Product intelligent traceability method and system based on radio frequency tags

Abstract

The present invention relates to the technical field of data processing, and provides a product intelligent traceability method and system based on radio frequency tags, including: obtaining the set node information, production and circulation node information, and node detection information of all products; determining the node detection information sequence, obtaining the product information consistency of the nodes, obtaining the cumulative change consistency of the nodes, and further obtaining the range influence degree of the nodes; obtaining the number of products passing through the associated path, obtaining the association degree of the nodes, obtaining the local information consistency, and further obtaining the necessity of distance adjustment between the nodes, obtaining the distance adjustment value between two nodes, and updating the distance adjustment value according to the distance adjustment value; according to the distance adjustment value between the nodes, obtaining the information credibility of the nodes, and realizing the intelligent traceability of products based on radio frequency tags according to the information credibility of the nodes. The present invention solves the problem that the multi-correspondence relationship between circulation nodes makes the product traceability result unreliable.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to a method and system for intelligent product traceability based on radio frequency tags. Background Art

[0002] Intelligent product traceability based on radio frequency tags means collecting, recording, storing, and querying information on the entire process of product production, circulation, and sales through radio frequency identification technology. During the product traceability process, the product involves the circulation and transportation of multiple links from production and manufacturing to transportation and sales. Different links correspond to different circulation nodes, and there are multiple corresponding relationships between the circulation nodes. At the same time, the product transportation method and route are restricted by the product itself. Therefore, the data of the production and circulation processes corresponding to different products may have great similarities.

[0003] When it is necessary to trace the product to obtain the node where the problem occurs, due to the multiple corresponding relationships between the circulation nodes, the possibilities of different nodes in the entire production, circulation, and transportation process of the product being the node where the problem occurs are different. Therefore, generally, the traceability information corresponding to the product is determined according to the possibility of the node being the node where the problem occurs to achieve intelligent product traceability. However, the multiple corresponding relationships between the circulation nodes often lead to inaccurate evaluation of the possibility of the nodes, making the product traceability result unreliable. Summary of the Invention

[0004] The present invention provides a method and system for intelligent product traceability based on radio frequency tags to solve the problem that the multiple corresponding relationships between the circulation nodes make the product traceability result unreliable. The specific technical solutions adopted are as follows:

[0005] In a first aspect, an embodiment of the present invention provides a method for intelligent product traceability based on radio frequency tags, and the method includes the following steps:

[0006] Obtain the set node information and production and circulation node information of all products, and obtain node detection information according to the set node information;

[0007] Obtain the node position sequence of the product, determine the node detection information sequence, obtain the product information consistency of the node, obtain the cumulative change consistency of the node according to the node detection information sequence and the product information consistency of the node, and obtain the range influence degree of the node according to the cumulative change consistency of the node;

[0008] Define the node to be analyzed and the previous node of the node to be analyzed, determine the association path between the previous node and the node to be analyzed, obtain the number of passing products of the association path, obtain the association degree of the node according to the range influence degree of the node and the number of passing products of the association path, obtain the local information consistency of two different nodes in the same node position sequence, obtain the necessity of distance adjustment between nodes according to the association degree of the node and the local information consistency of different nodes, obtain the distance adjustment value between two nodes according to the necessity of distance adjustment between two nodes in the same node position sequence and the measured distance between nodes, and update the distance adjustment value according to the distance adjustment value;

[0009] Obtain the information credibility of the node according to the distance adjustment value between nodes, and realize the intelligent traceability of products based on radio frequency tags according to the information credibility of the node.

[0010] Furthermore, the specific method for obtaining the cumulative change consistency of the node is as follows:

[0011] Take each node in the node position sequence as the first node respectively, and record the nodes before the first node in the node position sequence as the second node;

[0012] Record the mean value of the product information consistency of all nodes before and including the first node in the node position sequence as the first product information consistency of the first node;

[0013] Record the absolute value of the difference between the product information consistency of the second node and the first product information consistency of the first node as the information consistency difference of the second node;

[0014] Record the mean value of the information consistency differences of all second nodes as the first mean value of the first node;

[0015] Record the power with the natural constant as the base and the opposite number of the first mean value of the first node as the exponent as the cumulative change consistency of the first node.

