Data processing method and device for Maotai-flavor liquor base liquor, electronic equipment and medium

Abstract

The application discloses a data processing method and device for Maotai-flavor base liquor, electronic equipment and medium, and relates to the technical field of data security. The method comprises the following steps: acquiring a triple data subjected to a digital signature and an encryption operation, wherein the triple data is obtained by processing real-time data collected by a sensor array by a sensor control unit, the sensor array is arranged around a base liquor jar body of a depositary, and is connected to the sensor control unit; decrypting and checking the triple data, and after the checking is passed, calling a dynamic Bayesian network probability parameter corresponding to the current base liquor in a pre-constructed feature library of a cloud trusted data space, and inferring a state type of the real-time data; performing zero-knowledge proof verification on the state type, grading early warning according to the verification result, and writing a hash value of an early warning log into a customer interest block of a block chain. By using the method, the state of the base liquor can be monitored in real time, and the credibility is improved.

Description

Technical Field

[0001] This application relates to the field of data security technology, and in particular to a data processing method, apparatus, electronic device and medium for a sauce-flavored baijiu base liquor. Background Technology

[0002] Base liquor refers to the original, undiluted liquor, which is the basic element that makes up baijiu (Chinese white liquor) and has unique brewing techniques and aging value-added characteristics. Currently, base liquor is usually produced through a customer pre-order and distillery-managed storage model. This means that after customers purchase base liquor, it is stored in a dedicated storage area of ​​the distillery, which is responsible for its daily care.

[0003] However, in actual storage, wineries may engage in unauthorized opening, substitution of base liquor, and alteration of storage records, resulting in damage to customer rights. At the same time, abnormal changes in the storage environment can also affect the quality of base liquor, and existing manual inspection methods are insufficient to provide real-time and reliable risk warnings. Summary of the Invention

[0004] In view of the above-mentioned defects or deficiencies in the related technologies, it is desirable to provide a data processing method, device, electronic device and medium for Maotai-flavor liquor base liquor, which can monitor the status of base liquor in real time and improve reliability.

[0005] Firstly, this application provides a data processing method for Maotai-flavor liquor base liquor, the data processing method for Maotai-flavor liquor base liquor includes:

[0006] The triplet data is obtained after digital signature and encryption. The triplet data is obtained by the sensor control unit processing the real-time data collected by the sensor array. The triplet data includes the collection timestamp, the device code of the sensor control unit, and the hash value of the real-time data. The sensor array is deployed around the storage base wine jar and connected to the sensor control unit.

[0007] The triplet data is decrypted and verified. After the verification is successful, the dynamic Bayesian network probability parameters corresponding to the current base wine in the pre-built feature library of the cloud trusted data space are called to infer the state type of the real-time data. The dynamic Bayesian network probability parameters are encrypted and stored through a pre-uploaded client public key and can only be decrypted and called temporarily. The client public key corresponds to the client's private key.

[0008] The state type is verified using zero-knowledge proof, and warnings are issued in different levels based on the verification results. The hash value of the warning log is written into the customer equity block in the blockchain.

[0009] Optionally, in some embodiments of this application, the method of inferring the state type of the real-time data by calling the dynamic Bayesian network probability parameters corresponding to the current base wine in the pre-built feature library of the cloud trusted data space includes:

[0010] Using the observation probability distribution parameters in the dynamic Bayesian network probability parameters, the observation probability of the real-time data is calculated. Combining the state transition probability matrix in the dynamic Bayesian network probability parameters and the previous state probability of the real-time data, the posterior probability of each state of the real-time data is calculated. The state type with the highest posterior probability is taken as the state type of the real-time data.

[0011] Optionally, in some embodiments of this application, the state transition probability matrix and the observation probability distribution parameters are pre-calibrated through the following steps:

[0012] Obtain the preprocessed dataset and split it into multiple state sub-datasets according to state type. The datasets include industry standard data, historical normal data of the winery, and simulated abnormal data.

[0013] By traversing each of the aforementioned state subsets, the frequency proportion of state transitions is statistically analyzed using the maximum likelihood estimation method to obtain the state transition probability matrix. The mean and variance of the data within each state are calculated using the moment estimation method to obtain the observation probability distribution parameters.

