CN116503080B - Method, system and medium for tracing faking point based on big data and reuse prevention label - Google Patents

Method, system and medium for tracing faking point based on big data and reuse prevention label Download PDF

Info

Publication number
CN116503080B
CN116503080B CN202310760497.6A CN202310760497A CN116503080B CN 116503080 B CN116503080 B CN 116503080B CN 202310760497 A CN202310760497 A CN 202310760497A CN 116503080 B CN116503080 B CN 116503080B
Authority
CN
China
Prior art keywords
identification
point
matrix
data
suspicious
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202310760497.6A
Other languages
Chinese (zh)
Other versions
CN116503080A (en
Inventor
邓洋
张世杰
李征
代华国
冉君
王爱明
王坚
杨阳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Push Information & Automation Chengdu Co ltd
Original Assignee
Push Information & Automation Chengdu Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Push Information & Automation Chengdu Co ltd filed Critical Push Information & Automation Chengdu Co ltd
Priority to CN202310760497.6A priority Critical patent/CN116503080B/en
Publication of CN116503080A publication Critical patent/CN116503080A/en
Application granted granted Critical
Publication of CN116503080B publication Critical patent/CN116503080B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/018—Certifying business or products
    • G06Q30/0185—Product, service or business identity fraud
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/248—Presentation of query results
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K19/00—Record carriers for use with machines and with at least a part designed to carry digital markings
    • G06K19/06—Record carriers for use with machines and with at least a part designed to carry digital markings characterised by the kind of the digital marking, e.g. shape, nature, code
    • G06K19/067—Record carriers with conductive marks, printed circuits or semiconductor circuit elements, e.g. credit or identity cards also with resonating or responding marks without active components
    • G06K19/07—Record carriers with conductive marks, printed circuits or semiconductor circuit elements, e.g. credit or identity cards also with resonating or responding marks without active components with integrated circuit chips
    • G06K19/077—Constructional details, e.g. mounting of circuits in the carrier
    • G06K19/0772—Physical layout of the record carrier
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K19/00—Record carriers for use with machines and with at least a part designed to carry digital markings
    • G06K19/06—Record carriers for use with machines and with at least a part designed to carry digital markings characterised by the kind of the digital marking, e.g. shape, nature, code
    • G06K19/067—Record carriers with conductive marks, printed circuits or semiconductor circuit elements, e.g. credit or identity cards also with resonating or responding marks without active components
    • G06K19/07—Record carriers with conductive marks, printed circuits or semiconductor circuit elements, e.g. credit or identity cards also with resonating or responding marks without active components with integrated circuit chips
    • G06K19/077—Constructional details, e.g. mounting of circuits in the carrier
    • G06K19/0772—Physical layout of the record carrier
    • G06K19/07722—Physical layout of the record carrier the record carrier being multilayered, e.g. laminated sheets
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K19/00—Record carriers for use with machines and with at least a part designed to carry digital markings
    • G06K19/06—Record carriers for use with machines and with at least a part designed to carry digital markings characterised by the kind of the digital marking, e.g. shape, nature, code
    • G06K19/067—Record carriers with conductive marks, printed circuits or semiconductor circuit elements, e.g. credit or identity cards also with resonating or responding marks without active components
    • G06K19/07—Record carriers with conductive marks, printed circuits or semiconductor circuit elements, e.g. credit or identity cards also with resonating or responding marks without active components with integrated circuit chips
    • G06K19/077—Constructional details, e.g. mounting of circuits in the carrier
    • G06K19/07743—External electrical contacts
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K19/00—Record carriers for use with machines and with at least a part designed to carry digital markings
    • G06K19/06—Record carriers for use with machines and with at least a part designed to carry digital markings characterised by the kind of the digital marking, e.g. shape, nature, code
    • G06K19/067—Record carriers with conductive marks, printed circuits or semiconductor circuit elements, e.g. credit or identity cards also with resonating or responding marks without active components
    • G06K19/07—Record carriers with conductive marks, printed circuits or semiconductor circuit elements, e.g. credit or identity cards also with resonating or responding marks without active components with integrated circuit chips
    • G06K19/077—Constructional details, e.g. mounting of circuits in the carrier
    • G06K19/07749—Constructional details, e.g. mounting of circuits in the carrier the record carrier being capable of non-contact communication, e.g. constructional details of the antenna of a non-contact smart card
    • G06K19/07758—Constructional details, e.g. mounting of circuits in the carrier the record carrier being capable of non-contact communication, e.g. constructional details of the antenna of a non-contact smart card arrangements for adhering the record carrier to further objects or living beings, functioning as an identification tag
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Microelectronics & Electronic Packaging (AREA)
  • Computer Hardware Design (AREA)
  • Databases & Information Systems (AREA)
  • Business, Economics & Management (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Finance (AREA)
  • General Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • Computational Linguistics (AREA)
  • Development Economics (AREA)
  • Accounting & Taxation (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Remote Sensing (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a method, a system and a medium for tracing a faking point based on big data and an anti-reuse label; relating to the technical field of tracing fake points; on one hand, the RFID chip is structurally improved based on the existing RFID tag technology, an anti-reuse tag is arranged, and the RFID chip is automatically damaged when being recycled and reused through a physical method; on the other hand, tracing the faking points based on the big data and the reuse prevention labels, creating a big data database of the product, and screening the abnormal behavior of the identification data according to the big data database to obtain important identification data and suspicious identification data; drawing a suspicious relationship network based on the screened important identification data and suspicious identification data; and tracing the product fake-making point according to the suspicious relation network to assist in guiding the tracing confirmation of the product fake-making point.

