A valuable item security encryption and traceability system

Abstract

The present invention relates to the technical field of secure encryption and traceability, and discloses a secure encryption and traceability system for precious items, including: constructing a blockchain for secure encryption and traceability of precious items by using a blockchain modeling method based on the precious item transaction chain; collecting identity data of precious item transaction users; extracting voice features and lip features from the identity data, and sending the voice features to the blockchain consensus node if the voice features and lip features match successfully; uploading transaction proof data, and the blockchain consensus node conducts consensus on the uploaded transaction proof data. If the consensus is passed, the transaction proof data is encrypted and stored in the blockchain node corresponding to the precious item transaction user; conducting transaction traceability of precious items according to the transaction vouchers in the blockchain node. The present invention stores precious item information based on blockchain technology to achieve encrypted traceability, adds identity authentication technology based on voice signals and lip movements, reduces invalid calculations, and improves user authentication efficiency and security.

Description

Technical Field

[0001] The present invention relates to the technical field of traceability of valuable items, and particularly to a secure encryption traceability system for valuable items. Background Art

[0002] Traditional valuable item storage systems based on identity authentication have data security problems such as data loss and tampering. Data loss and tampering of the central server caused by network security will seriously affect the security of valuable item storage. On the other hand, increasingly frequent and complex network attacks are likely to crack the encryption key, resulting in the leakage of valuable item information. To address this problem, this patent stores valuable item traceability information based on blockchain technology, encrypts and transmits valuable item information through operations such as exclusive OR and bit rotation to ensure the privacy and security of valuable items, and adds an identity authentication technology based on voice signals and lip movements to reduce invalid calculations and improve user authentication efficiency and security. Summary of the Invention

[0003] In view of this, the present invention provides a secure encryption traceability method for valuable items, aiming to construct a blockchain for secure encryption traceability of valuable items based on a blockchain modeling method for the valuable item transaction chain, use the blockchain to achieve decentralized encrypted storage of valuable item traceability information, propose an identity authentication strategy based on user voice signals and lip movement features, and improve user authentication security through dual authentication.

[0004] To achieve the above object, a secure encryption traceability method for valuable items provided by the present invention includes the following steps:

[0005] S1: Construct a blockchain for secure encryption traceability of valuable items by using a blockchain modeling method based on the valuable item transaction chain, where the blockchain allocates blockchain nodes to users participating in the production and transaction of valuable items, and users complete identity registration at the blockchain nodes;

[0006] S2: Collect the identity data of valuable item transaction users, where the identity data includes voice data and the corresponding lip movement data, and the valuable item transaction users are users participating in the production and transaction of valuable items;

[0007] S3: Extract voice features from the voice data by using an improved voice feature extraction algorithm, and extract lip features from the lip movement data by using a lip feature extraction algorithm, match the voice features and lip features of the valuable item transaction users, if the match is successful, indicating that the two come from the same user, then send the voice features to the blockchain consensus node;

[0008] S4: The user of the valuable item transaction uploads the transaction proof data, and the blockchain consensus nodes conduct consensus on the uploaded transaction proof data. If the consensus is passed, the transaction proof data is encrypted and stored in the blockchain node corresponding to the valuable item transaction user, where the transaction proof data is the transaction voucher between the current valuable item transaction user and the upstream user;

[0009] S5: Conduct the transaction traceability of valuable items based on the transaction vouchers in the blockchain nodes.

[0010] As a further improvement method of the present invention:

[0011] Optionally, in the step S1 of constructing a blockchain for the secure encryption and traceability of valuable items, it includes:

[0012] Construct a valuable item transaction chain, and the nodes of the constructed valuable item transaction chain include valuable item producers, valuable item traders, and valuable item owners;

[0013] The valuable item producers are responsible for completing the production stage of valuable items, including manufacturing, processing, and packaging, where the set of valuable item producers is , is the manufacturer of valuable items, is the processor of valuable items, is the packager of valuable items;

[0014] The valuable item traders are the historical owners after the production of valuable items, where the set of valuable item traders is , is the (n - 4)th owner of valuable items;

[0015] The valuable item owner is the current owner of valuable items;

[0016] Allocate blockchain nodes to the users in the user node set of the valuable item transaction chain. The users upload their voice data and electronic signatures to complete identity registration. Among them, adjacent blockchain nodes store the transaction vouchers recording the transactions between the two parties. The total number of nodes in the blockchain is n. Then the set of blockchain nodes allocated to the users in the user node set of the valuable item transaction chain is:

[0017] ;

[0018] Among them:

[0019] is the blockchain node allocated to the valuable item owner ;

[0020] The transaction voucher records the completion time, completion location, item number, and the electronic signatures of both parties; if a new precious item transaction is added to the precious item transaction chain, the owner of the precious item needs to upload the transaction voucher to the consensus nodes of the blockchain, and after viewing the transaction voucher, the consensus nodes add blockchain nodes .

[0021] Optionally, in step S2, the identity data of the precious item transaction user is collected, where the identity data includes voice data and the corresponding lip movement data, including:

[0022] Taking the users in the precious item transaction chain as precious item transaction users, when the i-th user in the precious item transaction chain completes a transaction and needs to upload the transaction voucher for the precious item transaction, the system terminal collects the identity data of the precious item transaction user, where the identity data includes voice data and the corresponding lip movement data, then the identity data of the i-th user collected in the precious item transaction chain is:

[0023] ;

[0024] ;

[0025] Where:

[0026] is the voice data of the i-th user collected in the precious item transaction chain, is the user voice signal collected at the initial moment of the collection, is the user voice signal collected at the cut-off moment of the collection, then the collection time range of the user data is ;

[0027] is the lip movement data of the i-th user collected in the precious item transaction chain, is the user lip movement image collected at the initial moment of the collection, is the user lip movement image collected at the cut-off moment of the collection.