[0014] Optionally, the zero-knowledge proof verification of the state type described in some embodiments of this application includes:

[0015] Based on the ZK-SNARKs protocol, a proof file containing mathematical constraint solutions corresponding to the state type is generated, and the proof file is sent to the client so that the client can verify the validity of the proof file through the discrete logarithm algorithm. The mathematical constraint solutions are constructed based on the warning threshold and the observation probability distribution parameters in the dynamic Bayesian network probability parameters corresponding to the current base wine.

[0016] Receive feedback from the client and correct the status type based on the feedback.

[0017] Optionally, in some embodiments of this application, before obtaining the triplet data after digital signature and encryption, the data processing method for the base liquor of Maotai-flavor liquor further includes:

[0018] After the base liquor is placed in the jar, the base liquor information and customer information are processed through the smart contract of the blockchain to generate an ownership certificate containing a digital identity code, and the customer's public key is written into the sensor control unit. The customer's private key corresponding to the customer's public key is then sent to the client.

[0019] Optionally, in some embodiments of this application, the encryption operation includes sequentially performing quantum key encryption and client public key encryption.

[0020] Optionally, in some embodiments of this application, the blockchain also connects all the base wine data to form a complete data chain through a Merkle tree structure.

[0021] Secondly, this application provides a data processing device for Maotai-flavor liquor base liquor, the data processing device for Maotai-flavor liquor base liquor includes an acquisition module, an inference module and an early warning module that are interconnected;

[0022] The acquisition module is used to acquire triplet data that has undergone digital signature and encryption operations. The triplet data is obtained by the sensor control unit processing the real-time data collected by the sensor array. The triplet data includes the acquisition timestamp, the device code of the sensor control unit, and the hash value of the real-time data. The sensor array is deployed around the base wine jar and connected to the sensor control unit.

[0023] The inference module is used to decrypt and verify the triplet data. After the verification is successful, it calls the dynamic Bayesian network probability parameters corresponding to the current base wine in the pre-built feature library of the cloud trusted data space to infer the state type of the real-time data. The dynamic Bayesian network probability parameters are encrypted and stored through a pre-uploaded client public key and can only be temporarily decrypted and called. The client public key corresponds to the client's private key.

[0024] The early warning module is used to perform zero-knowledge proof verification on the state type, issue warnings in different levels based on the verification results, and write the hash value of the early warning log into the customer equity block in the blockchain.

[0025] Thirdly, this application provides an electronic device, which includes a processor and a memory. The memory stores at least one instruction, at least one program, a code set, or an instruction set. The instruction, the program, the code set, or the instruction set is loaded and executed by the processor to implement the steps of the data processing method for the base liquor of Maotai-flavor liquor according to any one of the first aspects.

[0026] Fourthly, this application provides a computer-readable storage medium storing one or more programs that can be executed by one or more processors to implement the steps of the data processing method for Maotai-flavor liquor base liquor as described in any one of the first aspects.

[0027] As can be seen from the above technical solutions, the embodiments of this application have the following advantages:

[0028] This application provides a data processing method, apparatus, electronic device, and medium for Maotai-flavor liquor base liquor. By deploying a sensor array around the base liquor storage jars, real-time data is efficiently collected around the clock without manual intervention. The real-time data is then processed by a sensor control unit connected to the sensor array to obtain a triplet data containing a collection timestamp, device code, and real-time data hash value. After digital signature and encryption, the data authenticity and reliable transmission are ensured. The triplet data is then decrypted and verified. After successful verification, the state type of the real-time data can be inferred based on the dynamic Bayesian network probability parameters corresponding to the current base liquor in the pre-built feature library of the cloud trusted data space, and zero-knowledge proof verification can be performed. This enables automatic hierarchical early warning based on the verification results, early detection of base liquor storage anomalies, and the hash value of the early warning log is written into the customer rights block in the blockchain for record-keeping and immutability, greatly improving credibility. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1 A flowchart illustrating a data processing method for a base liquor of a sauce-flavored baijiu provided in this application embodiment;

[0031] Figure 2 A structural block diagram of a data processing device for a base liquor of Maotai-flavor liquor provided in this application embodiment;

[0032] Figure 3 A structural block diagram of another data processing device for Maotai-flavor liquor base provided in this application embodiment;

[0033] Figure 4 This is a structural block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0034] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0035] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0036] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. The following examples illustrate this. Figures 1 to 4 This application provides a detailed description of the data processing method, apparatus, electronic equipment, and medium for Maotai-flavor liquor base provided in its embodiments.

