A product electronic resume intelligent traceability management system and method

Abstract

The present invention discloses a product electronic resume intelligent traceability management system and method, which belongs to the field of product traceability technology and solves the problem of insufficient anti-counterfeiting verification function of product traceability method. The system includes: a user traceability management client, which obtains the product number and quality inspection data of the product to be traced; the MES batch management server includes a storage module and a retrieval module; the storage module stores the product electronic resume of the product, including: product number, batch fingerprint characteristics of the current production batch and its matching AI model; the retrieval module retrieves the electronic resume of the product with the same product number according to the product number of the product to be traced; the traceability matching module, if the retrieval is successful, uses the retrieved AI model to process the quality inspection data of the product to be traced, and obtains the batch fingerprint characteristics of the product to be traced; if the batch fingerprint characteristics of the product to be traced match the retrieved batch fingerprint characteristics, the traceability of the product to be traced is successful; otherwise, the traceability of the product to be traced fails.

Description

Technical Field

[0001] The present invention relates to the technical field of product traceability, and in particular to an intelligent traceability management system and method for product electronic resumes. Background Art

[0002] During batch management, the MES system can automatically generate batch information for each production batch, record it, and allow for subsequent query. If a problem occurs during product use, the MES system can quickly locate the problem batch through traceability, allowing for timely resolution and ensuring product quality and safety. However, current production batch management methods still have many flaws, particularly in terms of anti-counterfeiting verification functions. The following deficiencies exist:

[0003] (1) Batch management relies on manual record-keeping and post-inquiry: The existing production batch management method is mainly responsible for recording the production process and post-inquiry, lacking the ability to monitor and manage in real time. This method that relies on manual record-keeping is susceptible to human error and fraud. Once someone tampers with records or falsifies item information during the production process, the entire production batch management and traceability management will become ineffective.

[0004] (2) Lack of anti-counterfeiting verification function: Many MES systems lack effective anti-counterfeiting verification function. If the information on the product label is copied by malicious counterfeiters, the counterfeit products produced can be traced through the label, which makes the traceability system lose its due significance and function.

[0005] (3) Vulnerability to tampering and counterfeiting: Due to the lack of adequate security measures, information in the production process can be easily tampered with. For example, if someone deliberately changes production data or introduces counterfeit products into the supply chain, existing traceability methods may not be able to detect these changes, resulting in counterfeit products entering the market.

[0006] (4) Lack of digital management of the entire process: Anti-counterfeiting traceability requires recording the entire process of the product from raw material procurement to finished product, but the existing batch management solutions often only focus on the production process and ignore the digital management of other links such as warehousing, distribution, and logistics, which limits the comprehensiveness and accuracy of traceability.

[0007] (5) Singleness of technical means: Existing anti-counterfeiting and traceability technical means are relatively single, such as relying solely on QR codes or barcodes, which are easy to copy and forge.

[0008] (6) Limitations of data analysis and application: Existing traceability systems have limitations in data analysis and application, and are unable to fully utilize traceability data for in-depth analysis and support corporate decision-making. More advanced data analysis technologies are needed to extract valuable information to optimize production processes and improve product quality.

[0009] In summary, the existing production batch management methods have obvious shortcomings in anti-counterfeiting verification, real-time monitoring, full-process management, and data analysis. How to improve the anti-counterfeiting verification function of products and optimize the traceability management method of product electronic resumes are technical issues that need to be urgently addressed. Summary of the Invention

[0010] In view of the above analysis, the embodiments of the present invention aim to provide a product electronic resume intelligent traceability management system and method to solve the problem that the existing product electronic resume traceability method has insufficient anti-counterfeiting verification function.

[0011] First, the present invention discloses an intelligent traceability management system for product electronic records, which includes a user traceability management client, an MES batch management server and a traceability matching module; wherein,

[0012] User traceability management client to obtain product number and quality inspection data of the product to be traced;

[0013] The MES batch management server includes a storage module and a retrieval module; wherein,

[0014] A storage module stores the electronic product history of the product; the electronic product history includes: product number, batch fingerprint characteristics of the current production batch and its matching AI model;

[0015] The retrieval module searches for electronic records of products with the same product number according to the product number of the product to be traced. If the search fails, the traceability of the product to be traced fails, and the traceability results are fed back to the user's traceability management client;

[0016] The traceability matching module, if the retrieval is successful, uses the retrieved AI model to process the quality inspection data of the product to be traced to obtain the batch fingerprint characteristics of the product to be traced; if the batch fingerprint characteristics of the product to be traced match the retrieved batch fingerprint characteristics, the traceability of the product to be traced is successful; otherwise, the traceability of the product to be traced fails.

