Product label anti-counterfeiting identification and early warning platform based on multi-source data perception

Abstract

The present application provides a multi-source data-aware commodity label anti-counterfeiting identification and early warning platform, which relates to the field of label anti-counterfeiting identification technology, including: parsing user verification request information, obtaining commodity identity information and user identity information; extracting multi-source historical anti-counterfeiting verification records; determining whether there is a commodity label risk, and obtaining commodity individual risk early warning results; performing consistency verification of user identity information according to the user's standard behavior space; evaluating the degree of anti-counterfeiting identification abnormality, and performing anti-counterfeiting identification early warning based on the identification abnormality coefficient. This application can solve the technical problem in the prior art that it is difficult to effectively identify counterfeit labels that are copied in large quantities through illegal channels due to the lack of comprehensive analysis and correlation comparison of commodity homology verification records, achieve the technical goal of comprehensive analysis and correlation comparison of commodity homology verification records, and achieve the technical effect of effectively identifying counterfeit commodity labels and improving anti-counterfeiting early warning capabilities.

Description

Technical Field

[0001] The present application relates to the field of label anti-counterfeiting identification technology, and in particular to a commodity label anti-counterfeiting identification and early warning platform based on multi-source data perception. Background Art

[0002] Existing product label anti-counterfeiting technology still has certain limitations when dealing with the complexity and scale of counterfeit labels. First, existing technologies mainly rely on single label information, such as the barcode or QR code of the product for anti-counterfeiting verification, but once this information is forged or copied, it is easy for criminals to use it in batches, resulting in counterfeit goods entering the market. In addition, the current anti-counterfeiting system focuses more on the verification of individual products, but lacks a comprehensive analysis and comparison of product homology verification records, and cannot effectively identify counterfeit labels that are copied in large quantities through illegal means. For example, a product label may be repeatedly verified at multiple locations and multiple time periods, but if there is a lack of correlation analysis of homology data, abnormal behavior cannot be detected.

[0003] In summary, the existing technology has a technical problem that due to the lack of comprehensive analysis and correlation comparison of product homology verification records, the anti-counterfeiting system is unable to effectively identify counterfeit labels that are copied in large quantities through illegal means, further affecting the timely early warning of counterfeit goods and the control of counterfeit goods in market circulation. Summary of the invention

[0004] The purpose of this application is to provide a multi-source data-aware product label anti-counterfeiting identification and early warning platform to solve the technical problem in the prior art that, due to the lack of comprehensive analysis and correlation comparison of product homology verification records, the anti-counterfeiting system is unable to effectively identify counterfeit labels that are copied in large quantities through illegal channels, further affecting the timely early warning of counterfeit products and the control of counterfeit products in market circulation.

[0005] In view of the above problems, the present application provides a multi-source data-aware product label anti-counterfeiting identification and early warning platform, including: an information parsing module, which is used to obtain user verification request information from an interactive user end, parse the user verification request information, and obtain product identity information and user identity information; an information extraction module, which is used to transmit the product identity information and the user identity information to a multi-source database, and extract multi-source historical anti-counterfeiting verification records, wherein the multi-source historical anti-counterfeiting verification records include user verification records and product verification records; an anti-counterfeiting analysis module, which is used to analyze anti-counterfeiting identification behavior according to the product verification record, determine whether there is a product label risk, and obtain a product individual risk early warning result; a consistency verification module, which is used to extract and construct a user standard behavior space according to the user verification record, and perform consistency verification of the user identity information according to the user standard behavior space, and output a user individual risk early warning result; an abnormality evaluation module, which is used to combine the product individual risk early warning result and the user individual risk early warning result, evaluate the degree of anti-counterfeiting identification abnormality, obtain an identification abnormality coefficient, and perform anti-counterfeiting identification early warning based on the identification abnormality coefficient.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] Obtain user verification request information through the interactive user terminal, parse the user verification request information, and obtain product identity information and user identity information; transmit the product identity information and the user identity information to a multi-source database, and extract multi-source historical anti-counterfeiting verification records, wherein the multi-source historical anti-counterfeiting verification records include user verification records and product verification records; analyze anti-counterfeiting identification behavior according to the product verification record, determine whether there is a product label risk, and obtain product individual risk warning results; extract and construct a user standard behavior space according to the user verification record, and perform consistency verification of the user identity information according to the user standard behavior space, and output the user individual risk warning result; combine the product individual risk warning result with the user individual risk warning result, evaluate the degree of anti-counterfeiting identification abnormality, obtain the identification abnormality coefficient, and perform anti-counterfeiting identification warning based on the identification abnormality coefficient, so as to achieve the technical goal of comprehensive analysis and correlation comparison of product homologous verification records, and achieve the technical effect of effectively identifying counterfeit product labels and improving anti-counterfeiting warning capabilities.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0010] Figure 1 This is a schematic diagram of the structure of the product label anti-counterfeiting identification and early warning platform based on multi-source data perception in this application;