[0037] Please refer to Figure 1 This is a flowchart illustrating a data processing method for a sauce-flavored baijiu base liquor provided in an embodiment of this application. The data processing method specifically includes the following steps:

[0038] S101, Obtain triplet data that has undergone digital signature and encryption operations. The triplet data is obtained by the sensor control unit processing the real-time data collected by the sensor array. The triplet data includes the acquisition timestamp, the device code of the sensor control unit, and the hash value of the real-time data.

[0039] The sensor array is deployed around the storage jars of base liquor and connected to a sensor control unit. This sensor array includes, but is not limited to, jar vibration sensors, cap pressure sensors, ambient temperature and humidity sensors, and trace gas sensors. For example, the jar vibration sensor is installed at the bottom of the jar and can be a high-precision piezoelectric vibration sensor with a sampling frequency of 1 time per minute. It can detect parameters such as the amplitude and frequency of jar vibration, providing a basis for identifying actions such as forced opening and movement. The cap pressure sensor is installed at the contact point between the electromagnetic cap and the jar body at the jar's opening. It can be a strain gauge pressure sensor that can monitor changes in cap pressure in real time, determining that the cap is loose or has been opened when the pressure suddenly drops.

[0040] In addition, an ambient temperature and humidity sensor is installed in the base liquor storage area. An SHT30 model sensor can be used, measuring a temperature range of -40℃ to 125℃ and a humidity range of 0 to 100% RH (Relative Humidity), with an accuracy of ±0.3℃ and ±2% RH, enabling real-time monitoring of changes in the storage environment's temperature and humidity. A trace gas sensor is installed near the mouth of the base liquor jars, using an MQ-4 model gas sensor, capable of detecting alcohol gas concentration. An abnormally high concentration indicates a seal failure. Furthermore, the sensor array can also include a positioning sensor integrated with the sensor control unit, employing a BeiDou positioning component, capable of recording the base liquor's storage location coordinates to prevent unauthorized relocation.

[0041] In some embodiments of this application, after the base liquor is placed in the jar, the base liquor information and customer information can be processed through a blockchain smart contract to generate an ownership certificate containing a digital identity code. For example, the base liquor information includes, but is not limited to, brewing batch, distillation date, alcohol content test value, jar number, packaging time, and packaging location. Customer information includes, but is not limited to, identity authentication and purchase vouchers. The customer's public key is written into the sensor control unit, and the customer's private key corresponding to the public key is sent to the client, thus using asymmetric encryption to grant the customer the highest privileges. In other words, the customer can log in to the cloud-based trusted data space through the client's application (APP) and decrypt and view all data using their private key. The manufacturer, however, can only view basic data such as storage environment temperature and humidity. To view detailed abnormal data, operation records, or perform maintenance operations, the manufacturer must initiate an authorization request to the client, specifying the operation content and time. After the client's consent, temporary viewing and operation permissions are granted. The authorization information is stored on the blockchain, clearly defining the permissions. Furthermore, during the operation, a high-definition camera records video, which is encrypted and uploaded to the cloud-based trusted data space. The video header embeds a timestamp and the biometric hash value of the operating employee, effectively preventing the manufacturer from unauthorizedly modifying data or manipulating the base liquor. The cloud-based trusted data space adopts a distributed storage architecture, consisting of multiple nodes. The stored content includes raw sensor data, pre-built feature libraries, and blockchain block records. After the uploaded data is verified by more than three blockchain nodes, a block record containing device code, manufacturer signature, customer information digest, and timestamp (accurate to milliseconds) is generated and written to the blockchain ledger. At the same time, the cloud database sets read and write protection tags for the raw sensor data, prohibiting any modification operations.

[0042] In actual use, the manufacturer and the customer, as the purchaser, witness the packaging of the base liquor together. High-definition cameras record videos in real time of cleaning the jar mouth, affixing the seal, and installing the electromagnetic cap. Simultaneously, microscopic texture images of the seal and information such as the electromagnetic cap code are collected. The customer and manufacturer complete digital signature confirmation using a portable blockchain signature device to ensure the authenticity of the data. Then, these videos and information are encrypted and uploaded to the cloud trusted data space for reliable storage through the narrow band-Internet of Things (NB-IoT) communication module of the sensor control unit. The encryption operation includes sequential execution of quantum key encryption and customer public key encryption, that is, quantum key encryption first, followed by customer public key encryption. The quantum key ensures the security of data transmission, while the customer public key ensures the privacy of storage. The two complement each other.