Description

Method, system and medium for tracing faking point based on big data and reuse prevention label
Technical Field
The invention relates to the technical field of fake-making point tracing, in particular to a fake-making point tracing method, a fake-making point tracing system and a fake-making point tracing medium based on big data and anti-reuse labels.
Background
The product with high added value is a main target of counterfeiters, and the counterfeiters can re-bind the recovered RFID chips and reuse the recovered RFID chips although RFID anti-counterfeiting technology is used for the product at present; wine products are recycled by counterfeiters by utilizing the characteristics of the RFID chip, and in the prior art, the anti-counterfeiting identification of the products is mainly concentrated, only the judgment of single products can be realized, and the identification of counterfeiters cannot be realized. In addition, in the existing anti-counterfeiting recognition process, characteristic attributes such as time sequence characteristics and the like are not considered, the model accuracy is not high, and the model robustness is not strong.
Disclosure of Invention
The technical problems to be solved by the invention are as follows: the prior art mainly focuses on the anti-counterfeiting identification of products, can only realize the judgment of single products, and can not realize the identification and tracking of fake-making points. The invention aims to provide a method, a system and a medium for tracing a faking point based on big data and an anti-reuse label; on one hand, the RFID chip is structurally improved based on the existing RFID tag technology, an anti-reuse tag is arranged, and the RFID chip cannot be recognized or can be recognized to be reused in the process of recycling and reuse through a physical method; on the other hand, the tracing of the fake making point is performed based on the big data and the reuse prevention label, a suspicious relation network is drawn based on the important identification data and the suspicious identification data screened by the big data database, the tracing of the fake making point of the product is performed based on the suspicious relation network, and the tracing confirmation of the fake making point of the product is guided.
The invention is realized by the following technical scheme:
the scheme provides a fake point tracing method based on big data and anti-reuse labels, which comprises the following steps:
step one: creating a big data database of the product, and acquiring identification data of the product; the identification data includes: product data, identification tags, identification terminals, identification sites and identification time;
step two: screening abnormal behaviors of the identification data according to the big data database to obtain important identification data and suspicious identification data;
step three: drawing a suspicious relationship network based on the screened important identification data and suspicious identification data;
step four: and tracing the false point of the product based on the suspicious relation network.
The big data repository comprises:
the production data and the packaging data of the product (acquired by the acquisition equipment of the packaging line and comprising a chip uid, a unique identification of the chip, association relation data such as a laser code, a box code, a bottle box and the like), an identification record, an IP address attribution of the identification terminal (when the identification terminal communicates with a data center, the identification terminal must be realized by an IP address, a big data database can record the instant public network IP of the identification terminal, the attribution of the public network IP address is analyzed by inquiring a national IP database through the IP), the geographic position of the identification terminal (acquired by acquiring GPS information of a mobile phone through a mobile phone app or the IP address analysis of the super inquiry of a store merchant), a historical identification record of the identification terminal (processing analysis is carried out on the inquiry record by using the unique number of the identification terminal to obtain a historical identification record view), the activity track of the identification terminal, the logistics data of the product, an anti-reuse label blacklist database, an identification terminal blacklist database and a fake-making list.
The working principle of the scheme is as follows: the prior art mainly focuses on the anti-counterfeiting identification of products, can only realize the judgment of single products, and can not realize the identification and tracking of fake-making points. The invention aims to provide a method, a system and a medium for tracing a faking point based on big data and an anti-reuse label; on one hand, the RFID chip is structurally improved based on the existing RFID tag technology, an anti-reuse tag is arranged, and the RFID chip cannot be recognized or can be recognized to be reused in the process of recycling and reuse through a physical method; on the other hand, the tracing of the fake making point is performed based on the big data and the reuse prevention label, a suspicious relation network is drawn based on the important identification data and the suspicious identification data screened by the big data database, and the tracing of the fake making point of the product is performed according to the suspicious relation network, so that the tracing confirmation of the fake making point of the product is guided.
The reuse-preventing label comprises a conductive adhesive layer, a chip layer and an insulating layer; the surface of the chip layer is provided with n convex contacts, wherein the surface of part of the contacts is covered with an insulating layer, and the whole surface of the chip layer is covered with the conductive adhesive layer.
In order to avoid recycling the RFID chip, the scheme is provided with the reuse prevention tag, and the RFID chip cannot be identified or is identified to be recycled in the identification process when recycling and reusing the RFID chip by a physical method.
In order to achieve the aim of recycling the RFID chip, the conductive adhesive layer attached to the RFID chip is required to be cleaned by using a solvent and then the antenna is bound again, and by utilizing the characteristic, the surface of part of the contacts is covered with an insulating layer; the insulating layer in the RFID chip is coated with a special coating, so that when the contact binding pins of the RFID chip are cleaned, the insulating layer can be cleaned along with the conductive adhesive, and a contact circuit isolated by the insulating layer is exposed, so that a part which is not communicated is communicated, the connection state of the relevant contact of the RFID chip is changed, and the operation is impossible or the contact zone bit stored in the chip is changed.
The short circuit or contact connection state changes in the rebinding process after the RFID chip is recovered, the condition that the RFID chip is used once or repeatedly is recorded is ensured, and the effects of tracing and anti-counterfeiting are achieved by combining with the subsequent suspicious relation network.
The further optimization scheme is that the second step comprises the following substeps:
s1, judging whether product data are in a product database, if so, entering S2, otherwise, judging that the product data are important identification data;
s2, judging whether the identification data has any abnormal behavior, if so, judging the identification data to be suspicious identification data;
the abnormal behavior includes:
