A traceability system and device based on RFID tablet

Abstract

The present invention relates to the field of traceability technology, and discloses a traceability system and device based on RFID tablet, an information entry module, a data acquisition module, a traceability information marking module, a traceability performance analysis module, a traceability safety management module, a comprehensive analysis module, an early warning module and a human-computer interaction module; by providing a traceability performance analysis module, it is beneficial to analyze the traceability width to obtain a traceability width index; analyze the traceability depth to obtain a traceability depth index; comprehensively analyze the traceability performance from three aspects of traceability width, depth and accuracy, laying a foundation for subsequent analysis of the comprehensive analysis module, and at the same time, through the analysis and judgment of the traceability accuracy, setting a traceability consensus mechanism to improve the security of the traceability system, and at the same time taking corresponding measures to improve and perfect it according to the overall analysis of the traceability performance, so as to meet the requirement of rapid response to market demand.

Description

Technical Field

[0001] The present invention relates to the field of traceability technology, and more specifically to a traceability system and device based on RFID tablet. Background Art

[0002] RFID (Radio-Frequency Identification) technology is an automatic recognition technology that uses radio signals to identify specific targets and read related data without establishing direct mechanical or optical contact. RFID technology has the advantages of fast recognition speed, large data capacity, and strong anti-interference ability. It is widely used in logistics, manufacturing, retail, medical care, food and other fields; RFID tablets can read the information on RFID tags and transmit the data to the backend server.

[0003] The existing traceability system uses RFID technology to collect product traceability information in real time. It has the characteristics of fast recognition speed, large data capacity, and strong anti-interference ability, which ensures the accuracy of the data. Users can query the traceability information of products at any time and understand the production, processing, transportation and other links of products, which improves the transparency of products and provides a strong line of defense for product safety. Through the advantages of real-time monitoring, accurate data, and transparent information, the rights and interests of consumers are protected. The traceability system plays an increasingly important role.

[0004] However, the existing traceability system based on RFID tablets is highly dependent on the stable operation of sensors and computer systems. If it encounters an attack, it will cause traceability information errors, affecting the security of traceability information and data confidentiality. In addition, the traceability efficiency at this stage is uneven, and this traceability efficiency cannot meet the requirements of rapid response to market demand. The existing traceability system cannot conduct an overall analysis of the traceability performance, and thus cannot take corresponding measures to improve and perfect it. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, the present invention provides a traceability system and device based on an RFID tablet to solve the problems existing in the above-mentioned background technology.

[0006] The present invention provides the following technical solutions: a traceability system based on RFID tablet, comprising an information entry module, a data acquisition module, a traceability information marking module, a traceability performance analysis module, a traceability safety management module, a comprehensive analysis module, an early warning module and a human-computer interaction module;

[0007] The information entry module enters product related information into the system via RFID tags;

[0008] The data acquisition module reads the RFID tag of the product based on the RFID tablet to obtain the traceability information of the product;

[0009] The traceability information marking module is used to mark the traceability information; each information category in the traceability information is regarded as a node, and there are n nodes in the traceability information;

[0010] The traceability performance analysis module is used to analyze the traceability performance, and the traceability performance analysis module includes a traceability width analysis unit, a traceability depth analysis unit and a traceability accuracy analysis unit;

[0011] The traceability security management module is used to receive data from the traceability accuracy analysis unit and set a traceability consensus mechanism to perform security management on the traceability system;

[0012] The comprehensive analysis module is used to receive data from the traceability performance analysis module for comprehensive analysis, obtain a comprehensive performance index, and perform performance discrimination, and transmit the discrimination result to the early warning module;

[0013] The warning module is used to receive warning instructions and issue corresponding warnings, and transmit them to the human-computer interaction module for display;

[0014] The human-computer interaction module is used to perform human-computer interaction display on the data.

[0015] Preferably, the traceability width analysis unit is used to analyze the traceability width, obtain the traceability width index and make a judgment; the traceability depth analysis unit is used to analyze the traceability depth, obtain the traceability depth index and make a judgment; the traceability accuracy analysis unit is used to analyze the traceability accuracy.