[0028] Optionally, in step S3, an improved voice feature extraction algorithm is used to extract voice features from the voice data, including:

[0029] For the collected user voice data at any moment in the , a discrete speech signal is obtained through discrete time-domain sampling, and the discrete speech signal is subjected to short-time Fourier transform processing. The formula for the short-time Fourier transform processing is: ;

[0030] Where:

[0031] is a time-domain sampling point;

[0032] r is the length of the speech signal;

[0033] is the discrete speech signal after discrete time-domain sampling;

[0034] is the window sequence;

[0035] is the speech signal of the short-time Fourier transform result;

[0036] The short-time Fourier transform result is subjected to discrete Fourier transform processing to obtain the discrete Fourier transform result :

[0037] ;

[0038] Extract the energy spectrum in the discrete Fourier transform result as the speech feature of the speech signal :

[0039] ;

[0040] Where:

[0041] is the calculation formula for the conjugate value;

[0042] Perform the above feature extraction on the speech signals at all times to obtain the speech feature vector of the user speech data:

[0043] ;

[0044] Upload the speech feature vector of the user speech data to the blockchain node registered by the valuable item trading user.

[0045] Optionally, in the S3 step, a lip feature extraction algorithm is used to extract lip features from the lip movement data, including:

[0046] For the collected user lip movement data , use the lip feature extraction algorithm to extract lip features from . The extraction process of the lip features is as follows:

[0047] 1) For the user's lip movement data at any moment in the lip movement image , use the lip region localization algorithm based on color components to complete the lip region localization in the image. For any pixel in the lip movement image , weight the G-channel color component based on the B-channel color component and the R-channel color component. If the weighted result is greater than the threshold , it indicates that the pixel is a lip region pixel. The weighting formula is:

[0048] ;

[0049] where:

[0050] is the weighted result of the pixel;

[0051] are the values of the pixel in the color channel components respectively;

[0052] is the weight, which is set to 0.2;

[0053] 2) Use the OSTU binarization method to segment the foreground and background of the lip region, and take the segmented foreground region as the target lip region;

[0054] 3) Generate the connected components of the binarized target lip region. Set the coordinate origin in the target lip region, establish a coordinate system based on the coordinate origin, and construct a lip edge parabola as the lip feature:

[0055] ;

[0056] ;

[0057] where:

[0058] is the upper lip edge parabola of the lip movement image ;

[0059] is the lower lip edge parabola of the lip movement image ;

[0060] is the height of the region above the target lip, is the height of the region below the target lip;

[0061] w is the width of the lip in the target lip region;

[0062] x is the X-axis coordinate point of the parabola;

[0063] 4) Perform the above feature extraction on all lip movement images in the user's lip movement data to obtain the user's lip feature vector:

[0064] ;

[0065] Wherein:

[0066] is the lip feature of the lip movement image ;

[0067] Upload the lip feature vector of the user's lip movement data to the blockchain node registered by the valuable item trading user.

[0068] Optionally, in the step S4, the voice feature and the lip feature of the valuable item trading user are matched. If the match is successful, the voice feature is sent to the blockchain consensus node, including:

[0069] After receiving the voice feature vector and the lip feature vector, the blockchain node matches the voice feature and the lip feature at any same moment, that is, matches the lip feature at any moment and the voice feature . The feature matching method is the cosine similarity calculation method. If the energy of the voice feature is high and the lip edge of the lip feature is large at the same time, the cosine similarity calculation result is high. Set the cosine similarity threshold. If the cosine similarity calculation results of 80% of the features in the voice feature vector and the lip feature vector are higher than the cosine similarity threshold, it means the match is successful and the two come from the same user, then the voice feature is sent to the blockchain consensus node;

[0070] The selection method of the blockchain consensus node is:

[0071] Each blockchain node votes for the other blockchain nodes, and the selected node will generate a credit score. The calculation formula of the credit score is:

[0072] ;

[0073] Wherein:

[0074] represents the number of votes obtained by the blockchain node;

[0075] represents the total number of blockchain nodes;

[0076] Select the blockchain nodes with the highest credit scores as the consensus nodes.

[0077] Optionally, in step S4, the blockchain consensus nodes perform consensus on the uploaded transaction proof data and perform encrypted storage, including:

[0078] When the uploaded user identity characteristics match successfully, the blockchain consensus nodes calculate the cosine similarity between the voice characteristics and the user's registered voice. If the similarity between the two is higher than 0.85, the user can use the terminal device to upload the transaction proof data to the consensus nodes, where the transaction proof data is the transaction voucher between the current precious item trading user and the upstream user. The blockchain performs consensus on the received transaction proof data, and the consensus process is as follows:

[0079] 1) The consensus nodes check whether the transaction proof data is legal, including whether the signature is complete and whether the data format is correct, and simulate the transaction locally. If the transaction is unqualified, the consensus nodes will reject the uploaded transaction proof data and feedback the information of rejecting the transaction to the user;

[0080] 2) After the transaction proof data to be uploaded is confirmed to be correct, the consensus nodes perform consensus on the transaction proof data uploaded by the terminal device according to the pre-set negotiation consistency algorithm;

[0081] 3) If the consensus nodes reach a consensus, the transaction proof data uploaded by the user will be added to the blockchain node registered by the user and a message will be broadcast to the entire network; if the consensus is not reached under normal circumstances of the nodes, the transaction proof data will be rejected and the information of rejecting the transaction will be feedback to the user;

[0082] When the consensus nodes reach a consensus, the blockchain encryption algorithm is used to encrypt the transaction proof data uploaded by the user. The encryption process of the transaction proof data is as follows:

[0083] 1) The consensus nodes generate a random number , and calculate the verification code of the precious item number and the random number , where ID is the number of the precious item;

[0084] 2) The consensus nodes send the generated verification code to the blockchain node, and the blockchain node generates an encryption key based on the timestamp of the transaction completion , where is the timestamp information of the transaction completion;

[0085] 3) Use the encryption key to encrypt the transaction proof data uploaded by the user, and the encryption result is:

[0086] ;

[0087] Where:

[0088] is a rotation function, indicating that is rotated to the right by characters, is the number of characters of the valuable item number, and is the transaction proof data uploaded by the user;

[0089] 4) is the encryption result of the transaction proof data, and the encryption result is stored in the blockchain node.

