Steel product type data standardization conversion method and system

Abstract

The invention relates to a steel product type data standardization conversion method and system, and the method comprises the following steps: S1, obtaining corpus data describing a steel product, constructing a data set, and obtaining a plurality of keywords representing the properties of the steel product through word decomposition; s2, aiming at each property of the steel product, configuring an unambiguous standard property word, and constructing a mapping relation between the keyword and the standard property word; s3, configuring a steel product naming rule based on the property of the steel product; and S4, to-be-converted steel product type data are obtained, a plurality of standard property words are obtained through matching of the mapping relation, and converted steel product type data are obtained through the steel product naming rule. Compared with the prior art, the method has the advantages of improving the data quality, improving the user experience of an internet platform and the like.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for standardizing and converting steel product category data. Background Art

[0002] As the platformization of the steel industry continues to advance, the number of steel mills connected to the Internet steel platform continues to increase. As a platform, it is necessary to integrate and merge the category data of each steel mill to form a unified standard for the platform. Since each steel mill is located in different regions and has different customs, and the national standard for steel mill categories is not a mandatory requirement, there are many problems with the naming of steel categories.

[0003] When the Internet steel platform connects with a large number of steel mills, it usually directly imports the category data of each steel mill. The large amount of data accumulated over the years has different standards and repeated classifications. Manual data cleaning is inefficient, and an automated data standardization method is needed. Summary of the invention

[0004] The purpose of the present invention is to overcome the defects of the above-mentioned prior art and to provide a method and system for standardizing and converting steel product category data, so as to solve or partially solve the problems of inconsistent naming of steel categories and inconvenience of Internet steel platforms.

[0005] The purpose of the present invention can be achieved by the following technical solutions:

[0006] One aspect of the present invention provides a method for standardizing and converting steel product category data, comprising the following steps:

[0007] Step S1, obtaining corpus data describing steel products and constructing a data set, and obtaining multiple keywords representing the properties of steel products through word decomposition;

[0008] Step S2, for each property of the steel product, configure an unambiguous standard property word, and construct a mapping relationship between the keyword and the standard property word;

[0009] Step S3, configuring steel product naming rules based on the properties of the steel products;

[0010] Step S4, obtaining the steel product category data to be converted, using the mapping relationship to match to obtain a plurality of standard property words, and using the steel product naming rules to obtain the converted steel product category data.

[0011] As a preferred technical solution, the step S1 includes:

[0012] Step S101, obtaining corpus data describing steel products, and constructing a data set by deduplication and partitioning;

[0013] Step S102, for the data set, a plurality of keywords with independent meanings are obtained by word decomposition.

[0014] As a preferred technical solution, the step S2 includes:

[0015] Step S201, for each property of the steel product, according to industry practice, a commonly used and unambiguous standard property word is configured for each property;

[0016] Step S202, matching the standard property words with the keywords extracted in step S1, and constructing a mapping relationship between the keywords and the standard property words.

[0017] As a preferred technical solution, the category properties of steel products include chemical element composition, morphology, finished product process, specifications, uses, characteristics, quality grades, surfaces, processing, heat treatment, coating properties and pipe properties.

[0018] As a preferred technical solution, in the step S3, the naming rules of the steel products are configured by configuring the order of the properties of the steel products.

[0019] As a preferred technical solution, the naming rule of the steel products is: purpose + characteristics + process characteristics + process + coating composition + composition + specification + surface + processing + location + morphology + quality grade.

[0020] As a preferred technical solution, it also includes:

[0021] Step S5, manually checking and correcting the steel product type data converted in step S4.

[0022] Another aspect of the present invention provides a steel product category data standardization conversion system, comprising:

[0023] The keyword extraction module is used to obtain the corpus data describing steel products and construct a data set, and obtain multiple keywords that characterize the properties of steel products through word decomposition;

[0024] A mapping relationship building module is used to configure an unambiguous standard property word for each property of the steel product and to build a mapping relationship between the keyword and the standard property word;

[0025] A naming relationship configuration module is used to configure steel product naming rules based on the properties of steel products;

[0026] The steel product category data standardization conversion module is used to obtain the steel product category data to be converted, use the mapping relationship to match to obtain multiple standard property words, and use the steel product naming rules to obtain the converted steel product category data.

[0027] As a preferred technical solution, it also includes:

[0028] The verification module is used to manually verify and correct the converted steel product type data.

[0029] As a preferred technical solution, the category properties of steel products include chemical element composition, morphology, finished product process, specifications, uses, characteristics, quality grades, surfaces, processing, heat treatment, coating properties and pipe properties.

[0030] Compared with the prior art, the present invention has at least one of the following beneficial effects:

[0031] (1) Improve data quality: This invention adopts the standardization method of "decomposition-induction-standard-example", which is not only applicable to the complex classification of steel categories, but also provides new ideas for the standardization of complex things in other fields. From decomposing keywords to summarizing standard properties, and then to determining naming standards and conversion verification, a systematic standardization process is formed. Through standardized naming and classification, the quality and consistency of steel category data on the platform are improved, providing reliable guarantee for subsequent data analysis, mining and application.