[0011] Figure 2 This is a flow chart of extracting multi-source historical anti-counterfeiting verification records from the multi-source data-aware product label anti-counterfeiting identification and early warning platform of this application.

[0012] Description of reference numerals:

[0013] Information parsing module 11, information extraction module 12, anti-counterfeiting analysis module 13, consistency verification module 14, anomaly evaluation module 15. DETAILED DESCRIPTION

[0014] This application solves the technical problem in the prior art that the anti-counterfeiting system is difficult to effectively identify counterfeit labels that are copied in large quantities through illegal means due to the lack of comprehensive analysis and correlation comparison of commodity homology verification records, which further affects the timely warning of counterfeit commodities and the control of counterfeit commodities in market circulation by providing a multi-source data-aware commodity label anti-counterfeiting identification and early warning platform. The technical goal of comprehensive analysis and correlation comparison of commodity homology verification records is achieved, and the technical effect of effectively identifying counterfeit commodity labels and improving anti-counterfeiting early warning capabilities is achieved.

[0015] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0016] Please see attached Figure 1 This application provides a multi-source data-aware commodity label anti-counterfeiting identification and early warning platform, which specifically includes:

[0017] The information parsing module 11 is used for the interactive user terminal to obtain the user verification request information, parse the user verification request information, and obtain the commodity identity information and the user identity information.

[0018] Specifically, when the interactive user terminal receives the user verification request information, it parses the request information, that is, analyzes and processes it to determine the key data therein. Then, the parsed information includes product identity information and user identity information. Product identity information is the unique identifier of the product, such as the product number or the data contained in the QR code. For example, the identity information of a product is "product ID12345", which is obtained by scanning the QR code or barcode of the product. User identity information refers to the unique identifier associated with the user, that is, the user's account or identity information, such as the user's email address or mobile phone number. Assume that the user's identity information is "user ID67890". By obtaining the product identity information and user identity information, the user terminal can further match or verify the user and the product, thereby ensuring that only users with legal identities can operate on specific products, such as purchasing or commenting.

[0019] The information extraction module 12 is used to transmit the commodity identity information and the user identity information to a multi-source database, and extract multi-source historical anti-counterfeiting verification records, wherein the multi-source historical anti-counterfeiting verification records include user verification records and commodity verification records.

[0020] Specifically, when the product identity information and user identity information are transmitted to the multi-source database, the relevant historical records are queried and extracted, including user verification records and product verification records. User verification records refer to the verification history related to a specific user, and other product verification behaviors that the user has participated in, which serve as reference data for the user's verification behavior pattern. The product verification record is the verification behavior record in the history of the product label, including information such as verification time, location, and method.

[0021] The anti-counterfeiting analysis module 13 is used to analyze the anti-counterfeiting identification behavior according to the commodity verification record, determine whether there is a commodity label risk, and obtain the commodity individual risk warning result.

[0022] Specifically, the anti-counterfeiting identification behavior is analyzed based on the product verification records. Based on the product's past anti-counterfeiting verification history, such as how many times "product ID12345" has been verified at different locations and times, and whether the verification results are consistent, it is determined whether there is a product label risk, that is, whether the product may be counterfeited, tampered with, or the label is reused. Assuming that the product has abnormally frequent verification requests in a short period of time, or the verification results show that the anti-counterfeiting label has been scanned many times but cannot pass the verification, it is determined that there is a label risk. Next, the individual product risk warning results are generated, that is, an assessment of the potential risks of the product. For example, the product is marked as "high risk" or "low risk", and the relevant personnel are prompted to take appropriate measures based on the risk information, such as further testing or recalling the product.

[0023] The consistency verification module 14 is used to extract and construct a user standard behavior space according to the user verification record, and perform consistency verification of the user identity information according to the user standard behavior space, and output a user individual risk warning result.