[0090] In an embodiment of the present invention, security analysis is performed by eavesdropping on the constructed blockchain. The attacker of the eavesdropping attack can intercept the communication information sent between blockchain nodes. The communication information may contain plaintext data or encrypted information. If the attacker obtains the key information of the system through analysis, it means that the communication process is insecure. For the encryption storage solution proposed in this solution, when eavesdropped, it will not disclose the key information of the system, such as valuable item numbers, encryption keys, etc. During the entire encryption process, the key information will not be transmitted in plaintext in the channel. In the communication channel, the blockchain node only transmits random numbers, and the encryption key is not transmitted in the channel. It is difficult for the attacker to analyze the encryption key based on the eavesdropped information to calculate other key information, and it is also impossible to tamper with the corresponding information to cause legitimate nodes in the system to trust forged information.

[0091] Optionally, in the step S5, the traceability of the valuable item transaction is performed by viewing the transaction vouchers stored in the blockchain node, including:

[0092] The process of the traceability of the valuable item transaction is as follows:

[0093] When the traceability of the valuable item transaction is required, the blockchain node initiating the transaction traceability performs identity authentication by inputting identity data;

[0094] After the authentication is passed, the blockchain node initiating the transaction traceability sends a traceability request to the consensus node. After passing the consensus, the blockchain node initiating the transaction traceability can view the transaction vouchers stored in the traceability blockchain node to complete the traceability of the valuable item transaction.

[0095] To solve the above problems, the present invention also provides a valuable item security encryption traceability system, which includes:

[0096] A blockchain construction module, which is used to construct a blockchain for valuable item security encryption traceability by using a blockchain modeling method based on the valuable item transaction chain;

[0097] A data acquisition and processing module is used to acquire the identity data of users in precious item transactions. The identity data includes voice data and corresponding lip movement data. An improved voice feature extraction algorithm is used to extract voice features from the voice data, and a lip feature extraction algorithm is used to extract lip features from the lip movement data. The voice features and lip features of the precious item transaction users are matched. If the match is successful, indicating that the two come from the same user, the voice features are sent to the blockchain consensus node;

[0098] A precious item traceability device is used for precious item transaction users to upload transaction proof data. The blockchain consensus node conducts consensus on the uploaded transaction proof data. If the consensus is passed, the transaction proof data is encrypted and stored in the blockchain node corresponding to the precious item transaction user. The transaction proof data is the transaction voucher between the current precious item transaction user and the upstream user, and the transaction of the precious item is traced according to the transaction voucher in the blockchain node.

[0099] To solve the above problems, the present invention also provides an electronic device, which includes:

[0100] A memory that stores at least one instruction; and

[0101] A processor that executes the instructions stored in the memory to implement the above-mentioned precious item security encryption and traceability method.

[0102] To solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored, and the at least one instruction is executed by a processor in an electronic device to implement the above-mentioned precious item security encryption and traceability method.

[0103] Compared with the prior art, the present invention proposes a precious item security encryption and traceability method, which has the following advantages:

[0104] First, the present solution proposes a precious item security encryption and traceability method based on blockchain. By allocating blockchain nodes to users in the user node set of the precious item transaction chain, users upload their own voice data and electronic signatures to complete identity registration. The adjacent blockchain nodes store the transaction vouchers recording the transactions between the two parties. When the user identity authentication is passed, the user can use the terminal device to upload the transaction proof data to the consensus node. The transaction proof data is the transaction voucher between the current precious item transaction user and the upstream user. The blockchain conducts consensus on the received transaction proof data. When the consensus node reaches a consensus, the blockchain encryption algorithm is used to encrypt the transaction proof data uploaded by the user. The encryption process of the transaction proof data is as follows: The consensus node generates a random number , calculates the verification code of the precious item number and the random number , where ID is the serial number of the valuable item; the consensus node sends the generated verification code to the blockchain node, and the blockchain node generates an encryption key based on the timestamp of the completed transaction , where is the timestamp information of the completed transaction; the transaction proof data uploaded by the user is encrypted using the encryption key, and the encryption result is:

[0105] ;

[0106] Where: is the rotation function, represents rotated to the right by characters, is the number of characters of the valuable item serial number, is the transaction proof data uploaded by the user; is the encryption result of the transaction proof data, and the encryption result is stored in the blockchain node. Through a security analysis of eavesdropping attacks on the constructed blockchain, the attacker of the eavesdropping attack can intercept the communication information sent between blockchain nodes. The communication information may contain plaintext data or encrypted information. If the attacker obtains the key information of the system through analysis, it means that the communication process is insecure. For the encryption storage scheme proposed in this solution, when eavesdropped, it will not disclose the key information of the system, such as the valuable item serial number, encryption key, etc. During the entire encryption process, the key information will not be transmitted in plaintext in the channel. In the communication channel, the blockchain node only transmits random numbers, and the encryption key is not transmitted in the channel. It is difficult for the attacker to analyze the encryption key based on the eavesdropped information to calculate other key information, and it is also impossible to tamper with the corresponding information to cause legitimate nodes in the system to trust forged information. When it is necessary to trace the transaction of valuable items, the blockchain node initiating the transaction traceability performs identity authentication by inputting identity data; after verification, the blockchain node initiating the transaction traceability sends a traceability request to the consensus node. After passing the consensus, the blockchain node initiating the transaction traceability can view the transaction vouchers stored in the traceability blockchain node to complete the transaction traceability of the valuable item.

[0107] At the same time, this solution proposes a user identity authentication method based on user voice data and lip movement data. By collecting the energy spectrum of the voice signal as the voice feature, for the collected user lip movement data , using the lip feature extraction algorithm to extract lip features from , the extraction process of the lip features is as follows: for the lip movement data of the user at any moment of the lip movement image , using the lip region localization algorithm based on color components to complete the lip region localization in the image. For the lip movement image For any pixel in, the G-channel color component is weighted based on the B-channel color component and the R-channel color component. If the weighted result is greater than the threshold , it indicates that the pixel is a pixel in the lip region. The weighting formula is:

[0108] ;

[0109] Where: is the weighted result of the pixel; is the value of the pixel in the color channel component respectively; is the weight, which is set to 0.2. The OSTU binarization method is used to segment the foreground and background of the lip region, and the segmented foreground region is used as the target lip region; the connected components of the binarized target lip region are generated. The coordinate origin is set in the target lip region, a coordinate system is established based on the coordinate origin, and a lip edge parabola is constructed as the lip feature:

