CN108876213B - Block chain-based product management method, device, medium and electronic equipment - Google Patents

Abstract

The embodiment of the invention provides a product management method, a device, a medium and electronic equipment based on a block chain, wherein the product management method based on the block chain comprises the following steps: storing a plurality of product-supply-chain information over a blockchain network; determining attribute information of various types of products based on a plurality of product supply chain information stored in the blockchain network; and if detecting that new product supply chain information is input into the block chain network, determining whether the new product supply chain information is abnormal or not according to the attribute information of each type of product and the new product supply chain information. The technical scheme of the embodiment of the invention avoids the problems of information omission, recording error, illegal data tampering and the like of the product supply chain information caused by manual recording of the product supply chain information, can effectively improve the analysis efficiency of the product supply chain information, saves the labor cost, and promotes the effective popularization of the block chain technology in the product supply chain information management scheme.

Description

Blockchain-based product management method, device, medium and electronic equipment

technical field

The present invention relates to the technical field of blockchain, in particular, to a product management method, device, medium and electronic device based on blockchain.

Background technique

At present, the management of product supply chain information is mainly carried out through manual recording and analysis or centralized system entry and analysis. Manual recording and analysis is not only inefficient, but also takes up a lot of labor costs. Although the centralized system entry and analysis improves efficiency, the traceability and security of supply chain information are lacking, so information omission, recording errors, illegal data tampering, and inability to accurately identify supply chain sources are inevitable. And other issues.

It should be noted that the information disclosed in the above Background section is only for enhancing understanding of the background of the invention, and therefore may contain information that does not form the prior art known to a person of ordinary skill in the art.

SUMMARY OF THE INVENTION

The purpose of the embodiments of the present invention is to provide a blockchain-based product management method, device, medium and electronic device, thereby at least to a certain extent overcoming the difficulty of product supply chain information management, and the easy occurrence of information omission, recording error, data Illegal tampering, etc.

Other features and advantages of the present invention will become apparent from the following detailed description, or be learned in part by practice of the present invention.

According to a first aspect of the embodiments of the present invention, a blockchain-based product management method is provided, including: storing a plurality of product supply chain information through a blockchain network; Product supply chain information to determine the attribute information of various products; if it is detected that new product supply chain information has been entered in the blockchain network, the attribute information of the various products and the new product supply chain information, and determine whether the new product supply chain information is abnormal.

In some embodiments of the present invention, based on the foregoing solution, and based on a plurality of product supply chain information stored in the blockchain network, determining the attribute information of various products includes: based on the information stored in the blockchain network. A plurality of product supply chain information, the attribute features of each product supply chain information are extracted; the machine learning model is trained according to the attribute features of the respective product supply chain information to determine the attribute information of the various products.

In some embodiments of the present invention, based on the foregoing solution, training the machine learning model according to the attribute features of the respective product supply chain information includes: weighting the attribute features of the respective product supply chain information to obtain The training samples corresponding to the attribute features of each product supply chain information; the machine learning model is trained through the training samples.

In some embodiments of the present invention, based on the foregoing solution, the machine learning model includes a clustering model, and the attribute information of the various types of products includes cluster centers of the various types of products.

In some embodiments of the present invention, based on the foregoing solution, according to the attribute information of the various types of products and the new product supply chain information, determining whether the new product supply chain information is abnormal includes: extracting the attribute features of the new product supply chain information; input the attribute features of the new product supply chain information into the trained clustering model to determine the target product type corresponding to the new product supply chain information, and the target distance between the attribute feature of the new product supply chain information and the cluster center of the target product type; according to the target product type and the target distance, determine whether the new product supply chain information is There is an exception.

In some embodiments of the present invention, based on the foregoing solution, according to the target product type and the target distance, determining whether the new product supply chain information is abnormal, including: if the new product supply chain information contains If the identified product type is the same as the target product type, and the target distance is less than or equal to the distance threshold, it is determined that there is no abnormality in the new product supply chain information.

In some embodiments of the present invention, based on the foregoing solution, the blockchain-based product management method further includes: if it is determined that there is no abnormality in the new product supply chain information, passing the new product supply chain The chain information adjusts the determined attribute information of the various types of products.

According to a second aspect of the embodiments of the present invention, a blockchain-based product management device is provided, including: a storage unit for storing a plurality of product supply chain information through a blockchain network; a determination unit for The multiple product supply chain information stored in the blockchain network is used to determine the attribute information of various products; the processing unit is used to detect new product supply chain information entered in the blockchain network, The attribute information of the various products and the new product supply chain information are used to determine whether the new product supply chain information is abnormal.