a, identifying that the place is not at the actual sales place of the product; if the goods are in a series, inquiring the products sold in the first province in the second province;
b, identifying products of n different distributors in the same identification terminal within a time period T1, wherein n is greater than an identification threshold;
c, identifying n2 products in a time period T2 by the same identification terminal, wherein the matching rate of the packaged n2 products is lower than a matching threshold;
the same identification terminal identifies n3 products in a time period T3, and the difference of the production dates of the n3 products is larger than a date threshold value; identifying wine queried by a terminal in one end time, wherein the wine relates to a plurality of production dates, and the difference between the production dates is larger;
e, the identification site occurs in a regional blacklist, the identification terminal belongs to a terminal blacklist or the reuse prevention label belongs to a label blacklist library.
The further optimization scheme is that the drawing method of the suspicious relation network comprises the following steps:
t1, respectively taking identification terminals of important identification data and suspicious identification data as center points, and drawing a center point relationship network as a primary relationship network according to the sequence of identification time; the method for drawing the central point relation network comprises the following steps:
screening out an associated identification terminal of the center point as a connection point, and pointing to the center point from the connection point when the identification time of the connection point is earlier than the identification time of the center point; when the identification time of the connection point is later than the identification time of the central point, pointing to the connection point from the central point; the association identification terminal includes: the identification terminal is provided with an identification intersection corresponding to the identification location or the anti-reuse label of the identification terminal; for example, the anti-reuse tag A is recognized by the association recognition terminal A and the center point recognition terminal, and the recognition process is performed by the association recognition terminal B and the center point recognition terminal at the recognition site A;
t2, according to the method for drawing the central point relation network in the step T1, using the connection point of the primary relation network as a central point, and drawing the central point relation network as a secondary relation network according to the sequence of the identification time;
…；
the connection point of the ith-1 level relation network is used as a central point, and the central point relation network is drawn according to the sequence of the identification time and used as the ith level relation network to obtain a suspicious relation network;
and T3, cleaning the suspicious relation network based on the deep neural network model, merging repeated central points and outputting.
In a further optimized scheme, the step T3 comprises the following substeps:
t31, randomly splitting the suspicious relation network into a plurality of block networks: each block network at least comprises 1 important center point, and the important center points are center points where important identification data are located;
creating a combination matrix R for each block network: establishing a combination matrix R, and arranging all center points and connection points in a block network in an array of the combination matrix R; taking the center point with the largest occurrence number in the block network as the middle row of the matrix, and arranging other connection points above and below the middle row according to the connection relation;
the element without the central point or connecting point arrangement position in the array of the combined matrix R is 0, and the filling element with the central point or connecting point arrangement position is u, wherein u is the difference value between the number of lines where the central point or connecting point is located and the number of lines where the important central point is located;
describing the combination matrix R as the sum of the output point matrix L, the abnormal points S and the random noise V to obtain a matrix model:
R=L+S+V；
the output point matrix L is a low-rank matrix, the repeated points S are sparse matrices, and the random noise V is a Gaussian white noise matrix with zero mean value;
extracting an output point matrix L from the combined matrix R based on the matrix model and a least square method;
t32, analyzing the output point matrix L of all the block networks to synthesize an output block network, merging repeated center points of the output block network and outputting the merged center points;
randomly splitting the merging relation network into a plurality of block networks: each block network at least comprises 1 important center point, and the important center points are center points where important identification data are located;
creating a combination matrix R for each block network: establishing a combination matrix R, and arranging all center points and connection points in a block network in an array of the combination matrix R; the element without center point or connection point arrangement position in the array of the combined matrix R is 0, the filling element with center point or connection point arrangement position is u, and u is the difference value between the number of lines where the center point or connection point is located and the number of lines where the important center point is located;
describing the combination matrix R as the sum of the output point matrix L, the abnormal points S and the random noise V to obtain a matrix model: r=l+s+v;
the output point matrix L is a low-rank matrix, the repeated points S are sparse matrices, and the random noise V is a Gaussian white noise matrix with zero mean value;
extracting an output point matrix L from the combined matrix R based on the matrix model and a least square method;
when the relation network is drawn, important identification data and suspicious identification data are grasped as center points, and then the relation network taking the center point equipment as a core is drawn around the center, wherein the relation network is a sub-network; each sub-network may have cross points, and the networks with cross points are combined, and a more comprehensive relational network is drawn by using the cross points as keys.
And T33, analyzing the output point matrix L of all the block networks into output block networks, and merging the output block networks to obtain a suspicious relation network.
According to the directed suspicious relation network diagram, the product flow diagram of the suspicious product can be known, according to the product flow diagram, the roles of the identification terminals can be drawn by combining the geographic positions of the identification terminals in the suspicious relation network, so that the method is not only beneficial to tracing the fake-making point of the product more accurately, but also can trace and trace the fake-making line of the whole product.
A further optimization is that the step T12 comprises the following sub-steps:
t311, extracting an output point matrix L from the matrix model, and minimizing the square sum of errors, and converting the matrix model into:
；