[0016] Preferably, the formula used by the traceability width analysis unit to analyze the traceability width is: , where S a is the traceability breadth index, P a is the number of product types that have been successfully traced, P z Total quantity of product for traceability;

[0017] If S a Satisfy S a ≥US a , if the judgment result is passed, there is no need to send a warning instruction to the warning module; otherwise, a warning instruction is sent to the warning module; the US a is the width threshold, satisfying US a ≥75%.

[0018] Preferably, the formula used by the traceability depth analysis unit to analyze the traceability depth is: , where S b is the traceability depth index, J is the number of nodes with successful traceability, and n is the total number of nodes;

[0019] If S b Satisfy S b ≥US b , if the judgment result is passed, there is no need to send a warning instruction to the warning module; otherwise, a warning instruction is sent to the warning module; the US b is the depth threshold, satisfying US b ≥75%.

[0020] Preferably, the traceability accuracy analysis unit analyzes the traceability accuracy including the following steps:

[0021] Step S01: construct a deep belief network, extract the data features of n nodes entered by the information entry module, mark them as reference features and store them; the reference features are represented by a set as: , where q = 1, 2, 3, ... n, C q represents the reference feature data set of the qth node, c qu is the u-th reference feature data vector of the q-th node, u=1, 2, 3…m, m is the total number of feature data vectors in the node;

[0022] Step S02: Input the successfully traced node data into the constructed deep belief network, extract the data features and mark them as comparative features, recorded as: , where q = 1, 2, 3, ... n, X q represents the contrast feature data set of the qth node, x qu is the u-th contrast feature data vector of the q-th node, u=1, 2, 3…m, m is the total number of feature data vectors in the node;

[0023] Step S03: Compare the reference features in step S01 with the comparison features in step S02 to analyze the accuracy of the traceability data.

[0024] Preferably, the deep belief network is formed by interconnecting RBMs, wherein the RBMs are composed of a hidden layer and a display layer, the biases of the two layers are denoted by A and B respectively, and the weight value between the two layers is denoted by W ij Indicates that the hidden layer and the display layer of RBM are connected to each other, and the function is expressed as: , where h is the hidden layer, v is the display layer, and h j is the jth hidden layer, v i is the i-th display layer, E(·) is the function of RBM, M is the total number of hidden layers, N is the total number of display layers, θ is the RBM network parameter, B i is the bias of the i-th display layer, A j is the bias of the jth hidden layer, i=1, 2, 3...N, j=1, 2, 3...M;

[0025] Get the joint probability density between the hidden layer and the display layer. The calculation formula is: , where p(v,h) is the joint probability density between the hidden layer and the display layer, and Z is the normalization factor;

[0026] The unit activation function of the hidden layer is expressed as follows: , where L(h j =1|v) is the unit activation function of the hidden layer; is the unit activation function expression of the hidden layer;

[0027] The unit activation function of the display layer is expressed as follows: , where L(v i =1|h) is the unit activation function of the display layer; The unit activation function expression for the display layer;

[0028] The input layer of the deep belief network is composed of the display layer of RBM, the middle layer is composed of the hidden layer of RBM, and the regression layer is used as the output layer.

[0029] Preferably, the step S03 uses the Pearson correlation coefficient to analyze the accuracy of the traceability data, and the calculation formula is expressed as: , where r is the Pearson correlation coefficient between the reference feature and the comparison feature;

[0030] When |r| satisfies |r|<0.4, a safety management instruction is sent to the traceability safety management module;

[0031] When |r| satisfies 0.4≤|r|<0.6, a safety management instruction is also sent to the traceability safety management module;

[0032] When |r| satisfies |r|≥0.6, no safety management instructions are sent to the traceability safety management module, and the data is directly transmitted to the comprehensive analysis module.