[0110] ;

[0111] ;

[0112] Where: is the upper lip edge parabola of the lip motion image ; is the lower lip edge parabola of the lip motion image ; is the height of the area above the target lip, is the height of the area below the target lip; w is the width of the lip in the target lip region; x is the X-axis coordinate point of the parabola; for all lip motion images in the user's lip motion data , the above features are extracted to obtain the user's lip feature vector:

[0113] ;

[0114] Where: is the lip feature of the lip motion image ; The lip feature vector of the user's lip motion data is uploaded to the blockchain node registered by the valuable item trading user. After receiving the voice feature vector and the lip feature vector, the blockchain node matches the voice feature and the lip feature at any same moment, that is, matches the lip feature at any moment and the voice feature , the feature matching method is the cosine similarity calculation method. A cosine similarity threshold is set. If the calculation results of the cosine similarities of 80% of the features in the voice feature vector and the lip feature vector are higher than the cosine similarity threshold, it indicates a successful match, and the two are from the same user. Then the voice feature is sent to the blockchain consensus node; the blockchain consensus node calculates the cosine similarity between the voice feature and the user's registered voice. If the similarity between the two is higher than 0.85, the user identity authentication is passed. Compared with the traditional solution, this solution combines the amplitude of the lip edge and the energy of the voice signal at the same moment. If the energy of the voice feature is high and the lip edge of the lip feature is large at the same time, the lip feature and the voice feature are from the same user. Since there may be an out-of-sync phenomenon between the sound and the picture in the video recording result, the problem of using recording or video equipment for identity authentication is avoided, and the user authentication efficiency and security are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0115] Figure 1 FIG. is a schematic flowchart of a method for securely encrypting and tracing valuable items provided by an embodiment of the present invention;

[0116] Figure 2 FIG. is a functional module diagram of a valuable item security encryption and traceability system provided by an embodiment of the present invention;

[0117] Figure 3 FIG. is a schematic structural diagram of an electronic device for implementing the method for securely encrypting and tracing valuable items provided by an embodiment of the present invention.

[0118] The implementation, functional features, and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0119] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0120] An embodiment of the present application provides a method for securely encrypting and tracing valuable items. The execution subject of the method for securely encrypting and tracing valuable items includes, but is not limited to, at least one of electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided by this embodiment of the present application. In other words, the method for securely encrypting and tracing valuable items can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to: a single server, a server cluster, a cloud server, or a cloud server cluster, etc.

[0121] Embodiment 1:

[0122] S1: Construct a blockchain for secure encrypted traceability of valuables using a blockchain modeling method based on the valuables trading chain. The blockchain assigns blockchain nodes to users participating in the production and trading of valuables, and users complete identity registration at the blockchain nodes.

[0123] In the S1 step, constructing a blockchain for secure encrypted traceability of valuables includes:

[0124] Construct a valuables trading chain. The nodes of the constructed valuables trading chain include valuables producers, valuables traders, and valuables owners;

[0125] The valuables producers are responsible for completing the production stage of valuables, including manufacturing, processing, and packaging. The set of valuables producers is , is the manufacturer of valuables, is the processor of valuables, is the packager of valuables;

[0126] The valuables traders are the historical owners after the production of valuables is completed. The set of valuables traders is , is the (n - 4)th owner of valuables;

[0127] The valuables owner is the current owner of valuables;

[0128] Assign blockchain nodes to the user nodes set in the valuables trading chain. Users upload their voice data and electronic signatures to complete identity registration. The adjacent blockchain nodes store the transaction vouchers recording the transactions between the two parties. The total number of nodes in the blockchain is n. Then the set of blockchain nodes assigned to users in the user nodes set of the valuables trading chain is:

[0129] ;

[0130] Where:

[0131] is the blockchain node assigned to the valuables owner ;

[0132] The transaction voucher records the completion time, completion location, item number, and the electronic signatures of both parties. If a new valuables transaction is added to the valuables trading chain, the valuables owner needs to upload the transaction voucher to the consensus nodes of the blockchain. After viewing the transaction voucher, the consensus nodes add blockchain nodes .

[0133] S2: Collect the identity data of users in precious item transactions, where the identity data includes voice data and corresponding lip movement data, and the users in precious item transactions are those who participate in the production and transactions of precious items.

[0134] In the step S2 of collecting the identity data of users in precious item transactions, where the identity data includes voice data and corresponding lip movement data, it includes:

[0135] Regarding the users in the precious item transaction chain as the users in precious item transactions, when the i-th user in the precious item transaction chain completes a transaction and needs to upload the transaction certificate of the precious item transaction, the system terminal collects the identity data of the user in the precious item transaction, where the identity data includes voice data and corresponding lip movement data. Then, the identity data of the i-th user in the precious item transaction chain collected is:

[0136] ;

[0137] ;

[0138] Where:

[0139] is the voice data of the i-th user in the precious item transaction chain collected, is the user voice signal at the initial moment collected, is the user voice signal at the cut-off moment collected. Then, the acquisition time range of the user data is ;

[0140] is the lip movement data of the i-th user in the precious item transaction chain collected, is the user lip movement image at the initial moment collected, is the user lip movement image at the cut-off moment collected.

[0141] It should be noted that after the two parties in the precious item transaction complete the transaction, they need to fill in the transaction certificate. At this time, the precious item completes the transaction transfer. After the transaction certificate is filled in, it needs to be uploaded to a third-party institution for authentication. After the authentication is completed, it can be uploaded by the user in the precious item transaction to the corresponding blockchain node for storage.

[0142] S3: Extract speech features from the speech data using an improved speech feature extraction algorithm, and extract lip features from the lip movement data using a lip feature extraction algorithm. Match the speech features and lip features of the valuable item transaction user. If the match is successful, indicating that the two are from the same user, send the speech features to the blockchain consensus node.