In some embodiments of the present invention, based on the foregoing solution, the determining unit includes: a feature extraction unit, configured to extract attributes of each product supply chain information based on a plurality of product supply chain information stored in the blockchain network feature; a training unit, configured to train the machine learning model according to the attribute features of the supply chain information of each product, so as to determine the attribute information of the various types of products.

In some embodiments of the present invention, based on the foregoing solution, the training unit is configured to: perform weighting processing on the attribute features of the respective product supply chain information, so as to obtain training corresponding to the attribute features of the respective product supply chain information sample; train the machine learning model through the training sample.

In some embodiments of the present invention, based on the foregoing solution, the machine learning model includes a clustering model, and the attribute information of the various types of products includes cluster centers of the various types of products.

In some embodiments of the present invention, based on the foregoing solution, the processing unit is configured to: extract the attribute features of the new product supply chain information; input the attribute features of the new product supply chain information into the trained In the clustering model, the target product type corresponding to the new product supply chain information is determined, and the target distance between the attribute feature of the new product supply chain information and the cluster center of the target product type ; According to the target product type and the target distance, determine whether the new product supply chain information is abnormal.

In some embodiments of the present invention, based on the foregoing solution, the processing unit is configured to: if the product type identified by the new product supply chain information is the same as the target product type, and the target distance is less than or equal to If the distance threshold is set, it is determined that there is no abnormality in the new product supply chain information.

In some embodiments of the present invention, based on the foregoing solution, the blockchain-based product management device further includes: an adjustment unit configured to, when it is determined that the new product supply chain information is not abnormal, The new product supply chain information is used to adjust the determined attribute information of the various types of products.

According to a third aspect of the embodiments of the present invention, there is provided a computer-readable medium on which a computer program is stored, and when the program is executed by a processor, implements the blockchain-based method described in the first aspect of the above embodiments product management approach.

According to a fourth aspect of the embodiments of the present invention, there is provided an electronic device, comprising: one or more processors; a storage device for storing one or more programs, when the one or more programs are stored by the one When executed by the one or more processors, the one or more processors are caused to implement the blockchain-based product management method described in the first aspect of the above embodiment.

The technical solutions provided by the embodiments of the present invention may include the following beneficial effects:

In the technical solutions provided by some embodiments of the present invention, by storing a plurality of product supply chain information in the blockchain network, it is possible to ensure that the product supply chain information is not tampered with through the blockchain network, and the product supply can be realized. The traceability of chain information avoids problems such as information omission, recording errors, and illegal data tampering in product supply chain information caused by manual recording or centralized system management of product supply chain information. Based on multiple product supply chain information stored in the blockchain network, the attribute information of various products is determined, and whether new product supply chain information exists according to the attribute information of various products and new product supply chain information. Anomaly, which enables the analysis of new product supply chain information based on the reliable data stored in the blockchain network, effectively improves the analysis efficiency of product supply chain information, saves labor costs, and promotes blockchain technology in product supply. Effective promotion of chain information management solutions.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention.

Description of drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description serve to explain the principles of the invention. Obviously, the drawings in the following description are only some embodiments of the present invention, and for those of ordinary skill in the art, other drawings can also be obtained from these drawings without creative effort. In the attached image:

Fig. 1 schematically shows a flow chart of a blockchain-based product management method according to a first embodiment of the present invention;

2 schematically shows a flowchart of determining attribute information of various products based on multiple product supply chain information stored in a blockchain network according to an embodiment of the present invention;

FIG. 3 schematically shows a flowchart of determining whether new product supply chain information is abnormal according to an embodiment of the present invention;

FIG. 4 schematically shows a flow chart of a blockchain-based product management method according to a second embodiment of the present invention;

5 schematically shows a block diagram of a system for implementing product supply chain information management in a blockchain network according to an embodiment of the present invention;

FIG. 6 schematically shows a block diagram of a blockchain-based product management apparatus according to an embodiment of the present invention;

FIG. 7 shows a schematic structural diagram of a computer system suitable for implementing an electronic device according to an embodiment of the present invention.

Detailed ways

Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments, however, can be embodied in various forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art.

Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided in order to give a thorough understanding of embodiments of the present invention. However, those skilled in the art will appreciate that the technical solutions of the present invention may be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be employed. In other instances, well-known methods, devices, implementations, or operations have not been shown or described in detail to avoid obscuring aspects of the present invention.

The block diagrams shown in the figures are merely functional entities and do not necessarily necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices entity.

The flowcharts shown in the figures are only exemplary illustrations and do not necessarily include all contents and operations/steps, nor do they have to be performed in the order described. For example, some operations/steps can be decomposed, and some operations/steps can be combined or partially combined, so the actual execution order may be changed according to the actual situation.