[0033] Preferably, the comprehensive analysis module performs comprehensive analysis in a specific manner by calculating a comprehensive performance index, which is expressed as follows: , where δ is the comprehensive performance index, and γ1, γ2, and γ3 are the corresponding proportional factors.

[0034] A traceability device based on an RFID tablet includes a connecting line and a tablet body, wherein the tablet body also includes:

[0035] one or more processors;

[0036] a storage device having one or more programs stored thereon;

[0037] When the one or more programs are executed by the one or more processors, the one or more processors implement a traceability system based on an RFID tablet as described above.

[0038] Technical effects and advantages of the present invention:

[0039] The present invention is provided with a traceability width analysis unit, a traceability depth analysis unit and a traceability precision analysis unit, which is conducive to analyzing the traceability width through the traceability width analysis unit to obtain the traceability width index; analyzing the traceability depth through the traceability depth analysis unit to obtain the traceability depth index; analyzing the traceability precision through the traceability precision analysis unit; and comprehensively analyzing the traceability performance through the three aspects of traceability width, depth and precision, laying the foundation for subsequent analysis of the comprehensive analysis module. At the same time, through the analysis and judgment of the traceability precision, a traceability consensus mechanism is set to improve the security of the traceability system. At the same time, according to the overall analysis of the traceability performance, corresponding measures are taken to improve and perfect it, so as to meet the requirement of rapid response to market demand. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is a structural diagram of the traceability system based on RFID tablet of the present invention.

[0041] Figure 2 It is a schematic diagram of the overall structure of the traceability device based on RFID tablet of the present invention.

[0042] The reference numerals in the drawings are: 1. connecting line; 2. tablet computer body. DETAILED DESCRIPTION

[0043] The technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the present invention. In addition, the forms of the various structures recorded in the following embodiments are merely illustrative. The traceability system and device based on RFID tablets involved in the present invention are not limited to the various structures recorded in the following embodiments. All other implementations obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0044] like Figure 1 As shown, the present invention provides a traceability system based on RFID tablet, including an information entry module, a data acquisition module, a traceability information marking module, a traceability performance analysis module, a traceability safety management module, a comprehensive analysis module, an early warning module and a human-computer interaction module;

[0045] The information entry module enters product-related information into the system through RFID tags; the product-related information includes but is not limited to product type, source, flow direction, raw material procurement, production date, batch number and place of origin;

[0046] The data acquisition module reads the RFID tag of the product based on the RFID tablet to obtain the traceability information of the product; the traceability information includes but is not limited to product type, source, flow direction, raw material procurement, production and processing, warehousing and logistics, terminal sales, production date, batch number and inspection report;

[0047] The traceability information marking module is used to mark the traceability information; each information category in the traceability information is regarded as a node, and there are n nodes in the traceability information; product type, product source, product flow direction, etc. are all information categories. For example, product type, source, flow direction, raw material procurement, production and processing, warehousing and logistics, terminal sales, production date, batch number and inspection report are marked as nodes 1, 2, 3...10 in sequence, and there are multiple data in each node; the value of n is equal to the number of product-related information entered by the information entry module;

[0048] The traceability performance analysis module is used to analyze the traceability performance, and the traceability performance analysis module includes a traceability width analysis unit, a traceability depth analysis unit and a traceability accuracy analysis unit; the traceability width analysis unit is used to analyze the traceability width, obtain the traceability width index and make a judgment; the traceability width is the type and range of products covered; the traceability depth analysis unit is used to analyze the traceability depth, obtain the traceability depth index and make a judgment; the traceability depth is the degree of traceability of the product from raw material procurement to terminal sales; the traceability accuracy analysis unit is used to analyze the traceability accuracy, that is, the accuracy, reliability and real-time performance of the data in the traceability process;

[0049] The traceability security management module is used to receive data from the traceability accuracy analysis unit, perform security management on the traceability system, and set a traceability consensus mechanism to improve the security of the traceability system;

[0050] The comprehensive analysis module is used to receive data from the traceability performance analysis module for comprehensive analysis, obtain a comprehensive performance index, and perform performance discrimination, and transmit the discrimination result to the early warning module;

[0051] The warning module is used to receive warning instructions and issue corresponding warnings, and transmit them to the human-computer interaction module for display;

[0052] The human-computer interaction module is used to perform human-computer interaction display on the data.