[0143] In the S3 step, extracting speech features from the speech data using an improved speech feature extraction algorithm includes:

[0144] For the collected user speech data at any moment of the speech signal , obtain a discrete speech signal through discrete time-domain sampling, and perform short-time Fourier transform processing on the discrete speech signal. The formula for the short-time Fourier transform processing is: ;

[0145] where:

[0146] is the time-domain sampling point;

[0147] r is the length of the speech signal;

[0148] is the discrete speech signal after discrete time-domain sampling;

[0149] is the window sequence;

[0150] is the speech signal of the short-time Fourier transform result;

[0151] Perform discrete Fourier transform processing on the short-time Fourier transform result to obtain the discrete Fourier transform result :

[0152] ;

[0153] Extract the energy spectrum in the discrete Fourier transform result as the speech feature of the speech signal : :

[0154] ;

[0155] where:

[0156] is the calculation formula for the conjugate value;

[0157] Perform the above feature extraction on the speech signals at all moments to obtain the speech feature vector of the user speech data:

[0158] ;

[0159] Upload the voice feature vector of the user voice data to the blockchain node registered by the valuable item trading user.

[0160] In the step S3, the lip feature extraction algorithm is used to extract lip features from the lip motion data, including:

[0161] For the collected user lip motion data , use the lip feature extraction algorithm to extract lip features from . The extraction process of the lip features is as follows:

[0162] 1) For the lip motion image at any moment in the user lip motion data , use the lip region localization algorithm based on color components to complete the lip region localization in the image. For any pixel in the lip motion image , weight the G channel color component based on the B color channel component and the R channel color component. If the weighted result is greater than the threshold , it means that the pixel is a lip region pixel. The weighted formula is: ;

[0163] ;

[0164] Where:

[0165] is the weighted result of the pixel;

[0166] are the values of the pixel in the color channel components respectively;

[0167] is the weight, which is set to 0.2;

[0168] 2) Use the OSTU binarization method to segment the foreground and background of the lip region, and take the segmented foreground region as the target lip region;

[0169] 3) Generate the connected components of the binarized target lip region, set the coordinate origin in the target lip region, establish a coordinate system based on the coordinate origin, and construct a lip edge parabola as the lip feature:

[0170] ;

[0171] ;

[0172] Where:

[0173] is the upper lip edge parabola of the lip movement image ;

[0174] is the lower lip edge parabola of the lip movement image ;

[0175] is the height of the area above the target lip is the height of the area below the target lip;

[0176] w is the width of the lip in the target lip area;

[0177] x is the X-axis coordinate point of the parabola;

[0178] 4) Perform the above feature extraction on all lip movement images in the user's lip movement data to obtain the user's lip feature vector:

[0179] ;

[0180] where:

[0181] is the lip feature of the lip movement image ;

[0182] Upload the lip feature vector of the user's lip movement data to the blockchain node registered by the valuable item trading user.

[0183] S4: The valuable item trading user uploads the transaction proof data, and the blockchain consensus node conducts consensus on the uploaded transaction proof data. If the consensus is passed, the transaction proof data is encrypted and stored in the blockchain node corresponding to the valuable item trading user, where the transaction proof data is the transaction voucher between the current valuable item trading user and the upstream user.

[0184] In the S4 step, the voice feature and the lip feature of the valuable item trading user are matched. If the match is successful, the voice feature is sent to the blockchain consensus node, including:

[0185] After receiving the voice feature vector and the lip feature vector, the blockchain node matches the voice feature and the lip feature at any same moment, that is, matches the lip feature at any moment and the voice feature , the feature matching method is the cosine similarity calculation method. If the energy of the voice feature is high and the lip edge of the lip feature is large at the same time, the cosine similarity calculation result is high. A cosine similarity threshold is set. If the cosine similarity calculation results of 80% of the features in the voice feature vector and the lip feature vector are higher than the cosine similarity threshold, it indicates a successful match and the two come from the same user. Then the voice feature is sent to the blockchain consensus node;

[0186] The selection method of the blockchain consensus node is as follows:

[0187] Each blockchain node votes for the other blockchain nodes. The selected node will generate a credit score. The calculation formula of the credit score is:

[0188] ;

[0189] Where:

[0190] represents the number of votes obtained by the blockchain node;

[0191] represents the total number of blockchain nodes;

[0192] Select the blockchain nodes with the highest credit scores as consensus nodes.

[0193] In the S4 step, the blockchain consensus node conducts consensus on the uploaded transaction proof data and encrypts and stores it, including:

[0194] When the uploaded user identity features match successfully, the blockchain consensus node calculates the cosine similarity between the voice feature and the user's registered voice. If the similarity between the two is higher than 0.85, the user can use the terminal device to upload the transaction proof data to the consensus node. The transaction proof data is the transaction voucher between the current valuable item trading user and the upstream user. The blockchain conducts consensus on the received transaction proof data. The consensus process is as follows:

[0195] 1) The consensus node checks whether the transaction proof data is legal, including whether the signature is complete and whether the data format is correct, and simulates the transaction locally. If the transaction is unqualified, the consensus node will reject the uploaded transaction proof data and feedback the information of rejecting the transaction to the user;

[0196] 2) After the transaction proof data to be uploaded is confirmed to be correct, the consensus node conducts consensus on the transaction proof data uploaded by the terminal device according to the pre-set negotiation consistency algorithm;

[0197] 3) If the consensus nodes reach a consensus, the transaction proof data uploaded by the user is added to the blockchain node registered by the user, and a message is broadcast to the entire network; if the consensus is not reached under normal circumstances of the nodes, the transaction proof data is rejected, and the information on the rejected transaction is fed back to the user;

[0198] When the consensus nodes reach a consensus, the transaction proof data uploaded by the user is encrypted using the blockchain encryption algorithm. The encryption process of the transaction proof data is as follows:

[0199] 1) The consensus node generates a random number , calculates the verification code of the valuable item number and the random number , where ID is the number of the valuable item;

[0200] 2) The consensus node sends the generated verification code to the blockchain node, and the blockchain node generates an encryption key based on the timestamp of the completed transaction , where is the timestamp information of the completed transaction;

[0201] 3) The transaction proof data uploaded by the user is encrypted using the encryption key, and the encryption result is:

[0202] ;

[0203] Among them:

[0204] is the rotation function, means to rotate to the right by characters, is the number of characters of the valuable item number, is the transaction proof data uploaded by the user;

[0205] 4) is the encryption result of the transaction proof data, and the encryption result is stored in the blockchain node.

[0206] In one embodiment of the present invention, security analysis is performed through a wiretapping attack on the constructed blockchain. The attacker of the wiretapping attack can intercept the communication information sent between blockchain nodes. The communication information may contain plaintext data or encrypted information. If the attacker obtains the key information of the system through analysis, it means that the communication process is insecure. For the encryption storage scheme proposed in this solution, when wiretapped, it will not disclose the key information of the system, such as valuable item numbers, encryption keys, etc. During the entire encryption process, the key information is not transmitted in plaintext over the channel. In the communication channel, the blockchain nodes only transmit random numbers, and the encryption key is not transmitted over the channel. It is difficult for the attacker to analyze the encryption key based on the wiretapped information to calculate other key information, and it is also impossible to tamper with the corresponding information to cause legitimate nodes in the system to trust forged information.

[0207] S5: Conduct transaction traceability of valuable items based on the transaction vouchers in the blockchain nodes.

[0208] In the S5 step, the transaction traceability of valuable items is conducted by viewing the transaction vouchers stored in the blockchain nodes, including:

[0209] The process of the transaction traceability of valuable items is as follows:

[0210] When transaction traceability of valuable items is required, the blockchain node initiating the transaction traceability performs identity authentication by inputting identity data;

[0211] After authentication is passed, the blockchain node initiating the transaction traceability sends a traceability request to the consensus node. After consensus is reached, the blockchain node initiating the transaction traceability can view the transaction vouchers stored in the traceability blockchain nodes to complete the transaction traceability of valuable items.

[0212] Embodiment 2:

[0213] As Figure 2 shown, it is a functional module diagram of a valuable item security encryption traceability system provided by an embodiment of the present invention, which can implement the valuable item encryption traceability method in Embodiment 1.

[0214] The valuable item security encryption traceability system 100 of the present invention can be installed in an electronic device. According to the implemented functions, the valuable item security encryption traceability system may include a blockchain construction module 101, a data acquisition and processing module 102, and a valuable item traceability device 103. The modules of the present invention can also be referred to as units, which refer to a series of computer program segments that can be executed by the processor of the electronic device and can complete fixed functions, and are stored in the memory of the electronic device.

[0215] The blockchain construction module 101 is used to construct a blockchain for secure encrypted traceability of valuables by using a blockchain modeling method based on the valuable item transaction chain;

[0216] The data acquisition and processing module 102 is used to acquire the identity data of the valuable item transaction user, where the identity data includes voice data and the corresponding lip movement data. An improved voice feature extraction algorithm is used to extract voice features from the voice data, and a lip feature extraction algorithm is used to extract lip features from the lip movement data. The voice features and lip features of the valuable item transaction user are matched. If the match is successful, it indicates that the two come from the same user, and then the voice features are sent to the blockchain consensus node;

[0217] The valuable item traceability device 103 is used for the valuable item transaction user to upload transaction proof data. The blockchain consensus node conducts consensus on the uploaded transaction proof data. If it passes the consensus, the transaction proof data is encrypted and stored in the blockchain node corresponding to the valuable item transaction user. The transaction proof data is the transaction voucher between the current valuable item transaction user and the upstream user, and the transaction traceability of the valuable item is carried out according to the transaction voucher in the blockchain node.

[0218] Specifically, each module in the valuable item secure encrypted traceability system 100 in the embodiment of the present invention adopts the same technical means as the Figure 1 valuable item secure encrypted traceability method described above and can produce the same technical effects, which will not be elaborated here.

[0219] Embodiment 3:

[0220] As Figure 3 shown, it is a schematic structural diagram of an electronic device for implementing the valuable item secure encrypted traceability method provided by an embodiment of the present invention.

[0221] The electronic device 1 may include a processor 10, a memory 11, and a bus, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as the valuable item secure encrypted traceability program 12.

[0222] Among them, the memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), magnetic memory, magnetic disk, optical disc, etc. The memory 11 can be an internal storage unit of the electronic device 1 in some embodiments, such as the mobile hard disk of the electronic device 1. The memory 11 can also be an external storage device of the electronic device 1 in some other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the electronic device 1. Further, the memory 11 can also include both the internal storage unit and the external storage device of the electronic device 1. The memory 11 can be used not only to store application software installed on the electronic device 1 and various types of data, such as the code of the valuable item security encryption and traceability program 12, etc., but also to temporarily store the data that has been output or will be output.

[0223] The processor 10 can be composed of integrated circuits in some embodiments. For example, it can be composed of a single packaged integrated circuit, or can also be composed of multiple integrated circuits with the same or different functions packaged together, including the combination of one or more Central Processing Units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips, etc. The processor 10 is the control core (Control Unit) of the electronic device, connecting all components of the entire electronic device through various interfaces and lines, and by running or executing programs or modules (such as the valuable item security encryption and traceability program) stored in the memory 11, and calling the data stored in the memory 11, to perform various functions of the electronic device 1 and process data.

[0224] The bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. The bus is set to realize the connection and communication between the memory 11 and at least one processor 10, etc.

[0225] Figure 3 Only the electronic device with components is shown, and those skilled in the art can understand that Figure 3The structure shown does not constitute a limitation on the electronic device 1, and it may include fewer or more components than those shown, or combine certain components, or have different component arrangements.

[0226] For example, although not shown, the electronic device 1 may further include a power source (such as a battery) for powering each component. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so as to implement functions such as charge management, discharge management, and power consumption management through the power management device. The power source may also include any components such as one or more DC or AC power sources, a recharge device, a power failure detection circuit, a power converter or inverter, and a power status indicator. The electronic device 1 may also include various sensors, a Bluetooth module, a Wi-Fi module, etc., which will not be elaborated here.

[0227] Furthermore, the electronic device 1 may further include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

[0228] Optionally, the electronic device 1 may further include a user interface. The user interface may be a display, an input unit (such as a keyboard), and optionally, the user interface may also be a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch liquid crystal display, and an OLED (Organic Light-Emitting Diode) toucher, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display the information processed in the electronic device 1 and to display a visual user interface.

[0229] It should be understood that the embodiments are only for illustration purposes and are not limited by this structure in the scope of the patent application.

[0230] The valuable item security encryption and traceability program 12 stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can implement:

[0231] Construct a blockchain for valuable item security encryption and traceability by using a blockchain modeling method based on the valuable item transaction chain;

[0232] Collect the identity data of valuable item transaction users;

[0233] Extract voice features from voice data using an improved voice feature extraction algorithm, and extract lip features from lip movement data using a lip feature extraction algorithm. Match the voice features and lip features of the user in the precious item transaction. If the match is successful, indicating that the two are from the same user, send the voice features to the blockchain consensus node;

[0234] The user in the precious item transaction uploads transaction proof data, and the blockchain consensus node conducts consensus on the uploaded transaction proof data. If the consensus is passed, encrypt and store the transaction proof data in the blockchain node corresponding to the user in the precious item transaction;

[0235] Conduct traceability of precious items based on the transaction vouchers in the blockchain node.

[0236] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to Figures 1 to 3 the description of the relevant steps in the corresponding embodiment, which will not be elaborated here.

[0237] It should be noted that the serial numbers of the above embodiments of the present invention are only for description and do not represent the superiority or inferiority of the embodiments. And the terms "including", "comprising" or any other variant thereof in this article are intended to cover a non-exclusive inclusion, so that a process, device, article or method including a series of elements not only includes those elements but also includes other elements not expressly listed, or also includes elements inherent to such process, device, article or method. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of another identical element in the process, device, article or method including the element.

[0238] Through the description of the above embodiments, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above and includes several instructions to enable a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in various embodiments of the present invention.

[0239] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A method for secure encryption and traceability of valuable items, characterized in that, The method includes: S1: Construct a blockchain for secure encrypted traceability of precious items using a blockchain modeling method based on the precious item trading chain. The blockchain assigns blockchain nodes to users participating in the production and trading of precious items, and users complete identity registration at the blockchain nodes. S2: Collect the identity data of precious item trading users, where the identity data includes voice data and the corresponding lip movement data. The precious item trading users are those participating in the production and trading of precious items. S3: Extract voice features from the voice data using an improved voice feature extraction algorithm, and extract lip features from the lip movement data using a lip feature extraction algorithm. Match the voice features and lip features of the precious item trading users. If the match is successful, indicating that they come from the same user, send the voice features to the blockchain consensus node. Extracting voice features from the voice data using an improved voice feature extraction algorithm includes: For the collected user voice data At any moment Of the voice signal , a discrete voice signal is obtained through discrete time-domain sampling, and the discrete voice signal is subjected to short-time Fourier transform processing. The formula for the short-time Fourier transform processing is: Where: is a time-domain sampling point; r is the length of the voice signal; is the discrete speech signal after discrete-time domain sampling; is a window sequence; is the short-time Fourier transform result of the voice signal; Perform discrete Fourier transform processing on the short-time Fourier transform result to obtain the discrete Fourier transform result : Extract the energy spectrum in the discrete Fourier transform result as the speech signal of the speech feature : Where: is the calculation formula for the conjugate value; Perform the above feature extraction on the voice signals at all times to obtain the voice feature vector of the user's voice data: Upload the voice feature vector of the user's voice data to the blockchain node registered by the precious item trading user. S4: The precious item trading user uploads transaction proof data, and the blockchain consensus node conducts consensus on the uploaded transaction proof data. If the consensus is passed, encrypt and store the transaction proof data in the blockchain node corresponding to the precious item trading user. The transaction proof data is the transaction voucher between the current precious item trading user and the upstream user. S5: Conduct transaction traceability of precious items based on the transaction vouchers in the blockchain node.

2. The method for secure encryption and traceability of valuable items according to claim 1, characterized in that, In the S1 step, constructing a blockchain for secure encrypted traceability of precious items includes: Construct a precious item trading chain. The nodes of the constructed precious item trading chain include precious item producers, precious item traders, and precious item owners. The producer of the valuable item is responsible for completing the production stage of the valuable item, including manufacturing, processing, and packaging, where the producers of valuable items are grouped as , is the manufacturer of the valuable item, is the processor of the valuable item, is the packager of the valuable item; The party involved in the transaction of the valuable item is the historical owner after the production of the valuable item is completed, and the set of parties involved in the transaction of the valuable item is , is the (n - 4)th owner of the valuable item; The owner of the valuable item is the current owner of the valuable item; Assign blockchain nodes to the user nodes in the precious item trading chain Users upload their own voice data and electronic signatures to complete identity registration. Adjacent blockchain nodes store transaction vouchers for recording bilateral transactions. The total number of nodes in the blockchain is n. Then, the set of blockchain nodes assigned to users in the user node set of the precious item trading chain is as follows: Where: The blockchain node allocated to the owner of valuable items ; The transaction voucher records the completion time, completion location, item number, and the electronic signatures of both parties; if a new valuable item transaction is added to the valuable item transaction chain, the owner of the valuable item is required to upload the transaction voucher to the consensus nodes of the blockchain, and the consensus nodes add blockchain nodes after viewing the transaction voucher .

3. The method for securely encrypting and tracing valuable items according to claim 1, characterized in that, In the S2 step, collecting the identity data of precious item trading users, where the identity data includes voice data and the corresponding lip movement data, includes: Take the users of the precious item trading chain as precious item trading users. When the i-th user in the precious item trading chain completes a transaction and needs to upload the transaction voucher of the precious item trading, the system terminal collects the identity data of the precious item trading user, where the identity data includes voice data and the corresponding lip movement data. Then, the identity data of the i-th user in the precious item trading chain collected is: Where: is the voice data of the i-th user in the collected valuable item transaction chain, is the initial moment collected of the user voice signal, is the cut-off moment collected of the user voice signal, then the acquisition time range of the user data is ; is the lip movement data of the i-th user in the collected precious item transaction chain, is the initial moment collected of the user's lip movement image, is the cut-off moment collected of the user's lip movement image.