Fig. 1 schematically shows a flow chart of a blockchain-based product management method according to the first embodiment of the present invention. The execution subject of the product management method may be a server or a terminal device.

As shown in FIG. 1, the blockchain-based product management method according to the first embodiment of the present invention includes the following steps S110, S120 and S130, which will be described in detail below:

In step S110, multiple product supply chain information is stored through the blockchain network.

In one embodiment of the present invention, the product supply chain information may include: product supply source, product supply price, product supplier's credit rating, product supply time, product supply duration, product supply scale, and supplied product quality (if possible Expressed by the return rate), customer feedback on the product, etc.

In one embodiment of the present invention, the product supply chain information may be stored in the blockchain network as transaction information in the blockchain network.

In step S120, attribute information of various types of products is determined based on a plurality of product supply chain information stored in the blockchain network.

In an embodiment of the present invention, the attribute information of various types of products can reflect the characteristics of various types of products, that is, the attribute information of various types of products can be used to identify various types of products. As shown in FIG. 2 , the process of determining attribute information of various products based on multiple product supply chain information stored in a blockchain network according to an embodiment of the present invention may specifically include:

Step S210, based on a plurality of product supply chain information stored in the blockchain network, extract attribute features of each product supply chain information.

In an embodiment of the present invention, the attribute feature of the product supply chain information may be a specific value of the product supply chain information, such as the supply source of the product, the supply price of the product, the credit rating of the product supplier, the supply time of the product, the product supply The specific value of information such as supply time, product supply scale, and supplied product quality.

In step S220, the machine learning model is trained according to the attribute features of the supply chain information of each product, so as to determine the attribute information of the various types of products.

In an embodiment of the present invention, the dimensions of attribute features of different product supply chain information may be the same or different. For example, the attribute features of type a product supply chain information may be {supply source, supply price, supplier credit rating, Supply time, supply time, quality of supply components}; the attribute characteristics of the supply chain information of class b products can be {supply source, supply price, supplier credit rating, supply component quality, market price changes, customer feedback issues} and so on.

In an embodiment of the present invention, since the proportion of each attribute feature of the product supply chain information may be different, before training the machine learning model according to the attribute feature of each product supply chain information, each product supply chain information The attribute features are weighted, and then the training samples corresponding to the attribute features of each product supply chain information are obtained, and then the machine learning model is trained through the training samples.

In an embodiment of the present invention, the machine learning model may be a clustering model, such as a K-Nearest Neighbor (KNN) clustering algorithm, or a K-means clustering algorithm or the like. The process of training the clustering model through the training samples is the process of clustering the training samples through the corresponding clustering algorithm, and the training is stopped after the clustering algorithm converges (that is, after the cluster center is determined). Among them, for the clustering model, the attribute information of various products may be the clustering centers of various products.

In other embodiments of the present invention, the machine learning model may also be other machine learning models, such as a convolutional neural network model (Convolutional Neural Network, CNN), a recurrent neural network model (Recurrent Neural Network, RNN) and other neural network models. Among them, for the neural network model, the attribute information of various products may be feature mapping information learned by the neural network model.

Continuing to refer to FIG. 1, in step S130, if it is detected that new product supply chain information has been entered in the blockchain network, then according to the attribute information of the various products and the new product supply chain information , to determine whether the new product supply chain information is abnormal.

In an embodiment of the present invention, if the attribute information of various products is determined according to the clustering model, as shown in FIG. 3 , in step S130, according to the attribute information of various products and the new product supply chain information, a new product is determined. The process of checking whether there is any abnormality in the product supply chain information, which may include the following steps:

Step S310, extracting attribute features of the new product supply chain information.

In an embodiment of the present invention, the attribute characteristics of the new product supply chain information are consistent with the attribute characteristics of the product supply chain information stored in the blockchain network, such as the supply source of the product, the supply price of the product, The specific numerical value of the credit rating of the product supplier, the product supply time, the product supply time, the product supply scale, and the supplied product quality.

Step S320, input the attribute features of the new product supply chain information into the trained clustering model to determine the target product type corresponding to the new product supply chain information, and the new product supply chain information The target distance between the attribute feature of the chain information and the cluster center of the target product type.

In an embodiment of the present invention, since the machine learning model has been trained according to the attribute characteristics of the product supply chain information stored in the blockchain network, the attribute characteristics of the new product supply chain information are input to the trained After the clustering model of , the target product type corresponding to the new product supply chain information, and the target distance between the attribute feature of the new product supply chain information and the cluster center of the target product type can be obtained.