[0043] S102, decrypt and verify the triplet data, and after the verification is successful, call the dynamic Bayesian network probability parameters corresponding to the current base wine in the pre-built feature library of the cloud trusted data space to infer the state type of the real-time data.

[0044] It should be noted that in this embodiment, the probability parameters of the dynamic Bayesian network are encrypted and stored using a pre-uploaded client public key, and can only be temporarily decrypted and accessed. The client public key corresponds to the client's private key. The dynamic Bayesian network includes state nodes (Z) and observation nodes (G). The state nodes (Z) have four discrete states, namely Z={normal (Z0), mildly abnormal (Z1), moderately abnormal (Z2), and severely abnormal (Z3)}. The observation nodes (G) have six continuous observation values, namely G={temperature (G1), humidity (G2), vibration amplitude (G3), sealing pressure (G4), alcohol concentration (G5), and location (G6)}. The time step is 1 minute. The state Z(t) at time t is inferred based on the observation value G(t) at time t. This dynamic Bayesian network does not have neural network elements such as neurons, weights, and backpropagation, and belongs to the parameter calibration of a probabilistic graphical model. The parameters of the probabilistic graphical model include the state transition probability matrix A and the observation probability distribution parameters B. Each parameter must be stored encrypted and can only be temporarily decrypted and accessed; the plaintext must not be stored. For example, in the state transition probability matrix A, element A[i][j] = P(Z(t) = Z j |Z(t-1)=Z i ) represents the state Z from time t-1. i Transition to state Z at time t j The probabilities of Z are given by i and j, both ranging from 0 to 3. The element B[j] in the observation probability distribution parameter B represents state Z. j Below, the normal distribution parameters of the 6D sensor data, namely the mean μ and variance σ. 2 .

[0045] For example, when pre-calibrating the state transition probability matrix A and the observation probability distribution parameters B, a pre-processed dataset is first obtained, and then the dataset is split into multiple state subsets according to the state type. Pre-processing includes, but is not limited to, cleaning fault values ​​exceeding the sensor's range, normalizing the data scale to the [0,1] interval, and generating SHA-256 hash values. Hashization avoids exposing the original data. The dataset includes industry standard data, historical normal data from the distillery, and simulated abnormal data. The industry standard data comes from the storage environment parameter range specified in GB / T26760-2011 "Sauce-flavored Baijiu," and its purpose is to determine the initial distribution benchmark for normal data. The historical normal data from the distillery comes from sensor data from the distillery's storage without abnormalities over the past three years, and its purpose is to fit the normal characteristics of actual storage scenarios. The simulated abnormal data comes from labeled data from manually simulated scenarios such as loose caps, forced opening, seal failure, and location shifting, and its purpose is to optimize the abnormal probability parameters. Furthermore, after de-identifying various types of data, they are subjected to encrypted hashing and split into states Z0, Z1, Z2, and Z3 to obtain independent subsets of each state.

[0046] Then, traverse each state subset and use the maximum likelihood estimation method to count the frequency proportion of state transitions to obtain the state transition probability matrix A. For example, if the number of samples from state Z0 to state Z1 at time t-1 is 120, and this number is divided by the total number of samples in state Z0 (120,000), then A[0][1]=120 / 120000=0.001. Also, use the method of moments to calculate the mean and variance of the data within each state to obtain the observation probability distribution parameter B. Here, it is assumed that the sensor data in each state follows a normal distribution. For example, the temperature samples in state Z0 total 120,000, and the calculated mean μ=20 and variance σ... 2 =1.5, then the temperature observation probability distribution of state Z0 is N(20,1.5). All calculated state transition probability matrices A and observation probability distribution parameters B are immediately encrypted using the national cryptographic SM2 asymmetric encryption algorithm. The private key is controlled by the customer. The encrypted parameter file is synchronously stored in the pre-built feature library and the customer's rights block in the blockchain (write-protected, tamper-proof). No plaintext parameters are stored during the calibration process; only the encrypted parameter hash values ​​are retained for verification. Calibration can be completed with tens of thousands of samples, which is suitable for the scenario of "few abnormal samples" in base wine storage, and the parameter size is small. The state transition probability matrix A has only 4×4=16 values, and the observation probability distribution parameter B has only 6 dimensions×4 states×2=48 values. The encryption / decryption time is less than 10ms, which meets the requirements of real-time inference. In addition, when more than 10,000 new records of non-abnormal or abnormal data are added each quarter, the above pre-calibration process is repeated. Only the state transition probability matrix A and observation probability distribution parameters B are incrementally refreshed, without the need for full calculation. The updated records generate hash values ​​and are written to the blockchain, ensuring parameter traceability.

