Management method and device based on material product matching and automatic generation, equipment and storage medium

Abstract

The invention belongs to the technical field of material management, and discloses a management method and device based on material product matching and automatic generation, equipment and a storage medium. The method comprises the following steps: carrying out AI semantic analysis on a material product description of a heterogeneous source, and extracting key parameters of a product; constructing a dynamic product feature matrix based on the key parameters of the product, and performing multi-level matching by using the dynamic product feature matrix and a supply database to obtain a plurality of candidate product matching schemes; determining a target product matching scheme from the plurality of candidate product matching schemes according to a semantic similarity threshold; performing parameter specification alignment processing on the target product matching scheme through a parameter mapping engine; and based on the processed target product matching scheme, establishing a target mapping relationship between the materials and the products, and managing the materials and the products by using the mapping relationship. By means of the method, the mapping relation can be dynamically updated in real time, and meanwhile the accuracy can be improved by means of the constructed mapping relation.

Description

Technical Field

[0001] The present invention relates to the technical field of material management, and in particular to a management method, device, equipment and storage medium based on material product matching and automatic generation. Background Art

[0002] In modern material management, with the increasing complexity of global supply chains and the diversification of e-commerce platforms, the sources of material product descriptions are becoming increasingly heterogeneous. Descriptions of the same product often differ significantly across different suppliers, e-commerce platforms, and internal enterprise systems. These differences manifest themselves in parameter naming, unit usage, data format, and semantic expression, among other aspects.

[0003] Existing material product matching and management systems primarily rely on manual rule configuration or simple keyword matching algorithms. Manual rule configuration requires custom mapping rules for each heterogeneous source, resulting in high development costs and difficulty adapting to the rapid integration of new sources and dynamic rule updates. Furthermore, when faced with complex product descriptions and multi-tiered supply databases, it is prone to numerous mismatches and missed matches.

[0004] The above content is only used to assist in understanding the technical solution of the present invention and does not constitute an admission that the above content is prior art. Summary of the Invention

[0005] The main purpose of the present invention is to provide a management method, device, equipment and storage medium based on material product matching and automatic generation, aiming to solve the technical problems of low efficiency and poor accuracy in the management of material products using manual rules.

[0006] To achieve the above objectives, the present invention provides a management method based on material product matching and automatic generation, the management method based on material product matching and automatic generation comprising the following steps:

[0007] Perform AI semantic analysis on material product descriptions from heterogeneous sources to extract key product parameters;

[0008] Constructing a dynamic product feature matrix based on the key parameters of the product, and performing multi-level matching with the supply database using the dynamic product feature matrix to obtain multiple candidate product matching solutions;

[0009] Determine a target product matching solution from multiple candidate product matching solutions based on a semantic similarity threshold;

[0010] Perform parameter specification alignment processing on the target product matching solution through a parameter mapping engine;

[0011] A target mapping relationship between materials and products is established based on the processed target product matching solution, and the material products are managed using the mapping relationship.

[0012] In some embodiments, performing AI semantic parsing on heterogeneous source material product descriptions includes:

[0013] Build an industry knowledge graph covering the commodities sector;

[0014] Training a domain-adaptive BERT model based on the industry knowledge graph and using the domain-adaptive BERT model to perform named entity recognition on unstructured product descriptions to extract different types of parameters;

[0015] Parsing the different types of parameters in combination with the industry knowledge graph to generate a structured parameter tree with dependency tags;

[0016] Performing unit fusion processing on the numerical nodes in the structured parameter tree to obtain a standardized numerical vector;

[0017] The normalized numerical vector is aligned with an entity in the industry knowledge graph.