[0017] On the basis of the above solution, the present invention also makes the following improvements:

[0018] Furthermore, the product electronic history also includes product related information; the product related information includes at least one of a factory number and a data machine tool number;

[0019] The user traceability management client is also used to obtain product-related information of the product to be traced;

[0020] The traceability matching module, if the retrieval is successful, first determines whether the product-related information of the product to be traced corresponds to the product-related information in the retrieved product electronic resume. If they are consistent, the retrieved AI model is used to process the quality inspection data of the product to be traced; otherwise, the traceability of the product to be traced fails.

[0021] Furthermore, in the traceability matching module, a similarity measurement is used to determine whether the batch fingerprint feature of the product to be traced matches the retrieved batch fingerprint feature.

[0022] Furthermore, the traceability matching module is independently set, or is set in the user traceability management client, or is set in the MES batch management server;

[0023] If the traceability matching module is set up independently, or set up in the MES batch management server, the traceability results will also be fed back to the user's traceability management client.

[0024] Furthermore, in the MES batch management server, all quality inspection data of the same production batch are used in advance to train the AI ​​model as follows to obtain the batch fingerprint features of the corresponding production batch and its matching AI model:

[0025] Perform feature extraction on all quality inspection data of the same production batch to obtain the feature vector of the corresponding quality inspection data;

[0026] Use the feature vectors of all quality inspection data from the same production batch as positive sample data to train the AI ​​model to learn the common features in the positive sample data;

[0027] After the AI ​​model training is completed, the common features in the positive sample data extracted by the AI ​​model are used as the batch fingerprint features of the corresponding production batch, and the trained AI model is used as the AI ​​model for matching the batch fingerprint features of the corresponding production batch.

[0028] Furthermore, in the process of pre-training the AI ​​model using all the quality inspection data of the same production batch, the feature vector of the quality inspection data is obtained by performing the following operations:

[0029] Sort multiple dimensions involved in the quality inspection standards of products from the same production batch in a fixed manner to form a feature extraction template;

[0030] Feature extraction is performed on each quality inspection data in the same production batch according to the feature extraction template to obtain the feature vector of the corresponding quality inspection data.

[0031] Second, the present invention also discloses a method for intelligent traceability management of product electronic resumes, the method comprising:

[0032] Start the user traceability management client, obtain the product code of the product to be traced, and send it to the MES batch management server;

[0033] The MES batch management server retrieves the electronic product history of each product based on the product code of the product to be traced; the product electronic history includes: product number, batch fingerprint characteristics of the current production batch and its matching AI model; if the retrieval is successful, the retrieved product electronic history with the same product number will be sent to the user traceability management client; otherwise, if the retrieval fails, the traceability of the product to be traced fails, and the traceability result is fed back to the user traceability management client;

[0034] If the search is successful, the user's traceability management client starts the quality inspection program to conduct quality inspection on the product to be traced and obtains the quality inspection data of the product to be traced;

[0035] The user traceability management client uses the received AI model to process the quality inspection data of the product to be traced to obtain the batch fingerprint characteristics of the product to be traced; if the batch fingerprint characteristics of the product to be traced match the received batch fingerprint characteristics, the traceability of the product to be traced is successful; otherwise, the traceability of the product to be traced fails.

[0036] On the basis of the above solution, the present invention also makes the following improvements:

[0037] Furthermore, the product electronic history also includes product related information; the product related information includes at least one of a factory number and a data machine tool number;

[0038] The method further comprises:

[0039] After starting the user traceability management client, the product related information of the product to be traced is also obtained;

[0040] After receiving the electronic resume of the product with the same product number, the user traceability management client first determines whether the product association information of the product to be traced corresponds to the product association information in the received electronic resume. If they are consistent, it jumps to the step of starting the quality inspection procedure in the user traceability management client. Otherwise, the traceability of the product to be traced fails.

[0041] Third, the present invention also discloses a method for intelligent traceability management of product electronic resumes, the method comprising:

[0042] Start the user traceability management client to obtain the product code of the product to be traced; the user traceability management client starts the quality inspection program to conduct quality inspection on the product to be traced and obtain the quality inspection data of the product to be traced; the product code and quality inspection data of the product to be traced are sent to the MES batch management server;

[0043] The MES batch management server retrieves the electronic product history of each product based on the product code of the product to be traced; the product electronic history includes: product number, batch fingerprint characteristics of the current production batch and its matching AI model; if the retrieval fails, the traceability of the product to be traced fails, and the traceability result is fed back to the user traceability management client;

[0044] If the retrieval is successful, the MES batch management server directly uses the retrieved AI model to process the quality inspection data of the product to be traced to obtain the batch fingerprint characteristics of the product to be traced; if the batch fingerprint characteristics of the product to be traced match the retrieved batch fingerprint characteristics, the traceability of the product to be traced is successful; otherwise, the traceability of the product to be traced fails; and the traceability results are fed back to the user traceability management client.