[0047] In some embodiments of this application, the triplet data can be sequentially decrypted using quantum decryption and client public key decryption, and the acquisition timestamp, the device code of the sensor control unit, and the hash value of the real-time data can be extracted. The hash values ​​of the real-time data are then compared to prevent transmission errors and tampering. Then, using the observation probability distribution parameter B in the dynamic Bayesian network probability parameters, the observation probability P(G(t)|Z(t)=Z) of the real-time data is calculated. j For example, P(G(t)|Z(t)=Z j The product of the normal distribution probability densities of the 6-dimensional observation data, combined with the state transition probability matrix A in the probability parameters of the dynamic Bayesian network and the previous time-step state probability P(Z(t-1)= Z) of the real-time data. i |G(1)G(2)…G(t-1)), initially uniformly distributed, to calculate the posterior probability P(Z(t)=Z) of each state in the real-time data. j |G(1)G(2)…G(t))∝P(G(t)|Z j )×ΣP(Zj |Z i )×P(Z i |G(1)G(2)…G(t-1)), ∝ means proportional to the operation. Finally, the state type with the highest a posteriori probability is taken as the state type of the real-time data. For example, if P(Z0)=95%, P(Z1)=4%, P(Z2)=1%, P(Z3)=0, then the final state type is Z0 (normal).

[0048] In some embodiments of this application, the national cryptographic algorithm SM2 can also be used to accurately calculate state transition probabilities while ensuring the privacy and security of core parameters. That is, while protecting parameter privacy, the state at time t-1 is calculated as follows: At time t, the state transitions to... Conditional probability:

[0049]

[0050] In the above formula, This represents the decryption function of the Chinese national cryptographic algorithm SM2; This represents the client's private key; This represents the state transition parameters stored using the client's public key; Represents the state at time t-1 All states that can be transferred Summation, This represents the state transition parameters stored using the client's public key; , and All of them are elements in the state set Z.

[0051] S103 performs zero-knowledge proof verification of the state type, issues graded warnings based on the verification results, and writes the hash value of the warning log into the customer equity block in the blockchain.

[0052] It should be noted that customers can customize the warning thresholds within the industry-recommended range through the client application. For example, mild anomalies are temperature fluctuations of ±2℃ and vibration amplitude of <0.5g; moderate anomalies are temperature fluctuations of ±5℃ and a 10% decrease in capping pressure; and severe anomalies are vibration amplitude of >1g and an increase in alcohol concentration of >5ppm. As for the push notification method, customers can choose according to their own preferences, such as client message push, encrypted SMS, or voice call. The receiving time can be 24 hours a day or during working hours.

[0053] In some embodiments of this application, a proof file containing mathematical constraint solutions corresponding to the state type can be generated based on the ZK-SNARKs protocol. This proof file is then sent to the client, allowing the client to verify its validity using the Discrete Logarithm Problem (DLP) without decrypting any parameters. This approach avoids disclosing plaintext data such as real-time data, feature library parameters, and client thresholds, resolving the conflict between data sharing and privacy protection. The mathematical constraint solutions are constructed based on the warning threshold and the observed probability distribution parameters in the dynamic Bayesian network probability parameters corresponding to the current base liquor. For example, it proves the logical constraint that "the deviation between real-time data and normal feature library parameters is greater than or equal to or less than the warning threshold," containing only mathematical logic verification information. Then, feedback from the client is received, and the state type is corrected based on this feedback. For example, the initial judgment might be a slight anomaly; if verification passes, it is confirmed as "slight anomaly"; if verification fails, it is determined to be "normal."