[0016] Furthermore, the specific method for obtaining the range influence degree of the node according to the cumulative change consistency of the node includes:

[0017] Record the absolute value of the difference between the cumulative change consistency of the second node and the cumulative change consistency of the previous node of the second node as the first difference of the second node;

[0018] Record the absolute value of the difference between the cumulative change consistency of the first node and the cumulative change consistency of the previous node of the first node as the first difference of the first node;

[0019] Record the mean value of the first difference of the first node and the first differences of all second nodes as the range influence degree of the first node.

[0020] Further, the specific method for defining the node to be analyzed and the previous node of the node to be analyzed and determining the association path between the previous node and the node to be analyzed includes:

[0021] Denote the first node as the node to be analyzed and the second node as the previous node of the node to be analyzed;

[0022] Denote the path from the previous node of the node to be analyzed to the node to be analyzed as the association path between the previous node and the node to be analyzed.

[0023] Further, the specific formula for obtaining the association degree of the nodes is:

[0024]

[0025] Wherein, represents the association degree of the th node; represents the range influence degree of the th node; represents, in the node position sequence, the range influence degree of the th node before the th node; represents the linear normalization function; represents the th order of the th node in the node position sequence of the product; represents the th node and the th node, and the number of products passing through the association path between the two nodes;

[0026] Further, the specific method for obtaining the necessity of distance adjustment between the two nodes is:

[0027] Denote the product of the absolute value of the difference between the association degrees of the two nodes and the local information consistency of the two nodes as the first factor of the two nodes;

[0028] Denote the normalized value of the reciprocal of the sum of the first factor of the two nodes and the adjustment parameter as the necessity of distance adjustment between the two nodes.

[0029] Further, the specific method for obtaining the distance adjustment value between the two nodes is:

[0030] Denote the average value of the distances measured between all different nodes in the same node position sequence as the second average value of the node position sequence;

[0031] The ratio of the necessity of adjusting the distance between two nodes in the same node position sequence to the second mean value of the node position sequences where the two nodes are located is denoted as the first ratio;

[0032] The product of the first ratio and the measured distance between the two nodes is denoted as the distance adjustment value between the two nodes.

[0033] Furthermore, the method for updating the distance adjustment value according to the distance adjustment value includes the following specific method:

[0034] When the necessity of adjusting the distance between two nodes in the same node position sequence is greater than or equal to the adjustment necessity threshold, the distance measurement between the two nodes is assigned the distance adjustment value between the two nodes; otherwise, the distance measurement between the two nodes remains unchanged.

[0035] Furthermore, the method for obtaining the information credibility of a node according to the distance adjustment value between nodes and realizing the intelligent traceability of products based on radio frequency tags includes the following specific method:

[0036] Taking the distance adjustment value between nodes as the distance between nodes, clustering all nodes in the same node position sequence to obtain the clustering clusters of the nodes, and taking the mean value of the range influence degrees of all nodes included in the same clustering cluster as the information credibility of all nodes in the clustering cluster;

[0037] During the traceability process of defective products, the node with the highest information credibility is used as the defective node to realize the intelligent traceability of products based on radio frequency tags.

[0038] In a second aspect, an embodiment of the present invention further provides an intelligent product traceability system based on radio frequency tags, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the method described in any one of the above are implemented.

[0039] The beneficial effects of the present invention are:

[0040] Based on the set node information and node detection information extracted from the radio frequency tags of products, the present invention analyzes the characteristics of the node distribution structure, determines the importance of nodes in the entire production and circulation process of products, and then obtains the range influence degree of nodes. From the perspective of the node distribution structure, it measures the possibility of nodes being problem nodes, and analyzes from the perspective of the path distribution characteristics of products during production and transportation, so as to improve the accuracy of determining problem nodes in the product traceability process. Then, when considering that a node has a problem, before the node with the problem, the difference in the node detection information of the products of adjacent nodes is still caused by different arrangements in the production and circulation links of the products. However, after the node with the problem, due to the influence of the node with the problem, the node detection information of the products corresponding to all subsequent nodes will change or be abnormal, resulting in a relatively large range influence degree for multiple nodes in the product traceability process, and it is impossible to accurately locate the exact position of the abnormal node. Therefore, the hierarchical relationship of nodes of different products in the node position sequence is vertically adjusted according to the range influence degree of nodes to obtain the distance adjustment value between nodes. According to the distance adjustment value between nodes, the information credibility of nodes is obtained, and based on the information credibility of nodes, intelligent traceability of products based on radio frequency tags is realized, improving the accuracy of product traceability results and solving the problem that the multiple correspondence relationships between the circulation nodes of products make the product traceability results unreliable. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0042] Figure 1 It is a flowchart of the method for intelligent traceability of products based on radio frequency tags provided by an embodiment of the present invention;

[0043] Figure 2 It is a flowchart for obtaining the range influence degree;

[0044] Figure 3 It is a flowchart for obtaining the correlation degree. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the protection scope of the present invention.

[0046] Please refer toFigure 1 , which shows a flowchart of a product intelligent traceability method based on radio frequency tags provided by an embodiment of the present invention. The method includes the following steps:

[0047] Step S001, obtain the set node information and production and circulation node information of all products, and obtain node detection information.

[0048] Use an RFID scanner to scan the radio frequency tags of each product respectively, and extract the set node information of the products. The set node information of the products includes the node information of all nodes passed through before the products reach their current locations. The node information of each node includes: arrival node timestamp, departure node timestamp, handler information, and node detection information.

[0049] The node detection information includes the storage conditions of the products, storage temperature, product name, serial number, specifications, humidity, vibration, and appearance inspection records.

[0050] According to the layout of product production and circulation, obtain all nodes and the association relationships between the nodes. Record all nodes and the association relationships between the nodes as production and circulation node information.

[0051] So far, obtain the set node information, production and circulation node information, and node detection information of all products.

[0052] Step S002, determine the node detection information sequence, obtain the product information consistency of the nodes, obtain the cumulative change consistency of the nodes, and then obtain the range influence degree of the nodes.

[0053] During the process of product circulation and transportation, the radio frequency tags of each product not only relate to the stages of product production, transportation, sales, etc. at the nodes where information is updated, but also relate to the circulation paths of each stage. Therefore, when tracing products in case of problems at different positions on different transmission chains, it is necessary to extract nodes according to the distribution structure of the multi-product traceability paths at the product circulation and transportation nodes, and combine the traceability of different nodes to achieve accurate and efficient acquisition of product traceability results.

[0054] First, in the process of producing products of the same type, the production process is consistent. After the products are produced and enter the circulation stage, due to the limitations of the transportation requirements for different product characteristics, the node information of different products in the circulation stage will be different. At the same time, due to the limitations of the transportation route planning, different products may also have the same node information. Therefore, when tracing the origin of products, a single node in product production and circulation may correspond to multiple other nodes, resulting in insufficient credibility in judging the circulation status of products at the node during the tracing process. Therefore, to ensure the accuracy of the tracing results, it is necessary to analyze the structural characteristics of the node distribution based on the production and circulation node information, which is convenient for subsequent judgment of information errors in the tracing process.

[0055] According to the set node information of the product, arrange all the nodes passed by the product in the order of arrival time to obtain the node position sequence of the product.

[0056] Take the node detection information of each node in the node position sequence of the product as the data corresponding to the node, and arrange the data corresponding to each node in the node position sequence of the product in the order of the nodes in the node position sequence to obtain the node detection information sequence.

[0057] Use the Doc2Vec model to obtain the vectors of the node detection information sequences of all products passing through the same node, and take the mean value of the cosine similarities between all the vectors of this node as the product information consistency of the node.

[0058] According to the node detection information sequence and the product information consistency of the node, obtain the cumulative change consistency of the node.

[0059]

[0060] In the formula, represents the cumulative change consistency of the th node in the node position sequence; represents that in the node position sequence, the product information consistency of the th node before the th node; represents the mean value of the product information consistency of all nodes before the th node and the th node in the node position sequence of the product; represents the order of the th node in the node position sequence of the product; represents the exponential function with the natural constant as the base.

[0061] When the order of a node in the node position sequence of a product is more forward, and the difference in product information consistency among the node and all the nodes before it is smaller, the possibility of a problem occurring at this node is smaller, and this node is more important in the entire production and circulation process of the product. At this time, the cumulative change consistency of the node is greater.

[0062] According to the positional relationship of the cumulative change consistency of the nodes in the node position sequence, continue to analyze the cumulative change consistency. Specifically, according to the cumulative change consistency of the nodes, obtain the range influence degree of the nodes.

[0063]

[0064] Among them, represents the range influence degree of the th node; represents the cumulative change consistency of the th node in the node position sequence; represents the cumulative change consistency of the th node in the node position sequence; represents the order of the th node in the node position sequence of the product; represents the linear normalization function.

[0065] When the difference between the range influence degrees of adjacent nodes is greater, the difference in node detection information of the products of adjacent nodes is greater. At this time, the range influence degree of the node is greater, and it is more likely to correspond to the node with a problem.

[0066] The range influence degree of the node measures the possibility of the node being a node with a problem from the node distribution structure characteristics of the product production process.

[0067] So far, obtain the range influence degree of the node. The flow chart for obtaining the range influence degree is as Figure 2 shown.

[0068] Step S003, obtain the number of products passing through the associated path, obtain the association degree of the node, obtain the local information consistency of two different nodes in the same node position sequence, obtain the necessity of distance adjustment between nodes, and then obtain the distance adjustment value between two nodes, and update the distance adjustment value according to the distance adjustment value.

[0069] When a problem occurs in a certain node, before the node where the problem occurs, the differences in the node detection information of the products of adjacent nodes are still caused by different arrangements in the production and circulation links of the products. However, after the node where the problem occurs, due to the influence of the node where the problem occurs, the node detection information of the products corresponding to all subsequent nodes will change or become abnormal, resulting in a relatively large range of influence on multiple nodes during the product traceability process, and it is impossible to accurately locate the exact position of the abnormal node. Therefore, the hierarchical relationship of the nodes of different products in the node position sequence is vertically adjusted according to the range of influence of the nodes to improve the accuracy of the product traceability result.

[0070] Take each node in the node position sequence as the node to be analyzed, and denote all the nodes before the node to be analyzed in the node position sequence as the pre-order nodes of the node to be analyzed.

[0071] The greater the difference between the range of influence of the node to be analyzed and the range of influence of the pre-order node of the node to be analyzed, the greater the possible influence of the pre-order node of the node to be analyzed on the node to be analyzed.

[0072] Obtain the path from the pre-order node of the node to be analyzed to the node to be analyzed, and denote the path from the pre-order node of the node to be analyzed to the node to be analyzed as the associated path between the pre-order node and the node to be analyzed.

[0073] According to the node position sequences of all products, obtain the number of products corresponding to the node position sequence containing the associated path between the pre-order node and the node to be analyzed, and denote the obtained number of products as the number of passing products of the associated path.

[0074] The greater the number of passing products of the associated path, the more products pass through this associated path. When problem products appear among these products, the node causing the problem is more likely to be the pre-order node and the node to be analyzed corresponding to the associated path. That is: when determining the problem node based on the problem product, the greater the number of passing products of the associated path, the greater the possibility that the pre-order node and the node to be analyzed corresponding to the associated path are the problem nodes.

[0075] Obtain the association degree of the node according to the range of influence of the node and the number of passing products of the associated path.

[0076]

[0077] Among them, represents the association degree of the th node; represents the range of influence of the th node; represents that in the node position sequence, the th node before the The influence degree of the range of a node; Represents a linear normalization function; Represents the Order of the Represents the Number of products passed by the association path between the th node and the

[0078] Among them, the th node is the node to be analyzed, and the th node is the previous node of the node to be analyzed.

[0079] When the difference in the influence degree of the range between the node to be analyzed and the previous node of the node to be analyzed is smaller, and the number of products passed by the association path between the previous node and the node to be analyzed is larger, the association degree between the nodes is larger. At this time, the possibility that the previous node and the node to be analyzed corresponding to the association path are problem nodes is greater, and the possibility that the node corresponding to the association degree is a problem node is greater.

[0080] The flowchart for obtaining the association degree is as Figure 3 shown.

[0081] In the node position sequence, with the node to be analyzed as the center, a window with a length of the first preset threshold is established, and the node detection information of each node within the window is arranged in the order of the nodes in the node position sequence to obtain the adjacent sequence of the node to be analyzed.

[0082] Use the Doc2Vec model to obtain the vectors of the adjacent sequences of two different nodes in the same node position sequence, and use the cosine similarity between the vectors of the adjacent sequences of these two different nodes as the local information consistency of these two different nodes.

[0083] Based on the association degree of the nodes, combined with the local information consistency of different nodes, analyze the degree of information response of the product at other subsequent nodes when the product information changes at the current node, and adjust the hierarchical relationship between the nodes during the product traceability process according to the degree of information response.

[0084] According to the association degree of the nodes and the local information consistency of different nodes, obtain the necessity of distance adjustment between the nodes.

[0085]

[0086] Among them, Represents the necessity of distance adjustment between node a and node b in the same node position sequence; Represents the association degree of node a; Represents the association degree of node b; Indicates the local consistency of information between node a and node b; Indicates a linear normalization function; Indicates a regulation parameter, whose function is to prevent the denominator from being zero, and the value in this embodiment is 0.01.

[0087] When the local consistency of information between two nodes in the same node position sequence is greater and the difference in the correlation degree between the two nodes is greater, the necessity of adjusting the distance between the two nodes is smaller. During the process of intelligent tracing of the product corresponding to the node position sequence, the evaluation of the distance between the two nodes is more accurate, and the necessity of adjusting the distance between the two nodes is smaller.

[0088] When the necessity of adjusting the distance between two nodes in the same node position sequence is greater than or equal to the adjustment necessity threshold, it is considered that the distance measurement between the two nodes is inaccurate and needs to be adjusted.

[0089] Taking the arrangement order of the nodes in the node position sequence as the abscissa and the range influence degree of the nodes as the ordinate, a two-dimensional coordinate system of the node position sequence is established, and the Euclidean distance between two different nodes in the two-dimensional coordinate system of the node position sequence is recorded as the measurement distance between the nodes.

[0090] According to the necessity of adjusting the distance between two nodes in the same node position sequence and the measurement distance between the nodes, the distance adjustment value between the two nodes is obtained.

[0091]

[0092] Among them, Indicates the distance adjustment value between node a and node b in the same node position sequence; Indicates the measurement distance between node a and node b; Indicates the necessity of adjusting the distance between node a and node b in the same node position sequence; Indicates the mean value of the measurement distances between all different nodes in the node position sequence where node a and node b are located.

[0093] When the distance measurement between two nodes is inaccurate and needs to be adjusted, the distance measurement between the two nodes is assigned the distance adjustment value between the two nodes.

[0094] Thus, the distance adjustment value between the nodes is obtained.

[0095] Step S004, according to the distance adjustment value between the nodes, obtain the information credibility of the nodes, and realize the intelligent tracing of the product based on the radio frequency tag according to the information credibility of the nodes.

[0096] Take the distance adjustment value between nodes as the distance between nodes, and use the hierarchical clustering algorithm to process all nodes in the same node position sequence to obtain the clustering clusters of the nodes.

[0097] Take the average value of the range influence degrees of all nodes included in the same clustering cluster as the information credibility of all nodes within the clustering cluster.

[0098] During the process of intelligent tracing of products, when multiple nodes that may correspond to problem nodes are obtained during the tracing process of problem products, take the node with the highest information credibility as the problem node to achieve efficient and rapid positioning of the problem node.

[0099] Thus, the intelligent tracing of products based on radio frequency tags is realized.

[0100] Based on the same inventive concept as the above method, the embodiment of the present invention also provides an intelligent tracing system for products based on radio frequency tags, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any one of the above methods for the intelligent tracing method of products based on radio frequency tags.

[0101] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. The intelligent traceability method for products based on radio frequency tags, characterized in that, The method includes the following steps: Obtain the set node information and production and circulation node information of all products, and obtain node detection information according to the set node information; Obtain the node position sequence of the product, determine the node detection information sequence, use the Doc2Vec model to obtain the vectors of the node detection information sequences of all products passing through the same node, take the mean of the cosine similarities between all vectors of the node as the product information consistency of the node, and obtain the cumulative change consistency of the node according to the node detection information sequence and the product information consistency of the node. Take each node in the node position sequence as the first node respectively, and denote the nodes before the first node in the node position sequence as the second nodes; Denote the absolute value of the difference between the cumulative change consistency of the second node and the cumulative change consistency of the previous node of the second node as the first difference of the second node; Denote the absolute value of the difference between the cumulative change consistency of the first node and the cumulative change consistency of the previous node of the first node as the first difference of the first node; Denote the mean of the first difference of the first node and the first differences of all second nodes as the range influence degree of the first node; Define the node to be analyzed and the predecessor node of the node to be analyzed, determine the association path between the predecessor node and the node to be analyzed, obtain the number of passing products of the association path, and obtain the association degree of the node according to the range influence degree of the node and the number of passing products of the association path. The calculation formula for the association degree of the node is: , where represents the association degree of the th node; represents the range influence degree of the th node; represents, in the node position sequence, the range influence degree of the th node before the th node; represents the linear normalization function; represents the th order of the th node in the node position sequence of the product; represents the number of passing products of the association path between the th node and the represents the exponential function with the natural constant as the base; Use the Doc2Vec model to obtain the vectors of the adjacent sequences of two different nodes in the same node position sequence, take the cosine similarity between the vectors of the adjacent sequences of these two different nodes as the information local consistency of these two different nodes, and record the product of the absolute value of the difference between the association degrees of the two nodes and the information local consistency of these two nodes as the first factor of these two nodes; Record the normalized value of the reciprocal of the sum of the first factor of these two nodes and the adjustment parameter as the distance adjustment necessity between these two nodes; Take the arrangement order of the nodes in the node position sequence as the abscissa and the range influence degree of the nodes as the ordinate to establish a two-dimensional coordinate system of the node position sequence, record the Euclidean distance between two different nodes in the two-dimensional coordinate system of the node position sequence as the measurement distance between the nodes, and record the mean value of the measurement distances between all different nodes in the same node position sequence as the second mean value of the node position sequence; Record the ratio of the distance adjustment necessity between two nodes in the same node position sequence to the second mean value of the node position sequence where these two nodes are located as the first ratio; Record the product of the first ratio and the measurement distance between the two nodes as the distance adjustment value between the two nodes; Judge whether to adjust the measurement distance according to the distance adjustment necessity; When adjustment is needed, take the distance adjustment value between nodes as the distance between nodes, cluster all nodes in the same node position sequence, obtain the clustering clusters of the nodes, take the mean of the range influence degrees of all nodes included in the same clustering cluster as the information credibility of all nodes in the clustering cluster, and realize the intelligent traceability of products based on radio frequency tags according to the information credibility of the nodes.

2. The method for intelligent product traceability based on radio frequency tags according to claim 1, wherein The specific method for obtaining the cumulative change consistency of the node is as follows: Denote the mean of the product information consistencies of the first node and all nodes before the first node in the node position sequence as the first product information consistency of the first node; Denote the absolute value of the difference between the product information consistency of the second node and the first product information consistency of the first node as the information consistency difference of the second node; Denote the mean of the information consistency differences of all second nodes as the first mean of the first node; Denote the power with the natural constant as the base and the opposite of the first mean of the first node as the exponent as the cumulative change consistency of the first node.

3. The product intelligent traceability method based on radio frequency tags according to claim 1, wherein The specific method for defining the node to be analyzed and the previous node of the node to be analyzed and determining the association path between the previous node and the node to be analyzed includes: Denote the first node as the node to be analyzed, and denote the second node as the previous node of the node to be analyzed; Denote the path from the previous node of the node to be analyzed to the node to be analyzed as the association path between the previous node and the node to be analyzed.

4. The product intelligent traceability method based on radio frequency tags according to claim 1, wherein The specific method for judging whether to adjust the measurement distance according to the necessity of distance adjustment includes: When the necessity of distance adjustment between two nodes in the same node position sequence is greater than or equal to the adjustment necessity threshold, assign the distance measurement between the two nodes as the distance adjustment value between the two nodes; otherwise, the distance measurement between the two nodes remains unchanged.

5. The intelligent product traceability method based on radio frequency tags according to claim 1, wherein The specific method for realizing the intelligent traceability of products based on radio frequency tags according to the information credibility of the nodes includes: During the process of tracing the problematic product, the node with the highest information credibility is used as the problem node to achieve intelligent product traceability based on radio frequency tags.

6. The product intelligent traceability system based on radio frequency tags includes a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1-5.

Images