Information verification method and device, electronic equipment and storage medium

Abstract

The application discloses an information verification method and device and electronic equipment, and mainly comprises the following technical solutions: the biological characteristic information is subjected to multi-modal fusion verification to generate an identity verification result; the file information is analyzed to extract key information; the identity verification result and the key information are sent to a server, so that the server performs consistency comparison on the identity verification result and the key information and historical bidding data to generate an identity verification result and a data verification result; the identity verification result and the data verification result are subjected to comprehensive determination through a block chain smart contract, and finally, the identity verification result and the data verification result are chained and stored. Real-time dynamic verification of the identity of a bidder and file information in an opening bidding site can be realized, the information verification efficiency and the fraud identification rate are improved, and the credibility and the non-tamperability of the verification process and the result are ensured.

Description

Technical Field

[0001] This application relates to the field of Internet of Things (IoT) technology, and in particular to an information verification method and apparatus, electronic device and storage medium. Background Technology

[0002] With the deep integration of information technology and engineering management, the informatization and intelligentization of the bidding process have become a research focus. Existing technologies mainly achieve the technical goal of verifying bidder information through data security mechanisms and identity verification methods. On the one hand, a secure communication framework based on encrypted signatures and certificate verification is constructed through a trusted device access mechanism; on the other hand, a technical framework for data operation verification and change storage is designed based on blockchain technology and hierarchical access control. These solutions provide technical support for information security in engineering bidding scenarios.

[0003] In the area of ​​verifying bidder information at the bid opening site, existing technical solutions include manual review methods and electronic review technologies. Some solutions encrypt and sign request data using the private keys of edge node devices, and send the data and device identifiers to the central cloud. The central cloud then uses device certificates to verify the validity and legality of the data signature, thereby building a secure channel and ensuring trusted device access. Other solutions are based on industrial identification and blockchain technology. They generate request data through user-preset operations, combine semantic recognition and location information verification mechanisms to determine data operation requirements and execution permissions, and verify user identity through blockchain to improve the accuracy and security of logistics data changes. In addition, there are information payment systems based on 5G communication networks and blockchain platforms. These systems establish account connections between users and merchant apps, upload operation information to the edge subsystem, and transmit it to the blockchain platform for processing. Combined with encryption modules and transaction level control, they ensure the security of payment information and transaction efficiency. All of the above technical solutions achieve information verification and data security in different application scenarios, but their technical framework mainly revolves around communication security, access control, and data storage, without involving the integrated application of multimodal biometrics and intelligent analysis technologies.

[0004] While existing technologies have improved data transmission security, logistics change verification, and payment system security, none of them involve multimodal biometrics or intelligent bid document parsing, making it difficult to achieve real-time, dynamic, and reliable verification of bidder information. Furthermore, these solutions neglect information fraud detection rates, resulting in significant shortcomings in identifying falsified bidder information. Therefore, there is an urgent need for a technical solution that integrates multimodal biometrics, intelligent parsing, and blockchain notarization to improve the accuracy and reliability of bid information verification, effectively identify information fraud, and meet the high requirements for information authenticity verification in engineering bidding scenarios. Summary of the Invention

[0005] This application provides a method, apparatus, electronic device, and storage medium for verifying information to overcome the problems of existing technologies. While existing technologies have improved in terms of data transmission security, logistics change verification, and payment system security, they do not involve multimodal biometrics and intelligent bid document parsing technology, making it difficult to achieve real-time, dynamic, and reliable verification of bidder information. Furthermore, these solutions do not address the rate of information forgery detection, resulting in significant deficiencies in identifying falsified bidder information. Therefore, there is an urgent need for a technical solution that integrates multimodal biometrics, intelligent parsing, and blockchain notarization to improve the accuracy and reliability of bid information verification, effectively identify information forgery, and meet the high requirements for information authenticity verification in engineering bidding scenarios.

[0006] Firstly, a method for verifying information is provided. This includes: performing multimodal fusion verification on biometric information to generate an identity verification result; parsing the document information to extract key information; sending the identity verification result and key information to the server, so that the server can compare the identity verification result and key information with historical bidding data to generate an identity verification result and a data verification result; executing a comprehensive judgment of the identity verification result and data verification result through a blockchain smart contract, and storing the final identity verification result and data verification result on the blockchain for evidence.

[0007] Based on the methods described above, this invention significantly improves the efficiency, accuracy, and credibility of information verification by combining multimodal fusion verification with blockchain smart contracts. Utilizing 5G and edge computing technologies, it achieves real-time collection and rapid processing of biometric and document information, increasing verification efficiency tenfold. Employing multimodal biometrics and OCR / NLP technologies effectively improves the accuracy of key information extraction and logical contradiction identification, achieving a forgery detection rate of up to 99.8%. Blockchain-based evidence storage and automatic execution of smart contracts ensure the immutability and transparency of verification results, enhancing information credibility. Simultaneously, data encryption and privacy protection mechanisms safeguard the information security of bidders. This method is applicable to various bidding scenarios, possessing good flexibility and broad application prospects, providing an efficient, accurate, and reliable means of information verification for engineering bidding.

[0008] In conjunction with the first aspect, in some possible implementations of the first aspect, biometric information includes at least two of face, fingerprint, and iris. Multimodal fusion verification of biometric information to generate identity verification results includes: performing feature matching of the collected biometric information of at least two types with registration information in the database, calculating a comprehensive score of matching degree; and verifying the user's identity based on the comprehensive score of matching degree.

[0009] In conjunction with the first aspect, in some possible implementations of the first aspect, the document information includes a bid document image; parsing the document information and extracting key information includes: extracting text information from the bid document image using OCR; performing logical contradiction detection on the extracted text information using NLP; and obtaining the key information once the logical contradiction detection is successful.

[0010] In conjunction with the first aspect, in some possible implementations of the first aspect, before performing multimodal fusion verification on the biometric information to generate an authentication result, the method further includes: collecting biometric information and file information through the perception layer, and transmitting the biometric information and file information to the edge layer; performing multimodal fusion verification on the biometric information to generate an authentication result includes: performing multimodal fusion verification on the biometric information at the edge layer to generate an authentication result.

[0011] In conjunction with the first aspect, in some possible implementations of the first aspect, sending the authentication result and key information to the server includes: sending the authentication result and key information of the edge layer to the server of the cloud layer.

[0012] In conjunction with the first aspect, in some possible implementations of the first aspect, the comprehensive determination of the identity verification result and the data verification result by executing the blockchain smart contract, and storing the final identity verification result and the data verification result on the blockchain for evidence includes: automatically executing the comprehensive determination of the identity verification result and the data verification result based on the blockchain smart contract to generate the target verification result; and storing the target verification result on the blockchain for evidence through blockchain technology.

[0013] Secondly, an information verification device is provided. It includes: The generation unit is used to perform multimodal fusion verification of biometric information to generate identity verification results; The extraction unit is used to parse file information and extract key information; The sending unit is used to send the authentication result and key information to the server so that the server can compare the authentication result and key information with historical bidding data to generate authentication result and data verification result. The determination unit is used to make a comprehensive determination of the identity verification result and the data verification result through the blockchain smart contract, and to store the final identity verification result and the data verification result on the blockchain.

[0014] In conjunction with the second aspect, in some possible implementations of the second aspect, the biometric information includes at least two of face, fingerprint, and iris scans, and the generation unit includes: The calculation module is used to perform feature matching between the collected biometric information of at least two types and the registration information in the database, and calculate a comprehensive score of the matching degree; The verification module is used to verify the user's identity based on the comprehensive score of the matching degree.

[0015] In conjunction with the second aspect, in some possible implementations of the second aspect, the document information includes an image of the tender document; The extraction unit includes: The extraction module is used to extract text information from the tender document image using OCR. The determination module is used to perform logical contradiction detection on the extracted text information using NLP. Once the logical contradiction detection is successful, the key information is obtained.

[0016] In conjunction with the second aspect, in some possible implementations of the second aspect, the apparatus further includes: The acquisition unit is used to acquire the biometric information and the file information through the perception layer before the generation unit performs multimodal fusion verification on the biometric information to generate an identity verification result, and to transmit the biometric information and the file information to the edge layer; The generation unit is also used to perform multimodal fusion verification on the biometric information at the edge layer to generate an identity verification result.

[0017] In conjunction with the second aspect, in some possible implementations of the second aspect, the sending unit is further configured to send the authentication result of the edge layer and the key information to the server of the cloud layer.

[0018] In conjunction with the second aspect, in some possible implementations of the second aspect, the determination unit includes: The generation module is used to automatically perform a comprehensive judgment based on the identity verification result and the data verification result according to the blockchain smart contract, and generate the target verification result; The storage module is used to store the target verification results on the blockchain using blockchain technology.

[0019] Thirdly, an electronic device is provided, comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in any one of the first aspects.

[0020] Fourthly, a non-transitory computer-readable storage medium is provided storing computer instructions for causing the computer to perform the method according to any one of the first aspects.

[0021] Fifthly, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method according to any one of the first aspects.

[0022] Based on the verification methods, devices, electronic equipment, and storage media described above, the biometric information is subjected to multimodal fusion verification to generate an identity verification result; the document information is parsed to extract key information; the identity verification result and the key information are sent to the server, so that the server can compare the identity verification result and the key information with historical bidding data to generate an identity verification result and a data verification result; the comprehensive judgment of the identity verification result and the data verification result is executed through a blockchain smart contract, and the final identity verification result and the data verification result are stored on the blockchain for evidence. This enables real-time dynamic verification of the bidder's identity and document information at the bid opening site, improving information verification efficiency and fraud detection rate, and ensuring the credibility and immutability of the verification process and results.

[0023] Thirdly, an electronic device includes: at least one processor; and the ability to perform the methods described above.

[0024] Fourthly, a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method according to any one of the first aspects, so that the method of any one of the preceding aspects is executed.

[0025] Fifthly, a computer program product includes a computer program that, when executed by a processor, implements the method according to any one of the first aspects, so that the method of any one of the preceding aspects is performed.

[0026] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0027] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein: Figure 1 This is a flowchart illustrating an information verification method applicable to the embodiments of this application; Figure 2 This is a flowchart illustrating another information verification method applicable to the embodiments of this application; Figure 3 This is a schematic diagram of an information verification device applicable to the embodiments of this application; Figure 4This is a schematic diagram of another information verification device applicable to the embodiments of this application. Detailed Implementation

[0028] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0029] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The specific operating methods in the method embodiments can also be applied to the device embodiments or system embodiments. In the description of this application, unless otherwise stated, "multiple" means two or more.

[0030] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of different embodiments are consistent and can be referenced by each other. The technical features of different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0031] It is understood that the various numerical designations used in this application are merely for descriptive convenience and are not intended to limit the scope of this application. The order of the process numbers does not imply the order of execution; the execution order of each process should be determined by its function and internal logic.

[0032] The terms "first," "second," "third," "fourth," and other various terminology (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0033] To facilitate understanding of the embodiments of this application, the terminology involved in the embodiments of this application will be briefly explained below.

[0034] Multimodal fusion verification refers to the comprehensive comparison and scoring of multiple biometric information (such as face, fingerprint, iris) to improve the accuracy and reliability of identity verification.

[0035] OCR: Optical Character Recognition, is a technology used to extract text information from tender document images and is an important means of document information parsing.

[0036] NLP: Natural Language Processing technology is used to detect logical contradictions and extract key information from extracted text information, ensuring the rationality and consistency of the document content.

[0037] Blockchain smart contracts: Automatic execution protocols based on blockchain technology, used to automatically determine the comprehensive judgment of identity verification results and data verification results without the intervention of third parties, and to store the results on the blockchain.

[0038] Edge layer: Located between the perception layer and the cloud, this computing node is responsible for real-time processing and preliminary verification of the collected biometric and file information, thereby improving system response speed and data processing efficiency.

[0039] Based on this, this application provides an information verification method, apparatus, electronic device, and storage medium to overcome the problems of existing technologies. Although these solutions offer improvements in data transmission security, logistics change verification, and payment system security, they do not involve multimodal biometrics or intelligent bid document parsing technologies, making it difficult to achieve real-time, dynamic, and reliable verification of bidder information. Furthermore, these solutions do not address the rate of information forgery detection, resulting in significant technical deficiencies in identifying forged bidder information.

[0040] Figure 1 This is a schematic diagram of an information verification method included in an embodiment of this application. For example... Figure 1 As shown, the method includes: 101. Perform multimodal fusion verification on biometric information to generate identity verification results. Specifically, by collecting at least two biometric information, such as face, fingerprint or iris, and matching them with registration information in the database, a comprehensive score of matching degree is calculated; based on the comprehensive score, the authenticity of the user's identity is determined, thereby generating an identity verification result. Specifically, in edge computing nodes, the use of multimodal biometric technology to fuse and verify biometric information is one of the core steps in this invention to achieve real-time, dynamic, and reliable verification of bidder identities. This step integrates three biometric features—facial recognition, fingerprint recognition, and iris recognition—to construct a multimodal identity verification model, thereby significantly improving the accuracy and anti-counterfeiting capabilities of identity recognition.

[0041] In some embodiments, multimodal biometric terminals (such as high-definition cameras, fingerprint sensors, and iris recognition devices) deployed through edge computing nodes simultaneously collect facial, fingerprint, and iris images of the bidders. Each biometric feature is extracted using a dedicated algorithm: face recognition uses OpenCV for facial feature point detection and feature vector extraction; fingerprint recognition uses the Minutiae matching algorithm to extract fingerprint detail features; and iris recognition uses a Gabor filter to extract texture features. The extracted feature vectors are input into the fusion verification module of the edge node, which employs a weighted fusion strategy to comprehensively score the matching degree of each modality. This meets the real-time requirements of the bid opening process.

[0042] In this application scenario, this step is deployed on the edge computing server at the bidding site, working in conjunction with the biometric terminals in the perception layer. When a bidder enters the bidding area, their biometric features are collected in real time and transmitted to the edge node. The system completes multimodal fusion verification within a preset time interval and feeds the results back to on-site staff or the smart contract module. This step is particularly suitable for bidding scenarios with high security requirements, such as large-scale infrastructure projects, and can effectively prevent impersonation and identity fraud.

[0043] By fusing and verifying multimodal biometrics, the robustness and anti-counterfeiting capabilities of identity recognition are significantly improved, while effectively reducing the risk of identity theft. This provides a reliable identity foundation for subsequent intelligent parsing of tender documents and blockchain-based evidence storage, thereby ensuring the fairness and legality of the entire bidding process.

[0044] 102. Parse the file information and extract key information. Specifically, text information in the tender document image is extracted using OCR technology, and natural language processing technology is used to detect logical contradictions in the extracted text information. After the logical contradiction detection is successful, key information such as company name, project experience, and qualification certificates is extracted. Specifically, the method for parsing file information in this disclosure is not limited. In addition to the parsing method described above, any method in related technologies can also be used.

[0045] 103. Send the identity verification result and key information to the server so that the server can compare the identity verification result and key information with historical bidding data to generate the identity verification result and data verification result. Specifically, the authentication results generated at the edge layer and the extracted key information are transmitted to the server at the cloud layer. The server compares this information with the stored historical bidding data and uses a similarity algorithm to detect the consistency of the information, thereby generating data verification results. In the technical solution of this invention, transmitting the identity verification results and key information to the cloud server and comparing them with historical bidding data is one of the core steps in achieving reliable verification of bidder information. This step ensures that data is uploaded within millisecond-level latency by constructing a transmission mechanism that coordinates 5G IoT and edge computing, and performs multi-dimensional comparative analysis in the cloud to generate highly reliable data verification results.

[0046] In some implementations, the authentication results processed at the edge layer (such as facial recognition matching score, fingerprint feature consistency, and iris recognition confidence score) and key information extracted from the tender document through intelligent parsing (such as company name, project experience, qualification number, etc.) are first encapsulated in JSON or XML format via the 5G communication network and then transmitted end-to-end encrypted using the TLS 1.3 protocol. During transmission, the data packet size is controlled to be within 100KB to adapt to the low latency and high bandwidth characteristics of the 5G network (e.g., with 200MHz bandwidth support, the transmission latency is ≤10ms).

[0047] After receiving the data, the cloud server initiates a historical data consistency comparison process. Specifically, the cloud database stores structured data such as the bidder's historical bidding records, winning bids, and qualification change logs. The comparison algorithm uses the Levenshtein distance algorithm to calculate the similarity of the text information; however, this invention does not limit the method of similarity calculation.

[0048] Through cloud-based comparison, the system can achieve data consistency verification across projects and time periods, improving the overall accuracy and credibility of verification. Furthermore, centralized cloud processing and intelligent comparison with historical data not only enhance the comprehensiveness of verification but also provide a reliable data foundation for the subsequent automatic execution of smart contracts, thereby ensuring the fairness and transparency of the entire bidding process.

[0049] 104. The blockchain smart contract is used to make a comprehensive judgment on the identity verification result and the data verification result, and the final identity verification result and data verification result are stored on the blockchain. Specifically, the system automatically determines the target verification result by combining the identity verification result and the data verification result based on the blockchain smart contract; then, the target verification result is stored on the blockchain to ensure the transparency and immutability of the verification process. The core step in achieving reliable verification of bidder information is to automatically execute a comprehensive judgment of identity verification and data verification results through blockchain smart contracts and then store the final verification results on the blockchain. This step, based on the blockchain's smart contract mechanism and combined with verification results from the edge computing layer and the cloud layer, achieves automated, tamper-proof comprehensive judgment and storage.

[0050] The cloud layer encapsulates the verification results into structured data and automatically executes the judgment logic through smart contracts. These smart contracts are deployed on blockchain platforms (such as Hyperledger Fabric or Ethereum), and their execution logic includes determining the identity verification score threshold, verifying the logical consistency of the tender document content, and analyzing historical data comparison results. Once a judgment result is generated, a unique identifier is generated using a hash algorithm (such as SHA-256) and stored on the blockchain as a transaction record, ensuring the immutability and traceability of the data.

[0051] By leveraging the automated execution mechanism of smart contracts, the possibility of human intervention is eliminated, enhancing the fairness and transparency of the verification process. Simultaneously, the distributed ledger nature of blockchain ensures the long-term preservation of verification results, providing reliable technical support for subsequent auditing, traceability, and judicial determination. In practical applications, this step can be widely used in various engineering bidding scenarios, particularly in government projects or large-scale infrastructure projects requiring high credibility and security.

[0052] The information verification method provided in this disclosure performs multimodal fusion verification on the biometric information to generate an identity verification result; parses the document information to extract key information; sends the identity verification result and the key information to a server, so that the server compares the identity verification result and the key information with historical bidding data to generate an identity verification result and a data verification result; executes a comprehensive judgment of the identity verification result and the data verification result through a blockchain smart contract, and finally stores the final identity verification result and the data verification result on the blockchain for evidence. This method enables real-time dynamic verification of the bidder's identity and document information at the bid opening site, improving information verification efficiency and the rate of forgery detection, and ensuring the credibility and immutability of the verification process and results.

[0053] In some implementations, such as Figure 2 In the method shown, the biometric information includes at least two of the following: face, fingerprint, and iris. When performing multimodal fusion verification of the biometric information to generate the identity verification result in step 101, the following methods can be used, but are not limited to: Step 201: The collected biometric information of at least two types is matched with the registration information in the database to calculate the comprehensive score of the matching degree.

[0054] In some embodiments, the comprehensive scoring formula is as follows:

[0055] in, For comprehensive scoring, , , The scores represent the matching scores for facial recognition, fingerprint recognition, and iris recognition, respectively. The weighting coefficients for each modality are dynamically adjusted based on the actual application scenario, and typically satisfy the following: .

[0056] Step 202: Verify the user's identity based on the comprehensive score of the matching degree.

[0057] When the overall score S exceeds the preset threshold (e.g.) If the overall score S does not exceed the preset threshold, the identity verification is deemed successful; if the overall score S does not exceed the preset threshold, the identity verification is deemed unsuccessful.

[0058] The technical effect of this step is that it significantly improves the accuracy and reliability of identity recognition through the fusion and verification of multimodal biometrics. In some implementations, such as Figure 1 The method described includes a bid document image as the document information. Parsing the document information and extracting key information involves: extracting text information from the bid document image using OCR; performing logical contradiction detection on the extracted text information using NLP; and obtaining the key information once the logical contradiction detection is successful. This improves the accuracy and completeness of key information extraction. IoT terminals were deployed at the bidding site, including high-definition cameras, fingerprint sensors, iris recognition devices, and high-resolution scanners. These devices were uniformly scheduled through an embedded operating system (such as Linux or RTOS), supporting multi-threaded concurrent data acquisition. For example, the face recognition module used the OpenCV library to detect facial feature points and extract LBP (Local Binary Pattern) or HOG (Histogram of Oriented Gradients) features; the fingerprint recognition module used the Minutiae matching algorithm to extract the bifurcation and endpoint features of the fingerprint; and the iris recognition module extracted texture features using a Gabor filter. Bidding document information was extracted from images using OCR technology (such as Tesseract OCR) and combined with NLP technology (such as spaCy) for semantic parsing and logical contradiction detection.

[0059] In some implementations, such as Figure 1 The method described includes, before performing multimodal fusion verification on the biometric information to generate an authentication result, the following steps: collecting biometric information and file information through the perception layer and transmitting the biometric information and file information to the edge layer; performing multimodal fusion verification on the biometric information to generate an authentication result includes performing multimodal fusion verification on the biometric information at the edge layer to generate the authentication result. This enables real-time processing and verification of information, improving system response speed. When bidders enter the bid opening site, their biometric data and bid document information are simultaneously collected and uploaded to edge nodes, providing a data foundation for subsequent multimodal identity verification and intelligent bid document parsing. This step effectively prevents impersonation, identity forgery, or fraudulent documents, ensuring the fairness of the bidding process.

[0060] Leveraging the high-speed transmission capabilities of 5G networks and the low-latency processing mechanisms of edge computing, the efficiency of information collection and transmission is significantly improved, reducing the verification response time to less than 500ms, more than 10 times faster than traditional solutions. Simultaneously, standardized collection processes and encrypted transmission mechanisms (such as TLS) ensure data integrity and security, providing reliable data input for subsequent blockchain notarization and smart contract verification.

[0061] In some implementations, such as Figure 1 The method described includes sending the authentication result and key information to the server, specifically from the edge layer, to the cloud layer. This enables centralized data processing and analysis, improving verification efficiency and accuracy. In some implementations, such as Figure 1 The method described involves using a blockchain smart contract to comprehensively determine the identity verification result and the data verification result, and then storing the final identity verification result and data verification result on the blockchain for evidence. This includes: automatically executing the comprehensive determination of the identity verification result and data verification result based on the blockchain smart contract to generate the target verification result; and storing the target verification result on the blockchain for evidence. This ensures the authenticity and immutability of the verification result, enhancing the system's credibility. In such Figure 1 The method described above collects biometric and document information through the perception layer, performs multimodal identity verification and intelligent parsing of tender documents through the edge layer, compares historical data consistency through the cloud layer, and executes a comprehensive judgment and stores the evidence on the blockchain through a blockchain smart contract. This achieves high efficiency, accuracy and credibility in information verification, ensuring the fairness and impartiality of the bidding process.

[0062] The embodiments of the present invention can also achieve the following beneficial effects: This invention significantly improves the efficiency, accuracy, and credibility of information verification through multimodal fusion verification and blockchain smart contract technology. The generation unit combines 5G and edge computing technologies to achieve rapid processing and identity verification of biometric information, improving verification efficiency. The extraction unit utilizes OCR and NLP technologies to accurately parse document information, improving the recognition rate and effectively preventing information forgery. The sending unit uploads the verification results and key information to the server in real time, performing consistency comparisons with historical data to ensure rigorous data logic. The judgment unit automatically executes a comprehensive judgment through a blockchain smart contract and stores the results on the blockchain, ensuring the fairness and immutability of the verification process. Simultaneously, the system employs encryption and privacy protection mechanisms to ensure data security and the privacy of bidders. This device is suitable for various bidding scenarios, possessing the technical advantages of high efficiency, accuracy, credibility, and security, providing a reliable means of information verification for engineering bidding.

[0063] Figure 3 This is a schematic diagram of the structure of an information verification device provided in an embodiment of this application. For example... Figure 3 As shown, the information verification device includes a generation unit 21, an extraction unit 22, a sending unit 23, and a judgment unit 24. The generation unit 21 is used to perform multimodal fusion verification of biometric information to generate an identity verification result. Specifically, the generation unit 21 can collect the bidder's biometric information through three methods: face recognition, fingerprint recognition, and iris recognition. It then performs feature matching on each recognition result, calculates the matching degree, and performs a comprehensive score based on preset weight coefficients to generate the identity verification result. Extraction unit 22 is used to parse the document information and extract key information. Specifically, extraction unit 202 can use OCR technology to extract text information from the tender document, and use natural language processing technology to detect logical contradictions and extract key information from the text content, such as company name, project experience, qualification certificates, etc. The sending unit 23 is used to send the authentication result and key information to the server, so that the server can perform a consistency comparison between the authentication result and key information and historical bidding data, and generate authentication result and data verification result. Specifically, the sending unit 23 can encrypt and transmit the generated authentication result and extracted key information to the cloud server through a network communication module for historical data consistency comparison. The determination unit 24 is used to perform a comprehensive determination of the identity verification result and the data verification result through a blockchain smart contract, and to store the final identity verification result and the data verification result on the blockchain for evidence storage. Specifically, the determination unit 204 can call a smart contract deployed on the blockchain to perform a comprehensive determination of the identity verification result and the data verification result returned by the cloud server, and write the determined result into the blockchain for evidence storage to ensure the authenticity and immutability of the information.

[0064] The information verification method and apparatus provided in this disclosure perform multimodal fusion verification on the biometric information to generate an identity verification result; parse the document information to extract key information; send the identity verification result and the key information to a server, so that the server can compare the identity verification result and the key information with historical bidding data to generate an identity verification result and a data verification result; execute a comprehensive judgment of the identity verification result and the data verification result through a blockchain smart contract, and finally store the final identity verification result and the data verification result on the blockchain for evidence. This enables real-time dynamic verification of the bidder's identity and document information at the bid opening site, improving information verification efficiency and the rate of forgery detection, and ensuring the credibility and immutability of the verification process and results. Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 4 As shown, the biometric information includes at least two of the following: face, fingerprint, and iris. The generation unit 21 includes: The calculation module 211 is used to perform feature matching between the collected biometric information of at least two types and the registration information in the database, and calculate a comprehensive score of matching degree; The verification module 212 is used to verify the user's identity based on the comprehensive score of the matching degree.

[0065] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 4 As shown, the document information includes an image of the tender document; The extraction unit 22 includes: Extraction module 221 is used to extract text information from the tender document image using OCR; The determination module 222 is used to perform logical contradiction detection on the extracted text information through NLP. Once the logical contradiction detection is successful, the key information is obtained.

[0066] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 4 As shown, the device further includes: The acquisition unit 25 is used to acquire the biometric information and the file information through the perception layer before the generation unit 21 performs multimodal fusion verification on the biometric information to generate an identity verification result, and to transmit the biometric information and the file information to the edge layer. The generation unit 21 is also used to perform multimodal fusion verification on the biometric information at the edge layer to generate an identity verification result.

[0067] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 4 As shown, the sending unit 23 is also used to send the authentication result and the key information of the edge layer to the server of the cloud layer.

[0068] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 4 As shown, the determination unit 24 includes: The generation module 241 is used to automatically perform a comprehensive judgment of the identity verification result and the data verification result based on the blockchain smart contract, and generate a target verification result; Storage module 242 is used to store the target verification result on the blockchain using blockchain technology.

[0069] The method of this application will now be described in conjunction with specific embodiments. Example 1 In some implementations, the perception layer acquires facial images of the bidder using a high-definition camera and performs facial feature point detection and extraction using the OpenCV algorithm. Simultaneously, it acquires fingerprint images of the bidder using a fingerprint sensor and extracts fingerprint feature points using the Minutiae matching algorithm. Furthermore, it acquires iris images of the bidder using an iris recognition device and extracts iris feature points using a Gabor filter. Regarding document information acquisition, images of the bid documents are acquired using a scanner or high-resolution camera, and OCR technology (such as the Tesseract OCR engine) is used to extract text information. This is then combined with NLP technology (such as the spaCy library) to parse the text content and detect logical contradictions, extracting key information such as company name, project experience, and qualification certificates, and performing logical consistency verification.

[0070] Example 2 In some implementations, the edge layer performs multimodal authentication and intelligent bid parsing. Specifically, this includes the following steps: First, the biometric information of the bidder, including facial images, fingerprint images, and iris images, collected by the perception layer, is transmitted to the edge layer device. The edge layer employs multimodal fusion verification logic to comprehensively process the results of face recognition, fingerprint recognition, and iris recognition. Specifically, face recognition uses the OpenCV algorithm for facial feature point detection and extraction, fingerprint recognition uses the Minutiae matching algorithm for fingerprint feature point extraction, and iris recognition uses a Gabor filter for iris feature point extraction. Subsequently, the extracted biometrics are compared with pre-registered feature information in the database, the matching degree of each modality is calculated, and a weighted comprehensive score is applied to the matching degree according to set weight coefficients to determine the authenticity of the bidder's identity.

[0071] Simultaneously, intelligent parsing of the bid documents is performed at the edge layer. Images of the bid documents captured by scanners or high-resolution cameras are used to extract text content using OCR technology (such as the Tesseract OCR engine), and NLP technology (such as the spaCy library) is employed to detect logical contradictions and extract key information from the text content. Key information includes company name, project experience, qualification certificates, etc., and further logical consistency checks are performed. If logical contradictions or inconsistencies in key information are detected in the text content, an anomaly alert is generated and fed back to the staff at the bid opening site.

[0072] The edge layer provides real-time feedback of multimodal authentication results and intelligent tender document parsing results to on-site staff, ensuring the real-time and dynamic nature of the verification process. Simultaneously, the edge layer uploads preliminary verification results to the cloud layer for use in verifying historical data consistency.

[0073] Example 3 In some implementations, the cloud layer's verification of historical data consistency includes the following steps: First, the biometric information and document information of the bidders collected by the perception layer are uploaded to the cloud server and compared with historical data stored in the cloud. Specifically, the Levenshtein distance algorithm is used to calculate the similarity of the text content to determine whether there are any discrepancies between the information submitted by the current bidder and the historical records. If the similarity is lower than a preset threshold, it is determined to be abnormal information, and an anomaly marker is generated. Simultaneously, the cloud layer also verifies the consistency of the bidder's identity by comparing the bidder's biometric data (such as face, fingerprint, iris) with historical registration data. For contradictory or abnormal data, the cloud system will trigger an early warning mechanism and feed back the relevant results to the edge layer and smart contract module for further processing and evidence preservation. Furthermore, the cloud layer also has a data archiving function to permanently store the original data and comparison results from all verification processes for subsequent auditing and traceability.

[0074] Example 4 In some implementations, the smart contract automatically executes verification logic, and the process of storing the results on the blockchain includes the following steps: First, after completing multimodal identity verification and intelligent parsing of the tender document at the edge layer, the verification results are transmitted to the cloud layer for historical data consistency verification. The cloud layer compares the bidder information with historical data using a data comparison algorithm, calculates the similarity, and detects whether there are any anomalies or contradictions. If an anomaly is detected, the bidder information is marked as abnormal, and a corresponding verification result is generated.

[0075] Subsequently, based on the verification results returned by the cloud layer, the smart contract automatically executes the preset verification logic, including a comprehensive score for multimodal identity verification, detection of logical contradictions in the tender document content, and verification of the consistency of historical data. During execution, the smart contract integrates the processing results of all verification steps to generate the final verification conclusion.

[0076] After the verification results are generated, they are stored on the blockchain using blockchain technology. Specifically, using blockchain platforms that support smart contracts, such as Ethereum, the verification results are written as transaction data to the blockchain, ensuring their immutability and traceability. Simultaneously, the verification results are displayed in real-time on the terminal devices of staff at the bidding site for immediate viewing and confirmation. Furthermore, the system provides a historical record query function, allowing staff to access historical blocks on the blockchain to trace the results and timestamps of any verification process, thereby achieving transparency and credibility of information.

[0077] Example 5 In some implementations, data security and privacy protection are achieved through measures such as transmission encryption, storage encryption, anonymization, and access control. During data transmission, the TLS encryption protocol is used to encrypt all collected biometric information and file information, ensuring data security during transmission and preventing eavesdropping or tampering. During data storage, the AES encryption algorithm is used to encrypt sensitive information stored on local devices, edge computing nodes, and cloud servers, ensuring that even if the data is illegally obtained, its content cannot be directly read.

[0078] To protect the privacy of bidders, the system anonymizes collected sensitive information. For example, it uses the SHA-256 hash algorithm to transform bidders' identity information and biometric data, generating irreversible hash values ​​to replace the original sensitive data. This allows for information comparison and verification without revealing their true identities. Simultaneously, the system employs a strict access control mechanism, allowing only authorized personnel to access relevant sensitive information. Multi-level permission management ensures that users with different roles can only access data within their assigned scope of responsibility, preventing unauthorized access and data leaks.

[0079] In addition, the system was designed with full consideration of the security management of the entire data lifecycle. From collection, transmission, storage to processing and destruction, the principle of minimizing data exposure is followed to ensure that the privacy of bidders is effectively protected, while meeting the requirements of relevant laws and regulations on data security and privacy protection.

[0080] The sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0081] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of different embodiments are consistent and can be referenced by each other. The technical features of different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0082] Those skilled in the art will recognize that, based on the units and algorithm steps described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is implemented in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0083] The apparatus provided in the embodiments of this application will be described in detail below with reference to the accompanying drawings. The description of the apparatus embodiments corresponds to the description of the method embodiments. Therefore, for content not described in detail, please refer to the method embodiments above. For the sake of brevity, some content will not be repeated.

[0084] This application also provides a computer program product comprising instructions which, when executed by a computer, implement the methods described in the above method embodiments by the devices or apparatus described above.

[0085] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0086] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0087] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of apparatus or units may be electrical, mechanical, or other forms.

[0088] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0089] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0090] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0091] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for verifying information, characterized in that, include: Multimodal fusion verification of biometric information generates identity verification results; The file information is then parsed to extract key information; The authentication result and the key information are sent to the server so that the server can compare the authentication result and the key information with historical bidding data to generate authentication result and data verification result. The authentication result and the data verification result are comprehensively determined by a blockchain smart contract, and the final authentication result and the data verification result are stored on the blockchain for evidence.

2. The method according to claim 1, characterized in that, The biometric information includes at least two of the following: face, fingerprint, and iris. The step of performing multimodal fusion verification on the biometric information to generate an identity verification result includes: The collected biometric information is matched with the registration information in the database, and a comprehensive score of matching degree is calculated. The user's identity is verified based on the comprehensive score of the matching degree.

3. The method according to claim 1, characterized in that, The document information includes images of the tender documents; The step of parsing the file information and extracting key information includes: Text information was extracted from the tender document image using OCR. The extracted text information is subjected to logical contradiction detection using NLP. Once the logical contradiction detection is successful, the key information is obtained.

4. The method according to claim 1, characterized in that, Before performing multimodal fusion verification on the biometric information to generate an authentication result, the method further includes: The biometric information and file information are collected by the perception layer and transmitted to the edge layer. The step of performing multimodal fusion verification on the biometric information to generate an identity verification result includes: The biometric information is multimodal fusion verification is performed at the edge layer to generate an identity verification result.

5. The method according to claim 4, characterized in that, Sending the authentication result and the key information to the server includes: The authentication result and key information of the edge layer are sent to the server of the cloud layer.

6. The method according to any one of claims 1-4, characterized in that, The step of performing a comprehensive determination of the identity verification result and the data verification result through a blockchain smart contract, and storing the final identity verification result and the data verification result on the blockchain for evidence storage, includes: Based on the blockchain smart contract, the system automatically performs a comprehensive judgment of the identity verification result and the data verification result to generate the target verification result; The verification results of the target will be stored on the blockchain using blockchain technology.

7. An information verification device, characterized in that, include: The generation unit is used to perform multimodal fusion verification of biometric information to generate identity verification results; The extraction unit is used to parse file information and extract key information; A sending unit is used to send the authentication result and the key information to the server, so that the server can perform a consistency comparison between the authentication result and the key information and historical bidding data, and generate an authentication result and a data verification result. The determination unit is used to perform a comprehensive determination of the identity verification result and the data verification result through a blockchain smart contract, and to store the final identity verification result and the data verification result on the blockchain for evidence.

8. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.

9. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method according to any one of claims 1-6.

Images