[0024] Specifically, based on the user verification records, the user's behavior data is extracted, including verification time, location, device type, etc. By analyzing the user verification records, the user standard behavior space is constructed, which is a collection of users' regular behavior patterns.

[0025] Next, the user's standard behavior space is used to verify the consistency of the user's identity information and check whether the current user's behavior conforms to their previous standard pattern. Assuming that the user selects a completely different time period or uses an uncommon verification method during a verification, the behavior is detected to be inconsistent with the user's standard pattern and the degree of deviation of the user's current behavior is evaluated.

[0026] Finally, based on the results of the consistency verification, the user's individual risk warning results are output. If a large deviation is detected, for example, the user usually verifies on weekdays, but this time verifies multiple times late at night, a "high risk" warning prompt is generated, requiring further investigation or measures, thereby effectively identifying potential abnormal behaviors and providing timely risk warnings.

[0027] The abnormality evaluation module 15 is used to evaluate the degree of anti-counterfeiting identification abnormality by combining the individual risk warning result of the commodity with the individual risk warning result of the user, obtain the identification abnormality coefficient, and perform anti-counterfeiting identification warning based on the identification abnormality coefficient.

[0028] Specifically, combining the individual risk warning results of the product with the individual risk warning results of the user can more comprehensively evaluate the abnormality of anti-counterfeiting identification. If both the product and the user have high risks, the overall abnormality is considered to be high.

[0029] Next, the recognition anomaly coefficient is obtained through comprehensive risk assessment. The recognition anomaly coefficient is used to measure the degree of anomaly in the anti-counterfeiting recognition process, and is obtained by analyzing the multi-dimensional risk data of goods and users. For example, if a certain product has frequent anomalies in past verifications, and the user's verification behavior is inconsistent with historical behavior, a higher anomaly coefficient is calculated, such as 0.85 (the full score is 1, indicating high anomaly).

[0030] Finally, based on the recognition anomaly coefficient, an anti-counterfeiting identification warning is issued. When the anomaly coefficient exceeds the set threshold, such as 0.7, an anti-counterfeiting identification warning is triggered, prompting relevant personnel or users that there may be problems with the product and suggesting further investigation or measures.

[0031] The multi-source data-aware product label anti-counterfeiting identification and early warning platform can achieve the technical goal of comprehensive analysis and correlation comparison of product homology verification records, and achieve the technical effect of effectively identifying counterfeit product labels and improving anti-counterfeiting early warning capabilities.

[0032] For further information, please see the attached Figure 2 , this application also includes:

[0033] The multi-source database is connected using the product identity information and the user identity information as index keys; a record extraction space is defined based on the risk warning requirements of the target scenario, wherein the record extraction space includes a user record extraction space and a product record extraction space; all historical anti-counterfeiting verification records related to the product identity information and the user identity information are called and record extraction is performed until the record extraction space is filled, and the multi-source historical anti-counterfeiting verification records are output.

[0034] Specifically, when product identity information and user identity information are used as index keys, the relevant information in the multi-source database is connected through these two unique identifiers. Among them, product identity information, such as "product ID12345", and user identity information, such as "user ID67890", are used as key parameters for search. Find the corresponding data source in multiple different databases to achieve information integration across data platforms. For example, a multi-source database may store production information, sales records, user reviews, etc. related to the product, and then quickly find the corresponding data based on the product identity information and user identity information.

[0035] Next, according to the risk warning requirements of the target scenario, define a record extraction space. The record extraction space is a virtual container for storing relevant information, including user record extraction space and product record extraction space. The user record extraction space may be used to store information such as the user's purchase history and anti-counterfeiting query history, while the product record extraction space contains the production, transportation and past anti-counterfeiting verification information of the product. For example, the user record extraction space may contain all the product information that "user ID67890" has ever purchased, while the product record extraction space may contain the anti-counterfeiting verification records of "product ID12345" from production to sales.

[0036] Call all historical anti-counterfeiting verification records related to product identity information and user identity information, and extract records until the defined record extraction space is filled. This can be a random extraction or a probabilistic extraction based on the freshness of the record, such as a high probability for a new record and a 0 probability for an old record. Then, traverse the historical records in all multi-source databases, such as the number of times, time points, and verification results of the user's previous anti-counterfeiting verifications, until enough records are obtained to meet the needs of the record extraction space. Assuming that the user has performed 5 anti-counterfeiting verifications in the past, and each verification is associated with a different product, all records are extracted, and finally a complete multi-source historical anti-counterfeiting verification record report is output.

[0037] Connect multiple databases through the identity information of goods and users, then define data storage space according to specific risk warning scenarios, and finally extract anti-counterfeiting verification records related to multiple identity information to ensure that comprehensive verification data is provided for subsequent analysis.

[0038] Furthermore, the present application also includes:

[0039] Parse the user verification request information to obtain the verification capability information of the user end, wherein the verification capability information includes a multi-dimensional verification path; traverse the product verification record based on the verification capability information to perform dimensional matching, and perform lightweight processing on the product verification record according to the dimensional matching result to obtain the target product verification record; take the verification capability information as the dimensional target, obtain the multi-dimensional indicator concentration feature of the target product verification record, and determine whether the product identity information has a product label risk based on the multi-dimensional indicator concentration feature.

[0040] Specifically, when parsing the user verification request information, the data sent by the user is analyzed to obtain the user's verification capability information. Verification capability information refers to the ability of the user's device to verify the product, including verification information of multiple dimensional verification paths, such as verification IP, verification location, verification method, verification language, verification frequency, etc.

[0041] Next, based on the obtained verification capability information, the product verification records are traversed and dimension matching is performed, that is, the verification capability of the user end is compared with the dimensions in the product verification record one by one to find the matching parts. For example, based on the verification IP, verification location, verification method, verification language, verification frequency, etc., it is determined whether there is any product label counterfeiting behavior (product label duplication, reuse, etc.), and the product verification record is matched according to the verification capability of the user device. If the match is successful, the matched verification record is lightweight, that is, only the part related to the user device capability is retained, so as to obtain a more streamlined target product verification record. If there are 10 verification records for a product, it is reduced to 3 records related to verification based on the capabilities of the user device.

[0042] Subsequently, with verification capability information as the dimensional target, the multi-dimensional indicator concentration features of the verification records of the target product are further analyzed. The multi-dimensional indicator concentration features may include information such as the verification method, verification time, and verification location of the product. By analyzing the multi-dimensional indicator concentration features, it is determined whether the product identity information has a product label risk. For example, if the past verification records show that the product has been identified by counterfeit labels many times, or the verification results are abnormal, then it is determined that the product may have a label risk.

[0043] Through the user's verification ability, goods are verified and the potential risks of goods are assessed, thereby improving the accuracy and reliability of anti-counterfeiting.

[0044] Furthermore, the present application also includes:

[0045] Acquire a user behavior pattern feature set based on the user verification record; define multi-level confidence intervals for multiple types of behavior pattern features in the user behavior pattern feature set, and construct a user standard behavior space based on multiple groups of the multi-level confidence intervals.

[0046] Specifically, a user behavior pattern feature set based on user verification records is obtained. A user behavior pattern feature set refers to extracting user behavior patterns by analyzing the user's historical verification records. User behavior patterns may include verification sources (i.e., verification channels, such as web page verification, mini-program verification, or a specific unified verification platform), verification locations, time patterns, languages, device types, and frequencies, etc.

[0047] Next, define multi-level confidence intervals for multiple types of behavior patterns in the user behavior pattern feature set. Multi-level confidence intervals are used to indicate the credibility or confidence level of a behavior pattern. The high confidence intervals are the login locations that users frequently use, the medium confidence intervals are the locations that users occasionally log in to, and the low confidence intervals are the locations that users rarely or never log in to. For example, if 90% of a user's product verification behaviors occur between 9 and 11 a.m., a higher confidence level is defined, while for uncommon verification times (such as late at night), a lower confidence level is set. This allows the user's various behavior patterns to be classified, and a credibility interval is provided for each behavior pattern.

[0048] Then, based on multiple groups of confidence intervals, a user standard behavior space is constructed to reflect the typical behavior characteristics of users in different verification scenarios. For example, if a user's verification behavior usually occurs in a certain time period and is completed through a specific verification method, these behaviors are used as the user's standard behavior to construct a virtual behavior space.

[0049] The user's behavior pattern feature set is obtained through user verification records, confidence intervals are defined for different behavior patterns, and the user's standard behavior space is constructed based on these intervals to identify and verify the user's behavior, ensuring that anomalies or potential risks can be discovered in future verifications.

[0050] Furthermore, the present application also includes:

[0051] Synchronize the user identity information with the user standard behavior space to obtain the user identity mapping; identify the membership confidence interval of the user identity mapping in the user standard behavior space, and determine the user's individual multidimensional risk level; calculate the fitting confidence of the user identity mapping and store it as the multidimensional risk confidence; associate the user's individual multidimensional risk level with the multidimensional risk confidence, and output it as the user's individual risk warning result.

[0052] Specifically, the user identity information and the user standard behavior space are synchronized, that is, the user identity information is matched with the user standard behavior space, the specific position of the user's identity in its behavior pattern is determined, and the user identity mapping is formed.

[0053] Next, identify the membership confidence interval of the user identity mapping in the user's standard behavior space. The membership confidence interval refers to the degree of match between the user's behavior and the standard behavior. For example, if the user usually verifies in the morning on weekdays, and verifies at the same time this time, it is classified as a high confidence interval. By analyzing the membership confidence interval, the user's individual multidimensional risk level is determined, that is, the user's potential risk is assessed according to the different dimensions of the user's behavior. Assuming that the user's behavior deviates from the standard behavior, such as multiple abnormal verifications late at night, its risk level is set to "medium" or "high".

[0054] Subsequently, the fitting confidence of the user identity mapping is calculated by the interpolation method, the fit between the user behavior and the standard behavior is evaluated, and the data points of each dimension in the user identity mapping and standard behavior space are clarified. For example, assuming that the time of the user's verification behavior is 10:30, but the time point data in the standard behavior space is between 10 and 11 o'clock, the confidence of the behavior at 10:30 is estimated by linear interpolation. For example, if the confidence at 10 o'clock is 0.8 and the confidence at 11 o'clock is 0.7, the fitting confidence at 10:30 can be calculated as 0.75 using linear interpolation. Among them, if the user's verification behavior is very consistent with its previous pattern, the fitting confidence will be higher. On the contrary, if the behavior pattern has changed significantly, the fitting confidence will be lower. The fitting confidence will be stored as a multidimensional risk confidence, indicating the risk credibility of the user in different dimensions.

[0055] Finally, the user's individual multidimensional risk level is associated with the multidimensional risk confidence, and the output is the risk warning result of the user's individual, that is, a comprehensive assessment report is provided based on the risk level and confidence of the user's behavior, indicating whether preventive measures need to be taken. For example, if the user's risk level is "high" and the fitting confidence is low, a high-risk warning is triggered, and it is recommended to further monitor the user's behavior.

[0056] By synchronizing user identity information with the standard behavior space, identifying the membership confidence interval, and calculating the fitting confidence, the user's multi-dimensional risk level and confidence are finally associated to generate individual risk warning results, ensuring that user behavior is closely matched with the standard pattern, so as to better assess and manage potential risks.

[0057] Furthermore, the present application also includes:

[0058] If the recognition abnormality coefficient indicates that there is no abnormality in the user verification request information, anti-counterfeiting verification is performed on the product label based on the user verification request information, and verification feedback information is returned to the user end.

[0059] Specifically, if the recognition anomaly coefficient indicates that the user verification request information is normal, that is, the user's verification request information is detected for anomalies and no anomalies are found. The anomaly coefficient is an indicator to measure whether the user's request conforms to the normal behavior pattern, which is usually determined by analyzing the user's verification time, method, device and other characteristics. If the user's request behavior conforms to its historical pattern, such as usually verifying the product through the QR code in the morning, and the verification behavior this time also conforms to this characteristic, the anomaly coefficient is set to normal.

[0060] Next, the product label is verified for anti-counterfeiting based on the user's verification request information, and the anti-counterfeiting information in the database is queried to confirm the authenticity of the product label. For example, the unique identifier "product ID 12345" in the product label can be checked by querying the database to check its production and sales records to ensure that the product has not been counterfeited or tampered with.

[0061] Then, the verification feedback information is returned to the user. The verification feedback information is the result of the anti-counterfeiting verification, which may include "verification passed", "label abnormality" or "verification failed" and other statuses. Assuming that the product label is confirmed to be authentic and valid after verification, the "verification passed" information is sent to the user to inform the user that the product is authentic.

[0062] The abnormality coefficient is used to determine whether the user's verification request is normal. If there is no abnormality, the anti-counterfeiting verification of the product label is carried out. Finally, the verification result is fed back to the user end to ensure the user's verification behavior and the authenticity of the product, thereby improving overall security and reliability.

[0063] Furthermore, the present application also includes:

[0064] According to the user identity information, a user association verification record is obtained; the user additional risk is identified by combining the user verification record with the user association verification record; the user additional risk identification result is associated and stored with the user individual risk warning result, and consistency update verification of the user identity information is performed.

[0065] Specifically, the user's associated verification record is obtained based on the user's identity information. The user's associated verification record includes all verification behaviors related to the user, such as account association, from the same gateway device / IP address / user end (hardware code), etc.

[0066] Next, the user's verification record is combined with its associated verification records to identify the user's additional risk. For example, if the user's recent verification behavior is very different from his historical behavior, such as usually verifying at home, but recently frequently verifying outside the city, then the user is judged to have additional risks, or whether there is a "small account" for other users involved in counterfeiting product labels, whether the user belongs to a counterfeiting group, etc.

[0067] Then, the user's additional risk identification result is associated with the user's individual risk warning result and stored. The user's additional risk identification result is an assessment of the newly discovered potential risks, while the user's individual risk warning result is an overall risk assessment based on the previous analysis. Through associated storage, a more comprehensive user risk assessment is obtained.

[0068] Finally, the consistency update verification of user identity information is performed to ensure that the update of user identity information is based on real verification records and behaviors, ensure the legitimacy of user identity and update the corresponding information.

[0069] The associated verification records are obtained through the user's identity information, and then additional risk identification is performed. The risk identification results are then associated and stored with the individual risk warning results. Finally, the accuracy of the user's identity information is ensured through consistency verification, thereby comprehensively assessing the user's risks and ensuring the consistency of the verification behavior with the user's identity information.

[0070] Furthermore, the present application also includes:

[0071] According to the commodity identity information, obtain the commodity homology verification record; merge the commodity verification record with the commodity homology verification record to perform commodity additional risk identification; associate and store the commodity additional risk identification result with the commodity individual risk warning result, and perform commodity label risk update identification.

[0072] Specifically, based on the product identity information, the same-source verification record of the product is queried, and all verification records related to the product are obtained from the database through the unique identity of the product. The same-source verification record refers to the anti-counterfeiting verification record of products of the same series or brand as the target product.

[0073] Next, the verification record of the product is merged with the same-source verification record, and the additional risk of the product is judged to determine whether the product has potential risks. For example, if a batch of products indicates that the product has the risk of counterfeiting or tampering, it will be marked as "additional risk".

[0074] Then, the additional risk identification results of the goods are associated with the individual risk warning results of the goods and stored, so as to obtain a more complete product risk assessment and further improve the safety of the goods.

[0075] Finally, the product label risk is updated to confirm whether there are any changes or abnormalities in the product label, such as whether the anti-counterfeiting label has been replaced or tampered with. The risk level of the product label is then updated through new verification records and risk analysis to ensure that the product label information is accurate.

[0076] The same-source verification records are obtained through the product identity information, and additional risk identification is performed. The additional risk results are then associated and stored with the individual risk warning results. Finally, the risk identification of the product label is updated to comprehensively evaluate the safety of the product and ensure the reliability of the product label and verification records.

[0077] In summary, the multi-source data-aware product label anti-counterfeiting identification and early warning platform provided by this application has the following technical effects:

[0078] Obtain user verification request information through the interactive user terminal, parse the user verification request information, and obtain product identity information and user identity information; transmit the product identity information and the user identity information to a multi-source database, and extract multi-source historical anti-counterfeiting verification records, wherein the multi-source historical anti-counterfeiting verification records include user verification records and product verification records; analyze anti-counterfeiting identification behavior according to the product verification record, determine whether there is a product label risk, and obtain product individual risk warning results; extract and construct a user standard behavior space according to the user verification record, and perform consistency verification of the user identity information according to the user standard behavior space, and output the user individual risk warning result; combine the product individual risk warning result with the user individual risk warning result, evaluate the degree of anti-counterfeiting identification abnormality, obtain the identification abnormality coefficient, and perform anti-counterfeiting identification warning based on the identification abnormality coefficient, so as to achieve the technical goal of comprehensive analysis and correlation comparison of product homologous verification records, and achieve the technical effect of effectively identifying counterfeit product labels and improving anti-counterfeiting warning capabilities.

[0079] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0080] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A product label anti-counterfeiting identification and early warning platform based on multi-source data perception, characterized by: include: An information parsing module, used for the interactive user end to obtain user verification request information, parse the user verification request information, and obtain commodity identity information and user identity information; An information extraction module, used to transmit the commodity identity information and the user identity information to a multi-source database, and extract multi-source historical anti-counterfeiting verification records, wherein the multi-source historical anti-counterfeiting verification records include user verification records and commodity verification records; An anti-counterfeiting analysis module is used to analyze anti-counterfeiting identification behavior based on the commodity verification record, determine whether there is a commodity label risk, and obtain individual commodity risk warning results; The consistency verification module is used to extract and construct a user standard behavior space according to the user verification record, and perform consistency verification of the user identity information according to the user standard behavior space, and output the user individual risk warning result. The steps of extracting and constructing the user standard behavior space according to the user verification record include: Acquire a user behavior pattern feature set based on the user verification record; Defining multi-level confidence intervals for multiple types of behavior pattern features in the user behavior pattern feature set, and constructing a user standard behavior space based on multiple groups of the multi-level confidence intervals; The consistency verification of the user identity information is performed according to the user standard behavior space, and the user individual risk warning result is output, and the execution step further includes: Synchronize the user identity information with the user standard behavior space to obtain user identity mapping; Identify the membership confidence interval of the user identity mapped to the user standard behavior space, and determine the user's individual multi-dimensional risk level; Calculating the fitting confidence of the user identity mapping and storing it as a multi-dimensional risk confidence; Associating the user's individual multi-dimensional risk level with the multi-dimensional risk confidence, and outputting the user's individual risk warning result; The abnormality evaluation module is used to combine the individual risk warning result of the commodity with the individual risk warning result of the user, evaluate the degree of abnormality of anti-counterfeiting identification, obtain the abnormality coefficient of identification, and make an anti-counterfeiting identification warning based on the abnormality coefficient of identification.

2. The multi-source data-aware commodity label anti-counterfeiting identification and early warning platform according to claim 1, characterized in that: The commodity identity information and the user identity information are transmitted to a multi-source database, and multi-source historical anti-counterfeiting verification records are extracted. The execution steps include: Using the commodity identity information and the user identity information as index keys, connecting to the multi-source database; Based on the risk warning requirements of the target scenario, define a record extraction space, wherein the record extraction space includes a user record extraction space and a commodity record extraction space; All historical anti-counterfeiting verification records related to the commodity identity information and the user identity information are called and extracted until the record extraction space is filled, and the multi-source historical anti-counterfeiting verification records are output.

3. The multi-source data-aware commodity label anti-counterfeiting identification and early warning platform according to claim 2, characterized in that: Analyze the anti-counterfeiting identification behavior according to the product verification record, determine whether there is a product label risk, and obtain the product individual risk warning result. The execution steps include: Parsing the user verification request information to obtain verification capability information of the user terminal, wherein the verification capability information includes a multi-dimensional verification path; Based on the verification capability information, the commodity verification record is traversed to perform dimension matching, and the commodity verification record is light-weighted according to the dimension matching result to obtain the target commodity verification record, wherein the light-weighted processing means that if the match is successful, the matched verification record is light-weighted, that is, only the part related to the user device capability is retained, so as to obtain a more streamlined target commodity verification record; Taking the verification capability information as a dimensional target, a multi-dimensional indicator concentration feature of the target commodity verification record is obtained, and whether the commodity identity information has a commodity label risk is determined based on the multi-dimensional indicator concentration feature.

4. The multi-source data-aware commodity label anti-counterfeiting identification and early warning platform according to claim 1, characterized in that: The execution steps also include: If the recognition abnormality coefficient indicates that there is no abnormality in the user verification request information, anti-counterfeiting verification is performed on the product label based on the user verification request information, and verification feedback information is returned to the user end.

5. The multi-source data-aware commodity label anti-counterfeiting identification and early warning platform according to claim 1, characterized in that: The execution steps also include: Obtaining user association verification records according to the user identity information; Combining the user verification record with the user association verification record, performing additional risk identification for the user; The user's additional risk identification result and the user's individual risk warning result are stored in association, and the consistency update verification of the user's identity information is performed.

6. The multi-source data-aware commodity label anti-counterfeiting identification and early warning platform according to claim 1, characterized in that: The execution steps also include: Obtaining a product homology verification record based on the product identity information; Combining the commodity verification record with the commodity homology verification record to identify the additional risks of the commodity; The additional risk identification result of the commodity and the individual risk warning result of the commodity are stored in association, and the updated identification of the commodity label risk is performed.

Images