[0053] In this embodiment, it should be specifically explained that the formula used by the traceability width analysis unit to analyze the traceability width is: , where S a is the traceability breadth index, P a is the number of product types that have been successfully traced, P zis the total amount of products to be traced; for example, if the traceable product is tea, the total amount of tea to be traced is 5, the number of teas successfully traced to the product type is 3, and the number of teas that cannot be traced to the product type is 2, then the traceability width is 60%; the larger the traceability width index, the wider the width, which means that the traceability system can trace more product types, the wider the application range, and the better the performance;

[0054] If S a Satisfy S a ≥US a , the judgment result is passed, indicating that the traceability width index meets the set requirements, and there is no need to send an early warning instruction to the early warning module; otherwise, it means that the traceability width index does not meet the set requirements, and an early warning instruction is sent to the early warning module at this time, and the traceability width needs to be improved and optimized;

[0055] The US a is the width threshold, satisfying US a ≥75%, US a The specific value of is set by technicians in the field, and this embodiment does not specifically limit this specific value.

[0056] In this embodiment, it should be specifically explained that the formula for analyzing the traceability depth by the traceability depth analysis unit is: , where S b is the traceability depth index, J is the number of nodes with successful traceability, and n is the total number of nodes; for example, if a product is traced, the traceability results include the product type, source, flow, procurement, and production and processing, and the remaining traceability information is not successfully traced, then the numerator of the traceability depth index is 5 and the denominator is n; the larger the traceability depth index, the deeper the depth, indicating that the traceability system can record every link of the product in detail, provide more comprehensive information, and the better the traceability performance;

[0057] If S b Satisfy S b ≥US b , the judgment result is passed, indicating that the traceability depth index meets the set requirements, and there is no need to send an early warning instruction to the early warning module; otherwise, it means that the traceability depth index does not meet the set requirements, and an early warning instruction is sent to the early warning module at this time, and the traceability depth needs to be improved and optimized;

[0058] The US b is the depth threshold, satisfying US b ≥75%, US b The specific value of is set by technicians in the field, and this embodiment does not specifically limit this specific value.

[0059] In this embodiment, it should be specifically explained that the traceability accuracy analysis unit analyzes the traceability accuracy by the following steps:

[0060] Step S01: construct a deep belief network, extract the data features of n nodes entered by the information entry module, mark them as reference features and store them; the deep belief network is a feature extraction model based on probability generation and deep learning in nature, obtained by superposition of Boltzmann machines; the reference features are represented by a set as: , where q = 1, 2, 3, ... n, C q represents the reference feature data set of the qth node, c qu is the u-th reference feature data vector of the q-th node, u=1, 2, 3…m, m is the total number of feature data vectors in the node;

[0061] Step S02: Input the successfully traced node data into the constructed deep belief network, extract the data features and mark them as comparative features, recorded as: , where q = 1, 2, 3, ... n, X q represents the contrast feature data set of the qth node, x qu is the u-th contrast feature data vector of the q-th node, u=1, 2, 3…m, m is the total number of feature data vectors in the node;

[0062] Step S03: Compare the reference features in step S01 with the comparison features in step S02 to analyze the accuracy of the traceability data.