[0045] On the basis of the above solution, the present invention also makes the following improvements:

[0046] Furthermore, the product electronic history also includes product related information; the product related information includes at least one of a factory number and a data machine tool number;

[0047] The method further comprises:

[0048] After starting the user traceability management client, the product-related information of the product to be traced is also obtained; the product code, product-related information and quality inspection data of the product to be traced are sent to the MES batch management server;

[0049] The MES batch management server retrieves the product electronic history of each product based on the product code of the product to be traced. If the retrieval is successful, it first determines whether the product-related information of the product to be traced corresponds to the product-related information in the retrieved product electronic history. If they are consistent, it jumps to the step of directly using the retrieved AI model to process the quality inspection data of the product to be traced by the MES batch management server; otherwise, the traceability of the product to be traced fails, and the traceability results are fed back to the user traceability management client.

[0050] Compared with the prior art, the present invention can achieve at least one of the following beneficial effects:

[0051] The product electronic resume intelligent traceability management system disclosed in the present invention can use the product number of the product to be traced to retrieve the electronic resume of products with the same product number. It also uses the batch fingerprint characteristics in the product electronic resume and the specificity of the AI ​​model it matches to determine whether the product to be traced matches the pre-stored product information, thereby achieving anti-counterfeiting verification and effectively solving the problem of insufficient anti-counterfeiting verification functions of product electronic resume traceability methods in the prior art. In the specific implementation process, by also defining the specific functions and mutual coordination relationships of each component, it can well realize the intelligent traceability management of product electronic resumes and meet the system configuration requirements under different hardware conditions.

[0052] The method for intelligent traceability management of product electronic histories disclosed in the present invention can also utilize the batch fingerprint characteristics in the product electronic histories and the specificity of the AI ​​model they match to determine whether the product to be traced matches the pre-stored product information, thereby achieving anti-counterfeiting verification and effectively resolving the problem of insufficient anti-counterfeiting verification capabilities of product electronic histories traceability methods in the prior art. At the same time, by limiting the process steps of the two different implementation methods, it is convenient for relevant technical personnel to select the optimal process implementation steps based on actual R&D conditions. This method has strong applicability and can meet the needs of intelligent traceability management of product electronic histories in different application scenarios.

[0053] In the present invention, the above-mentioned technical solutions can be combined with each other to achieve more preferred combinations. Other features and advantages of the present invention will be described in the following description, and some advantages will become apparent from the description or be learned through practice of the present invention. The objectives and other advantages of the present invention can be realized and obtained through the contents particularly pointed out in the description and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The accompanying drawings are only used for the purpose of illustrating specific embodiments and are not to be considered as limiting the present invention. Like reference symbols denote like components throughout the accompanying drawings.

[0055] Figure 1 This is a schematic diagram of the structure of the product electronic resume intelligent traceability management system provided in Example 1 of the present invention;

[0056] Figure 2 Flowchart of the product electronic history intelligent traceability management method provided in Example 2 of the present invention;

[0057] Figure 3 A flowchart of another method for intelligent traceability management of product electronic records provided in Example 2 of the present invention;

[0058] Figure 4 This is a flowchart of the product electronic resume intelligent traceability management method provided in Example 3 of the present invention. DETAILED DESCRIPTION

[0059] The preferred embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, and are not used to limit the scope of the present invention.

[0060] After a user purchases a product, it should normally be printed with the product number, and may also include other information such as the claimed manufacturing plant and CNC machine tool number. However, this information could be forged by malicious counterfeiters with the same product number. Therefore, it is necessary to use the following methods to trace the authenticity of the product. The following embodiment provides an intelligent traceability management solution for product electronic records to solve this technical problem, and is described in detail below.

[0061] A specific embodiment 1 of the present invention discloses a product electronic resume intelligent traceability management system, the structural diagram of which is shown as follows: Figure 1 As shown, the system includes a user traceability management client, an MES batch management server and a traceability matching module; wherein,

[0062] User traceability management client to obtain product number and quality inspection data of the product to be traced;

[0063] The MES batch management server includes a storage module and a retrieval module; wherein,

[0064] A storage module stores the electronic product history of the product; the electronic product history includes: product number, batch fingerprint characteristics of the current production batch and its matching AI model;

[0065] The retrieval module searches for electronic records of products with the same product number according to the product number of the product to be traced. If the search fails, the traceability of the product to be traced fails, and the traceability results are fed back to the user's traceability management client;

[0066] The traceability matching module, if the retrieval is successful, uses the retrieved AI model to process the quality inspection data of the product to be traced to obtain the batch fingerprint characteristics of the product to be traced; if the batch fingerprint characteristics of the product to be traced match the retrieved batch fingerprint characteristics, the traceability of the product to be traced is successful; otherwise, the traceability of the product to be traced fails.

