sentence are sorted from large to small, the word with the largest inverse text frequency index is used as the first term of the membership equation, the word with the second largest inverse text frequency index is used as the second term of the membership equation, and so on, to form a membership equation that can reflect the importance distribution of all words in the sentence.
[0043] In this embodiment of the present invention, S22 includes the following sub-steps:
[0044] S221, determining a membership matrix of the supply information according to the membership equation value of each sentence;
[0045] S222, transforming the membership matrix of the supply information to obtain a transformed membership matrix of the supply information;
[0046] S223. Determine the membership of each sentence according to the conversion membership matrix of the supply information.
[0047] In the embodiment of the present invention, in S221, the membership matrix of the supply information D The expression is: ; In the formula, F 1 represents the membership equation value of the first sentence in the supply information, min 1 represents the value of the minimum term of the membership equation of the first sentence, max 1 represents the value of the maximum term of the membership equation of the first sentence, F 2 represents the membership equation value of the second sentence in the supply information, min 2 represents the value of the minimum term of the membership equation of the second sentence, max 2 represents the value of the maximum term of the membership equation of the second sentence, F n Indicates the supply information n The membership equation value of the sentence, min n Indicates n The value of the minimum term of the membership equation of the sentence, max n Indicates n The value of the maximum term of the membership equation of the sentence, F N Indicates the supply information N The membership equation value of the sentence, min N Indicates N The value of the minimum term of the membership equation of the sentence, max N Indicates N The value of the maximum term of the membership equation of the sentence.
[0048] In the present invention, the membership equation contains multiple items, each of which can be substituted into the corresponding word vector and the inverse text frequency index value of the word for calculation to obtain the corresponding value of each item, and then the final membership degree is determined based on the maximum and minimum terms of the membership equation.
[0049] In the embodiment of the present invention, in S222, the first i The calculation formula for the row element value is: ; In the formula, d irepresents the first i The values of the elements of the row at the same position in the membership matrix, c represents a constant, N The number of sentences representing supply information, Indicates a round-up operation.
[0050] The number of rows of the conversion membership matrix is the same as that of the membership matrix. The elements of each row in the membership matrix are processed to obtain the conversion membership matrix.
[0051] In the embodiment of the present invention, the membership degree of a sentence e The calculation formula is: ; In the formula, E represents the transition membership matrix of supply information, Represents the membership equation value of the sentence.
[0052] In the embodiment of the present invention, in S23, the sentences whose membership degree satisfies the characteristic condition are taken as the characteristic description set, wherein the expression of the characteristic condition is: ; In the formula, N The number of sentences representing supply information, e n Indicates n The membership degree of a sentence.
[0053] In this embodiment of the present invention, S3 includes the following sub-steps:
[0054] S31. Obtain storage information of storage warehouses included in the construction project;
[0055] S32. Calculate the similarity between the feature description set and the storage information of each storage warehouse, and use the storage warehouse with the highest similarity as the classification result of the construction materials.
[0056] The storage information of each storage warehouse contains the storage conditions of the warehouse, so when matching with the supply information, the storage warehouse with the highest text similarity is the most suitable. For example, if the supply information requires construction materials to be stored in a flame retardant manner, a warehouse with flame retardant function needs to be matched for the construction materials.
[0057] Those skilled in the art will appreciate that the embodiments described herein are intended to help readers understand the principles of the present invention, and should be understood that the protection scope of the present invention is not limited to such specific statements and embodiments. Those skilled in the art can make various other specific variations and combinations that do not deviate from the essence of the present invention based on the technical revelations disclosed by the present invention, and these variations and combinations are still within the protection scope of the present invention.
Claims
1. A construction supply chain classification method, characterized in that: The following steps are involved: S1. Obtain supply information of each construction material by scanning the QR code image of each construction material in the supply chain of the construction project; S2, construct a membership equation for each sentence of the supply information and generate a corresponding feature description set; S3, determining the classification result of the construction materials based on the feature description set corresponding to the supply information; The S2 comprises the following sub-steps: S21, calculating the membership equation of each sentence in the supply information of construction materials; S22, traversing the membership equations of all sentences to determine the membership degree of each sentence; S23, determining a feature description set corresponding to the supply information according to the membership degree of all sentences; In S21, the membership equation of the sentence F The expression is: ; In the formula, M Indicates the number of words in the sentence, IDF 1 represents the maximum inverse text frequency index of a word in a sentence, X 1 represents the word vector corresponding to the maximum inverse text frequency index in the sentence, IDF 2 represents the inverse text frequency index of the second-ranked sentence, X 2 represents the word vector corresponding to the second-ranked inverse text frequency index in the sentence. IDF M represents the minimum inverse text frequency index of a word in a sentence, X M Represents the word vector corresponding to the minimum inverse text frequency index in the sentence; The S22 comprises the following sub-steps: S221, determining a membership matrix of the supply information according to the membership equation value of each sentence; S222, transforming the membership matrix of the supply information to obtain a transformed membership matrix of the supply information; S223, determining the membership degree of each sentence according to the conversion membership matrix of the supply information; In S221, the membership matrix of the supply information D The expression is: ; In the formula, F 1 represents the membership equation value of the first sentence in the supply information, min 1 represents the value of the minimum term of the membership equation of the first sentence, max 1 represents the value of the maximum term of the membership equation of the first sentence, F 2 represents the membership equation value of the second sentence in the supply information, min 2 represents the value of the minimum term of the membership equation of the second sentence, max 2 represents the value of the maximum term of the membership equation of the second sentence, F n Indicates the supply information n The membership equation value of the sentence, min n Indicates n The value of the minimum term of the membership equation of the sentence, max n Indicates n The value of the maximum term of the membership equation of the sentence, F N Indicates the supply information N The membership equation value of the sentence, min N Indicates N The value of the minimum term of the membership equation of the sentence, max N Indicates N The value of the maximum term of the membership equation of the sentence; In S222, the conversion membership matrix i The calculation formula for the row element value is: ; In the formula, d i represents the first i The values of the elements of the row at the same position in the membership matrix, c represents a constant, N The number of sentences representing supply information, Indicates rounding up operation; The membership degree of the sentence e The calculation formula is: ; In the formula, E represents the transition membership matrix of supply information, Represents the membership equation value of the sentence; In S23, the sentences whose membership degree satisfies the characteristic condition are taken as the characteristic description set, wherein the expression of the characteristic condition is: ; In the formula, N The number of sentences representing supply information, e n Indicates n The membership degree of a sentence.
2. The construction supply chain classification method according to claim 1, characterized in that: The S3 comprises the following sub-steps: S31. Obtain storage information of storage warehouses included in the construction project; S32. Calculate the similarity between the feature description set and the storage information of each storage warehouse, and use the storage warehouse with the highest similarity as the classification result of the construction materials.
Citation Information
Patent Citations
Log classification method and system
CN110633371A
Small sample text classification method and device, computer equipment and storage medium
CN112989049A
Building whole-process consultation management system based on intelligent data analysis
CN117892734A
Class-based language model and use
US8812299B1