[0018] In some embodiments, the parsing of the different types of parameters in combination with the industry knowledge graph to generate a structured parameter tree with dependency tags includes:

[0019] Based on the industry knowledge graph, the triple relationship between quantifiers, entities, and modifiers in product descriptions is annotated to generate weighted grammatical dependency templates;

[0020] Parsing the nested structure of different types of parameters based on the grammatical dependency template to generate a dependency tree with topology markings;

[0021] performing contextual disambiguation on ambiguous nodes in the dependency tree;

[0022] When conflicting parameters are identified among different types of parameters, traceability annotation is triggered and anomaly confidence scores are generated;

[0023] The dependency tree topology, disambiguation results, and anomaly confidence scores are integrated to build a structured parameter tree with dependency labels.

[0024] In some embodiments, determining a target product matching solution from a plurality of candidate product matching solutions according to a semantic similarity threshold includes:

[0025] Determine the semantic similarity between each candidate product matching solution and the target material description;

[0026] Dynamically adjust the similarity threshold based on the statistical distribution of historical matching data;

[0027] Filtering out candidate product matching solutions that exceed the similarity threshold from multiple candidate product matching solutions;

[0028] Determine the candidate product solution with the largest parameter dimension from the candidate product matching solutions that exceed the similarity threshold as the target product matching solution.

[0029] In some embodiments, the parameter mapping engine is used to align the target product matching solution with its parameter specifications, including:

[0030] Converting parameters from different sources in the target product matching solution into a unified parameter specification, and converting parameters in different units in the target product matching solution so that parameters of the same type have the same unit;

[0031] Fill in the missing parameters in the processed target product matching solution;

[0032] For conflicting parameters from different sources, the final parameters are determined according to the preset priority rules.

[0033] In some embodiments, the filling of missing parameters in the target product matching solution after processing includes:

[0034] Determine the first parameter and the second parameter adjacent to the missing parameter;

[0035] Determine the parameter sequence numbers corresponding to the first parameter and the second parameter, respectively, and the parameter sequence numbers corresponding to the missing parameters;

[0036] The parameter value corresponding to the missing parameter is calculated based on the parameter serial number corresponding to each of the first parameter and the second parameter, the parameter value corresponding to each of the first parameter and the second parameter, and the parameter serial number, and the missing parameter is filled based on the parameter value.

[0037] In some embodiments, establishing a target mapping relationship between materials and products based on the processed target product matching solution includes:

[0038] Based on the parameter alignment results of the target matching solution, a triple containing the material code, product feature vector, and mapping weight is extracted, and reference mapping rules are generated by combining the process constraint relationship in the knowledge graph;

[0039] Analyzing weight conflicts between the reference mapping rule and old mapping rules in a historical rule base;

[0040] If the weight conflict rate does not exceed the threshold, the material node and the product node are connected through a multidimensional edge to construct a target mapping relationship. The edge attributes include the matching score, parameter deviation threshold, and effective time window.

[0041] In addition, to achieve the above-mentioned purpose, the present invention further proposes a management device based on material product matching and automatic generation, the management device based on material product matching and automatic generation comprising:

[0042] The extraction module is used to perform AI semantic analysis on material product descriptions from heterogeneous sources and extract key product parameters;

[0043] a matching module for constructing a dynamic product feature matrix based on the key parameters of the product, and performing multi-level matching using the dynamic product feature matrix and a supply database to obtain multiple candidate product matching solutions;

[0044] A screening module is used to determine a target product matching solution from multiple candidate product matching solutions based on a semantic similarity threshold;

[0045] A processing module, configured to perform parameter specification alignment processing on the target product matching solution through a parameter mapping engine;

[0046] The construction module is used to establish a target mapping relationship between materials and products based on the processed target product matching solution, and use the mapping relationship to manage the material products.

[0047] In addition, to achieve the above-mentioned purpose, the present invention also proposes a management device based on material product matching and automatic generation, and the management device based on material product matching and automatic generation includes: a memory, a processor, and a management program based on material product matching and automatic generation stored on the memory and runnable on the processor, and the management program based on material product matching and automatic generation is configured to implement the steps of the management method based on material product matching and automatic generation as described above.