[0067] Compared with the existing technology, this embodiment uses the product number of the product to be traced to retrieve the electronic history of the product with the same product number, and uses the batch fingerprint characteristics in the product electronic history and the particularity of the AI ​​model it matches to determine whether the product to be traced matches the pre-retained product information, thereby realizing anti-counterfeiting verification, and effectively solving the problem of insufficient anti-counterfeiting verification function of the product electronic history traceability method in the existing technology.

[0068] Preferably, in this embodiment, the product electronic history also includes product-related information; the product-related information includes at least one of a factory number and a data machine tool number. In this case:

[0069] The user traceability management client is further used to obtain product-related information of the product to be traced; the product-related information includes at least one of a factory number and a data machine tool number;

[0070] The traceability matching module, if the retrieval is successful, first determines whether the product-related information of the product to be traced corresponds to the product-related information in the retrieved product electronic resume. If they are consistent, the retrieved AI model is used to process the quality inspection data of the product to be traced; otherwise, the traceability of the product to be traced fails.

[0071] In this process, by determining whether the product-related information of the product to be traced corresponds to the product-related information in the retrieved product electronic resume, counterfeit products with obvious information inconsistencies are prioritized from a relatively simple level. This can effectively improve traceability efficiency, shorten traceability time, and reduce the workload of AI model prediction and subsequent batch fingerprint feature matching. Preferably, in the traceability matching module, a similarity measurement is used to determine whether the batch fingerprint features of the product to be traced match the retrieved batch fingerprint features.

[0072] Preferably, the traceability matching module is independently set, or is set in the user traceability management client, or is set in the MES batch management server. Since the user traceability management client is designed directly for users, if the traceability matching module is independently set, or is set in the MES batch management server, the traceability results will also be fed back to the user traceability management client. The setting location of the traceability matching module can be set according to the actual situation of the system. When the memory of the user traceability management client and the MES batch management server is relatively limited, the AI ​​model that takes up more memory can be run through the independently set traceability matching module to improve the overall operation efficiency of the system. When the memory of the user traceability management client is large, it can be considered to set the traceability matching module in the user traceability management client, and the traceability results can be directly output. In addition, when the memory of the MES batch management server is large, the traceability matching module can also be set on the MES batch management server, saving the transmission time and transmission cost of the product electronic resume, and avoiding the batch fingerprint characteristics of the production batch and the AI ​​model that matches it from being illegally intercepted and obtained.

[0073] It should be noted that, in the MES batch management server of this embodiment, the AI ​​model is trained in advance using all quality inspection data of the same production batch to obtain the batch fingerprint features of the corresponding production batch and its matching AI model.

[0074] (1) Feature extraction is performed on all quality inspection data of the same production batch to obtain the feature vector of the corresponding quality inspection data.

[0075] During the specific implementation process, the feature vector of the quality inspection data can be obtained by performing the following operations: sorting the multiple dimensions involved in the quality inspection standards of products in the same production batch in a fixed manner to form a feature extraction template; performing feature extraction on each quality inspection data in the same production batch according to the feature extraction template to obtain the feature vector of the corresponding quality inspection data.

[0076] (2) Use the feature vectors of all quality inspection data of the same production batch as positive sample data to train the AI ​​model to learn the common features in the positive sample data.

[0077] During the specific implementation process, we can select a suitable AI model based on actual experience or conduct a large number of experiments, such as a deep learning model (using DNN, CNN, Transformer, etc.), use the feature vectors of all quality inspection data from the same batch as positive sample data, and train the AI ​​model to learn the common features in the positive sample data. These common features can characterize the common properties of all products produced in the same production batch.

[0078] During the specific implementation process, unsupervised learning methods such as autoencoders can be used to automatically learn useful feature representations from the feature vectors of all quality inspection data of the same production batch.

[0079] During AI model training, appropriate evaluation metrics, such as precision, recall, and F1 score, can be used to assess the model's performance. This ensures that the model can effectively extract common features from positive sample data and has good generalization capabilities. Based on the evaluation results, the AI ​​model can be adjusted and optimized to improve its accuracy and practicality.

[0080] In practical applications, both feature extraction and model training for AI models require consideration of specific production requirements and data characteristics, selecting the appropriate model architecture and training strategy. Furthermore, AI model evaluation and optimization is an ongoing process, requiring continuous adjustments based on training feedback. In this way, AI models can help companies more effectively conduct quality control and make product counterfeiting more difficult.