In an embodiment of the present invention, before the attribute features of the new product supply chain information are input into the trained clustering model, weighting processing may be performed on the attribute features of the new product supply chain information, and then the weighting processing may be performed on the attribute features of the new product supply chain information The resulting attribute features are input into the trained clustering model.

Step S330, according to the target product type and the target distance, determine whether the new product supply chain information is abnormal.

In an embodiment of the present invention, the process of determining whether the new product supply chain information is abnormal according to the target product type and the target distance in step S330 may specifically include: if the product type identified by the new product supply chain information If the type of the target product is the same, and the target distance is less than or equal to the distance threshold, it is determined that there is no abnormality in the new product supply chain information.

In one embodiment of the present invention, since the product type is identified in the product supply chain information, if the product type identified by the new product supply chain information is the same as the target product type identified through the clustering model, and the new When the target distance between the attribute feature of the product supply chain information and the cluster center of the target product type is less than or equal to the distance threshold, it can be determined that there is no abnormality in the new product supply chain information. On the contrary, it can be determined that the new product supply chain information is abnormal, for example, it can be determined that the new product supply chain has irregularities or fraudulent behaviors.

The technical solution of the embodiment shown in FIG. 3 can determine whether there is an abnormality in the new product supply chain information through the processing of the clustering model. In other embodiments of the present invention, other machine learning models can also be used for processing, for example, a neural network model can be used for processing. Specifically, the attribute features of the new product supply chain information can be input into the trained neural network model. In order to determine the product type corresponding to the new product supply chain information through the trained neural network model, and then determine the new product type based on the product type determined by the trained neural network model and the product type identified in the new product supply chain information. Whether the product supply chain information of the new product is abnormal, for example, if the product type determined based on the trained neural network model is the same as the product type identified in the new product supply chain information, it is determined that the new product supply chain information is not abnormal; otherwise, Then it can be determined that the new product supply chain information is abnormal.

Based on the foregoing solution, in an embodiment of the present invention, if it is determined that there is no abnormality in the new product supply chain information, the determined attribute information of various products can be adjusted through the new product supply chain information, thereby optimizing the system. parameters to improve the accuracy of identifying whether there is anomaly in new product supply chain information.

In an embodiment of the present invention, when adjusting the attribute information of the determined products of various types through the new product supply chain information, the machine learning model may be retrained specifically through the attribute features of the new product supply chain information. , to optimize the parameters of the machine learning model, thereby improving the output accuracy of the machine learning model.

The technical solutions of the foregoing embodiments of the present invention avoid problems such as information omission, recording errors, and illegal tampering of data in product supply chain information caused by manual recording or centralized system management of product supply chain information. And it can realize the analysis of new product supply chain information based on the reliable data stored in the blockchain network, which effectively improves the analysis efficiency of product supply chain information, saves labor costs, and promotes the application of blockchain technology in product supply chain information. Effective promotion of management programs.

The implementation details of the embodiments of the present invention are described in detail below with reference to FIGS. 4 to 5 :

As shown in Figure 4, the blockchain-based product management method according to the second embodiment of the present invention includes the following steps:

Step S410, a blockchain node and a blockchain network are constructed.

In one embodiment of the present invention, after a blockchain node is selected, a blockchain network can be constructed based on the selected blockchain node. For example, the grass-roots business organization of an insurance company can be the smallest node, and a blockchain network can be constructed based on the participation of one or more insurance groups/company.

In step S420, the product supply chain information is stored based on the data structure and storage method in the embodiment of the present invention.

In one embodiment of the present invention, the product supply chain information may be stored in the blockchain network in the form of product supply chain transaction information, and the input of the product supply chain transaction information may be the supply time information record and the supplier's public key The output of the transaction information of the product supply chain can be the storage link of the supply time material, the public key (account address) of the relevant information visitor, and so on. Optionally, product supply chain transaction information can be stored through the data structure shown in Table 1 to ensure high efficiency of information storage and information processing:

Table 1

In the data structure shown in Table 1, because supply-related information materials and other materials usually contain some images, documents and other information with a relatively large amount of data, in order to improve the storage efficiency and solve the problem of excessive block information, in this paper In the embodiment of the invention, relatively large materials such as images can be stored in the block in the form of a link, and the value of this link is the hash value obtained by encrypting the material through a hash function, such as SHA1, etc. The way the hash function gets the pointer link ensures that the content cannot be tampered with. The actual material can be stored either in the local storage device of the blockchain node or in the form of cloud storage. At the same time, in order to ensure the high reliability of material storage, the material can be stored in the form of redundant coding, such as RS coding (that is, Reed-Solomon codes, which is a forward error correction channel coding, which is used to correct oversampling by correction). The polynomial generated by the data is valid) or LDPC (Low Density Parity CheckCode, Low Density Parity Check Code) encoding method to perform redundant encoding processing on the material.