wherein I F For the F norm, the sum of absolute squares of each element of the matrix is represented, i is equal to i * Is the F kernel norm, which is a convex substitute for the rank of the matrix, |x|| | | 1 L representing the matrix S 1 Norms, i 0 Convex substitution of norm lambda 1 And lambda (lambda) 2 For balancing the data fitting error against the rank of the approximation matrix;
t312, separating out the output point matrix L in the matrix model by using Moreau near-end operator f And repetition point S f And matrix L of separated output points f And repetition point S f And carrying out conversion matrix model to obtain an output point matrix L.
The further optimization scheme is that the k+1th iteration expression of the output point matrix L is as follows:
wherein L is f Is the Lipoz constant, L, of the order 2 term in the transformation matrix model k For the kth iterative expression of the output point matrix L, S k The kth iterative expression of the sparse matrix S is represented, SVT represents a singular value threshold operator.
The further optimization scheme is that the fourth step comprises the following sub-steps:
the role of each identification terminal in the suspicious relation network is drawn; the roles include: counterfeiters, sellers, and packaging material recyclers; the roles of the identification terminals are reset according to the change of the follow-up data monitoring conditions;
and determining the specific address of the counterfeiter in the suspicious relationship network as a product counterfeiting point.
The high-quality data cleaning is an important premise of making a correct strategy by utilizing a big data technology, the existing data cleaning method is a general method for coping with common data, the effect is poor in processing massive fake-making line data with fluidity, and the scheme combines the flow direction of identification tags and identification terminals and the flow of a fake-making industrial chain, and forms a set of data cleaning method for the fake-making industrial chain through data range selection, data format arrangement and missing data filling.
The scheme also provides a fake-making point tracing system based on the big data and the reuse-preventing label, which is used for realizing the fake-making point tracing method based on the big data and the reuse-preventing label, and comprises the following steps:
the acquisition module is used for creating a big data database of the product and acquiring identification data of the product; the identification data includes: product data, identification tags, identification terminals, identification sites and identification time;
the screening module is used for screening abnormal behaviors of the identification data according to the big data database to obtain suspicious identification data;
the drawing module is used for drawing the suspicious relationship network based on the selected suspicious identification data;
and the tracing module is used for tracing the false point of the product based on the suspicious relation network.
The present solution also provides a computer readable medium having stored thereon a computer program to be executed by a processor to implement the above method for tracing a point of falsification based on big data and anti-reuse labels.
Compared with the prior art, the invention has the following advantages and beneficial effects:
according to the method, the system and the medium for tracing the faking point based on the big data and the reuse prevention label, on one hand, structural improvement is carried out based on the existing RFID label technology, the reuse prevention label is arranged, and the RFID chip cannot be recognized or can be recognized to be reused in the process of recycling and reuse through a physical method; on the other hand, the tracing of the fake making point is performed based on the big data and the reuse prevention label, a suspicious relation network is drawn based on the important identification data and the suspicious identification data screened by the big data database, and the tracing of the fake making point of the product is performed according to the suspicious relation network, so that the tracing confirmation of the fake making point of the product is guided.
Drawings
In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the drawings that are needed in the examples will be briefly described below, it being understood that the following drawings only illustrate some examples of the present invention and therefore should not be considered as limiting the scope, and that other related drawings may be obtained from these drawings without inventive effort for a person skilled in the art. In the drawings:
FIG. 1 is a schematic flow diagram of a method for tracing a faking point based on big data and anti-reuse labels;
FIG. 2 is a schematic cross-sectional view of a chip structure of a conventional RFID tag;
FIG. 3 is a schematic cross-sectional view of a chip structure of the anti-reuse label of embodiment 1;
FIG. 4 is a schematic diagram of a chip structure of the reuse-preventing tag of embodiment 1;
FIG. 5 is a partial schematic diagram of the output block network of embodiment 1;
FIG. 6 is a partial output schematic diagram of the output block network of embodiment 1;
fig. 7 is a schematic diagram of the trend of the data in the blacklist database of the false wine in 2018 of example 2.
In the drawings, the reference numerals and corresponding part names:
1-conductive adhesive layer, 2-chip layer, 21-contact, 3-insulating layer, 4-antenna layer.
Detailed Description
For the purpose of making apparent the objects, technical solutions and advantages of the present invention, the present invention will be further described in detail with reference to the following examples and the accompanying drawings, wherein the exemplary embodiments of the present invention and the descriptions thereof are for illustrating the present invention only and are not to be construed as limiting the present invention.
Example 1
The embodiment provides a method for tracing a faking point based on big data and anti-reuse labels, as shown in fig. 1, comprising the following steps:
step one: creating a big data database of the product, and acquiring identification data of the product; the identification data includes: product data, identification tags, identification terminals, identification sites and identification time;
as shown in fig. 2, the conventional RFID tag includes a conductive adhesive layer 1, a chip layer 2, and an antenna layer 4; the surface of the chip layer 2 is provided with n protruding contacts 21, the conductive adhesive layer 1 covers the whole surface of the chip layer 2, and the antenna layer 4 is arranged on the surface of the conductive adhesive layer 1;
as shown in fig. 3, the chip structure of the reuse-preventing tag according to the embodiment includes a conductive adhesive layer 1, a chip layer 2 and an insulating layer 3; the surface of the chip layer 2 is provided with n contacts 21 in a protruding mode, wherein the surface of part of the contacts 21 is covered with an insulating layer 3, the whole surface of the chip layer 2 is covered with the conductive adhesive layer 1, and the surface of the conductive adhesive layer 1 is covered with the antenna layer 4.
When the surface of part of the contact 21 is covered with the insulating layer 3, the insulating layer 3 may cover only the top of the contact 21, or as shown in the second chip structure of the reuse-preventing tag of fig. 4, the insulating layer 3 covers the entire protruding portion of the contact 21.