[0054] During tiered alerts, there are no alerts for normal conditions, only status logs are recorded; minor anomalies are alerted via client-side push notifications (including anomaly type and time), without manufacturer notification; moderate anomalies are pushed via both client-side and encrypted SMS, with the manufacturer only receiving anomaly types such as temperature anomalies, without specific data; severe anomalies are pushed via client-side, encrypted SMS, and voice calls, simultaneously triggering local audible and visual alarms in the base liquor storage area, with the manufacturer receiving the anomaly type and emergency handling prompts. The alert log, containing anomaly type, time, location, push method, and customer feedback, is hashed and written to the customer rights block. This specially designed customer rights block can also record base liquor purchase voucher hashes, ownership transfer records, and authorized operation logs. Ownership changes require dual signature confirmation from both the customer and the manufacturer, with the smart contract automatically executing the confirmation process. After receiving the alert information, the customer can view real-time monitoring footage and sensor data curves through the client application and remotely lock the storage area or instruct the manufacturer to suspend operations as needed.

[0055] Furthermore, the blockchain adopts a consortium blockchain architecture, with nodes including customers, wineries, and third-party notary institutions. Each node has an independent ledger and maintains data consistency through a consensus mechanism. Each uploaded data entry carries equipment codes, manufacturer signatures (including factory area codes and operator biometric hash values), unique base liquor codes (associated with brewing batches and jar numbers), customer information summaries (processed using SHA-256 hashing), timestamps, and location coordinates (obfuscated). The blockchain also uses a Merkle tree structure to link these base liquor data into a complete data chain. The leaf nodes of the Merkle tree contain a six-dimensional identifier of "equipment-manufacturer-base liquor-customer-time-location" and data hashes, while the root node is bound to the blockchain. The traceability granularity can reach a single jar and a single state. By integrating sensors, blockchain, data storage, and encryption algorithms, data association and traceability are achieved, ensuring the unique identity of the base liquor and its historical verifiability. During actual traceability, the blockchain can be queried through the unique base liquor code or digital identity code to obtain sensor data, operation records, and ownership change information throughout the entire lifecycle of the base liquor, verifying data continuity and integrity.

[0056] The data processing method for Maotai-flavor liquor base provided in this application embodiment utilizes a sensor array deployed around the base liquor storage jars to efficiently collect real-time data around the clock without manual intervention. The real-time data is then processed by a sensor control unit connected to the sensor array, resulting in a triplet data set containing a collection timestamp, device code, and real-time data hash value. This data is then digitally signed and encrypted to ensure authenticity and reliable transmission. The triplet data is then decrypted and verified. Upon successful verification, the state type of the real-time data can be inferred based on the dynamic Bayesian network probability parameters corresponding to the current base liquor in a pre-built feature library in the cloud-based trusted data space. Zero-knowledge proof verification is then performed, enabling automatic graded early warning based on the verification results. This allows for early detection of base liquor storage anomalies. Simultaneously, the hash value of the warning log is written into the customer rights block in the blockchain for record-keeping and immutability, significantly improving credibility.

[0057] Based on the foregoing embodiments, this application provides a data processing device for Maotai-flavor liquor base liquor. This Maotai-flavor liquor base liquor data processing device 100 can be applied to… Figure 1 In the data processing method for the base liquor of Maotai-flavor liquor in the corresponding embodiment, please refer to... Figure 2 The data processing device 100 for the base liquor of the sauce-flavored baijiu includes an acquisition module 101, an inference module 102, and an early warning module 103 that are interconnected.

[0058] The acquisition module 101 is used to acquire triplet data that has been digitally signed and encrypted. The triplet data is obtained by the sensor control unit processing the real-time data collected by the sensor array. The triplet data includes the acquisition timestamp, the device code of the sensor control unit, and the hash value of the real-time data. The sensor array is deployed around the base wine jar and connected to the sensor control unit.

[0059] The inference module 102 is used to decrypt and verify the triplet data. After the verification is successful, it calls the dynamic Bayesian network probability parameters corresponding to the current base wine in the pre-built feature library of the cloud trusted data space to infer the state type of the real-time data. The dynamic Bayesian network probability parameters are encrypted and stored through the pre-uploaded customer public key and can only be temporarily decrypted and called. The customer public key corresponds to the customer private key of the client.