[0081] (3) After the AI ​​model training is completed, the common features in the positive sample data extracted by the AI ​​model are used as the batch fingerprint features of the corresponding production batch, and the trained AI model is used as the AI ​​model for matching the batch fingerprint features of the corresponding production batch.

[0082] An AI model that matches the batch fingerprint of the current production batch can ensure that the quality inspection data of all products in the current production batch conforms to the batch fingerprint of the current production batch (that is, the batch fingerprint obtained by inputting the feature vectors of each quality inspection data of the same production batch into the corresponding AI model matches the batch fingerprint of the current production batch), while the quality inspection data of products from other production batches does not conform to the batch fingerprint of the current production batch (that is, the batch fingerprint obtained by inputting the feature vectors of the quality inspection data of other production batches into the corresponding AI model does not match the batch fingerprint of the current production batch). This allows product traceability to be performed using the trained AI model and batch fingerprint of the corresponding batch.

[0083] In addition, the product electronic history can also include product-related information such as production batch number, production program version number, tool number, and quality inspection data. During implementation, the product-related information available on the product to be traced can be matched with the product-related information in the product electronic history to further optimize the traceability management process.

[0084] The specific embodiment 2 of the present invention also provides a method for intelligent traceability management of product electronic resumes, the flow chart of which is as follows: Figure 2 and Figure 3 The method comprises the following steps.

[0085] Step S1: Start the user traceability management client, obtain the product code of the product to be traced, and send it to the MES batch management server.

[0086] In this step, the product number of the product to be traced can be obtained by scanning the code of the product to be traced or directly reading it.

[0087] Step S2: The MES batch management server retrieves the product electronic resume of each product according to the product code of the product to be traced; the product electronic resume includes: product number, batch fingerprint characteristics of the current production batch and its matching AI model; if the retrieval is successful, the retrieved product electronic resume with the same product number is sent to the user traceability management client; otherwise, the retrieval fails, the traceability of the product to be traced fails, and the traceability result is fed back to the user traceability management client.

[0088] Step S3: If the search is successful, the user traceability management client starts the quality inspection program to perform quality inspection on the product to be traced and obtains the quality inspection data of the product to be traced.

[0089] It is important to emphasize that the quality inspection procedure initiated by the user traceability management client should be consistent with the quality inspection procedure of the genuine product with the same product number to ensure that it is carefully inspected according to the same quality inspection standards. Generally, multiple dimensions of quality inspection standards can be set to conduct quality inspections on products in multiple dimensions to obtain the quality inspection data of the corresponding products. For example, the quality inspection standards of products can be designed based on the following dimensions:

[0090] (1) Product dimensional accuracy: Ensure that the product dimensions meet the design requirements, which usually involves the accuracy of dimensions such as length, diameter, angle, shape and position.

[0091] (2) Surface roughness of the product: Evaluate the smoothness of the product surface, which is usually measured by surface roughness parameters.

[0092] (3) Material defects of the product: Check whether there are defects in the material, such as cracks, pores, inclusions, etc. These defects may affect the strength and durability of the parts.

[0093] (4) Casting and forging defects of products: For castings and forgings, it is necessary to check whether they have casting defects or forging defects, such as shrinkage holes, porosity, overburning, etc.

[0094] In the actual product quality inspection process, other specific requirements may also be involved. These requirements depend on the specific application scenarios and industry standards.

[0095] In the above-mentioned quality inspection standards, the quality inspection results for two dimensions, product dimensional accuracy and product surface roughness, can be presented in numerical form. The quality inspection results for two dimensions, product material defects and product casting and forging defects, can be presented in the form of logical data. Logical data can be expressed as 0 / 1 data, with "0" corresponding to "no" and "1" corresponding to "yes." It should be noted that in this embodiment, since each product is naturally generated based on the inherent characteristics of the data machine and tool, it is difficult to forge even if it is made public, and the production tasks of the same production batch are completed using the same CNC machine and tool. Therefore, there are commonalities between products produced in the same production batch, and the quality inspection data of products produced in the same production batch also has common characteristics. The above-mentioned quantifiable quality inspection data can objectively reflect the commonalities between all products in the same production batch due to being produced using the same CNC machine and tool, and can also objectively reflect the differences between products in different production batches due to being produced using different CNC machine and tool. Based on this technical concept, this embodiment uses an AI model to extract the common characteristics of the quality inspection data of the same production batch to achieve intelligent management of product information for the same production batch. In Example 1, the specific process of using all quality inspection data of the same production batch to train the AI ​​model and obtain the batch fingerprint features of the corresponding production batch and its matching AI model is given, which will not be repeated here.

[0096] Step S4: The user traceability management client uses the received AI model to process the quality inspection data of the product to be traced to obtain the batch fingerprint characteristics of the product to be traced; if the batch fingerprint characteristics of the product to be traced match the received batch fingerprint characteristics, the traceability of the product to be traced is successful; otherwise, the traceability of the product to be traced fails.

[0097] This method is suitable for situations where the user traceability management client has a large memory. It can effectively ensure that the AI ​​model can quickly process the quality inspection data of the product to be traced and obtain the batch fingerprint characteristics of the product to be traced.

[0098] Preferably, the product electronic history also includes product-related information; the product-related information includes at least one of a factory number and a data machine tool number. In this case, the method further includes:

[0099] During the execution of step S1 , after the user traceability management client is started, the product code of the product to be traced is obtained, and the product association information of the product to be traced is also obtained.

[0100] During the execution of step S4, after receiving the electronic resume of the product with the same product number, the user traceability management client first determines whether the product association information of the product to be traced corresponds to the product association information in the received electronic resume of the product. If they correspond, the process jumps to the step of starting the quality inspection procedure on the user traceability management client. Otherwise, the traceability of the product to be traced fails.

[0101] Specific embodiment 3 of the present invention also provides another product electronic resume intelligent traceability management method, the flow chart is as follows Figure 4 As shown, the method includes the following steps.

[0102] Step S1: Start the user traceability management client to obtain the product code of the product to be traced; the user traceability management client starts the quality inspection program to perform quality inspection on the product to be traced and obtain the quality inspection data of the product to be traced; the product code and quality inspection data of the product to be traced are sent to the MES batch management server.

[0103] Step S2: The MES batch management server retrieves the electronic product history of each product based on the product code of the product to be traced; the electronic product history includes: product number, batch fingerprint characteristics of the current production batch and its matching AI model; if the retrieval fails, the traceability of the product to be traced fails, and the traceability result is fed back to the user traceability management client.

[0104] Step S3: If the retrieval is successful, the MES batch management server directly uses the retrieved AI model to process the quality inspection data of the product to be traced to obtain the batch fingerprint characteristics of the product to be traced; if the batch fingerprint characteristics of the product to be traced match the retrieved batch fingerprint characteristics, the traceability of the product to be traced is successful; otherwise, the traceability of the product to be traced fails; and the traceability results are fed back to the user traceability management client.

[0105] Preferably, the product electronic history also includes product-related information; the product-related information includes at least one of a factory number and a data machine tool number. In this case, the method further performs the following operations.

[0106] During the execution of step S1, after starting the user traceability management client, while obtaining the product code of the product to be traced, the product-related information of the product to be traced is also obtained; the product code, product-related information and quality inspection data of the product to be traced are sent together to the MES batch management server.

[0107] During the execution of step S4, the MES batch management server retrieves the product electronic history of each product based on the product code of the product to be traced. If the retrieval is successful, it first determines whether the product-related information of the product to be traced corresponds to the product-related information in the retrieved product electronic history. If they correspond, it jumps to the step in which the MES batch management server directly uses the retrieved AI model to process the quality inspection data of the product to be traced; otherwise, the traceability of the product to be traced fails, and the traceability results are fed back to the user traceability management client.

[0108] This method is suitable for situations where the MES batch management server has a large memory. It can effectively ensure that the AI ​​model can quickly process the quality inspection data of the products to be traced and obtain the batch fingerprint characteristics of the products to be traced.

[0109] The specific implementation process of Example 2 and Example 3 of the present invention can be found in the above-mentioned system Example 1, and the present Example 2 and Example 3 will not be described in detail here.

[0110] Since the principles of the present embodiments 2 and 3 are the same as those of the above-mentioned system embodiment 1, the present method embodiments 2 and 3 also have the corresponding technical effects of the above-mentioned method embodiment.

[0111] Those skilled in the art will appreciate that all or part of the process steps of the above-described embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, such as a magnetic disk, an optical disk, a read-only memory, or a random access memory.

[0112] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by any technician familiar with this technical field within the technical scope disclosed by the present invention should be covered by the scope of protection of the present invention.