In this embodiment, in order to avoid recycling the RFID chip, an anti-reuse tag is provided, so that the RFID chip cannot be recognized or recognized to be reused in the process of recycling the RFID chip by a physical method. In order to achieve the aim of recycling the RFID chip, the conductive adhesive layer attached to the RFID chip is required to be cleaned by using a solvent and then the antenna is bound again, and by utilizing the characteristic, the surface of part of the contact is covered with an insulating layer in the embodiment; the insulating layer in the RFID chip is coated with a special coating, so that when the contact binding pins of the RFID chip are cleaned, the insulating layer can be cleaned along with the conductive adhesive, and a contact circuit isolated by the insulating layer is exposed, so that a part which is not communicated is communicated, the connection state of the relevant contact of the RFID chip is changed, and the operation is impossible or the contact zone bit stored in the chip is changed.
The short circuit or the contact connection state change is carried out in the rebinding process after the RFID chip is recovered, the condition that the RFID chip is used once or repeatedly is recorded is ensured, and the effects of tracing and anti-counterfeiting are achieved by combining with the subsequent suspicious relation network.
The big data database comprises: production data and packaging data (acquired by acquisition equipment of a packaging line and comprising association relation data such as laser codes, box codes, bottle boxes and the like), identification records, IP address attribution of the identification terminals, geographic positions of the identification terminals, historical identification records of the identification terminals, activity tracks of the identification terminals, logistics data of products, reuse-preventing label blacklist database, identification terminal blacklist database and fake-making points.
Step two: screening abnormal behaviors of the identification data according to the big data database to obtain important identification data and suspicious identification data; the method specifically comprises the following substeps:
s1, judging whether product data are in a product database, if so, entering S2, otherwise, judging that the product data are important identification data;
s2, judging whether the identification data has any abnormal behavior, if so, judging the identification data to be suspicious identification data;
the abnormal behavior includes:
a, identifying that the place is not at the actual sales place of the product; if the goods are in a series, inquiring the products sold in the first province in the second province;
b, identifying products of n different distributors in the same identification terminal within a time period T1, wherein n is greater than an identification threshold;
c, identifying n2 products in a time period T2 by the same identification terminal, wherein the matching rate of the packaged n2 products is lower than a matching threshold;
the same identification terminal identifies n3 products in a time period T3, and the difference of the production dates of the n3 products is larger than a date threshold value; identifying wine queried by a terminal in one end time, wherein the wine relates to a plurality of production dates, and the difference between the production dates is larger;
e, the identification site occurs in a regional blacklist, the identification terminal belongs to a terminal blacklist or the reuse prevention label belongs to a label blacklist library.
Step three: drawing a suspicious relationship network based on the screened important identification data and suspicious identification data;
the drawing method of the concrete suspicious relation network comprises the following steps:
t1, respectively taking identification terminals of important identification data and suspicious identification data as center points, and drawing a center point relationship network as a primary relationship network according to the sequence of identification time; the method for drawing the central point relation network comprises the following steps:
screening out an associated identification terminal of the center point as a connection point, and pointing to the center point from the connection point when the identification time of the connection point is earlier than the identification time of the center point; when the identification time of the connection point is later than the identification time of the central point, pointing to the connection point from the central point; the association identification terminal includes: the identification terminal is provided with an identification intersection corresponding to the identification location or the anti-reuse label of the identification terminal; for example, the anti-reuse tag a is recognized by both the association recognition terminal a and the center point recognition terminal, and the recognition process is performed by both the association recognition terminal B and the center point recognition terminal at the recognition site a.
T2, according to the method for drawing the central point relation network in the step T1, using the connection point of the primary relation network as a central point, and drawing the central point relation network as a secondary relation network according to the sequence of the identification time;
…；
the connection point of the ith-1 level relation network is used as a central point, and the central point relation network is drawn according to the sequence of the identification time and used as the ith level relation network to obtain a suspicious relation network;
and T3, cleaning the suspicious relation network based on the deep neural network model, merging repeated central points and outputting.
Step T3 comprises the sub-steps of:
t31, randomly splitting the suspicious relation network into a plurality of block networks: each block network at least comprises 1 important center point, and the important center points are center points where important identification data are located; taking the center point with the largest occurrence number in the block network as the middle row of the matrix, and arranging other connection points above and below the middle row according to the connection relation;
creating a combination matrix R for each block network: establishing a combination matrix R, and arranging all center points and connection points in a block network in an array of the combination matrix R; the element without the central point or connecting point arrangement position in the array of the combined matrix R is 0, and the filling element with the central point or connecting point arrangement position is u, wherein u is the difference value between the number of lines where the central point or connecting point is located and the number of lines where the important central point is located;
describing the combination matrix R as the sum of the output point matrix L, the abnormal points S and the random noise V to obtain a matrix model:
R=L+S+V；
the output point matrix L is a low-rank matrix, the repeated points S are sparse matrices, and the random noise V is a Gaussian white noise matrix with zero mean value;
extracting an output point matrix L from the combined matrix R based on the matrix model and a least square method;
and T32, analyzing the output point matrix L of all the block networks to synthesize an output block network, merging the repeated center points of the output block network, and outputting.
The structure of the output block network part is shown in fig. 5, the connection points corresponding to the associated identification terminals of the central point A1 are B1, B2, B3, C1, C2 and C3, the connection points B1, B2 and B3 are obtained according to the identification time sequence and all point to the central point A1, the central point A1 points to the connection points C1, C2 and C3 respectively, and a part of the primary relation network is formed; wherein the connection points B3 and C3 have the connection point of the next stage, so the connection points B3 and C3 are taken as central points, the connection point D1 points to B3, and the connection point C3 points to E1;