4. The security encryption and traceability method for valuables according to claim 1, wherein In the S3 step, extracting lip features from the lip movement data using a lip feature extraction algorithm includes: For the collected user lip movement data , use the lip feature extraction algorithm to extract lip features from . The extraction process of the lip features is as follows: 1) For the user's lip movement data at any moment of the lip movement image , use the lip region localization algorithm based on color components to complete the lip region localization in the image. For any pixel in the lip movement image , weight the G-channel color component based on the B-channel color component and the R-channel color component. If the weighted result is greater than the threshold , it indicates that the pixel is a lip region pixel. The weighting formula is: Where: is the weighted result of the pixel; are the values of the pixel in the color channel components respectively; is the weight, which is set to 0.2; 2) Use the OSTU binarization method to segment the foreground and background of the lip region, and take the segmented foreground region as the target lip region. 3) Generate the connected components of the binarized target lip region, set the coordinate origin in the target lip region, establish a coordinate system based on the coordinate origin, and construct a lip edge parabola as the lip feature: Where: is the lip motion image the parabola of the upper edge of the lip; is the lip movement image of the parabola of the lower lip edge; is the height of the area above the target lip, is the height of the area below the target lip; w is the width of the lip in the target lip region; x is the X-axis coordinate point of the parabola; 4) For the user's lip movement data Perform the above feature extraction on all lip movement images in it to obtain the user's lip feature vector: Where: is an image of lip movement and the lip features; Upload the lip feature vector of the user's lip movement data to the blockchain node registered by the user of the valuable item transaction.

5. A method for secure encryption and traceability of valuables according to claim 1, characterized in that, In the step S3, the voice feature and the lip feature of the user of the valuable item transaction are matched. If the match is successful, the voice feature is sent to the blockchain consensus node, including: After receiving the voice feature vector and the lip feature vector, the blockchain node matches the voice feature and the lip feature at any same moment, that is, matches the lip feature at any moment and the voice feature . The feature matching method is the cosine similarity calculation method. If the energy of the voice feature is high and the lip edge of the lip feature is large at the same time, the cosine similarity calculation result is high. A cosine similarity threshold is set. If the cosine similarity calculation results of 80% of the features in the voice feature vector and the lip feature vector are higher than the cosine similarity threshold, it indicates a successful match and the two are from the same user. Then the voice feature is sent to the blockchain consensus node; The method for selecting the blockchain consensus node is: Each blockchain node votes on the other blockchain nodes. The selected node will generate a credit score. The calculation formula of the credit score is: Where: Indicates the number of votes obtained by the blockchain node; represents the total number of blockchain nodes; Select the blockchain nodes with the highest credit scores as the consensus nodes.

6. The method for secure encryption and traceability of valuables according to claim 1, wherein, In the step S4, the blockchain consensus node conducts consensus on the uploaded transaction proof data and performs encrypted storage, including: When the uploaded user identity feature matches successfully, the blockchain consensus node calculates the cosine similarity between the voice feature and the user's registered voice. If the similarity between the two is higher than 0.85, the user can use the terminal device to upload the transaction proof data to the consensus node. The transaction proof data is the transaction voucher between the current valuable item transaction user and the upstream user. The blockchain conducts consensus on the received transaction proof data. The consensus process is: 1) The consensus node checks whether the transaction proof data is legal, including whether the signature is complete and whether the data format is correct, and simulates the transaction locally. If the transaction is unqualified, the consensus node will reject the uploaded transaction proof data and feedback the information of rejecting the transaction to the user; 2) After the transaction proof data to be uploaded is confirmed to be correct, the consensus node conducts consensus on the transaction proof data uploaded by the terminal device according to the pre-set negotiation consistency algorithm; 3) If the consensus node reaches a consensus, the transaction proof data uploaded by the user is added to the blockchain node registered by the user and a message is broadcast to the entire network; if the consensus is not reached under normal circumstances of the node, the transaction proof data is rejected and the information of rejecting the transaction is feedback to the user; When the consensus node reaches a consensus, the blockchain encryption algorithm is used to encrypt the transaction proof data uploaded by the user. The encryption process of the transaction proof data is: 1) The consensus node generates a random number , calculates the verification code of the number of the valuable item and the random number , where ID is the number of the valuable item; 2) The consensus node sends the generated verification code to the blockchain node, and the blockchain node generates an encryption key based on the timestamp of the completed transaction , where is the timestamp information of the completed transaction; 3) Use the encryption key to encrypt the transaction proof data uploaded by the user. The encryption result is: Where: is a rotation function, indicating that is rotated to the right by characters, where is the number of characters of the valuable item number, and is the transaction proof data uploaded by the user; 4) Is the encrypted result of the transaction proof data, and store the encrypted result in the blockchain node.

7. The secure encryption and traceability method for valuables according to claim 1, wherein, In the step S5, the transaction traceability of the valuable item is carried out by viewing the transaction vouchers stored in the blockchain node, including: The process of the transaction traceability of the valuable item is: When the transaction traceability of the valuable item is required, the blockchain node initiating the transaction traceability performs identity authentication by inputting identity data; After the authentication is passed, the blockchain node initiating the transaction traceability sends a traceability request to the consensus node. After passing the consensus, the blockchain node initiating the transaction traceability can view the transaction vouchers stored in the traceability blockchain node to complete the transaction traceability of the valuable item.

8. A precious item security encryption and traceability system, characterized in that, The system includes: A blockchain construction module for constructing a blockchain for secure encryption traceability of valuable items by using a blockchain modeling method based on the valuable item transaction chain; The data acquisition and processing module is used to acquire the identity data of users in precious item transactions. The identity data includes voice data and the corresponding lip movement data. An improved voice feature extraction algorithm is used to extract voice features from the voice data, and a lip feature extraction algorithm is used to extract lip features from the lip movement data. The voice features and lip features of the precious item transaction users are matched. If the match is successful, indicating that the two come from the same user, the voice features are sent to the blockchain consensus node; The precious item traceability device is used for precious item transaction users to upload transaction proof data. The blockchain consensus node conducts consensus on the uploaded transaction proof data. If the consensus is passed, the transaction proof data is encrypted and stored in the blockchain node corresponding to the precious item transaction user. The transaction proof data is the transaction voucher between the current precious item transaction user and the upstream user. The transaction traceability of precious items is carried out according to the transaction vouchers in the blockchain node to implement a precious item security encryption traceability method as described in claim 1.

Images