In one embodiment of the present invention, each product supply chain information can be uploaded and stored in the blockchain network in the format of Table 1 above. The product supply chain information may include: product supply source, product supply price, product supplier's credit rating, product supply time, product supply time, product supply scale, product quality supplied (for example, it can be expressed by the return rate), Customer feedback on the product, etc.

For example, the attribute feature of a product supply chain information can be expressed as {supply source=value1; supply price=2000; supplier credit rating=v1; supply time=2016.01; supply duration=1 year; return rate=8%}, then The input of the supply chain transaction information can be the supply time information record and the supplier's public key and signature, and the output of the supply chain transaction information can be the supply time material, that is, the storage link of the attribute value, the nature of the transaction event (compliance/violation/ fraud, etc.), the public key (account address) of the visitor of the relevant information of the transaction event, etc., in which a supply chain transaction information can constitute a block.

In step S430, product supply chain management is performed according to the information stored in the blockchain network.

In one embodiment of the present invention, multi-dimensional discrete data can be constructed based on product supply chain information, such as product supply source, product supply price, product supplier's credit rating, product supply time, product supply duration, product supply scale, supply The product quality (return rate), market price changes, customer feedback problems, emergencies (embargoes, trade wars, natural disasters), etc. determine multi-dimensional discrete data, and then based on the supply chain information of each product stored in the blockchain network The corresponding multi-dimensional discrete data is used to construct training samples, and the K-nearest neighbor clustering model is trained through the training samples, so as to find and identify possible illegal and fraudulent behaviors based on the trained model.

For example, the blockchain network contains n types of products. According to the characteristics of the products, the attribute characteristics of the supply chain information of different types of products can be the same or different. For example, the attribute characteristics of the supply chain information of type a products can be {supply source, Supply price, supplier credit rating, supply time, supply duration, supply component quality}; the attribute characteristics of the supply chain information of type b products can be {supply source, supply price, supplier credit rating, supply component quality, market price change , Customer Feedback Questions}. According to the supply chain information of n types of products stored in the blockchain network (excluding violation information), according to the proportion of each attribute feature, the attribute features of the product supply chain information are weighted as input, and the KNN model is trained, where , each type of product corresponds to a cluster center. With the increase of product supply chain information stored in the blockchain network, parameter adjustment and model optimization of the KNN model are continuously performed to ensure the correct classification of the KNN model and each product. The distance between the attribute feature of the supply chain information and the corresponding cluster center point is less than the set threshold T.

When a new product supply chain transaction information is generated in the blockchain network (assuming that the product category is identified as a product in the product supply chain transaction information), the attribute characteristics of the product supply chain transaction information are extracted, for example, it can be {supply source=value1; supply price=2000; supplier credit rating=v1; supply time=2017.01; supply duration=1 year; return rate=10%}, and then input the extracted attribute features into the trained KNN model , the output result of the trained KNN model is "this product is a product of class a, and the distance from the cluster center of class a product is less than T", and then it can be judged that there is no violation of the supply chain information of this product. Conversely, if the output result of the trained KNN model indicates that the product is a class b product or does not belong to any class of known products, it can be basically determined that the product supply chain information has violations or fraudulent behavior, and then the product supply event can be determined. Carry out accountability.

Step S440, update and optimize system parameters based on system performance.

In one embodiment of the present invention, the timeliness and effectiveness of product supply chain management, as well as the identification accuracy of abnormal product supply chain information can be continuously adjusted and optimized to continuously adjust and optimize system parameters, in order to effectively Realize the tracking management of product supply chain, thus effectively promoting the effective promotion of blockchain technology in product supply chain information management.

The device embodiments of the present invention are described below with reference to the accompanying drawings.

FIG. 5 schematically shows a block diagram of a system for implementing product supply chain information management in a blockchain network according to an embodiment of the present invention.

Referring to FIG. 5, a system for implementing product supply chain information management in a blockchain network according to an embodiment of the present invention includes: a blockchain network construction subsystem 510, a data format definition subsystem 520, and product supply chain information Storage subsystem 530 , supply chain management subsystem 540 , and system performance evaluation subsystem 550 .

Among them, the blockchain network construction subsystem 510 is responsible for the construction, update and maintenance mechanism of the blockchain nodes and the construction, update and maintenance of the blockchain network. For example, the grass-roots business organization of an insurance company can be the smallest node, and a blockchain network can be constructed based on the participation of one or more insurance groups/company.