Claims

1. A product electronic resume intelligent traceability management system, characterized in that: The system includes a user traceability management client, an MES batch management server and a traceability matching module; wherein, User traceability management client to obtain product number and quality inspection data of the product to be traced; The MES batch management server includes a storage module and a retrieval module; wherein, A storage module for storing the electronic product history of the product; the electronic product history includes: product number, batch fingerprint characteristics of the current production batch and its matching AI model; The search module searches for the electronic history of products with the same product number according to the product number of the product to be traced. If the search fails, the traceability of the product to be traced fails, and the traceability result is fed back to the user traceability management client; The traceability matching module, if the retrieval is successful, uses the retrieved AI model to process the quality inspection data of the product to be traced to obtain the batch fingerprint characteristics of the product to be traced; if the batch fingerprint characteristics of the product to be traced match the retrieved batch fingerprint characteristics, the traceability of the product to be traced is successful; otherwise, the traceability of the product to be traced fails; In the MES batch management server, all quality inspection data of the same production batch are used to train the AI ​​model as follows in advance to obtain the batch fingerprint features of the corresponding production batch and its matching AI model: Perform feature extraction on all quality inspection data of the same production batch to obtain feature vectors of corresponding quality inspection data; Use the feature vectors of all quality inspection data of the same production batch as positive sample data to train the AI ​​model to learn the common features in the positive sample data; the common features represent the common attributes of all products produced in the same production batch; After the AI ​​model training is completed, the common features in the positive sample data extracted by the AI ​​model are used as the batch fingerprint features of the corresponding production batch, and the trained AI model is used as the AI ​​model for matching the batch fingerprint features of the corresponding production batch; In the process of pre-training the AI ​​model using all the quality inspection data of the same production batch, the feature vector of the quality inspection data is obtained by performing the following operations: Arrange multiple dimensions involved in the quality inspection standards of products of the same production batch in a fixed manner to form a feature extraction template; For each quality inspection data in the same production batch, feature extraction is performed according to the feature extraction template to obtain the feature vector of the corresponding quality inspection data.

2. The product electronic history intelligent traceability management system according to claim 1 is characterized in that: The product electronic history also includes product related information; the product related information includes at least one of a factory number and a data machine tool number; The user traceability management client is also used to obtain product-related information of the product to be traced; The traceability matching module, if the retrieval is successful, first determines whether the product-related information of the product to be traced corresponds to the product-related information in the retrieved product electronic resume. If they are consistent, the retrieved AI model is used to process the quality inspection data of the product to be traced; otherwise, the traceability of the product to be traced fails.

3. The product electronic history intelligent traceability management system according to claim 1 or 2, characterized in that: In the traceability matching module, the similarity measurement method is used to determine whether the batch fingerprint characteristics of the product to be traced match the retrieved batch fingerprint characteristics.

4. The product electronic history intelligent traceability management system according to claim 1 or 2, characterized in that: The traceability matching module is independently set, or is set in the user traceability management client, or is set in the MES batch management server; If the traceability matching module is set up independently, or is set up in the MES batch management server, the traceability results will also be fed back to the user's traceability management client.

5. A method for intelligent traceability management of product electronic records, characterized in that: The method comprises: Start the user traceability management client, obtain the product code of the product to be traced, and send it to the MES batch management server; The MES batch management server retrieves the product electronic resume of each product according to the product code of the product to be traced; the product electronic resume includes: product number, batch fingerprint characteristics of the current production batch and its matching AI model; if the retrieval is successful, the retrieved product electronic resume with the same product number is sent to the user traceability management client; otherwise, if the retrieval fails, the traceability of the product to be traced fails, and the traceability result is fed back to the user traceability management client; If the search is successful, the user traceability management client starts the quality inspection program to conduct quality inspection on the product to be traced and obtains the quality inspection data of the product to be traced; The user traceability management client uses the received AI model to process the quality inspection data of the product to be traced and obtains the batch fingerprint characteristics of the product to be traced; if the batch fingerprint characteristics of the product to be traced match the received batch fingerprint characteristics, the traceability of the product to be traced is successful; otherwise, the traceability of the product to be traced fails; In the MES batch management server, all quality inspection data of the same production batch are used to train the AI ​​model as follows in advance to obtain the batch fingerprint features of the corresponding production batch and its matching AI model: Perform feature extraction on all quality inspection data of the same production batch to obtain feature vectors of corresponding quality inspection data; Use the feature vectors of all quality inspection data of the same production batch as positive sample data to train the AI ​​model to learn the common features in the positive sample data; the common features represent the common attributes of all products produced in the same production batch; After the AI ​​model training is completed, the common features in the positive sample data extracted by the AI ​​model are used as the batch fingerprint features of the corresponding production batch, and the trained AI model is used as the AI ​​model for matching the batch fingerprint features of the corresponding production batch; In the process of pre-training the AI ​​model using all the quality inspection data of the same production batch, the feature vector of the quality inspection data is obtained by performing the following operations: Arrange multiple dimensions involved in the quality inspection standards of products of the same production batch in a fixed manner to form a feature extraction template; For each quality inspection data in the same production batch, feature extraction is performed according to the feature extraction template to obtain the feature vector of the corresponding quality inspection data.