[0048] In addition, to achieve the above-mentioned purpose, the present invention also proposes a computer program product, which stores a management program based on material product matching and automatic generation. When the management program based on material product matching and automatic generation is executed by a processor, it implements the steps of the management method based on material product matching and automatic generation as described above.

[0049] The present invention performs AI semantic analysis on the descriptions of material products from heterogeneous sources to extract the key parameters of the products; constructs a dynamic product feature matrix based on the key parameters of the products, and uses the dynamic product feature matrix to perform multi-level matching with the supply database to obtain multiple candidate product matching schemes; determines the target product matching scheme from the multiple candidate product matching schemes based on the semantic similarity threshold; performs parameter specification alignment processing on the target product matching scheme through a parameter mapping engine; establishes a target mapping relationship between materials and products based on the processed target product matching scheme, and uses the mapping relationship to manage material products. Through the above method, the mapping relationship can be dynamically updated in real time, and the constructed mapping relationship can be used to improve accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 This is a flow chart of a first embodiment of the management method based on material product matching and automatic generation according to the present invention;

[0051] Figure 2 This is a structural block diagram of the first embodiment of the management device based on material product matching and automatic generation of the present invention.

[0052] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0053] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0054] The embodiment of the present invention provides a management method based on material product matching and automatic generation, referring to Figure 1 , Figure 1 This is a flow chart of a first embodiment of a management method based on material product matching and automatic generation according to the present invention.

[0055] In this embodiment, the management method based on material product matching and automatic generation includes the following steps:

[0056] Step S10: Perform AI semantic analysis on the descriptions of material products from heterogeneous sources to extract key parameters of the products.

[0057] In this embodiment, the execution subject of this embodiment is a management device based on material product matching and automatic generation, wherein the management device based on material product matching and automatic generation has functions such as data processing, data communication and program running. The management device based on material product matching and automatic generation can be a computer terminal device or other network device, and of course it can also be other devices with similar functions, and this embodiment does not limit this.

[0058] It's important to note that existing material product matching and management systems primarily rely on manual rule configuration or simple keyword matching algorithms. Manual rule configuration requires custom mapping rules for each heterogeneous source, which is not only costly to develop but also difficult to adapt to the rapid integration of new sources and dynamic rule updates. Furthermore, when faced with complex product descriptions and multi-tiered supply databases, it's prone to numerous mismatches and missed matches.

[0059] In the specific implementation, for material products from heterogeneous sources, that is, material products from different sources, this embodiment adopts AI semantic analysis to extract the key parameters of the products. For example, a company's products are 12mm, 12m, rebar HRB400E. After extracting the key parameters, the product name can be obtained: thread, material: HRB400E, specification: 12*12. This example is only for illustration. In actual applications, the parameter dimensions of the extracted key parameters can be set according to actual needs, and this is not limited in this embodiment.

[0060] Furthermore, in this embodiment, when performing IA semantic parsing, it is necessary to construct an industry knowledge graph covering the commodity field; based on the industry knowledge graph, a domain-adaptive BERT model is trained, and the domain-adaptive BERT model is used to perform named entity recognition on unstructured product descriptions to extract different types of parameters; the different types of parameters are parsed in combination with the industry knowledge graph to generate a structured parameter tree with dependency tags; the numerical nodes in the structured parameter tree are subjected to unit fusion processing to obtain a standardized numerical vector; and the standardized numerical vector is aligned with the entity in the industry knowledge graph.