The data format definition subsystem 520 can store product supply chain transaction information according to the data structure shown in Table 1 above, so as to ensure high efficiency of information storage and information processing. The input of the product supply chain transaction information can be the supply time information record and the supplier's public key and signature, etc.; the output of the product supply chain transaction information can be the storage link of the supply time material, the public key (account) of the relevant information visitor. address), etc.

The product supply chain information storage subsystem 530 is used for storing product supply chain information. Specifically, each product supply chain information can be uploaded to the blockchain network in the format of Table 1 above, so that the product supply chain information storage subsystem 530 can store it. The product supply chain information may include: product supply source, product supply price, product supplier's credit rating, product supply time, product supply time, product supply scale, product quality supplied (for example, it can be expressed by the return rate), Customer feedback on the product, etc.

For example, the attribute feature of a product supply chain information can be expressed as {supply source=value1; supply price=2000; supplier credit rating=v1; supply time=2016.01; supply duration=1 year; return rate=8%}, then The input of the supply chain transaction information can be the supply time information record and the supplier's public key and signature, and the output of the supply chain transaction information can be the supply time material, that is, the storage link of the attribute value, the nature of the transaction event (compliance/violation/ fraud, etc.), the public key (account address) of the visitor of the relevant information of the transaction event, etc., in which a supply chain transaction information can constitute a block.

The supply chain management subsystem 540 is used for product supply chain management according to the information stored in the blockchain network.

In one embodiment of the present invention, multi-dimensional discrete data can be constructed based on product supply chain information, such as product supply source, product supply price, product supplier's credit rating, product supply time, product supply duration, product supply scale, supply The product quality (return rate), market price changes, customer feedback problems, emergencies (embargoes, trade wars, natural disasters), etc. determine multi-dimensional discrete data, and then based on the supply chain information of each product stored in the blockchain network The corresponding multi-dimensional discrete data is used to construct training samples, and the K-nearest neighbor clustering model is trained through the training samples, so as to find and identify possible illegal and fraudulent behaviors based on the trained model.

For example, the blockchain network contains n types of products. According to the characteristics of the products, the attribute characteristics of the supply chain information of different types of products can be the same or different. For example, the attribute characteristics of the supply chain information of type a products can be {supply source, Supply price, supplier credit rating, supply time, supply duration, supply component quality}; the attribute characteristics of the supply chain information of type b products can be {supply source, supply price, supplier credit rating, supply component quality, market price change , Customer Feedback Questions}. According to the supply chain information of n types of products stored in the blockchain network (excluding violation information), according to the proportion of each attribute feature, the attribute features of the product supply chain information are weighted as input, and the KNN model is trained, where , each type of product corresponds to a cluster center. With the increase of product supply chain information stored in the blockchain network, parameter adjustment and model optimization of the KNN model are continuously performed to ensure the correct classification of the KNN model and each product. The distance between the attribute feature of the supply chain information and the corresponding cluster center point is less than the set threshold T.

When a new product supply chain transaction information is generated in the blockchain network (assuming that the product category is identified as a product in the product supply chain transaction information), the attribute characteristics of the product supply chain transaction information are extracted, for example, it can be {supply source=value1; supply price=2000; supplier credit rating=v1; supply time=2017.01; supply duration=1 year; return rate=10%}, and then input the extracted attribute features into the trained KNN model , the output result of the trained KNN model is "this product is a product of class a, and the distance from the cluster center of class a product is less than T", and then it can be judged that there is no violation of the supply chain information of this product. Conversely, if the output result of the trained KNN model indicates that the product is a class b product or does not belong to any class of known products, it can be basically determined that the product supply chain information has violations or fraudulent behavior, and then the product supply event can be determined. Carry out accountability.

The system performance evaluation subsystem 550 can evaluate the timeliness and effectiveness of product supply chain management, as well as the identification accuracy of abnormal product supply chain information to continuously adjust and optimize system parameters, in order to effectively realize product supply through the blockchain network Chain tracking management, thus effectively promoting the effective promotion of blockchain technology in product supply chain information management.

FIG. 6 schematically shows a block diagram of a blockchain-based product management apparatus according to an embodiment of the present invention.

Referring to FIG. 6 , a blockchain-based product management apparatus 600 according to an embodiment of the present invention includes: a storage unit 602 , a determination unit 604 and a processing unit 606 .

The storage unit 602 is configured to store multiple product supply chain information through the blockchain network; the determining unit 604 is configured to determine attribute information of various products based on the multiple product supply chain information stored in the blockchain network; The processing unit 606 is configured to determine the new product supply chain according to the attribute information of the various types of products and the new product supply chain information when it is detected that new product supply chain information is entered in the blockchain network Whether the information is abnormal.