[0060] The early warning module 103 is used to perform zero-knowledge proof verification of the state type, issue graded early warnings based on the verification results, and write the hash value of the early warning log into the customer equity block in the blockchain.

[0061] Optionally, in some embodiments of this application, the inference module 102 is specifically used to calculate the observation probability of real-time data using the observation probability distribution parameters in the probability parameters of the dynamic Bayesian network, and to calculate the posterior probability of each state of the real-time data by combining the state transition probability matrix in the probability parameters of the dynamic Bayesian network and the state probability of the real-time data at the previous moment, and to take the state type with the highest posterior probability as the state type of the real-time data.

[0062] Optionally, in some embodiments of this application, the inference module 102 is further specifically used to obtain a preprocessed dataset and split the dataset into multiple state sub-datasets according to the state type. The dataset includes industry standard data, historical normal data of the winery, and simulated abnormal data.

[0063] By traversing each state subset, the frequency proportion of state transitions is statistically analyzed using the maximum likelihood estimation method to obtain the state transition probability matrix. The mean and variance of the data within each state are calculated using the moment estimation method to obtain the observation probability distribution parameters.

[0064] Optionally, in some embodiments of this application, the early warning module 103 is specifically used to generate a proof file containing mathematical constraint solutions corresponding to the state type based on the ZK-SNARKs protocol, and send the proof file to the client so that the client can verify the validity of the proof file through the discrete logarithm algorithm, wherein the mathematical constraint solutions are constructed based on the early warning threshold and the observation probability distribution parameters in the dynamic Bayesian network probability parameters corresponding to the current base wine;

[0065] Receive feedback from the client and correct the status type based on the feedback.

[0066] Optionally, such as Figure 3 As shown, in some embodiments of this application, the data processing device 100 for the base liquor of the sauce-flavored baijiu also includes a generation module 104, which is used to process the base liquor information and customer information through a blockchain smart contract after the base liquor is put into the jar, generate an ownership certificate containing a digital identity code, write the customer public key into the sensor control unit, and send the customer private key corresponding to the customer public key to the client.

[0067] Optionally, in some embodiments of this application, the encryption operation includes sequentially performing quantum key encryption and client public key encryption.

[0068] Optionally, in some embodiments of this application, the blockchain also uses a Merkle tree structure to connect all the base wine data to form a complete data chain.

[0069] It should be noted that the descriptions of the same steps and contents as in other embodiments in this embodiment can be found in the descriptions in other embodiments, and will not be repeated here.

[0070] The data processing device for Maotai-flavor liquor base provided in this application embodiment efficiently collects real-time data around the clock by deploying a sensor array around the base liquor storage jars without manual intervention. The real-time data is then processed by a sensor control unit connected to the sensor array to obtain a triplet data containing the collection timestamp, device code, and real-time data hash value. After digital signature and encryption, the data authenticity and reliable transmission are ensured. The triplet data is then decrypted and verified. After successful verification, the state type of the real-time data can be inferred from the pre-built feature library in the cloud trusted data space based on the dynamic Bayesian network probability parameters corresponding to the current base liquor, and zero-knowledge proof verification can be performed. This enables automatic graded early warning based on the verification results, early detection of base liquor storage anomalies, and the hash value of the early warning log is written into the customer rights block in the blockchain for record-keeping and immutability, greatly improving credibility.

[0071] Based on the foregoing embodiments, this application provides an electronic device. Please refer to... Figure 4 The electronic device 200 may include a processor 201 and a memory 202, and the electronic device 200 may be a server. The memory 202 stores at least one instruction, at least one program, code set, or instruction set, which is loaded and executed by the processor 201 to implement [the desired functionality]. Figure 1 The steps of the data processing method for the base liquor of Maotai-flavor liquor in the corresponding embodiment.

[0072] In another aspect, embodiments of this application provide a computer-readable storage medium for storing program code for executing the aforementioned... Figure 1Any implementation of the data processing method for the base liquor of sauce-flavored baijiu in the corresponding embodiment.