[0063] In this embodiment, it should be specifically explained that the deep belief network is formed by interconnecting RBMs, which are Boltzmann machines; the RBM consists of a hidden layer and a display layer, whose biases are A and B respectively, and the weight value between the two layers is denoted by W ij Indicates that the hidden layer and the display layer of RBM are connected to each other, but the neurons in the layer are not connected; for a fixed structure RBM, the function is expressed as: , where h is the hidden layer, v is the display layer, and h j is the jth hidden layer, v i is the i-th display layer, E(·) is the function of RBM, M is the total number of hidden layers, N is the total number of display layers, θ is the RBM network parameter, B i is the bias of the i-th display layer, A j is the bias of the jth hidden layer, i=1, 2, 3...N, j=1, 2, 3...M;

[0064] Get the joint probability density between the hidden layer and the display layer. The calculation formula is: , where p(v,h) is the joint probability density between the hidden layer and the display layer, and Z is the normalization factor;

[0065] Since neurons are independent, the unit activation functions of the hidden layer and the display layer can be derived;

[0066] The unit activation function of the hidden layer is expressed as follows: , where L(h j =1|v) is the unit activation function of the hidden layer; is the unit activation function expression of the hidden layer;

[0067] The unit activation function of the display layer is expressed as follows: , where L(v i =1|h) is the unit activation function of the display layer; The unit activation function expression for the display layer;

[0068] The input layer of the deep belief network is composed of the display layer of RBM, the middle layer is composed of the hidden layer of RBM, and the regression layer is used as the output layer.

[0069] In this embodiment, it should be specifically explained that the deep belief network is optimized by using a simulated annealing algorithm, which includes the following steps:

[0070] Step S11: Initializing deep belief network parameters, wherein the deep belief network parameters include but are not limited to initial learning rate, number of iterations, and number of random samples;

[0071] Step S12: Initialize the simulated annealing algorithm parameter settings, calculate the variance of the deep belief network model, and use the parameter as the fitness function;

[0072] Step S13: performing cooling processing to form a new solution and obtain the number of hidden layer nodes of the deep belief network;

[0073] Step S14: After reaching the termination condition of simulated annealing, the optimal network parameters are obtained and imported into the deep belief network model to obtain the final prediction result.

[0074] In this embodiment, it should be specifically explained that the step S03 uses the Pearson correlation coefficient to analyze the accuracy of the traceability data, and the calculation formula is expressed as: , where r is the Pearson correlation coefficient between the reference feature and the comparison feature; the larger the value of |r|, the higher the accuracy, indicating that the traceability system can provide users with more accurate data, help enterprises and consumers better understand the products, and the better the traceability performance;

[0075] When |r| satisfies |r|<0.4, it means that the traceability accuracy is low at this time, and a safety management instruction is sent to the traceability safety management module;

[0076] When |r| satisfies 0.4≤|r|<0.6, it means that the traceability accuracy is average, and the safety management instruction is also sent to the traceability safety management module;

[0077] When |r| satisfies |r|≥0.6, it means that the traceability accuracy is high. At this time, no safety management instructions are sent to the traceability safety management module, and the data is directly transmitted to the comprehensive analysis module.

[0078] In this embodiment, it should be specifically noted that after the traceability security management module receives the security management instruction, it means that the traceability accuracy is not high, indicating that the data may be tampered with or attacked during the traceability process. Therefore, it is necessary to establish a traceability consensus mechanism to improve the security of the traceability system while improving the traceability accuracy and ensuring data accuracy;

[0079] The traceability consensus mechanism includes the following steps:

[0080] Step S21: Calculate the positioning hash value, the formula is expressed as: , where H is the positioning hash value, V is the traceability execution efficiency, k is the traceability fault tolerance, and R1 is the traceability radius;

[0081] Step S22: Perform hash calculation to obtain the node traceability parameters of the product. The calculation formula is expressed as: , where d q is the traceability parameter of the qth node, and g is the consensus response;

[0082] Step S23: Calculate the traceability efficiency based on the traceability information data. The calculation formula is expressed as: , where D is the traceability efficiency, T is the legitimacy verification parameter, and λ is the submitting node response;

[0083] By establishing a traceability consensus mechanism, traceability information data can be processed in real time, and traceability information can be forced to be sorted, which improves the anti-interference ability of information traceability, ensures traceability reliability, and improves traceability accuracy.

[0084] In this embodiment, it should be specifically explained that the specific way in which the comprehensive analysis module performs comprehensive analysis is to calculate a comprehensive performance index, which is expressed as: , where δ is a comprehensive performance index, γ1, γ2, and γ3 are corresponding proportional factors, and the specific values ​​of γ1, γ2, and γ3 can be set by those skilled in the art according to product characteristics, and this embodiment does not specifically limit these specific values;

[0085] The specific method of the comprehensive analysis module to perform performance judgment is:

[0086] If δ satisfies δ≥UI, the judgment result is passed, indicating that the comprehensive performance index meets the set requirements, and there is no need to send an early warning instruction to the early warning module; otherwise, it means that the comprehensive performance index does not meet the set requirements. At this time, an early warning instruction is sent to the early warning module, and performance optimization needs to be carried out in time to ensure the normal operation of the traceability system;

[0087] The UI is a discrimination threshold, which satisfies UI≥80%. The specific value of the UI is set by technicians in the field, and this embodiment does not specifically limit this specific value.

[0088] In the present embodiment, it should be specifically explained that the information entry module enters product related information, the data acquisition module obtains the traceability information of the product and transmits it to the traceability information marking module, the traceability information marking module marks the traceability information and transmits it to the traceability performance analysis module, the traceability width analysis unit in the traceability performance analysis module calculates and determines the traceability width index, transmits the traceability width index to the comprehensive analysis module, and sends an early warning instruction to the early warning module according to the determination result, the traceability depth analysis unit in the traceability performance analysis module calculates and determines the traceability depth index, and transmits the traceability depth index to the comprehensive analysis module, The comprehensive analysis module sends an early warning instruction to the early warning module according to the discrimination result. The traceability accuracy analysis unit in the traceability performance analysis module analyzes the traceability accuracy and transmits the data to the traceability safety management module and the comprehensive analysis module. The traceability safety management module receives the data of the traceability accuracy analysis unit to set the traceability consensus mechanism. The comprehensive analysis module receives the data of the traceability performance analysis module to calculate the comprehensive performance index and transmits it to the human-computer interaction module for display. At the same time, it performs performance discrimination and sends an early warning instruction to the early warning module based on the discrimination result. The early warning module receives the early warning instruction for early warning and transmits it to the human-computer interaction module for display.

[0089] like Figure 2 As shown, the present invention provides a traceability device based on RFID tablet, including a connecting line 1 and a tablet body 2, the tablet body 2 also includes one or more processors and a storage device: one or more programs are stored thereon; when the one or more programs are executed by the one or more processors, the one or more processors implement the traceability system based on RFID tablet; one end of the connecting line 1 is fixedly connected to an interface, and the other end is fixedly connected to the tablet body 2.

[0090] In the present embodiment, it needs to be specifically explained that the difference between the present embodiment and the prior art mainly lies in that the present embodiment is equipped with a traceability width analysis unit, a traceability depth analysis unit and a traceability precision analysis unit, which is conducive to analyzing the traceability width through the traceability width analysis unit to obtain the traceability width index; analyzing the traceability depth through the traceability depth analysis unit to obtain the traceability depth index; analyzing the traceability precision through the traceability precision analysis unit; and comprehensively analyzing the traceability performance through the three aspects of traceability width, depth and precision, laying the foundation for the subsequent analysis of the comprehensive analysis module. At the same time, through the analysis and judgment of the traceability precision, a traceability consensus mechanism is set to improve the security of the traceability system. At the same time, corresponding measures are taken to improve and perfect it based on the overall analysis of the traceability performance to meet the requirements of rapid response to market demand.