In an embodiment of the present invention, the determining unit 604 includes: a feature extraction unit, configured to extract attribute features of each product supply chain information based on a plurality of product supply chain information stored in the blockchain network; a training unit, The method is used to train the machine learning model according to the attribute characteristics of the supply chain information of each product, so as to determine the attribute information of the various products.

In an embodiment of the present invention, the training unit is configured to: perform weighting processing on attribute features of each product supply chain information to obtain training samples corresponding to the attribute features of each product supply chain information; The training samples are used to train the machine learning model.

In an embodiment of the present invention, the machine learning model includes a clustering model, and the attribute information of the various types of products includes cluster centers of the various types of products.

In an embodiment of the present invention, the processing unit 606 is configured to: extract the attribute features of the new product supply chain information; input the attribute features of the new product supply chain information into the trained clustering model , to determine the target product type corresponding to the new product supply chain information, and the target distance between the attribute feature of the new product supply chain information and the cluster center of the target product type; according to the target The product type and the target distance determine whether the new product supply chain information is abnormal.

In one embodiment of the present invention, the processing unit 606 is configured to: if the product type identified by the new product supply chain information is the same as the target product type, and the target distance is less than or equal to a distance threshold, then determine There is no abnormality in the new product supply chain information.

In an embodiment of the present invention, the blockchain-based product management device 600 further includes: an adjustment unit, configured to pass the new product when it is determined that there is no abnormality in the supply chain information of the new product The supply chain information adjusts the determined attribute information of the various types of products.

Since each functional module of the blockchain-based product management device of the exemplary embodiment of the present invention corresponds to the steps of the above-mentioned exemplary embodiment of the blockchain-based product management method, details not disclosed in the device embodiment of the present invention are not disclosed. , please refer to the above-mentioned embodiments of the blockchain-based product management method of the present invention.

Referring next to FIG. 7 , it shows a schematic structural diagram of a computer system 700 suitable for implementing an electronic device according to an embodiment of the present invention. The computer system 700 of the electronic device shown in FIG. 7 is only an example, and should not impose any limitation on the function and scope of use of the embodiments of the present invention.

As shown in FIG. 7, a computer system 700 includes a central processing unit (CPU) 701 which can be loaded into a random access memory (RAM) 703 according to a program stored in a read only memory (ROM) 702 or a program from a storage section 708 Instead, various appropriate actions and processes are performed. In the RAM 703, various programs and data necessary for system operation are also stored. The CPU 701 , the ROM 702 , and the RAM 703 are connected to each other through a bus 704 . An input/output (I/O) interface 705 is also connected to bus 704 .

The following components are connected to the I/O interface 705: an input section 706 including a keyboard, a mouse, etc.; an output section 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc. ; and a communication section 709 including a network interface card such as a LAN card, a modem, and the like. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I/O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is mounted on the drive 710 as needed so that a computer program read therefrom is installed into the storage section 708 as needed.

In particular, the processes described above with reference to the flowcharts may be implemented as computer software programs according to embodiments of the present invention. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the method illustrated in the flowchart. In such an embodiment, the computer program may be downloaded and installed from the network via the communication portion 709 and/or installed from the removable medium 711 . When the computer program is executed by the central processing unit (CPU) 701, the above-described functions defined in the system of the present application are executed.

It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or a combination of any of the above. More specific examples of computer readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable Programmable read only memory (EPROM or flash memory), fiber optics, portable compact disk read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing. In the present invention, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present invention, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code therein. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device . Program code embodied on a computer readable medium may be transmitted using any suitable medium including, but not limited to, wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more logical functions for implementing the specified functions executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It is also noted that each block of the block diagrams or flowchart illustrations, and combinations of blocks in the block diagrams or flowchart illustrations, can be implemented in special purpose hardware-based systems that perform the specified functions or operations, or can be implemented using A combination of dedicated hardware and computer instructions is implemented.

The units involved in the embodiments of the present invention may be implemented in a software manner, or may be implemented in a hardware manner, and the described units may also be provided in a processor. Among them, the names of these units do not constitute a limitation on the unit itself under certain circumstances.

As another aspect, the present application also provides a computer-readable medium. The computer-readable medium may be included in the electronic device described in the above embodiments; it may also exist alone without being assembled into the electronic device. middle. The above computer readable medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device implements the blockchain-based product management method described in the above embodiment.

For example, the electronic device can implement as shown in FIG. 1: step S110, storing multiple product supply chain information through a blockchain network; step S120, based on multiple product supply chains stored in the blockchain network chain information, and determine the attribute information of various products; step S130, if it is detected that new product supply chain information has been entered in the blockchain network, then according to the attribute information of the various products and the new product supply chain information chain information, and determine whether the new product supply chain information is abnormal.