when the repeated center points are merged, a plurality of repeated center points A1 are found, all the repeated center points are merged into one, and finally a merged relation network is obtained, as shown in fig. 6.
According to the directed suspicious relation network diagram, the product flow diagram of the suspicious product can be known, according to the product flow diagram, the roles of the identification terminals can be drawn by combining the geographic positions of the identification terminals in the suspicious relation network, so that the method is not only beneficial to tracing the fake-making point of the product more accurately, but also can trace and trace the fake-making line of the whole product.
Step T31 comprises the sub-steps of:
t311, extracting an output point matrix L from the matrix model, and minimizing the square sum of errors, and converting the matrix model into:
；
wherein I F For the F norm, the sum of absolute squares of each element of the matrix is represented, i is equal to i * Is the F kernel norm, which is a convex substitute for the rank of the matrix, |x|| | | 1 L representing the matrix S 1 Norms, i 0 Convex substitution of norm lambda 1 And lambda (lambda) 2 For balancing the data fitting error against the rank of the approximation matrix;
t312, separating out the output point matrix L in the matrix model by using Moreau near-end operator f And repetition point S f And matrix L of separated output points f And repetition point S f And carrying out conversion matrix model to obtain an output point matrix L.
The k+1th iteration expression of the output point matrix L is:
wherein L is f Is the Lipoz constant, L, of the order 2 term in the transformation matrix model k For the kth iteration expression of the output point matrix L, SVT represents a singular value threshold operator.
Step four: and tracing the false point of the product based on the suspicious relation network.
Step four comprises the following sub-steps:
the roles of all the identification terminals in the suspicious relationship network are drawn; the roles include: counterfeiters, sellers, and packaging material recyclers; both the counterfeiter and the packaging material recoverer are personnel directly or indirectly connected with the counterfeiter, and can be well reflected in a suspicious relationship network.
And determining the specific address of the counterfeiter in the suspicious relationship network as a product counterfeiting point.
The high-quality data cleaning is an important premise of making a correct strategy by utilizing a big data technology, the existing data cleaning method is a general method for coping with common data, the effect is poor in processing massive fake-making line data with fluidity, and the scheme combines the flow direction of identification tags and identification terminals and the flow of a fake-making industrial chain, and forms a set of data cleaning method for the fake-making industrial chain through data range selection, data format arrangement and missing data filling.
Example 2
The embodiment provides a fake-making point tracing system based on big data and an anti-reuse label, which is used for realizing the fake-making point tracing method based on the big data and the anti-reuse label, and comprises the following steps:
the acquisition module is used for creating a big data database of the product and acquiring identification data of the product; the identification data includes: product data, identification tags, identification terminals, identification sites and identification time;
the screening module is used for screening abnormal behaviors of the identification data according to the big data database to obtain suspicious identification data;
the drawing module is used for drawing the suspicious relationship network based on the selected suspicious identification data;
and the tracing module is used for tracing the false point of the product based on the suspicious relation network.
The fake point tracing system based on big data and the reuse prevention label in the embodiment comprises a fake point tracing platform based on the big data and the reuse prevention label, wherein the platform monitors the identification record of the identification terminal, detects abnormal rows in identification, deeply analyzes the identification record of some abnormalities, draws a comprehensive suspicious relation network, and creates a product label data blacklist database, an identification terminal blacklist database, a product label data management system, a product management system and a product management system,
According to the suspicious relation network and GPS data thereof, accurately positioning to a specific address, and checking the surrounding specific environment in the field; whether it is a faked nest point or not is determined.
According to the overall analysis of suspicious relation network, all identification records of suspicious identification equipment are analyzed, the behavior of the identification equipment is determined to be fake, and the related fake wine product label data is added into a blacklist database; the tag data added to the blacklist repository will not pass online verification by any querying device. If true wine exists in the blacklist, the consumer feeds back to the after-sales department, the after-sales department gives out the final authentication result, and the final authentication result is fed back to the big data platform for further processing by the big data platform. The further processing scheme comprises measures such as single bottle deblocking, batch deblocking, false wine identification strategy adjustment and the like.
And determining the role of the identification equipment according to the suspicious relation network, and adding the identification equipment into a blacklist database if the identification equipment accords with the characteristics of the fake equipment.
The number of the false wine blacklist records of the product label data blacklist database (false wine blacklist database) recorded according to the false point tracing platform based on big data and the reuse prevention label is close to 19 ten thousand false wine data. The newly-increased data trend of the 2018 fake wine blacklist database is shown in fig. 7, the first peak value (2018-06-09) is the number of blacklists added when a certain fake-steamed corn is checked and sealed when a big data platform is started, the subsequent quantity is gradually reduced until the quantity is reduced to 0, the purpose of thoroughly dumping one fake-steamed corn is achieved, and the subsequent several peak values are all data characteristics of other fake-steamed corn detected by the big data platform.
At present, 4 pieces of data are in a blacklist database of identification equipment, and the blacklist of the equipment is in a test operation period.
The fake wine cannot pass through the inquiry through the fake point tracing platform based on big data and reuse prevention labels, so that the fake wine loses fluidity.
The consumer feeds back that the wine cannot pass verification, and the laser code provided by the consumer confirms that the wine is listed in a fake wine blacklist.
Example 3
The present embodiment provides a computer-readable medium having stored thereon a computer program that is executed by a processor to implement the tamper point tracing method based on big data and reuse prevention labels as described in embodiment 1.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.