[0032] (2) Improving the user experience of the Internet platform: The present invention adopts a naming rule that fully considers industry practices and reading fluency, so that the standardized names are both professional and easy to understand. Standardized naming and classification make it more convenient for users to search and compare steel categories, thereby improving user experience and satisfaction.

[0033] (3) Strong traceability: Standardized naming and classification allow each batch of steel to be traced back to its specific production process and raw material source, enhancing product traceability and quality control capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a flow chart of the method for standardizing and converting steel product category data in the embodiment;

[0035] Figure 2 Schematic diagram of the steel product type data standardization conversion method system in the embodiment. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0037] Example 1

[0038] In view of the problems existing in the above-mentioned prior art, this embodiment provides a method for standardizing and converting steel product category data. This embodiment classifies steel products by repeatedly grouping things with similar properties to form a classification tree. Considering that the properties of steel products are usually partially reflected in the category name, the unreflected part needs to be supplemented based on the experience of steel practitioners. Based on the above situation, on the basis of category, the "decomposition-induction-standard-example" method is adopted to standardize steel category data.

[0039] See also Figure 1 , this method mainly comprises the following steps:

[0040] Step S1, keyword decomposition: obtain corpus data describing steel products and construct a data set, and obtain multiple keywords that characterize the properties of steel products through word decomposition. This step specifically includes:

[0041] Step S101, obtaining corpus data describing steel products, and constructing a data set by deduplication and partitioning.

[0042] Step S102, for the data set, a plurality of keywords with independent meanings are obtained by word decomposition.

[0043] Specifically, for the category name, it is refined into multiple keywords with independent meanings. Each keyword reflects one or more characteristics. For example, for the category name "cold-rolled oriented coil", it can be decomposed into keywords such as "cold-rolled", "oriented", and "coil". "Cold-rolled" indicates that its process is cold rolling; "coil" indicates that its form is steel coil; "oriented" refers to oriented silicon steel, which is silicon steel, and the crystal structure of the steel plate has certain rules and directions.

[0044] In this embodiment, step S102 implements word decomposition based on a two-way matching method of dictionary matching, and the dictionary includes historically extracted keywords and standard property words in step S2.

[0045] Step S2, summarize standard properties: for each property of the steel product, configure an unambiguous standard property word, and construct a mapping relationship between the keyword and the standard property word. This step specifically includes:

[0046] Step S201, for each property of the steel product, according to industry practice, a commonly used and unambiguous standard property word is configured for each property.

[0047] Step S202, matching the standard property words with the keywords extracted in step S1, and constructing a mapping relationship between the keywords and the standard property words.

[0048] Specifically, according to industry practice, the properties of steel products have relatively fair names, for example, "oriented silicon steel" is often used but "oriented silicon steel" is rarely used, and "hot-dip galvanizing" is often used but "hot-dip galvanizing" is rarely used. Based on the principle of no duplication and no omission, for each property, a commonly used and unambiguous name should be selected as the standard property word, corresponding to the decomposed keywords, thus forming a comparison table of steel keywords and standard properties. The category properties of steel products include chemical element composition (ingredients), morphology, finished product process (i.e. the last process of the product), specifications (qualitative description), use, characteristics, quality grade, surface, processing, heat treatment, coating and plating properties and pipe properties.

[0049] Step S3, determine the naming standard: Based on the properties of the steel products, the naming rules of the steel products are configured by configuring the order of the properties of the steel products. Taking into account the industry habits and reading fluency, this method adopts the naming rules of steel products of "use + characteristics + process characteristics + process + coating composition + composition + specification + surface + processing + location + morphology + quality grade".

[0050] Step S4, conversion verification: obtaining the steel product category data to be converted, using the mapping relationship to match to obtain a plurality of standard property words, and using the steel product naming rules to obtain the converted steel product category data.

[0051] Specifically, computer programs are used to standardize the data of steel categories in batches. Multiple properties are extracted through keyword matching, and then the standard properties are combined according to the naming rules to obtain the converted steel categories. Finally, the operator only needs to determine whether the classification is correct and make a small amount of manual corrections.

[0052] This method has the following characteristics:

[0053] (1) Method improvement: A standardization method of "decomposition-induction-standard-example" is provided. This method is not only applicable to the complex classification of steel categories, but also provides new ideas for the standardization of complex things in other fields. From decomposing keywords to summarizing the properties of standards, to determining naming standards and conversion verification, a systematic standardization process has been formed.

[0054] (2) Naming rules: A detailed and comprehensive naming rule for steel products has been formulated, namely "purpose + characteristics + process characteristics + process + coating composition + composition + specification + surface + processing + location + morphology + quality grade". This rule fully takes into account industry practices and reading fluency, making the standardized names both professional and easy to understand.

[0055] (3) Automated processing: Automating the standardization process through programs improves the efficiency of processing large amounts of messy data and reduces the cost and error rate of manual processing. This automated processing method is particularly important in a big data environment and can quickly respond to and process the growing amount of data.

[0056] (4) Comparison table between keywords and standard properties: A comparison table between keywords and standard properties was established. This innovation solved the problems of chaotic standards, difficult traceability, and easy duplication caused by inconsistent naming. Through the comparison table, the standard properties corresponding to each keyword can be found quickly and accurately, providing a solid foundation for subsequent standardization work.

[0057] Example 2

[0058] Based on Example 1, see Figure 2 This embodiment provides a steel product category data standardization conversion system, including:

[0059] The keyword extraction module is used to obtain the corpus data describing steel products and construct a data set, and obtain multiple keywords that characterize the properties of steel products through word decomposition;

[0060] A mapping relationship building module is used to configure an unambiguous standard property word for each property of the steel product and to build a mapping relationship between the keyword and the standard property word;

[0061] A naming relationship configuration module is used to configure steel product naming rules based on the properties of steel products;

[0062] The steel product category data standardization conversion module is used to obtain the steel product category data to be converted, use the mapping relationship to match to obtain multiple standard property words, and use the steel product naming rules to obtain the converted steel product category data.

[0063] The verification module is used to manually verify and correct the converted steel product type data.

[0064] The method and system have the following beneficial effects:

[0065] (1) Improve data quality: Through standardized naming and classification, the quality and consistency of steel category data on the platform are improved, providing reliable guarantees for subsequent data analysis, mining and application.

[0066] (2) Enhanced user experience: Standardized naming and classification make it easier for users to search and compare steel categories, thus improving user experience and satisfaction.

[0067] (3) Reduce operating costs: Automated data processing processes reduce manual intervention, lower labor costs and time costs, while improving processing efficiency and accuracy.

[0068] (4) Promote industry integration: Standardized data formats facilitate data sharing and integration among different steel mills, and promote the integration and development of the steel industry.

[0069] (5) Enhanced traceability: Standardized naming and classification allow each batch of steel to be traced back to its specific production process and raw material source, enhancing product traceability and quality control capabilities.

[0070] Easy to expand and maintain: The standardized method and naming rules proposed in this solution have good scalability and maintainability, and can be continuously adjusted and improved with the development of the industry and technological progress.

[0071] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for standardizing and converting steel product type data, characterized in that: The steps include: Step S1, obtaining corpus data describing steel products and constructing a data set, and obtaining multiple keywords representing the properties of steel products through word decomposition; Step S2, for each property of the steel product, configure an unambiguous standard property word, and construct a mapping relationship between the keyword and the standard property word; Step S3, configuring steel product naming rules based on the properties of the steel products; Step S4, obtaining the steel product category data to be converted, using the mapping relationship to match to obtain a plurality of standard property words, and using the steel product naming rules to obtain the converted steel product category data.

2. A method for standardizing and converting steel product type data according to claim 1, characterized in that: The step S1 comprises: Step S101, obtaining corpus data describing steel products, and constructing a data set by deduplication and partitioning; Step S102, for the data set, a plurality of keywords with independent meanings are obtained by word decomposition.

3. The method for standardizing and converting steel product type data according to claim 1, characterized in that: The step S2 comprises: Step S201, for each property of the steel product, according to industry practice, a commonly used and unambiguous standard property word is configured for each property; Step S202, matching the standard property words with the keywords extracted in step S1, and constructing a mapping relationship between the keywords and the standard property words.

4. The method for standardizing and converting steel product type data according to claim 1, characterized in that: The category properties of steel products include chemical element composition, form, finished product process, specifications, uses, characteristics, quality grades, surface, processing, heat treatment, coating properties and pipe properties.

5. The method for standardizing and converting steel product type data according to claim 1, characterized in that: In the step S3, the naming rules of the steel products are configured by configuring the order of the properties of the steel products.

6. A method for standardizing and converting steel product type data according to claim 5, characterized in that: The naming rule of the steel products is: purpose + characteristics + process characteristics + process + coating composition + composition + specification + surface + processing + location + shape + quality grade.

7. A method for standardizing and converting steel product type data according to claim 1, characterized in that Also includes: Step S5, manually checking and correcting the steel product type data converted in step S4.

8. A steel product type data standardization conversion system, characterized in that: include: The keyword extraction module is used to obtain the corpus data describing steel products and construct a data set, and obtain multiple keywords that characterize the properties of steel products through word decomposition; A mapping relationship building module is used to configure an unambiguous standard property word for each property of the steel product and to build a mapping relationship between the keyword and the standard property word; A naming relationship configuration module is used to configure steel product naming rules based on the properties of steel products; The steel product category data standardization conversion module is used to obtain the steel product category data to be converted, use the mapping relationship to match to obtain multiple standard property words, and use the steel product naming rules to obtain the converted steel product category data.

9. A steel product type data standardization conversion system according to claim 8, characterized in that: Also includes: The verification module is used to manually verify and correct the converted steel product type data.

10. A steel product type data standardization conversion system according to claim 8, characterized in that: The category properties of steel products include chemical element composition, form, finished product process, specifications, uses, characteristics, quality grades, surface, processing, heat treatment, coating properties and pipe properties.

Images