For another example, the electronic device can implement the various steps shown in FIG. 2 to FIG. 4 .

It should be noted that although several modules or units of the apparatus for action performance are mentioned in the above detailed description, this division is not mandatory. Indeed, according to embodiments of the present invention, the features and functions of two or more modules or units described above may be embodied in one module or unit. Conversely, the features and functions of one module or unit described above may be further divided into multiple modules or units to be embodied.

From the description of the above embodiments, those skilled in the art can easily understand that the exemplary embodiments described herein may be implemented by software, or may be implemented by software combined with necessary hardware. Therefore, the technical solutions according to the embodiments of the present invention can be embodied in the form of software products, and the software products can be stored in a non-volatile storage medium (which can be CD-ROM, U disk, mobile hard disk, etc.) or on the network , which includes several instructions to cause a computing device (which may be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiment of the present invention.

Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses or adaptations of the invention which follow the general principles of the invention and which include common knowledge or conventional techniques in the art not disclosed by the invention . The specification and examples are to be regarded as exemplary only, with the true scope and spirit of the invention being indicated by the following claims.

It should be understood that the present invention is not limited to the precise structures described above and illustrated in the accompanying drawings, and that various modifications and changes may be made without departing from its scope. The scope of the present invention is limited only by the appended claims.

Claims (7)

1. A blockchain-based product management method, comprising: Store multiple product supply chain information through the blockchain network; the product supply chain information includes product supply source, product supply price, product supplier's credit rating, product supply time, product supply time, product supply scale, product supply Quality, customer feedback on the product; Determine attribute information of various products based on multiple product supply chain information stored in the blockchain network; Determining attribute information of various products based on multiple product supply chain information stored in the blockchain network includes: extracting each product supply chain information based on multiple product supply chain information stored in the blockchain network The attribute features of each product; the machine learning model is trained according to the attribute features of the supply chain information of each product to determine the attribute information of the various products; the machine learning model includes a clustering model, and the attributes of the various products are The information includes the cluster centers of the various types of products; If it is detected that new product supply chain information has been entered in the blockchain network, the attribute features of the new product supply chain information are extracted; Input the attribute features of the new product supply chain information into the trained clustering model to determine the target product type corresponding to the new product supply chain information, and the new product supply chain information. the target distance between the attribute feature and the cluster center of the target product type; According to the target product type and the target distance, it is determined whether the new product supply chain information is abnormal. 2. The blockchain-based product management method according to claim 1, wherein the machine learning model is trained according to the attribute characteristics of each product supply chain information, comprising: Perform weighting processing on the attribute features of each product supply chain information to obtain training samples corresponding to the attribute features of each product supply chain information; The machine learning model is trained through the training samples. 3. The blockchain-based product management method according to claim 1, wherein, according to the target product type and the target distance, determining whether the new product supply chain information is abnormal, comprising: If the product type identified by the new product supply chain information is the same as the target product type, and the target distance is less than or equal to the distance threshold, it is determined that there is no abnormality in the new product supply chain information. 4. The blockchain-based product management method according to any one of claims 1 to 3, further comprising: If it is determined that there is no abnormality in the new product supply chain information, the determined attribute information of the various types of products is adjusted through the new product supply chain information. 5. A product management device based on blockchain, characterized in that, comprising: The storage unit is used to store multiple product supply chain information through the blockchain network; the product supply chain information includes product supply source, product supply price, product supplier's credit rating, product supply time, product supply time, product supply Scale, quality of products supplied, customer feedback on products; A determination unit, used for extracting attribute features of each product supply chain information based on a plurality of product supply chain information stored in the blockchain network; training the machine learning model according to the attribute features of each product supply chain information, to determine attribute information of various types of products; the machine learning model includes a clustering model, and the attribute information of various types of products includes cluster centers of the various types of products; The processing unit is configured to extract the attribute features of the new product supply chain information when it is detected that the new product supply chain information has been entered in the blockchain network; Input into the trained clustering model to determine the target product type corresponding to the new product supply chain information, as well as the attribute characteristics of the new product supply chain information and the clustering center of the target product type The target distance between the two; according to the target product type and the target distance, determine whether the new product supply chain information is abnormal. 6. A computer-readable medium on which a computer program is stored, characterized in that, when the program is executed by a processor, the blockchain-based product management method according to any one of claims 1 to 4 is implemented . 7. An electronic device, characterized in that, comprising: one or more processors; A storage device for storing one or more programs that, when executed by the one or more processors, cause the one or more processors to implement any one of claims 1 to 4 A described blockchain-based approach to product management.

Images