Claims (7)

1. The method for tracing the faking point based on the big data and the reuse prevention label is characterized by comprising the following steps:
step one: creating a big data database of the product, and acquiring identification data of the product; the identification data includes: product data, identification tags, identification terminals, identification sites and identification time;
step two: screening abnormal behaviors of the identification data according to the big data database to obtain important identification data and suspicious identification data;
step three: drawing a suspicious relationship network based on the screened important identification data and suspicious identification data;
step four: tracing the false point of the product based on the suspicious relation network;
the reuse-preventing label comprises a conductive adhesive layer (1), a chip layer (2) and an insulating layer (3); the surface of the chip layer (2) is provided with n contacts (21) in a protruding mode, wherein the surface of part of the contacts (21) is covered with an insulating layer (3), and the whole surface of the chip layer (2) is covered with the conductive adhesive layer (1);
s1, judging whether product data are in a product database, if so, entering S2, otherwise, judging that the product data are important identification data;
s2, judging whether the identification data has any abnormal behavior, if so, judging the identification data to be suspicious identification data;
the abnormal behavior includes:
a, identifying that the place is not at the actual sales place of the product;
b, identifying products of n different distributors in the same identification terminal within a time period T1, wherein n is greater than an identification threshold;
c, identifying n2 products in a time period T2 by the same identification terminal, wherein the matching rate of the packaged n2 products is lower than a matching threshold;
the same identification terminal identifies n3 products in a time period T3, and the difference of the production dates of the n3 products is larger than a date threshold value;
e, identifying the place to occur in a region blacklist, identifying the terminal to belong to the terminal blacklist or identifying the reuse-preventing label to belong to a label blacklist library;
the drawing method of the suspicious relation network comprises the following steps:
t1, respectively taking identification terminals of important identification data and suspicious identification data as center points, and drawing a center point relationship network as a primary relationship network according to the sequence of identification time; the method for drawing the central point relation network comprises the following steps:
screening out an associated identification terminal of the center point as a connection point, and pointing to the center point from the connection point when the identification time of the connection point is earlier than the identification time of the center point; when the identification time of the connection point is later than the identification time of the central point, pointing to the connection point from the central point; the association identification terminal includes: the identification terminal is provided with an identification intersection corresponding to the identification location or the anti-reuse label of the identification terminal;
t2, according to the method for drawing the central point relation network in the step T1, using the connection point of the primary relation network as a central point, and drawing the central point relation network as a secondary relation network according to the sequence of the identification time;
…；
the connection point of the ith-1 level relation network is used as a central point, and the central point relation network is drawn according to the sequence of the identification time and used as the ith level relation network to obtain a suspicious relation network;
and T3, cleaning the suspicious relation network based on the deep neural network model, merging repeated central points and outputting.
2. The method for tracing a point of origin based on big data and reuse prevention labels according to claim 1, wherein the step T3 comprises the sub-steps of:
t31, randomly splitting the suspicious relation network into a plurality of block networks: each block network at least comprises 1 important center point, and the important center points are center points where important identification data are located;
creating a combination matrix R for each block network: establishing a combination matrix R, and arranging all center points and connection points in a block network in an array of the combination matrix R; the element without the central point or connecting point arrangement position in the array of the combined matrix R is 0, and the filling element with the central point or connecting point arrangement position is u, wherein u is the difference value between the number of lines where the central point or connecting point is located and the number of lines where the important central point is located;
describing the combination matrix R as the sum of the output point matrix L, the abnormal points S and the random noise V to obtain a matrix model:
R=L+S+V；
the output point matrix L is a low-rank matrix, the repeated points S are sparse matrices, and the random noise V is a Gaussian white noise matrix with zero mean value;
extracting an output point matrix L from the combined matrix R based on the matrix model and a least square method;
and T32, analyzing the output point matrix L of all the block networks to synthesize an output block network, merging the repeated center points of the output block network, and outputting.
3. The method for tracing a point of falsification based on big data and reuse prevention labels according to claim 2, wherein the step T31 comprises the following sub-steps:
t311, extracting an output point matrix L from the matrix model, and minimizing the square sum of errors, and converting the matrix model into:
；
wherein I F For the F norm, the sum of absolute squares of each element of the matrix is represented, i is equal to i * Is the F kernel norm, which is a convex substitute for the rank of the matrix, |x|| | | 1 L representing a sparse matrix S 1 Norms, i 0 Convex substitution of norm lambda 1 And lambda (lambda) 2 For use inWeighing the data fitting error and the rank of the approximate matrix;
t312, separating out the output point matrix L in the matrix model by using Moreau near-end operator f And repetition point S f And matrix L of separated output points f And repetition point S f And carrying out conversion matrix model to obtain an output point matrix L.
4. The method for tracing a faking point based on big data and reuse prevention labels according to claim 3, wherein the k+1th iterative expression of the output point matrix L is:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein L is f Is the Lipoz constant, L, of the order 2 term in the transformation matrix model k For the kth iterative expression of the output point matrix L, S k The kth iterative expression of the sparse matrix S is represented, SVT represents a singular value threshold operator.
5. The method for tracing a faking point based on big data and reuse prevention labels according to claim 1, wherein the fourth step comprises the following sub-steps:
the roles of all the identification terminals in the suspicious relationship network are drawn; the roles include: counterfeiters, sellers, and packaging material recyclers;
and determining the specific address of the counterfeiter in the suspicious relationship network as a product counterfeiting point.
6. The system for tracing the faking point based on the big data and the reuse prevention label is characterized by being used for realizing the method for tracing the faking point based on the big data and the reuse prevention label, which is disclosed in any one of claims 1 to 5, and comprises the following steps:
the acquisition module is used for creating a big data database of the product and acquiring identification data of the product; the identification data includes: product data, identification tags, identification terminals, identification sites and identification time;
the screening module is used for screening abnormal behaviors of the identification data according to the big data database to obtain suspicious identification data;
the drawing module is used for drawing the suspicious relationship network based on the selected suspicious identification data;
and the tracing module is used for tracing the false point of the product based on the suspicious relation network.
7. A computer readable medium having a computer program stored thereon, wherein the computer program is executable by a processor to implement a tamper point tracing method based on big data and anti-reuse labels according to any one of claims 1-5.
CN202310760497.6A 2023-06-27 2023-06-27 Method, system and medium for tracing faking point based on big data and reuse prevention label Active CN116503080B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310760497.6A CN116503080B (en) 2023-06-27 2023-06-27 Method, system and medium for tracing faking point based on big data and reuse prevention label