[0091] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0092] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A traceability system based on RFID tablet, characterized by: It includes information entry module, data collection module, traceability information marking module, traceability performance analysis module, traceability safety management module, comprehensive analysis module, early warning module and human-computer interaction module; The information entry module enters product related information into the system via RFID tags; The data acquisition module reads the RFID tag of the product based on the RFID tablet to obtain the traceability information of the product; The traceability information marking module is used to mark the traceability information; each information category in the traceability information is regarded as a node, and there are n nodes in the traceability information; The traceability performance analysis module is used to analyze the traceability performance, and the traceability performance analysis module includes a traceability width analysis unit, a traceability depth analysis unit and a traceability accuracy analysis unit; The traceability security management module is used to receive data from the traceability accuracy analysis unit and set a traceability consensus mechanism to perform security management on the traceability system; The comprehensive analysis module is used to receive the data from the traceability performance analysis module for comprehensive analysis, obtain the comprehensive performance index δ, and perform performance discrimination, and transmit the discrimination result to the early warning module; The warning module is used to receive warning instructions and issue corresponding warnings, and transmit them to the human-computer interaction module for display; The human-computer interaction module is used to perform human-computer interaction display on the data; The traceability width analysis unit is used to analyze the traceability width, obtain the traceability width index and make a judgment; the traceability depth analysis unit is used to analyze the traceability depth, obtain the traceability depth index and make a judgment; the traceability accuracy analysis unit is used to analyze the traceability accuracy; The formula for analyzing the traceability width by the traceability width analysis unit is: , where S a is the traceability breadth index, P a is the number of product types that have been successfully traced, P z Total quantity of product for traceability; If S a Satisfy S a ≥US a , if the judgment result is passed, there is no need to send a warning instruction to the warning module; otherwise, a warning instruction is sent to the warning module; the US a is the width threshold, satisfying US a ≥75%; The formula for analyzing the traceability depth by the traceability depth analysis unit is: , where S b is the traceability depth index, J is the number of nodes with successful traceability, and n is the total number of nodes; If S b Satisfy S b ≥US b , if the judgment result is passed, there is no need to send a warning instruction to the warning module; otherwise, a warning instruction is sent to the warning module; the US b is the depth threshold, satisfying US b ≥75%; The traceability accuracy analysis unit analyzes the traceability accuracy including the following steps: Step S01: construct a deep belief network, extract the data features of n nodes entered by the information entry module, mark them as reference features and store them; the reference features are represented by a set as: , where q = 1, 2, 3, ... n, C q represents the reference feature data set of the qth node, c qu is the u-th reference feature data vector of the q-th node, u=1, 2, 3…m, m is the total number of feature data vectors in the node; Step S02: Input the successfully traced node data into the constructed deep belief network, extract the data features and mark them as comparative features, recorded as: , where q = 1, 2, 3, ... n, X q represents the contrast feature data set of the qth node, x qu is the u-th contrast feature data vector of the q-th node, u=1, 2, 3…m, m is the total number of feature data vectors in the node; Step S03: Compare the reference feature in step S01 with the comparison feature in step S02 to analyze the accuracy of the traceability data; The step S03 uses the Pearson correlation coefficient to analyze the accuracy of the traceability data, and the calculation formula is expressed as: , where r is the Pearson correlation coefficient between the reference feature and the comparison feature; When |r| satisfies |r|<0.4, a safety management instruction is sent to the traceability safety management module; When |r| satisfies 0.4≤|r|<0.6, a safety management instruction is also sent to the traceability safety management module; When |r| satisfies |r|≥0.6, no safety management instruction is sent to the traceability safety management module, and the data is directly transmitted to the comprehensive analysis module; The specific method of the comprehensive analysis module to perform performance judgment is: If δ satisfies δ≥UI, the judgment result is passed, indicating that the comprehensive performance index meets the set requirements, and there is no need to send a warning instruction to the warning module; otherwise, it means that the comprehensive performance index does not meet the set requirements, and a warning instruction is sent to the warning module, and the UI is the judgment threshold.

2. The RFID tablet-based traceability system according to claim 1, characterized in that: The specific method of the comprehensive analysis module for comprehensive analysis is: calculating the comprehensive performance index, which is expressed as: , where δ is the comprehensive performance index, and γ1, γ2, and γ3 are the corresponding proportional factors.

3. A traceability device based on RFID tablet, characterized in that: It comprises a connecting line (1) and a tablet machine body (2), and the tablet machine body (2) further comprises: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement a traceability system based on an RFID tablet as described in any one of claims 1-2 above.

Images