6. The product electronic history intelligent traceability management method according to claim 5 is characterized in that: The product electronic history also includes product related information; the product related information includes at least one of a factory number and a data machine tool number; The method further comprises: After starting the user traceability management client, the product association information of the product to be traced is also obtained; After receiving the electronic resume of the product with the same product number, the user traceability management client first determines whether the product association information of the product to be traced corresponds to the product association information in the received electronic resume of the product. If they correspond, it jumps to the step of starting the quality inspection procedure of the user traceability management client. Otherwise, the traceability of the product to be traced fails.

7. A method for intelligent traceability management of product electronic records, characterized in that: The method comprises: Start the user traceability management client to obtain the product code of the product to be traced; the user traceability management client starts the quality inspection program to conduct quality inspection on the product to be traced and obtain the quality inspection data of the product to be traced; send the product code and quality inspection data of the product to be traced to the MES batch management server; The MES batch management server retrieves the electronic product history of each product according to the product code of the product to be traced; the electronic product history includes: product number, batch fingerprint characteristics of the current production batch and its matching AI model; if the retrieval fails, the traceability of the product to be traced fails, and the traceability result is fed back to the user traceability management client; If the retrieval is successful, the MES batch management server directly uses the retrieved AI model to process the quality inspection data of the product to be traced and obtains the batch fingerprint characteristics of the product to be traced; if the batch fingerprint characteristics of the product to be traced match the retrieved batch fingerprint characteristics, the traceability of the product to be traced is successful; otherwise, the traceability of the product to be traced fails; and the traceability results are fed back to the user traceability management client; In the MES batch management server, all quality inspection data of the same production batch are used to train the AI ​​model as follows in advance to obtain the batch fingerprint features of the corresponding production batch and its matching AI model: Perform feature extraction on all quality inspection data of the same production batch to obtain feature vectors of corresponding quality inspection data; Use the feature vectors of all quality inspection data of the same production batch as positive sample data to train the AI ​​model to learn the common features in the positive sample data; the common features represent the common attributes of all products produced in the same production batch; After the AI ​​model training is completed, the common features in the positive sample data extracted by the AI ​​model are used as the batch fingerprint features of the corresponding production batch, and the trained AI model is used as the AI ​​model for matching the batch fingerprint features of the corresponding production batch; In the process of pre-training the AI ​​model using all the quality inspection data of the same production batch, the feature vector of the quality inspection data is obtained by performing the following operations: Arrange multiple dimensions involved in the quality inspection standards of products of the same production batch in a fixed manner to form a feature extraction template; Feature extraction is performed on each quality inspection data in the same production batch according to the feature extraction template to obtain the feature vector of the corresponding quality inspection data.

8. A method for intelligent traceability management of product electronic records, characterized in that: The product electronic history also includes product related information; the product related information includes at least one of a factory number and a data machine tool number; The method further comprises: After starting the user traceability management client, the product association information of the product to be traced is also obtained; the product code, product association information and quality inspection data of the product to be traced are sent to the MES batch management server together; The MES batch management server retrieves the product electronic resume of each product according to the product code of the product to be traced. If the retrieval is successful, it first determines whether the product-related information of the product to be traced corresponds to the product-related information in the retrieved product electronic resume. If they correspond, it jumps to the step where the MES batch management server directly uses the retrieved AI model to process the quality inspection data of the product to be traced; otherwise, the traceability of the product to be traced fails, and the traceability result is fed back to the user traceability management client; In the MES batch management server, all quality inspection data of the same production batch are used to train the AI ​​model as follows in advance to obtain the batch fingerprint features of the corresponding production batch and its matching AI model: Perform feature extraction on all quality inspection data of the same production batch to obtain feature vectors of corresponding quality inspection data; Use the feature vectors of all quality inspection data of the same production batch as positive sample data to train the AI ​​model to learn the common features in the positive sample data; the common features represent the common attributes of all products produced in the same production batch; After the AI ​​model training is completed, the common features in the positive sample data extracted by the AI ​​model are used as the batch fingerprint features of the corresponding production batch, and the trained AI model is used as the AI ​​model for matching the batch fingerprint features of the corresponding production batch; In the process of pre-training the AI ​​model using all the quality inspection data of the same production batch, the feature vector of the quality inspection data is obtained by performing the following operations: Arrange multiple dimensions involved in the quality inspection standards of products of the same production batch in a fixed manner to form a feature extraction template; Feature extraction is performed on each quality inspection data in the same production batch according to the feature extraction template to obtain the feature vector of the corresponding quality inspection data.

Images