[0061] It should be noted that the industry knowledge graph includes product categories, parameter types, unit conversion relationships, etc. The industry knowledge graph is used to load the national standard parameter system and establish a three-dimensional entity relationship network of materials, processes, and specifications. By training the domain adaptive BERT model through the industry knowledge graph, the knowledge graph can provide entity relationship constraints for the BERT model to ensure that named entity recognition meets industry standards. The parameters extracted by the domain adaptive BERT model include but are not limited to material categories, geometric specifications, and process parameters. The unit system fusion processing in this embodiment is for metric conversion of imperial units (such as feet) and non-standard units (such as pieces / bundles). After conversion, a standardized numerical vector can be obtained. The essence of entity alignment is to compare the standardized numerical vector with the knowledge graph entity, and to identify regional expression differences through the discriminator. For example, coil and wire are expressions of regional differences, but in fact they refer to the same material. Through entity alignment, materials or products with regional expression differences can be referred to consistently.

[0062] In one embodiment, the parsing of the different types of parameters in combination with the industry knowledge graph to generate a structured parameter tree with dependency tags further includes: annotating the triple relationship of quantifiers, entities, and modifiers in the product description based on the industry knowledge graph to generate a weighted grammatical dependency template; parsing the nested structure of different types of parameters based on the grammatical dependency template to generate a dependency tree with topological tags; performing context disambiguation on ambiguous nodes in the dependency tree; when conflicting parameters are identified in different types of parameters, triggering traceability annotation and generating anomaly confidence scores; fusing the dependency tree topology structure, disambiguation results and anomaly confidence scores to establish a structured parameter tree with dependency tags.

[0063] It should be noted that, for example, the nested relationship identifies the parameter nested relationship of diameter Φ and length L, such as Φ12*12m. The process of context disambiguation can be to use a multi-head attention mechanism to analyze the semantic direction of the conjunction (and / include), and combine the knowledge graph process attribute library to resolve the actual reference of the polysemous parameters (such as the parallel relationship between galvanizing and coating). In actual situations, there will be conflicting parameters, such as stainless steel HRB400E. In this case, an abnormal confidence score will be performed in this embodiment. Finally, after fusing the dependency tree topology, disambiguation results and abnormal confidence scores, a four-tuple sequence is output. The four-tuple sequence consists of entity, attribute, value, and confidence.

[0064] Step S20: constructing a dynamic product feature matrix based on the key parameters of the product, and performing multi-level matching with the supply database using the dynamic product feature matrix to obtain multiple candidate product matching solutions.

[0065] In the specific implementation, after extracting the above-mentioned key parameters, this embodiment uses the key parameters to perform multi-level matching with the supply database. The multi-level in this embodiment refers to the matching of different parameter dimensions, such as first matching the material name, then matching the material material, and finally matching the material specifications. Since in actual situations, there are many similar products, especially products of similar types, after matching the above-mentioned key parameters, multiple candidate product matching schemes can be obtained, and each matching scheme corresponds to a different product.

[0066] Step S30: determining a target product matching solution from a plurality of candidate product matching solutions according to a semantic similarity threshold.

[0067] In this embodiment, after obtaining the above-mentioned multiple candidate product matching solutions, this embodiment needs to determine the semantic similarity between each candidate product matching solution and the target material description; dynamically adjust the similarity threshold based on the statistical distribution of historical matching data; screen out candidate product matching solutions that exceed the similarity threshold from the multiple candidate product matching solutions; and determine the candidate product solution with the largest parameter dimension from the candidate product matching solutions that exceed the similarity threshold as the target product matching solution.

[0068] It should be noted that the similarity threshold can be adjusted, for example, as θ = μ + k·σ, where μ represents the mean semantic similarity of the historical matching data, σ represents the standard deviation, and k is the preset confidence coefficient. The final target product matching solution corresponds to the largest parameter dimension. Designing for the largest parameter dimension can improve the effectiveness of the subsequent material-product mapping relationship, thereby increasing accuracy.

[0069] Step S40: aligning the parameters of the target product matching solution with the parameter mapping engine.

[0070] In a specific implementation, after determining the target product matching solution, in order to make the target product matching solution more standardized, the parameters from different sources in the target product matching solution are converted into unified parameter specifications, and the parameters of different units in the target product matching solution are converted so that parameters of the same type have the same unit. The above method is used to achieve unit unification, for example, meters are uniformly converted into millimeters, etc. In addition, in this embodiment, missing parameters can also be supplemented. The specific supplementation process is to determine the first parameter and the second parameter adjacent to the missing parameter; determine the parameter sequence number corresponding to each of the first parameter and the second parameter, and the parameter sequence number corresponding to the missing parameter; calculate the parameter value corresponding to the missing parameter based on the parameter sequence number corresponding to each of the first parameter and the second parameter, the parameter value corresponding to each of the first parameter and the second parameter, and the parameter sequence number, and fill in the missing parameter based on the parameter value.

[0071] It should be noted that the calculation formula for the parameter values corresponding to the above missing parameters is:

[0072]

[0073] Among them, x i and x i+1 are the parameter values corresponding to the first parameter and the second parameter respectively, t i and t i+1 are the parameter numbers corresponding to the first and second parameters respectively, t m is the parameter number corresponding to the missing parameter, x m That is, the parameter value of the missing parameter.

[0074] Furthermore, in the actual process, there may be parameter conflicts. Parameters of the same type may have different sources, resulting in different values. For example, the same material may have two specification ranges. In this case, the preset priority rules can be used in this embodiment to determine the final parameters. For example, the parameters within the parameter value range may be given the highest priority, or the parameters with smaller values may be given the highest priority.

[0075] Step S50: establishing a target mapping relationship between materials and products based on the processed target product matching solution, and managing the materials and products using the mapping relationship.

[0076] It should be noted that the mapping rules, that is, the mapping relationship between materials and products, are updated in real time. Therefore, the determination of the new mapping relationship requires analysis of the weight conflict with the old mapping rules of the historical rule base. It should be understood that the changes in materials and product parameters are real-time and there will be no large deviations. Therefore, the conflict rate between the corresponding new mapping relationship and the old mapping rules of the historical rule base should not exceed the threshold. The threshold in this embodiment can be set to 10%. Of course, it can also be set to other values according to actual needs. This is not limited in this embodiment. Reference mapping rules, that is, the mapping relationship between the triples of material codes, product feature vectors, and mapping weights

[0077] In a specific implementation, the weight conflict can be calculated by calculating the difference between the mapping weight of the reference mapping rule and the mapping weight of the old mapping rule in the historical rule base. Taking the above threshold as an example, if the difference does not exceed 10% of the mapping weight of the old mapping rule in the historical rule base, the conflict rate is considered to meet the requirements.

[0078] In this embodiment, AI semantic parsing is performed on the descriptions of material products from heterogeneous sources to extract the key parameters of the products; a dynamic product feature matrix is constructed based on the key parameters of the products, and the dynamic product feature matrix is used to perform multi-level matching with the supply database to obtain multiple candidate product matching schemes; a target product matching scheme is determined from the multiple candidate product matching schemes based on a semantic similarity threshold; parameter specification alignment processing is performed on the target product matching scheme through a parameter mapping engine; a target mapping relationship between materials and products is established based on the processed target product matching scheme, and the material products are managed using the mapping relationship. Through the above method, the mapping relationship can be dynamically updated in real time, and the constructed mapping relationship can be used to improve accuracy.

[0079] In addition, an embodiment of the present invention also proposes a computer program product, which stores a management program based on material product matching and automatic generation. When the management program based on material product matching and automatic generation is executed by a processor, the steps of the management method based on material product matching and automatic generation as described above are implemented.

[0080] Reference Figure 2 , Figure 2 This is a structural block diagram of the first embodiment of the management device based on material product matching and automatic generation of the present invention.

[0081] like Figure 2 As shown, the management device based on material product matching and automatic generation proposed in an embodiment of the present invention includes:

[0082] Extraction module 10, used to perform AI semantic analysis on material product descriptions from heterogeneous sources and extract key product parameters;

[0083] A matching module 20 is configured to construct a dynamic product feature matrix based on the key parameters of the product, and perform multi-level matching using the dynamic product feature matrix and a supply database to obtain multiple candidate product matching solutions;

[0084] A screening module 30 is configured to determine a target product matching solution from a plurality of candidate product matching solutions based on a semantic similarity threshold;

[0085] A processing module 40 is configured to perform parameter specification alignment processing on the target product matching solution through a parameter mapping engine;

[0086] The construction module 50 is used to establish a target mapping relationship between materials and products based on the processed target product matching solution, and manage the material products using the mapping relationship.

[0087] In this embodiment, AI semantic parsing is performed on the descriptions of material products from heterogeneous sources to extract the key parameters of the products; a dynamic product feature matrix is constructed based on the key parameters of the products, and the dynamic product feature matrix is used to perform multi-level matching with the supply database to obtain multiple candidate product matching schemes; a target product matching scheme is determined from the multiple candidate product matching schemes based on a semantic similarity threshold; parameter specification alignment processing is performed on the target product matching scheme through a parameter mapping engine; a target mapping relationship between materials and products is established based on the processed target product matching scheme, and the material products are managed using the mapping relationship. Through the above method, the mapping relationship can be dynamically updated in real time, and the constructed mapping relationship can be used to improve accuracy.

[0088] In some embodiments, the extraction module 10 is used to construct an industry knowledge graph covering the commodity field;

[0089] Training a domain-adaptive BERT model based on the industry knowledge graph and using the domain-adaptive BERT model to perform named entity recognition on unstructured product descriptions to extract different types of parameters;

[0090] Parsing the different types of parameters in combination with the industry knowledge graph to generate a structured parameter tree with dependency tags;

[0091] Performing unit fusion processing on the numerical nodes in the structured parameter tree to obtain a standardized numerical vector;

[0092] The normalized numerical vector is aligned with an entity in the industry knowledge graph.

[0093] In some embodiments, the extraction module 10 is used to annotate the triple relationship between quantifiers, entities, and modifiers in the product description based on the industry knowledge graph to generate a weighted grammatical dependency template;

[0094] Parsing the nested structure of different types of parameters based on the grammatical dependency template to generate a dependency tree with topology markings;

[0095] performing contextual disambiguation on ambiguous nodes in the dependency tree;

[0096] When conflicting parameters are identified among different types of parameters, traceability annotation is triggered and anomaly confidence scores are generated;

[0097] The dependency tree topology, disambiguation results, and anomaly confidence scores are integrated to build a structured parameter tree with dependency labels.

[0098] In some embodiments, the screening module 30 is used to determine the semantic similarity between each candidate product matching solution and the target material description;

[0099] Dynamically adjust the similarity threshold based on the statistical distribution of historical matching data;

[0100] Filtering out candidate product matching solutions that exceed the similarity threshold from multiple candidate product matching solutions;

[0101] Determine the candidate product solution with the largest parameter dimension from the candidate product matching solutions that exceed the similarity threshold as the target product matching solution.

[0102] In some embodiments, the processing module 40 is configured to convert parameters from different sources in the target product matching solution into a unified parameter specification, and to convert parameters in different units in the target product matching solution so that parameters of the same type have the same unit;

[0103] Fill in the missing parameters in the processed target product matching solution;

[0104] For conflicting parameters from different sources, the final parameters are determined according to the preset priority rules.

[0105] In some embodiments, the processing module 40 is configured to determine a first parameter and a second parameter adjacent to the missing parameter;

[0106] Determine the parameter sequence numbers corresponding to the first parameter and the second parameter, respectively, and the parameter sequence numbers corresponding to the missing parameters;

[0107] The parameter value corresponding to the missing parameter is calculated based on the parameter serial number corresponding to each of the first parameter and the second parameter, the parameter value corresponding to each of the first parameter and the second parameter, and the parameter serial number, and the missing parameter is filled based on the parameter value.

[0108] In some embodiments, the construction module 50 is configured to extract a triplet including a material code, a product feature vector, and a mapping weight based on the parameter alignment result of the target matching solution, and generate a reference mapping rule in combination with the process constraint relationship in the knowledge graph;

[0109] Analyzing weight conflicts between the reference mapping rule and old mapping rules in a historical rule base;

[0110] If the weight conflict rate does not exceed the threshold, the material node and the product node are connected through a multidimensional edge to construct a target mapping relationship. The edge attributes include the matching score, parameter deviation threshold, and effective time window.

[0111] An embodiment of the present application also provides a management device based on material product matching and automatic generation, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus, the memory is used to store a management program based on material product matching and automatic generation; the processor is used to implement the above-mentioned management method based on material product matching and automatic generation when executing the program stored in the memory.

[0112] The communication bus mentioned in the aforementioned management device based on matching and automatic generation of material products can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. This communication bus can be divided into an address bus, a data bus, a control bus, etc.

[0113] The communication interface is used for communication between the above-mentioned management device based on material product matching and automatic generation and other devices.

[0114] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage. Alternatively, the memory may be at least one storage device located remote from the processor.

[0115] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0116] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When software is used for implementation, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrations. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0117] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0118] Each embodiment in this specification is described in a related manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiment is generally similar to the method embodiment, so the description is relatively simple. For related parts, refer to the description of the method embodiment.

[0119] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

[0120] It should be understood that the above is only an example and does not constitute any limitation to the technical solution of the present invention. In specific applications, those skilled in the art can make settings as needed, and the present invention does not impose any limitation on this.

[0121] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of it according to actual needs to achieve the purpose of the embodiment scheme, and no limitation is made here.

[0122] In addition, for technical details not fully described in this embodiment, please refer to the management method based on material product matching and automatic generation provided in any embodiment of the present invention, and will not be repeated here.

[0123] In addition, it should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0124] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0125] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, or of course by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0126] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

[0127] It is understandable that the system provided by the embodiment of the present invention corresponds to the method provided by the embodiment of the present invention, and the explanation, examples and beneficial effects of the relevant contents can refer to the corresponding parts of the above method.

Claims

1. A management method based on material product matching and automatic generation, characterized in that: The management method based on material product matching and automatic generation includes: Perform AI semantic analysis on material product descriptions from heterogeneous sources to extract key product parameters; Constructing a dynamic product feature matrix based on the key parameters of the product, and performing multi-level matching with the supply database using the dynamic product feature matrix to obtain multiple candidate product matching solutions; Determine a target product matching solution from multiple candidate product matching solutions based on a semantic similarity threshold; Perform parameter specification alignment processing on the target product matching solution through a parameter mapping engine; A target mapping relationship between materials and products is established based on the processed target product matching solution, and the material products are managed using the mapping relationship.

2. The management method based on material product matching and automatic generation according to claim 1, characterized in that: The AI semantic parsing of heterogeneous material product descriptions includes: Build an industry knowledge graph covering the commodities sector; Training a domain-adaptive BERT model based on the industry knowledge graph and using the domain-adaptive BERT model to perform named entity recognition on unstructured product descriptions to extract different types of parameters; Parsing the different types of parameters in combination with the industry knowledge graph to generate a structured parameter tree with dependency tags; Performing unit fusion processing on the numerical nodes in the structured parameter tree to obtain a standardized numerical vector; The normalized numerical vector is aligned with an entity in the industry knowledge graph.

3. The management method based on material product matching and automatic generation according to claim 2, characterized in that: The different types of parameters are parsed in combination with the industry knowledge graph to generate a structured parameter tree with dependency tags, including: Based on the industry knowledge graph, the triple relationship between quantifiers, entities, and modifiers in product descriptions is annotated to generate weighted grammatical dependency templates; Parsing the nested structure of different types of parameters based on the grammatical dependency template to generate a dependency tree with topology markings; performing contextual disambiguation on ambiguous nodes in the dependency tree; When conflicting parameters are identified among different types of parameters, traceability annotation is triggered and anomaly confidence scores are generated; The dependency tree topology, disambiguation results, and anomaly confidence scores are integrated to build a structured parameter tree with dependency labels.