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310760497.6A CN116503080B (en) 2023-06-27 2023-06-27 Method, system and medium for tracing faking point based on big data and reuse prevention label

Publications (2)

Publication Number Publication Date
CN116503080A CN116503080A (en) 2023-07-28
CN116503080B true CN116503080B (en) 2023-09-19

Family

ID=87316996

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310760497.6A Active CN116503080B (en) 2023-06-27 2023-06-27 Method, system and medium for tracing faking point based on big data and reuse prevention label

Country Status (1)

Country Link
CN (1) CN116503080B (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104820856A (en) * 2015-04-23 2015-08-05 汉广瑞丰包装(北京)有限公司 Packaged carton anti-unpacking tracing method based on multilayer structure anti-counterfeit label
CN106022805A (en) * 2016-05-25 2016-10-12 华中科技大学 Anti-fake traceablility system and method based on label reading
CN107451820A (en) * 2016-04-29 2017-12-08 卢念秋 On line, multiple, dynamic anti-fake under line, anti-channel conflict, can traceability system
CN111178480A (en) * 2019-12-23 2020-05-19 四川省宜宾普拉斯包装材料有限公司 RFID (radio frequency identification) tag capable of preventing chip from being reused and method
CN112528279A (en) * 2020-12-15 2021-03-19 华中科技大学 Method and device for establishing intrusion detection model
CN113129029A (en) * 2021-03-31 2021-07-16 杭州甘道智能科技有限公司 Wine anti-counterfeiting traceability system based on block chain and RFID
WO2022083226A1 (en) * 2020-10-21 2022-04-28 中兴通讯股份有限公司 Anomaly identification method and system, storage medium and electronic device
WO2022109752A1 (en) * 2020-11-27 2022-06-02 Gochip Pet Technology Inc. Identification tag, identification tag accessory, and methods and systems for using an identification tag and identification tag accessory

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104820856A (en) * 2015-04-23 2015-08-05 汉广瑞丰包装(北京)有限公司 Packaged carton anti-unpacking tracing method based on multilayer structure anti-counterfeit label
CN107451820A (en) * 2016-04-29 2017-12-08 卢念秋 On line, multiple, dynamic anti-fake under line, anti-channel conflict, can traceability system
CN106022805A (en) * 2016-05-25 2016-10-12 华中科技大学 Anti-fake traceablility system and method based on label reading
CN111178480A (en) * 2019-12-23 2020-05-19 四川省宜宾普拉斯包装材料有限公司 RFID (radio frequency identification) tag capable of preventing chip from being reused and method
WO2022083226A1 (en) * 2020-10-21 2022-04-28 中兴通讯股份有限公司 Anomaly identification method and system, storage medium and electronic device
WO2022109752A1 (en) * 2020-11-27 2022-06-02 Gochip Pet Technology Inc. Identification tag, identification tag accessory, and methods and systems for using an identification tag and identification tag accessory
CN112528279A (en) * 2020-12-15 2021-03-19 华中科技大学 Method and device for establishing intrusion detection model
CN113129029A (en) * 2021-03-31 2021-07-16 杭州甘道智能科技有限公司 Wine anti-counterfeiting traceability system based on block chain and RFID

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
"Application of radio frequency iIdentification (RFID) ownership transfer protocol on tracing of Chinese herbal-trace";Zhang Bo 等;《Editorial Office of Transactions of the Chinese Society of Agricultural Engineering》;第32卷(第2期);309-314 *
可扩展性增强的动态确定包标记溯源方法;鲁宁 等;《计算机学报》;第43卷(第08期);1493-1516 *
可扩展性增强的动态确定包标记溯源方法;鲁宁;张嘉伟;马建峰;丛鑫;史闻博;王尚广;;计算机学报(第08期);1493-1516 *

Also Published As

Publication number Publication date
CN116503080A (en) 2023-07-28

Similar Documents

Publication Publication Date Title
KR101779036B1 (en) Apparatus for detecting fraudulent transactions using machine learning and method thereof
CN111401809A (en) Product quality safety block chain traceability system
CN102708391B (en) A kind of antifalsification label based on fractal graph and anti-counterfeit authentication method
WO2003005149A3 (en) Systems and methods for providing purchase transaction incentives
CN102184506A (en) Digital anti-counterfeiting method based on chaos password encryption
CN104636473A (en) Data processing method and system based on electronic payment behaviors
CN107809762B (en) Security risk control method for card-raising identification by utilizing big data and equipment fingerprints
CN111461747B (en) Production method and system for traceable anti-channeling code of canned product
CN105701673A (en) Watch anti-fake traceablility method and system based on two-dimensional codes
CN110766384A (en) Method for tracking digital currency flow direction in block chain
CN110298676A (en) A kind of two dimensional code production traceability system implementation method
CN115496555B (en) Intelligent cross-border e-commerce website security quality assessment method and system
CN109801082A (en) A kind of disappear the fastly anti-fake method for preventing goods from altering of product, system, server and storage medium
CN116503080B (en) Method, system and medium for tracing faking point based on big data and reuse prevention label
CN101765224A (en) Mutually unique mark implementation method for terminal of Internet of Things
CN101482921A (en) Fingerprint identification method
CN109949059A (en) Case code association anti-fake traceability system, method and computer equipment based on block chain
CN102110257A (en) RFID (radio frequency identification) firework firecracker flow direction management system and management method
CN112308483A (en) Order management system and method applied to seafood industry
CN108021570A (en) A kind of farm produce sale tracking system analysis method
CN115952211A (en) Data processing method and system based on artificial intelligence
CN113052287A (en) One-object one-code commodity anti-counterfeiting and tracing system based on digital watermark two-dimensional code
CN113761407A (en) Agricultural product traceability two-dimensional code and process identification terminal application system
CN113435697A (en) Construction method of intelligent matching system
CN112686676A (en) Industrial Internet identification chain processing method, device and equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant