A product order data processing method, system, electronic device, and storage medium

By performing hierarchical structuring and correlation matching on order data, the problem of automatically extracting product configuration parameters and setting correlation constraints in unstructured order data was solved, enabling accurate generation of product information data and improving the efficiency and accuracy of order data processing.

CN123115256APending Publication Date: 2026-11-17HANGZHOU JIE DRIVE TECH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202611484152.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-09-22
Publication Date
2026-11-17

AI Technical Summary

Technical Problem

In existing technologies, it is difficult to automatically extract product configuration parameters from unstructured order data, and there is a lack of correlation constraints between multiple product configuration parameters, resulting in insufficient accuracy of product configuration data.

Method used

By performing hierarchical and structured processing on the order data to be processed, product configuration parameters are extracted, and correlation matching is performed based on preset product configuration relationships to determine the target configuration data. The data is then matched in the product parameter database to generate product information data.

Benefits of technology

It enables the automatic conversion of unstructured order data into product information data, improving the accuracy and efficiency of product order data processing and reducing the process of manual parsing and configuration verification.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123115256A_ABST
    Figure CN123115256A_ABST
Patent Text Reader

Abstract

This application discloses a product order data processing method, system, electronic device, and storage medium, relating to the field of industrial data processing technology. The method includes: performing hierarchical structuring processing on the order data to be processed, extracting product configuration parameters to obtain structured order data; based on preset product configuration relationships, performing association matching on multiple product configuration parameters to obtain target configuration data; determining relationships based on parameters corresponding to different types of product configuration parameters in the target configuration data to generate parameter matching conditions; matching product parameter data in a product parameter database based on the parameter matching conditions; and associating the product parameter data with the target configuration data to generate product information data. This application can realize the conversion of unstructured order data into product information data and improve the accuracy of product configuration parameter combinations and product parameter matching.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of industrial data processing technology, specifically to a product order data processing method, system, electronic device, and storage medium. Background Technology

[0002] As industrial products become increasingly customized, product orders typically include various types of information such as model, specifications, structural form, performance parameters, and special configuration requirements. In existing technologies, data processing for product orders usually employs a standard template-based order management system. This system parses the order information entered by the customer through pre-set fields, formats, and product configuration rules, and matches the corresponding product parameters based on the parsing results to convert order information into product data.

[0003] However, in real-world business scenarios, customer-submitted order data often doesn't fully conform to standard template requirements, instead describing product needs in free-text format. This type of order data frequently contains a mix of product models, parameter descriptions, unit information, and special configuration requirements, and the data representation varies between different orders. Existing order processing methods based on fixed templates struggle to directly identify valid product configuration parameters in unstructured orders, typically requiring manual organization and input of order content. Furthermore, existing technologies, after obtaining some product configuration parameters, often lack an automatic matching mechanism for the relationships between multiple product configuration parameters, making it difficult to effectively constrain combinations of product configuration parameters. This results in insufficient accuracy and automation in the generated product data. Summary of the Invention

[0004] The main objective of this invention is to provide a product order data processing method, system, electronic device, and storage medium. It addresses the problems in the prior art where it is difficult to automatically extract product configuration parameters from unstructured order data, and where the lack of correlation constraints between multiple product configuration parameters leads to insufficient accuracy of product configuration data. The invention achieves the automatic conversion of unstructured order data into product information data.

[0005] To achieve the above objectives, the embodiments of this application provide the following technical solutions: According to a first aspect of the embodiments of this application, a product order data processing method is provided, including: The order data to be processed is subjected to hierarchical and structured processing, and the product configuration parameters are extracted from the order data to obtain structured order data; Based on the preset product configuration relationship, multiple product configuration parameters in the structured order data are associated and matched to determine the target configuration data that satisfies the product configuration relationship; Based on the parameter determination relationship corresponding to different types of product configuration parameters in the target configuration data, determine the corresponding parameter matching conditions; Based on the parameter matching conditions, the product parameter database is matched to obtain product parameter data; The product parameter data is associated with the corresponding target configuration data to generate product information data.

[0006] Optionally, the step of performing hierarchical structuring processing on the order data to be processed, extracting product configuration parameters from the order data to obtain structured order data, includes: The order data to be processed is semantically segmented to obtain multiple order content fragments; Based on preset business information, business content identification is performed on multiple order content fragments, and order content fragments related to product requirements are filtered to obtain valid order data; The valid order data is processed to unify its format, resulting in standard order data; Product configuration parameters are extracted from the standard order data to obtain the structured order data.

[0007] Optionally, the step of extracting product configuration parameters from the standard order data to obtain the structured order data includes: Entity recognition is performed on the product description information in the standard order data to obtain candidate configuration parameters; According to the preset field classification rules, the candidate configuration parameters are classified into categories to obtain the classified product configuration parameters; Based on the correspondence between the categorized product configuration parameters, a data association relationship is established between the product configuration parameters to generate the structured order data.

[0008] Optionally, the step of associating and matching multiple product configuration parameters in the structured order data based on preset product configuration relationships to determine target configuration data that satisfies the product configuration relationships includes: Extract multiple product configuration parameters from the structured order data; Based on the product configuration relationship, the combination relationship between multiple product configuration parameters is matched to obtain the configuration matching result; Based on the configuration matching results, filter product configuration parameter combinations that satisfy the product configuration relationship; The target configuration data is generated based on the selected product configuration parameter combinations.

[0009] Optionally, the product configuration relationship includes product structure relationship and product selection relationship. The step of matching the combination relationships between multiple product configuration parameters based on the product configuration relationship to obtain a configuration matching result includes: Based on the product structure relationship, the structural combination relationship corresponding to multiple product configuration parameters is matched to obtain the structural matching result. The structural combination relationship is used to characterize the assembly association relationship between multiple product structural elements. Based on the product selection relationship, the parameter adaptation relationship corresponding to multiple product configuration parameters is matched to obtain the selection matching result. The parameter adaptation relationship is used to characterize the selection association relationship between multiple product configuration parameters. The configuration matching result is generated based on the structure matching result and the selection matching result.

[0010] Optionally, determining the corresponding parameter matching conditions based on the parameter determination relationship corresponding to different types of product configuration parameters in the target configuration data includes: Extract multiple product configuration parameters from the target configuration data; Based on the parameter determination relationship corresponding to the multiple product configuration parameters, the multiple product configuration parameters are classified to obtain multiple parameter categories. The parameter determination relationship is used to characterize the determination relationship between product configuration parameters and product parameter data. For different parameter categories, corresponding parameter matching conditions are generated based on the relationship determined by the corresponding parameters.

[0011] Optionally, the step of generating corresponding parameter matching conditions based on the corresponding parameter relationships for different parameter categories includes: Based on the parameter relationship corresponding to the first parameter category, the parameter combination of multiple product configuration parameters that jointly determine the same product parameter data is used as the matching basis to generate the first parameter matching condition; The relationship is determined based on the parameters corresponding to the second parameter category. The configuration parameters of a single product are used as the matching basis to generate the matching conditions for the second parameter. The first parameter matching condition and the second parameter matching condition are determined as the parameter matching condition.

[0012] According to a second aspect of the embodiments of this application, a product order data processing system is provided, comprising: The structured processing module is used to perform hierarchical structured processing on the order data to be processed, extract the product configuration parameters from the order data to be processed, and obtain structured order data. The configuration matching module is used to perform association matching on multiple product configuration parameters in the structured order data based on preset product configuration relationships, and determine the target configuration data that satisfies the product configuration relationships; The matching condition determination module is used to determine the corresponding parameter matching conditions based on the parameter determination relationship corresponding to different types of product configuration parameters in the target configuration data; The parameter acquisition module is used to match the product parameter database based on the parameter matching conditions to obtain product parameter data. The product information generation module is used to associate the product parameter data with the corresponding target configuration data to generate product information data.

[0013] According to a third aspect of the present application, an electronic device is provided, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method described in the first aspect above.

[0014] According to a fourth aspect of the embodiments of this application, a computer-readable storage medium is provided having computer-readable instructions stored thereon, the computer-readable instructions being executable by a processor to implement the method described in the first aspect above.

[0015] In summary, this application provides a product order data processing method, system, electronic device, and storage medium. By performing hierarchical structuring processing on the order data to be processed, product configuration parameters are extracted to obtain structured order data. Based on preset product configuration relationships, multiple product configuration parameters in the structured order data are correlated and matched to determine target configuration data that satisfies the product configuration relationships. According to the parameter determination relationships corresponding to different types of product configuration parameters in the target configuration data, corresponding parameter matching conditions are determined. Matching is performed in a product parameter database based on the parameter matching conditions to obtain product parameter data. The product parameter data is then correlated with the corresponding target configuration data to generate product information data. This solves the problems in the prior art where it is difficult to automatically extract product configuration parameters from unstructured order data, and the lack of correlation constraints between multiple product configuration parameters leads to insufficient accuracy of product configuration data, thus achieving automatic conversion of unstructured order data into product information data. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.

[0017] The structures, proportions, sizes, etc. illustrated in this specification are only for the purpose of assisting those skilled in the art in understanding and reading the content disclosed herein, and are not intended to limit the conditions under which the present invention can be implemented. Therefore, they have no substantial technical significance. Any modifications to the structure, changes in the proportions, or adjustments to the size, without affecting the effects and objectives that the present invention can produce, should still fall within the scope of the technical content disclosed in the present invention.

[0018] Figure 1 A flowchart illustrating a product order data processing method provided in this application embodiment; Figure 2 This application provides a schematic diagram of the overall process for product order data processing. Figure 3 This application provides a schematic diagram of a hierarchical structured processing flow for order data. Figure 4 This application provides a schematic diagram of a product configuration relationship matching process. Figure 5 A schematic diagram illustrating the parameter matching condition generation and product parameter database matching process provided in this application embodiment; Figure 6 This application provides a schematic diagram of a product information generation and production closed-loop process. Figure 7 A schematic diagram of a product order data processing system provided in this application embodiment; Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application; Figure 9 This is a schematic diagram of a computer-readable storage medium provided in an embodiment of this application.

[0019] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0021] Furthermore, in this invention, descriptions involving "first," "second," etc., are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0022] Furthermore, the technical solutions of the various embodiments of the present invention can be combined with each other, but only if they are feasible for those skilled in the art. If the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such combination of technical solutions does not exist and is not within the scope of protection claimed by the present invention.

[0023] Figure 1 This application illustrates a product order data processing method according to an embodiment, comprising: Step 101: Perform hierarchical structuring processing on the order data to be processed, extract the product configuration parameters from the order data to be processed, and obtain structured order data; Step 102: Based on the preset product configuration relationship, perform association matching on multiple product configuration parameters in the structured order data to determine the target configuration data that satisfies the product configuration relationship; Step 103: Determine the corresponding parameter matching conditions based on the parameter determination relationship corresponding to different types of product configuration parameters in the target configuration data; Step 104: Match the parameters in the product parameter database based on the parameter matching conditions to obtain product parameter data; Step 105: Associate the product parameter data with the corresponding target configuration data to generate product information data.

[0024] This application provides a product order data processing method for processing order data containing product requirement description information to obtain product information data related to product configuration. In practical applications, order data may contain different forms of product description content. When directly extracting product parameters and determining configurations based on the original order data, it is easily affected by differences in data expression methods. Therefore, this application performs hierarchical structuring processing on the order data to be processed, converting the product description information in the order into structured order data containing product configuration parameters, providing a data foundation for subsequent product configuration analysis.

[0025] Specifically, in the order data processing, the order data to be processed is first subjected to hierarchical structuring. This involves parsing, filtering, and extracting product configuration parameters from the order content to obtain structured order data. By processing the order content, data related to product configuration can be extracted from order information that includes different formats, reducing the impact of differences in order content formats on subsequent processing.

[0026] After obtaining structured order data, the relationships between multiple product configuration parameters in the structured order data are matched based on preset product configuration relationships, and the target configuration data is determined according to the matching results. By constraining the combination relationships between multiple product configuration parameters, it can be determined whether different configuration parameters meet the product configuration requirements, avoiding the problem of inaccurate configuration results due to independent matching of a single parameter.

[0027] Furthermore, since different types of product configuration parameters have different deterministic relationships with product parameter data, corresponding parameter matching conditions are determined based on the parameter deterministic relationships corresponding to different types of product configuration parameters in the target configuration data. Product parameter data is then retrieved from the product parameter database based on these matching conditions. By establishing corresponding matching conditions for different types of configuration parameters, the product parameter retrieval process can be made more consistent with product configuration logic.

[0028] Finally, the acquired product parameter data is associated with the corresponding target configuration data to generate product information data, thus realizing the conversion between order data and product information data. This processing method reduces the need for manual parsing of order content, configuration verification, and parameter organization, improving the accuracy and efficiency of product order data processing.

[0029] In one possible implementation, in step 101, the hierarchical structuring processing of the order data to be processed, extracting product configuration parameters from the order data to obtain structured order data, includes: semantically segmenting the order data to be processed to obtain multiple order content fragments; identifying business content from the multiple order content fragments according to preset business information, filtering order content fragments related to product requirements to obtain valid order data; uniformly formatting the valid order data to obtain standard order data; and extracting product configuration parameters from the standard order data to obtain the structured order data.

[0030] In one possible implementation, in step 101, when performing hierarchical structuring processing on the order data to be processed, the order data can first be semantically segmented, dividing it into multiple order content fragments according to their content expression relationships. Since order data typically contains product description information, parameter information, and other auxiliary information, different types of information may be mixed in description. By semantically segmenting the order data, the overall order content can be broken down into multiple information units with independent semantics, facilitating subsequent processing of different order content fragments.

[0031] Furthermore, based on preset business information, business content identification is performed on multiple order content fragments, and order content fragments related to product requirements are filtered out to obtain valid order data. The preset business information is used to characterize information features related to product configuration, such as product name, model description, parameter description, and configuration requirements. By matching order content fragments with preset business information, information related to product requirements can be determined from multiple order content fragments, reducing the impact of irrelevant content on the subsequent product configuration parameter extraction process.

[0032] In one possible implementation, the step of extracting product configuration parameters from the standard order data to obtain the structured order data includes: performing entity recognition on the product description information in the standard order data to obtain candidate configuration parameters; classifying the candidate configuration parameters according to preset field classification rules to obtain classified product configuration parameters; and establishing data association relationships between the classified product configuration parameters based on the correspondence between them to generate the structured order data.

[0033] After obtaining valid order data, the data is formatted to obtain standard order data. Since order data from different sources may have different character representations, parameter descriptions, and data formats, standardizing the format of valid order data converts order content in various forms into a unified data representation, providing a foundation for subsequent product configuration parameter extraction.

[0034] Furthermore, product configuration parameters are extracted from standard order data to obtain structured order data. Specifically, entity recognition can be performed on the product description information in the standard order data to obtain candidate configuration parameters. Subsequently, according to preset field classification rules, the candidate configuration parameters are categorized to determine the parameter categories corresponding to different candidate configuration parameters. Based on the correspondence between the categorized product configuration parameters, data association relationships between product configuration parameters are established to generate structured order data. Through the above method, the scattered descriptive information in the original order can be converted into structured data with parameter categories and association relationships.

[0035] In one possible implementation, the step of performing entity recognition on the product description information in the standard order data to obtain candidate configuration parameters includes: acquiring product order training data and configuration parameter annotation data corresponding to the product order training data; performing entity annotation on the product description information in the product order training data based on the configuration parameter annotation data to obtain training data; training an initial configuration parameter recognition model using the training data to obtain a configuration parameter recognition model; and performing entity recognition on the product description information in the standard order data using the configuration parameter recognition model to obtain the candidate configuration parameters.

[0036] In one possible implementation, to identify product configuration parameters in order description information, a configuration parameter identification model can be pre-built. Specifically, product order training data and corresponding configuration parameter annotation data can be obtained. The configuration parameter annotation data is used to identify product configuration parameter information in the product order training data. Based on the configuration parameter annotation data, the product description information in the product order training data is annotated to obtain training data. The initial configuration parameter identification model is then trained using the training data to obtain the configuration parameter identification model.

[0037] After model training is complete, product description information from standard order data can be input into the configuration parameter recognition model. The model then identifies configuration entities within the product description information to obtain candidate configuration parameters. By processing product description information using the configuration parameter recognition model, corresponding product configuration parameters can be extracted based on the actual description format in the order data, providing a data foundation for subsequent configuration matching and product parameter acquisition based on these parameters.

[0038] In one possible implementation, in step 102, the step of associating and matching multiple product configuration parameters in the structured order data based on a preset product configuration relationship to determine target configuration data that satisfies the product configuration relationship includes: extracting multiple product configuration parameters from the structured order data; matching the combination relationships between the multiple product configuration parameters based on the product configuration relationship to obtain a configuration matching result; filtering product configuration parameter combinations that satisfy the product configuration relationship according to the configuration matching result; and generating the target configuration data based on the filtered product configuration parameter combinations.

[0039] In step 102, based on preset product configuration relationships, multiple product configuration parameters in the structured order data are correlated and matched to determine the target configuration data. Specifically, multiple product configuration parameters can first be extracted from the structured order data, and the combination relationships between these parameters can be matched according to the preset product configuration relationships to obtain configuration matching results. The product configuration relationships characterize the association constraints between multiple product configuration parameters. By analyzing the combination relationships between these parameters, it can be determined whether the multiple product configuration parameters meet the corresponding product configuration requirements.

[0040] Furthermore, based on the configuration matching results, product configuration parameter combinations that satisfy product configuration relationships are filtered, and target configuration data is generated based on the filtered product configuration parameter combinations. This process avoids the problem of mismatches between different configuration parameters caused by judging based on only a single product configuration parameter, ensuring that the generated target configuration data reflects the relationships between multiple product configuration parameters.

[0041] In one possible implementation, the product configuration relationship includes product structure relationship and product selection relationship. The step of matching the combination relationships between multiple product configuration parameters based on the product configuration relationship to obtain a configuration matching result includes: Based on the product structure relationship, the structural combination relationship corresponding to multiple product configuration parameters is matched to obtain a structure matching result. The structural combination relationship is used to characterize the assembly association relationship between multiple product structural elements. Based on the product selection relationship, the parameter adaptation relationship corresponding to multiple product configuration parameters is matched to obtain a selection matching result. The parameter adaptation relationship is used to characterize the selection association relationship between multiple product configuration parameters. Based on the structure matching result and the selection matching result, the configuration matching result is generated.

[0042] Product configuration relationships can include product structure relationships and product selection relationships. Product structure relationships describe the combinational relationships between different product structural elements, while product selection relationships describe the selectional relationships between different product configuration parameters. Specifically, when matching the combinational relationships between multiple product configuration parameters based on product configuration relationships, the structural combination relationships corresponding to multiple product configuration parameters can be matched according to the product structure relationships to obtain structural matching results. Here, structural combination relationships characterize the assembly relationships between multiple product structural elements. Through structural combination relationship matching, it can be determined whether multiple product structural elements meet preset combination requirements. Further, based on product selection relationships, the parameter adaptation relationships corresponding to multiple product configuration parameters are matched to obtain selection matching results. Here, parameter adaptation relationships characterize the selectional relationships between multiple product configuration parameters. Through parameter adaptation relationship matching, it can be determined whether different product configuration parameters meet corresponding selection requirements. After obtaining the structural matching results and selection matching results, configuration matching results are generated based on the structural matching results and selection matching results, and product configuration parameter combinations that satisfy the product configuration relationships are determined based on the configuration matching results.

[0043] In one possible implementation, matching the structural combination relationships corresponding to multiple product configuration parameters based on the product structural relationships includes: obtaining structural association data corresponding to multiple product structural elements; establishing association relationships between product structural elements based on the structural association data; and matching the product structural elements corresponding to the product configuration parameters in the structured order data with the association relationships to obtain the structural matching result.

[0044] The structure matching result can be determined as follows: First, obtain the structure association data corresponding to multiple product structure elements. This structure association data describes the relationships between different product structure elements. Based on the structure association data, establish the relationships between product structure elements. Then, match the product structure elements corresponding to the product configuration parameters in the structured order data with the established relationships to obtain the structure matching result. For example, when multiple product configuration parameters correspond to different structure elements, analyze whether there are pre-defined relationships between the different structure elements to determine whether the structural combination formed by the multiple product configuration parameters meets the product configuration requirements.

[0045] In one possible implementation, matching the parameter adaptation relationships corresponding to multiple product configuration parameters according to the product selection relationship includes: obtaining historical selection data between product configuration parameters; determining the adaptation relationship between product configuration parameters based on the historical selection data; and matching the product configuration parameters in the structured order data with the adaptation relationship to obtain the selection matching result.

[0046] The selection matching result can be determined as follows: First, historical selection data on product configuration parameters is obtained. This historical data reflects the historical matching status between different product configuration parameters. The compatibility relationship between product configuration parameters is determined based on this historical data, and the product configuration parameters in the structured order data are matched with the determined compatibility relationship to obtain the selection matching result. This method utilizes existing product configuration data to form product selection relationships, enabling the correlation judgment between product configuration parameters to incorporate historical configuration data, thus improving the matching degree between the target configuration data determination process and the actual product selection rules.

[0047] In one possible implementation, the product configuration relationship is determined through the following steps: obtaining historical product order data and product configuration data; extracting multiple historical product configuration parameters from the historical product order data; determining the configuration correspondence between the multiple historical product configuration parameters based on the product configuration data; and generating the product configuration relationship based on the configuration correspondence.

[0048] Product configuration relationships can be generated based on historical product data. Specifically, historical order data and product configuration data can be obtained. Multiple historical product configuration parameters can be extracted from the historical order data, and the configuration correspondence between these parameters can be determined based on the product configuration data. Furthermore, product configuration relationships are generated based on these correspondences, which are then used to associate and match product configuration parameters in new structured order data.

[0049] The above method can be used to form configuration relationships suitable for product order processing based on existing product configuration data, so that the product configuration relationships can be improved as product data accumulates, and provide a basis for determining subsequent target configuration data.

[0050] In one possible implementation, in step 103, determining the corresponding parameter matching conditions based on the parameter determination relationships corresponding to different types of product configuration parameters in the target configuration data includes: extracting multiple product configuration parameters from the target configuration data; classifying the multiple product configuration parameters according to the parameter determination relationships corresponding to the multiple product configuration parameters to obtain multiple parameter categories, wherein the parameter determination relationships are used to characterize the determination relationships between product configuration parameters and product parameter data; and generating corresponding parameter matching conditions for different parameter categories based on the corresponding parameter determination relationships.

[0051] In one possible implementation, generating corresponding parameter matching conditions based on the corresponding parameter determination relationship for different parameter categories includes: generating a first parameter matching condition by using a combination of multiple product configuration parameters that jointly determine the same product parameter data as a matching basis according to the parameter determination relationship corresponding to the first parameter category; generating a second parameter matching condition by using a single product configuration parameter as a matching basis according to the parameter determination relationship corresponding to the second parameter category; and determining the first parameter matching condition and the second parameter matching condition as the parameter matching condition.

[0052] When generating parameter matching conditions for different parameter categories, the parameter combination of multiple product configuration parameters that jointly determine the same product parameter data can be used as the matching basis to generate the first parameter matching condition, based on the parameter determination relationship corresponding to the first parameter category. For example, for a product parameter that needs to be determined by multiple product configuration parameters, the parameter combination formed by multiple related product configuration parameters can be used as the matching condition to obtain the corresponding product parameter data.

[0053] Furthermore, relationships can be determined based on parameters corresponding to the second parameter category, using individual product configuration parameters as the matching basis to generate matching conditions for the second parameter. For example, for product parameters that can be directly determined by a single product configuration parameter, corresponding matching conditions can be generated based on that product configuration parameter to obtain the corresponding product parameter data.

[0054] After generating the first parameter matching condition and the second parameter matching condition, the first parameter matching condition and the second parameter matching condition are determined as parameter matching conditions, which are used for subsequent matching in the product parameter database to obtain product parameter data corresponding to the target configuration data.

[0055] In one possible implementation, in step 104, the step of matching the product parameter data in the product parameter database based on the parameter matching conditions includes: obtaining candidate product parameters from the product parameter database according to the parameter matching conditions; performing parameter consistency matching between the candidate product parameters and the target configuration data; filtering the corresponding candidate product parameters according to the parameter consistency matching results; and determining the filtered candidate product parameters as the product parameter data.

[0056] In step 104, matching is performed in the product parameter database based on parameter matching conditions to obtain product parameter data. Specifically, candidate product parameters can be retrieved from the product parameter database according to the parameter matching conditions. The product parameter database stores product parameter data corresponding to different product configurations, and the parameter matching conditions are used to limit the parameter query range corresponding to the target configuration data.

[0057] Furthermore, parameter consistency matching is performed between the candidate product parameters and the target configuration data to determine the correspondence between them. Specifically, the product attribute information corresponding to the candidate product parameters can be compared with the product configuration parameters in the target configuration data to determine whether the candidate product parameters meet the configuration requirements corresponding to the target configuration data.

[0058] Based on the parameter consistency matching results, candidate product parameters are filtered, and the filtered candidate product parameters are determined as product parameter data. This method allows for further identification of product parameter data that matches the target configuration data from among the candidate product parameters that meet the parameter matching conditions, reducing parameter acquisition errors caused by inconsistencies in product configuration parameters.

[0059] In one possible implementation, when no product parameter data corresponding to the target configuration data is obtained, the method further includes: generating supplementary parameter request information based on the target configuration data for which no matching product parameter data is found; obtaining supplementary product parameters in response to the input of the supplementary parameter request information; establishing a correspondence between the supplementary product parameters and the target configuration data; and updating the product parameter database based on the correspondence.

[0060] In step 104, when no product parameter data corresponding to the target configuration data is found in the product parameter database based on the parameter matching conditions, further supplementary processing can be performed on the unmatched target configuration data. Specifically, supplementary parameter request information is generated based on the target configuration data for which no product parameter data was found, and supplementary product parameters are obtained in response to the input of the supplementary parameter request information. Further, a correspondence between the supplementary product parameters and the target configuration data is established, and the product parameter database is updated according to the established correspondence. Through the above method, product configuration information not stored in the product parameter database can be supplemented, enabling the product parameter database to contain more parameter data corresponding to actual product configuration requirements, providing data support for subsequent order processing.

[0061] In one possible implementation, after updating the product parameter database, the method further includes: obtaining the updated product parameter database; re-matching the product parameter database according to the parameter matching conditions corresponding to the target configuration data; and obtaining the re-matched product parameter data.

[0062] After updating the product parameter database, parameter matching can be performed again based on the updated database. Specifically, the updated product parameter database is retrieved, and the parameter matching is re-performed according to the parameter matching conditions corresponding to the target configuration data to obtain the re-matched product parameter data. In this way, when the original product parameter data cannot meet the current product configuration requirements, the parameter matching process can be improved by supplementing product parameters and updating the product parameter database, enabling subsequent identical or similar configuration requirements to be processed based on the updated data.

[0063] In one possible implementation, the method further includes: generating product confirmation data based on the product information data; obtaining confirmation information input in response to the product confirmation data; and updating the product information data based on the confirmation information.

[0064] After generating product information data, a confirmation process can be performed. Specifically, product confirmation data is generated based on the product information data, and confirmation information for the input of the product confirmation data is obtained. The product information data is then updated based on the confirmation information, allowing the generated product information data to be adjusted in accordance with the confirmation results. Through this method, confirmation feedback can be obtained after the product information data is generated, and the product information data can be improved based on the confirmation results, thereby enhancing the consistency between the final generated data and actual product requirements.

[0065] The method provided in this application will be described below with reference to the accompanying drawings and specific embodiments. In the following embodiments, the descriptions of special rules for the reducer field, reducer parameter database, motor parameter database, etc., pertain to the specific implementation of the product order data processing method in the reducer business. For other industrial products with multiple configuration parameters and parameter adaptation relationships, the methods can be replaced according to the corresponding product's structural relationships, selection relationships, and parameter database.

[0066] Figure 2 This diagram illustrates the overall workflow for product order data processing. The entire process can include order data acquisition, hierarchical and structured processing of order data, product configuration relationship matching, parameter matching condition generation, product parameter database matching, and product information data generation. Each stage is interconnected based on the data generation relationships, with data generated in one stage serving as the processing object for the next.

[0067] First, obtain the order data to be processed. This data can come from customer emails, spreadsheets, portable document files, images, and other order attachments. For order content in spreadsheets, portable document files, or images, extract the text and field information first, then use this data to create the order data for subsequent processing.

[0068] The order data to be processed may include information such as product model, speed ratio or other transmission parameters, installation method, motor or other supporting component model, brake, encoder, junction box location, oil seal, bearing, corrosion resistance level, protection level, lubricant specification, nameplate language, etc. This information may appear in different orders in the free text order, and may also be described using a mix of Chinese and English, industry abbreviations, or special symbols.

[0069] In the hierarchical structuring stage of order data, the original order content is processed layer by layer. First, the impact of irrelevant content and mixed expressions on the recognition results is reduced. Then, the expression forms of model, unit, characters, etc. are unified. Finally, the product configuration entity is extracted and the relationship between different configuration parameters is established, thereby obtaining the structured order data.

[0070] During the product configuration relationship matching phase, product parameters are not queried directly based on a single field. Instead, it first determines whether multiple product configuration parameters satisfy product structure relationships and product selection relationships. Only parameter combinations that satisfy the corresponding product configuration relationships are used as target configuration data to continue participating in subsequent parameter retrieval.

[0071] During the parameter matching condition generation phase, product configuration parameters in the target configuration data are categorized based on the specific configuration parameters that determine the product parameters. For product parameters that require multiple configuration parameters to be jointly determined, joint matching conditions are formed; for product parameters that can be determined by a single configuration parameter, single-parameter matching conditions are formed. Different matching conditions are used to retrieve product parameter data of the corresponding type.

[0072] During the product information data generation phase, a correspondence is established between the target configuration data and the acquired product parameter data. If the corresponding parameter does not exist in the product parameter database, the parameter supplementation and database update process can be triggered, and the matching will be re-executed after the update, so that the newly added or non-standard configuration can enter the subsequent product confirmation and production process.

[0073] Figure 3 This illustration shows a schematic diagram of the hierarchical structured processing flow for order data provided in an embodiment of this application. In one specific implementation, the hierarchical structured processing of order data adopts a three-level progressive processing chain. The original non-standard text sequentially undergoes a first-level coarse noise reduction preprocessing, a second-level standardization and fine cleaning, and a third-level domain entity extraction, progressively removing noise, unifying the expression form, and extracting business entities. Taking a speed reducer order as an example, the entire data flow relationship can be represented as follows:

[0074] The first layer performs coarse noise reduction preprocessing on the original order content. A customer's original order may contain equipment model, selected configuration, customization requirements, special instructions, and text unrelated to product configuration. To ensure that subsequent standardization and parameter extraction can be performed on a relatively stable data basis, the first layer first performs semantic segmentation on the long text, then binds and normalizes special symbols and industry terms, and filters out irrelevant content based on its relevance to the industry benchmark corpus.

[0075]

[0076] in, This indicates the full text of the original gearbox order, including equipment model, selected configuration, customization requirements, special instructions, and information in both Chinese and English, as well as special symbols and redundant content; This indicates pre-processing guidance prompts specific to the gearbox industry; This is a specialized dictionary for industrial transmission units, used to store entries for professional units such as torque, speed, power, module, and transmission ratio. A table showing the mapping between Chinese and English terms for gearbox components; This indicates the industry-specific text similarity filtering threshold.

[0077] in, It can record different linguistic or symbolic expressions of the same business meaning. For example, in the specific business of speed reducers, it can record the mapping between R and the business meaning of speed reducers, the mapping between B and the business meaning of brakes, the mapping between angle symbols and angle descriptions, and the mapping between M1 to M6 and installation forms. This mapping relationship is used to unify the different representations of the same configuration item in orders from different sources into a recognizable business semantics.

[0078] The preprocessing operator consists of four serially coupled modules: preprocess = segmentation + symbol binding mapping + Chinese / English standardization + low-similarity segment filtering The segmentation module divides long texts into multiple independent semantic segments based on line breaks, delimiters, and technical punctuation. The symbol binding and mapping module associates dimension markers, tolerances, and process-specific symbols with corresponding business terms, preventing numbers, angles, or units from being separated from their described parameters. The Chinese-English unification module standardizes the mixed Chinese and English writing of component names, product models, and configuration items. The low-similarity segment filtering module uses a benchmark corpus in the product domain as a reference to determine the relevance of each semantic segment, filtering out advertisements, invalid garbled characters, irrelevant notes, and other low-similarity content unrelated to product configuration, forming a clean set of semantic blocks. .

[0079] After the first layer of processing, the resulting clean semantic block set may still contain inconsistencies in model numbers, drawing numbers, order codes, unit formats, and capitalization of English letters. Therefore, the second layer performs standardization and fine-grained cleaning on the output of the first layer, ensuring that data with the same meaning uses a consistent representation.

[0080]

[0081] in, This represents the set of clean semantic blocks output from the first layer of preprocessing; A unified and standardized rule base for product model, drawing number, and order code; This indicates the standardization and specifications of industry units; Indicates a consistent case-sensitive rule for the English designations of components; Standard industry text indicating that cleaning is complete.

[0082] The standardized cleaning operator consists of three serially coupled modules: Clean = unified encoding + standardized unit format + case-insensitive encoding of English letters.

[0083] The coding standardization module corrects irregularly written model numbers, part numbers, and order codes, reducing the number of different codes for the same product due to different writing styles. The unit format standardization module standardizes the writing format of parameters such as power, torque, and speed; for example, it unifies 90 degrees, 90°, and 90° into the same angle expression, and represents units such as kW, N·m, and r / min according to preset unit specifications. The English case normalization module performs a unified conversion on the English codes for components such as bearings, seals, and gears, ensuring that subsequent entity recognition is no longer affected by case differences.

[0084] The third layer is used to extract domain-specific business entities from standard industry text. In one specific implementation, a converter-based bidirectional encoder representation (BERT) model, fine-tuned from a reducer industry annotation corpus, can be used as the configuration parameter recognition model. It should be noted that the BERT model is only one optional implementation; other models capable of performing domain entity recognition and attribute classification can also be used to achieve the corresponding processing.

[0085]

[0086] in, This refers to the standard industry text after the second layer of cleaning; This indicates the tag set for the gearbox business entity. The tag set can cover entity categories such as model, transmission ratio, rated power, output torque, installation method, and material. This represents the business rule base for entity boundary correction; This represents the structured business dataset output.

[0087] The domain entity extraction operator consists of three serially coupled modules: = Gearbox fine-tuning model reasoning + entity boundary correction + business constraint decoding.

[0088] The gearbox fine-tuning model inference module uses annotated corpus of gearbox industry data to fine-tune the pre-trained model, completing entity recognition and attribute classification in order text through model inference. The entity boundary correction module corrects entity truncation and boundary offsets caused by numbers, special symbols, etc. For example, when numbers and special characters in speed ratio, angle, or model number are split by the model, they are reassembled into complete entities according to business rules. The business constraint decoding module constrains the field categories, unit types, and entity boundary relationships in the recognition results, filtering out recognition results with conflicting field categories, mismatched unit types, or abnormal entity relationships, and outputting a structured business dataset. Whether the product structure can be assembled and whether the model, speed ratio, and motor model meet the actual selection relationship are determined in the subsequent product configuration relationship matching stage.

[0089] During the model training phase, historical order data and corresponding product configuration data can be acquired, and a standard template for configuration parameters can be established based on the product configuration data. This standard template defines the field categories, standard expression formats, and entity annotation ranges for different product configuration parameters. Based on the standard template, entities such as product model, transmission ratio, rated power, output torque, installation type, material, matching motor, brake, and junction box location in historical orders are annotated, and the correspondence between different configuration entities is recorded, forming product order training data. The initial configuration parameter recognition model is trained using this product order training data to obtain the configuration parameter recognition model. When new standard order data enters the third layer, the configuration parameter recognition model outputs candidate configuration parameters, which are then used to form structured order data based on field classification rules and parameter relationships.

[0090] Through the three-level processing described above, the first level primarily addresses the issue of mixed original order content; the second level addresses the issue of different expressions for the same business meaning; and the third level primarily addresses the issues of product configuration entity extraction and parameter attribution. These three levels of processing are executed consecutively, gradually transforming the data from raw free text into data that can be used for subsequent verification of product configuration relationships.

[0091] Figure 4 A schematic diagram of the product configuration relationship matching process is shown. After obtaining structured order data, it is necessary to further determine whether the configuration composed of multiple product configuration parameters actually exists and meets the product selection requirements. Simply completing text entity recognition cannot guarantee that the product structure is manufacturable, the components are assembleable, or that the multiple parameters are compatible with each other. Therefore, this implementation divides the product configuration relationship into product structure relationship and product selection relationship, and generates structure matching results and selection matching results respectively.

[0092] Product configuration relationships can be established in advance based on product configuration data, or continuously improved by combining historical order data. Specifically, historical product configuration parameters such as product model, structural configuration, installation method, supporting components, and performance parameters can be extracted from historical order data. Then, the correspondence between multiple configuration parameters can be determined based on the final product configuration results adopted in historical orders. Structural combinations that can be directly obtained from product design, product samples, or mass-producible model data can be directly used as product structural relationships; configuration parameter combinations that reflect selection and adaptation rules can be used as product selection relationships.

[0093] In a specific implementation of the speed reducer, the product structural relationship can be represented by a whitelist of real, mass-producible model configurations. This whitelist includes legal physical combinations of structural elements such as model, brake, release device, installation method, hollow shaft diameter, and junction box structure. A multi-dimensional joint comparison is performed between the complete machine configuration identified from structured order data and the legal combinations in the whitelist. If the structural combination corresponding to the current order exists in the real model database, the structural matching result is determined to satisfy the structural relationship; if the current combination is non-existent in the industry, the structure cannot be assembled, or it is a non-standard incorrect combination, the corresponding combination is determined to not satisfy the structural relationship.

[0094] The aforementioned structural layer matching is primarily used to identify order combinations that are identifiable at the textual level but lack a corresponding actual mechanical structure. For example, a model might be able to identify the machine type, installation method, and structural components separately, but these combinations may not necessarily form a real product. Therefore, performing a combination validity check through structural relationships before retrieving configuration parameters from the product parameter database can prevent the use of non-existent complete machine structures for parameter generation.

[0095] After the structural matching results meet the requirements, product selection relationship matching can be further performed. In the gear reducer business, a specific gear reducer model usually corresponds to a certain range of speed ratios and forms a compatibility relationship with a specific motor model. Customer free text orders may contain errors such as incorrect model entries, speed ratios not belonging to the selected model range, motor models not matching gear reducer specifications, or cross-specification mixing; the entity recognition process may also result in incorrect or mixed field extraction. Therefore, an industry selection association rule base can be established to perform linked verification of the correspondence between model, speed ratio, and motor model.

[0096] Specifically, it can be determined whether the current reducer model and speed ratio are a compliant match, whether the current reducer model and motor model are a legally compatible combination, and whether the current speed ratio specifications and matching motor model meet the selection specifications. Selection matching results are generated based on these multiple determinations.

[0097] Configuration matching results are generated based on the structural matching results and the selection matching results. Only when the structural combination satisfies the product structural relationship and the main selection parameters satisfy the product selection relationship will the corresponding product configuration parameter combination be determined as the target configuration data. In the application of speed reducers, the above processing can obtain core index information such as model, speed ratio, installation method, and matching motor model for subsequent parameter database retrieval.

[0098] For orders where the configuration matching results do not match the product configuration relationships, the corresponding exception location can be output, and the structural and selection relationship matching can be re-executed based on the corrected configuration parameters. Therefore, the exception configuration will not directly enter the subsequent parameter database matching process.

[0099] Figure 5 The diagram illustrates the process of generating parameter matching conditions and matching product parameters to the database. After obtaining the target configuration data, not all product parameters are determined in the same way. Different product parameters have different data determination relationships with order configuration parameters. Based on this characteristic, we can first analyze the parameter determination relationships corresponding to the product configuration parameters in the target configuration data, and then form different parameter categories according to these relationships.

[0100] The first parameter category corresponds to product parameters that need to be determined jointly by multiple product configuration parameters. For this type of parameter, the combination relationship between multiple configuration parameters needs to be used as the matching basis. For example, in the application of speed reducers, the allowable torque, standard lubricating oil quantity, and total weight of the speed reducer body will vary depending on the model, speed ratio, and installation method. Therefore, the above parameters cannot be obtained solely based on the model; instead, the first parameter matching condition needs to be formed by the combination of model, speed ratio, and installation method.

[0101] The second parameter category corresponds to product parameters that can be determined by individual product configuration parameters. For example, in a scenario where a speed reducer and a motor are matched, the motor's rated parameters are independent of the speed reducer's mounting method and speed ratio; the motor model uniquely corresponds to the rated speed, rated power, and motor weight. Therefore, the motor model can be used as a separate matching criterion to form the second parameter matching condition.

[0102] In one specific implementation, the product parameter database employs a dual-database separation and matching mechanism, storing and retrieving the reducer's main parameters and the motor's matching parameters separately. This approach avoids mismatches caused by placing parameters with different defined logics into a single search condition.

[0103] The first database is the reducer body parameter database. A triple-linked search index is used, comprising the reducer model, speed ratio, and installation method. Based on these three configuration parameters, a first parameter matching condition is formed. The system uses this first parameter matching condition to determine the corresponding record in the reducer body parameter database and reads product parameter data such as allowable torque, standard lubricating oil quantity, and the overall weight of the reducer.

[0104] The second database is a motor matching parameter database. The system extracts the motor model code from the target configuration data, uses the motor model to form the second parameter matching condition, and independently searches for the corresponding record in the motor parameter database to obtain the rated speed, rated power, and motor weight.

[0105] The two databases are independent in their retrieval logic but complementary in their output parameters. The reducer's parameters are determined by multiple configuration parameters, while the motor parameters are determined by a single motor model. Ultimately, the parameters output from both databases are aggregated into the target configuration data corresponding to the same order, thus forming the complete set of parameters required for subsequent product information data.

[0106] During database retrieval, candidate product parameters can be obtained first based on matching criteria, and then the configuration indexes recorded in the candidate product parameters can be compared with the target configuration data for consistency. For example, the model, speed ratio, installation method, or motor model corresponding to the database record can be compared with the current target configuration data to determine the consistent candidate parameters as product parameter data. This secondary consistency matching is used to reduce erroneous selection when similar models or adjacent configurations exist in the database.

[0107] For standard products, if a corresponding record already exists in the product parameter database, the corresponding parameters can be read directly. For non-standard customized products, if no corresponding record is found based on the existing matching conditions, a "no match" result is output, and the process proceeds to the subsequent parameter supplementation stage. The supplemented non-standard product parameters are then associated with the corresponding target configuration data and written to the product parameter database, enabling subsequent orders of the same type to directly utilize the updated database for matching.

[0108] Figure 6 The diagram illustrates the closed-loop process of product information generation and production. After obtaining the target configuration data and product parameter data, the configuration parameters extracted and verified from the order and the performance parameters retrieved from the database are associated with each other based on the configuration correspondence between the two, and the product information data is generated by aggregating them into the same product data object.

[0109] Product information data can include order configuration data such as product model, speed ratio, installation method, and motor model, as well as database parameters such as allowable torque, lubricating oil quantity, overall weight, rated speed, rated power, and motor weight. For orders that also include configuration requirements such as brakes, encoders, protection levels, special bearings, oil seals, and nameplate language, the corresponding parsed and verified information can be linked to the product information data.

[0110] In one implementation, product confirmation data is generated based on product information data for customer confirmation. The parsed order requirements and automatically matched product performance parameters are then fed back to the customer. After obtaining customer confirmation, if the customer confirms that the current configuration and parameters are correct, the order continues to be generated; if the confirmation result contains modification information, the corresponding configuration relationship matching and product parameter matching are re-executed based on the modified configuration parameters.

[0111] When a product parameter corresponding to the target configuration data does not exist in the product parameter database, a supplementary parameter request message is generated based on the target configuration data for which no matching parameter was found. The supplementary parameter request message identifies the missing data item and its corresponding configuration. Technical personnel or other data maintenance personnel can input supplementary product parameters based on this request. The system establishes a correspondence between the supplementary product parameters and the target configuration data, and updates the product parameter database accordingly.

[0112] After the database update is complete, the parameter matching conditions corresponding to the original target configuration data are used to re-match the updated product parameter database to obtain the product parameter data corresponding to the newly added configuration. This process allows standard and non-standard products to enter the same main order processing flow, while retaining the update mechanism for writing back to the database after maintenance of non-standard parameters.

[0113] In one specific application of gearbox order processing, the generated product information data can be further used to create material information in batches. The system standardizes product data by combining order configuration parameters and product performance parameters, and sends it to the SAP Enterprise Resource Planning system to complete the batch creation of materials.

[0114] After a customer confirms an order online, the product parameter information can be used to generate electronic nameplate data for production, and the production-related parameters can be synchronized to the Manufacturing Execution System (MES). Production or packaging stations can retrieve the corresponding product parameters from the MES by scanning the work order barcode and print the product nameplate accordingly. This allows the front-end order parsing results to be transmitted along the same data link to the material creation, customer confirmation, and production nameplate generation stages.

[0115] The following examples of four gearbox orders from the data provided illustrate the specific process from order parsing to parameter output. The data below is for illustrative purposes only and represents one specific application scenario.

[0116] After three-level hierarchical parsing, the first order set yielded configuration entities including WJRTRF179, DU280M4, V, E, 47.65, M1, and 180°. The model combination formed by structural layer verification was WJRTRF179DU280M4-VE-180°. Business parameter linkage verification used core fields such as WJRTRF179, DU280M4, 47.65, and M1 to determine compatibility. Upon successful verification, based on the model, speed ratio, and installation method, the allowable torque was 32000 Nm, standard lubricating oil volume was 36 L, and the total weight of the reducer was 996 kg from the reducer body parameter database. Based on the motor model, the rated speed was 1490 r / min, rated power was 55 kW, and the motor weight was 646 kg from the motor parameter database.

[0117] The second group of orders, after parsing, yielded configuration entities such as JRTKA39, BDS71S4, 37.97, M1, and 270°. The structural layer generated a combined verification result of JRTKA39BDS71S4-270°, while business logic verification used fields such as JRTKA39, BDS71S4, 37.97, and M1. Database matching yielded the following specifications: allowable torque of the reducer 200 Nm, standard lubricating oil volume 0.5 L, reducer weight 11.5 kg, and motor rated speed 1380 r / min, rated power 0.37 kW, and motor weight 7.6 kg.

[0118] The third group of orders, after parsing, yielded configuration entities such as JRTR49, DN71M4, 93.68, and M1. The structural layer performed combined validation based on the extracted configuration fields (JRTR49, DN71M4, M1, etc.), while the business logic validation used these fields. Database matching resulted in the following specifications: allowable torque of the reducer 300 Nm, standard lubricating oil volume 0.7 L, reducer weight 14 kg, and motor rated speed 1415 r / min, rated power 0.37 kW, and motor weight 9.4 kg.

[0119] The fourth order parsed to obtain configuration entities such as WJRTFAF79, DP132S8, 12.20, M4, and 0°. The structural combination verification result is WJRTFAF79DP132S8-0°, and the business logic verification uses fields such as WJRTFAF79, DP132S8, 12.20, and M4. After database matching, the following parameters were obtained: allowable torque of the reducer 1500Nm, standard lubricating oil volume 8L, reducer weight 55kg, and motor rated speed 1500r / min, rated power 7.5kW, and motor weight 52kg.

[0120] The above example shows that the order initially presents a mixture of fields such as model, speed ratio, installation method, motor model and angle. The three-level hierarchical parsing first converts it into a standardized configuration entity. The two-level product configuration relationship matching further determines whether the structural combination and selection parameters meet the requirements. Subsequently, multi-parameter joint index and single-parameter index are used to access different product parameter databases, and finally the parameter set used for product confirmation and production is obtained.

[0121] Through the above implementation methods, the disordered text, mixed Chinese and English text, special symbols, and non-standard parameter expressions in the original order are sequentially processed through coarse noise reduction, standardization cleaning, and domain entity extraction, so that subsequent configuration relationship matching no longer directly deals with the original free text. By validating the extraction results through two types of product configuration relationships—structure layer and selection layer—combinations that do not exist in actual structure or whose main selection parameters are incompatible can be filtered out before database retrieval, thereby reducing the situation where fields can be correctly identified but the configuration itself is invalid.

[0122] By distinguishing between multi-parameter joint matching and single-parameter matching based on the relationship determined by parameters, and by using product parameter databases that are independent and complementary in terms of parameters, different types of parameters can be obtained according to their own actual determination logic, avoiding the use of a unified index for retrieval of all parameters.

[0123] In summary, this application provides a product order data processing method. It involves performing hierarchical structuring processing on the order data to be processed, extracting product configuration parameters from the order data to obtain structured order data; based on preset product configuration relationships, it performs association matching on multiple product configuration parameters in the structured order data to determine target configuration data that satisfies the product configuration relationships; based on the parameter determination relationships corresponding to different types of product configuration parameters in the target configuration data, it determines corresponding parameter matching conditions; based on the parameter matching conditions, it performs matching in a product parameter database to obtain product parameter data; and it associates the product parameter data with the corresponding target configuration data to generate product information data. This method solves the problems in the prior art where it is difficult to automatically extract product configuration parameters from unstructured order data, and where the lack of association constraints between multiple product configuration parameters leads to insufficient accuracy of product configuration data, thus achieving automatic conversion of unstructured order data into product information data.

[0124] Based on the same technical concept, embodiments of this application also provide a product order data processing system, such as... Figure 7 As shown, it includes: The structured processing module 701 is used to perform hierarchical structured processing on the order data to be processed, extract the product configuration parameters from the order data to be processed, and obtain structured order data. The configuration matching module 702 is used to perform association matching on multiple product configuration parameters in the structured order data based on preset product configuration relationships, and determine the target configuration data that satisfies the product configuration relationships; The matching condition determination module 703 is used to determine the corresponding parameter matching conditions based on the parameter determination relationship corresponding to different types of product configuration parameters in the target configuration data; The parameter acquisition module 704 is used to match the product parameter database based on the parameter matching conditions to obtain product parameter data. The product information generation module 705 is used to associate the product parameter data with the corresponding target configuration data to generate product information data.

[0125] This application also provides an electronic device corresponding to the method provided in the foregoing embodiments. Please refer to... Figure 8The diagram illustrates an electronic device provided by some embodiments of this application. The electronic device 20 may include: a processor 200, a memory 201, a bus 202, and a communication interface 203, wherein the processor 200, the communication interface 203, and the memory 201 are connected via the bus 202; the memory 201 stores a computer program that can run on the processor 200, and when the processor 200 runs the computer program, it executes the method provided by any of the foregoing embodiments of this application.

[0126] The memory 201 may include high-speed random access memory (RAM) or non-volatile memory, such as disk storage, flash memory, or other storage media capable of storing computer programs and data. The communication interface 203 is used to enable data communication between the electronic device 20 and external devices or systems.

[0127] Bus 202 can be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. The memory 201 is used to store programs. After receiving an execution instruction, the processor 200 executes the program. The method disclosed in any of the foregoing embodiments of this application can be applied to the processor 200, or implemented by the processor 200.

[0128] The processor 200 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of the processor 200 or by instructions in software form. The processor 200 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules may reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 201. The processor 200 reads the information in memory 201 and, in conjunction with its hardware, completes the steps of the above method.

[0129] The electronic devices and methods provided in the embodiments of this application are based on the same inventive concept and have the same beneficial effects as the methods they employ, operate, or implement.

[0130] This application also provides a computer-readable storage medium corresponding to the method provided in the foregoing embodiments. Please refer to... Figure 9 The computer-readable storage medium shown is an optical disc 30, on which a computer program (i.e., a program product) is stored, which, when run by a processor, executes the methods provided in any of the foregoing embodiments.

[0131] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical and magnetic storage media, which will not be elaborated here.

[0132] The computer-readable storage medium provided in the above embodiments of this application and the method provided in the embodiments of this application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the applications stored therein.

[0133] The above description is only a preferred embodiment of the present invention and does not limit the patent scope of the present invention. All equivalent structural transformations made under the concept of the present invention using the contents of the present invention specification and drawings, or direct / indirect applications in other related technical fields, are included within the patent protection scope of the present invention.

Claims

1. A product order data processing method, characterized by, include: The order data to be processed is subjected to hierarchical and structured processing, and the product configuration parameters are extracted from the order data to obtain structured order data; Based on the preset product configuration relationship, multiple product configuration parameters in the structured order data are associated and matched to determine the target configuration data that satisfies the product configuration relationship; Based on the parameter determination relationship corresponding to different types of product configuration parameters in the target configuration data, determine the corresponding parameter matching conditions; Based on the parameter matching conditions, the product parameter database is matched to obtain product parameter data; The product parameter data is associated with the corresponding target configuration data to generate product information data.

2. The method as described in claim 1, characterized in that, The process involves hierarchical structuring of the order data to be processed, extracting product configuration parameters from the order data to obtain structured order data, including: The order data to be processed is semantically segmented to obtain multiple order content fragments; Based on preset business information, business content identification is performed on multiple order content fragments, and order content fragments related to product requirements are filtered to obtain valid order data; The valid order data is processed to unify its format, resulting in standard order data; Product configuration parameters are extracted from the standard order data to obtain the structured order data.

3. The method as described in claim 2, characterized in that, The step of extracting product configuration parameters from the standard order data to obtain the structured order data includes: Entity recognition is performed on the product description information in the standard order data to obtain candidate configuration parameters; According to the preset field classification rules, the candidate configuration parameters are classified into categories to obtain the classified product configuration parameters; Based on the correspondence between the categorized product configuration parameters, a data association relationship is established between the product configuration parameters to generate the structured order data.

4. The method as described in claim 1, characterized in that, The step of associating and matching multiple product configuration parameters in the structured order data based on preset product configuration relationships to determine target configuration data that satisfies the product configuration relationships includes: Extract multiple product configuration parameters from the structured order data; Based on the product configuration relationship, the combination relationship between multiple product configuration parameters is matched to obtain the configuration matching result; Based on the configuration matching results, filter product configuration parameter combinations that satisfy the product configuration relationship; The target configuration data is generated based on the selected product configuration parameter combinations.

5. The method as described in claim 4, characterized in that, The product configuration relationships include product structure relationships and product selection relationships. Based on these product configuration relationships, the matching of combinations of multiple product configuration parameters to obtain configuration matching results includes: Based on the product structure relationship, the structural combination relationship corresponding to multiple product configuration parameters is matched to obtain the structural matching result. The structural combination relationship is used to characterize the assembly association relationship between multiple product structural elements. Based on the product selection relationship, the parameter adaptation relationship corresponding to multiple product configuration parameters is matched to obtain the selection matching result. The parameter adaptation relationship is used to characterize the selection association relationship between multiple product configuration parameters. The configuration matching result is generated based on the structure matching result and the selection matching result.

6. The method as described in claim 1, characterized in that, The step of determining the corresponding parameter matching conditions based on the parameter determination relationship corresponding to different types of product configuration parameters in the target configuration data includes: Extract multiple product configuration parameters from the target configuration data; Based on the parameter determination relationship corresponding to the multiple product configuration parameters, the multiple product configuration parameters are classified to obtain multiple parameter categories. The parameter determination relationship is used to characterize the determination relationship between product configuration parameters and product parameter data. For different parameter categories, corresponding parameter matching conditions are generated based on the relationship determined by the corresponding parameters.

7. The method as described in claim 6, characterized in that, The step of generating corresponding parameter matching conditions based on the relationship determined according to the corresponding parameters for different parameter categories includes: Based on the parameter relationship corresponding to the first parameter category, the parameter combination of multiple product configuration parameters that jointly determine the same product parameter data is used as the matching basis to generate the first parameter matching condition; The relationship is determined based on the parameters corresponding to the second parameter category. The configuration parameters of a single product are used as the matching basis to generate the matching conditions for the second parameter. The first parameter matching condition and the second parameter matching condition are determined as the parameter matching condition.

8. A product order data processing system, characterized in that, include: The structured processing module is used to perform hierarchical structured processing on the order data to be processed, extract the product configuration parameters from the order data to be processed, and obtain structured order data. The configuration matching module is used to perform association matching on multiple product configuration parameters in the structured order data based on preset product configuration relationships, and determine the target configuration data that satisfies the product configuration relationships; The matching condition determination module is used to determine the corresponding parameter matching conditions based on the parameter determination relationship corresponding to different types of product configuration parameters in the target configuration data; The parameter acquisition module is used to match the product parameter database based on the parameter matching conditions to obtain product parameter data. The product information generation module is used to associate the product parameter data with the corresponding target configuration data to generate product information data.

9. An electronic device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor, when running the computer program, performs an action to implement the method as claimed in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, It stores computer-readable instructions that can be executed by a processor to implement the method as described in any one of claims 1-7.