4. The management method based on material product matching and automatic generation according to claim 1, characterized in that: Determining a target product matching solution from a plurality of candidate product matching solutions according to a semantic similarity threshold includes: Determine the semantic similarity between each candidate product matching solution and the target material description; Dynamically adjust the similarity threshold based on the statistical distribution of historical matching data; Filtering out candidate product matching solutions that exceed the similarity threshold from multiple candidate product matching solutions; Determine the candidate product solution with the largest parameter dimension from the candidate product matching solutions that exceed the similarity threshold as the target product matching solution.

5. The management method based on material product matching and automatic generation according to claim 1, characterized in that: The parameter mapping engine is used to align the parameters of the target product matching solution, including: Converting parameters from different sources in the target product matching solution into a unified parameter specification, and converting parameters in different units in the target product matching solution so that parameters of the same type have the same unit; Fill in the missing parameters in the processed target product matching solution; For conflicting parameters from different sources, the final parameters are determined according to the preset priority rules.

6. The management method based on material product matching and automatic generation according to claim 5, characterized in that: The missing parameters in the target product matching solution after filling in the processing include: Determine a first parameter and a second parameter adjacent to the missing parameter; Determine the parameter sequence numbers corresponding to the first parameter and the second parameter, respectively, and the parameter sequence numbers corresponding to the missing parameters; The parameter value corresponding to the missing parameter is calculated based on the parameter serial number corresponding to each of the first parameter and the second parameter, the parameter value corresponding to each of the first parameter and the second parameter, and the parameter serial number, and the missing parameter is filled based on the parameter value.

7. The management method based on material product matching and automatic generation according to claim 1, characterized in that: The target mapping relationship between materials and products is established based on the processed target product matching solution, including: Based on the parameter alignment results of the target matching solution, a triple containing the material code, product feature vector, and mapping weight is extracted, and reference mapping rules are generated by combining the process constraint relationship in the knowledge graph; Analyzing weight conflicts between the reference mapping rule and old mapping rules in a historical rule base; If the weight conflict rate does not exceed the threshold, the material node and the product node are connected through a multidimensional edge to construct a target mapping relationship. The edge attributes include the matching score, parameter deviation threshold, and effective time window.

8. A management device based on material product matching and automatic generation, characterized in that: The management device based on material product matching and automatic generation includes: The extraction module is used to perform AI semantic analysis on material product descriptions from heterogeneous sources and extract key product parameters; a matching module for constructing a dynamic product feature matrix based on the key parameters of the product, and performing multi-level matching using the dynamic product feature matrix and a supply database to obtain multiple candidate product matching solutions; A screening module is used to determine a target product matching solution from multiple candidate product matching solutions based on a semantic similarity threshold; A processing module, configured to perform parameter specification alignment processing on the target product matching solution through a parameter mapping engine; The construction module is used to establish a target mapping relationship between materials and products based on the processed target product matching solution, and use the mapping relationship to manage the material products.

9. A management device based on material product matching and automatic generation, characterized in that: The management device based on material product matching and automatic generation includes: a memory, a processor, and a management program based on material product matching and automatic generation stored on the memory and executable on the processor. The management program based on material product matching and automatic generation is configured to implement the steps of the management method based on material product matching and automatic generation as described in any one of claims 1 to 7.

10. A computer program product, characterized in that The computer program product stores a management program based on material product matching and automatic generation, and when the management program based on material product matching and automatic generation is executed by a processor, the steps of the management method based on material product matching and automatic generation as described in any one of claims 1 to 7 are implemented.

Images