[0073] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and modules described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0074] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed between each other can be through some interfaces, indirect coupling or communication connection between devices or modules, and can be electrical, mechanical, or other forms. Modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, i.e., they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0075] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing unit, or each module can exist physically separately, or two or more units can be integrated into one module. The integrated unit can be implemented in hardware or as a software functional unit. If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0076] Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part 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, server, or network device, etc.) to execute all or part of the steps of the data processing method for Maotai-flavor liquor base liquor in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, portable hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0077] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0078] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A data processing method for base liquor of Maotai-flavor liquor, characterized in that, The data processing method for the base liquor of the Maotai-flavor baijiu includes: The triplet data is obtained after digital signature and encryption. The triplet data is obtained by the sensor control unit processing the real-time data collected by the sensor array. The triplet data includes the collection timestamp, the device code of the sensor control unit, and the hash value of the real-time data. The sensor array is deployed around the storage base wine jar and connected to the sensor control unit. The triplet data is decrypted and verified. After the verification is successful, the dynamic Bayesian network probability parameters corresponding to the current base wine in the pre-built feature library of the cloud trusted data space are called to infer the state type of the real-time data. The dynamic Bayesian network probability parameters are encrypted and stored through a pre-uploaded client public key and can only be decrypted and called temporarily. The client public key corresponds to the client's private key. The state type is verified using zero-knowledge proof, and warnings are issued in different levels based on the verification results. The hash value of the warning log is written into the customer equity block in the blockchain. The step of inferring the state type of the real-time data by calling the dynamic Bayesian network probability parameters corresponding to the current base wine in the pre-built feature library of the cloud trusted data space includes: using the observation probability distribution parameters in the dynamic Bayesian network probability parameters to calculate the observation probability of the real-time data, and combining the state transition probability matrix in the dynamic Bayesian network probability parameters and the state probability of the real-time data at the previous moment to calculate the posterior probability of each state of the real-time data, and taking the state type with the highest posterior probability as the state type of the real-time data; The zero-knowledge proof verification of the state type includes: generating a proof file containing mathematical constraint solutions corresponding to the state type based on the ZK-SNARKs protocol, and sending the proof file to the client so that the client can verify the validity of the proof file through a discrete logarithm algorithm, wherein the mathematical constraint solutions are constructed based on the warning threshold and the observation probability distribution parameters in the dynamic Bayesian network probability parameters corresponding to the current base wine; receiving the feedback result from the client, and correcting the state type according to the feedback result.

2. The data processing method for base liquor of sauce-flavored baijiu according to claim 1, characterized in that, The state transition probability matrix and the observation probability distribution parameters are pre-calibrated through the following steps: Obtain the preprocessed dataset and split it into multiple state sub-datasets according to state type. The datasets include industry standard data, historical normal data of the winery, and simulated abnormal data. By traversing each of the aforementioned state subsets, the frequency proportion of state transitions is statistically analyzed using the maximum likelihood estimation method to obtain the state transition probability matrix. The mean and variance of the data within each state are calculated using the moment estimation method to obtain the observation probability distribution parameters.

3. The data processing method for base liquor of sauce-flavored baijiu according to any one of claims 1 to 2, characterized in that, Before obtaining the triplet data after digital signature and encryption, the data processing method for the base liquor of Maotai-flavor liquor further includes: After the base liquor is placed in the jar, the base liquor information and customer information are processed through the smart contract of the blockchain to generate an ownership certificate containing a digital identity code, and the customer's public key is written into the sensor control unit. The customer's private key corresponding to the customer's public key is then sent to the client.

4. The data processing method for base liquor of sauce-flavored baijiu according to claim 3, characterized in that, The encryption operation includes sequentially performing quantum key encryption and client public key encryption.

5. The data processing method for base liquor of sauce-flavored baijiu according to claim 3, characterized in that, The blockchain also uses a Merkle tree structure to link all the base wine data together to form a complete data chain.

6. A data processing device for a base liquor of sauce-flavored baijiu, characterized in that, The data processing device for the base liquor of Maotai-flavor liquor includes an acquisition module, an inference module, and an early warning module that are interconnected. The acquisition module is used to acquire triplet data that has undergone digital signature and encryption operations. The triplet data is obtained by the sensor control unit processing the real-time data collected by the sensor array. The triplet data includes the acquisition timestamp, the device code of the sensor control unit, and the hash value of the real-time data. The sensor array is deployed around the base wine jar and connected to the sensor control unit. The inference module is used to decrypt and verify the triplet data. After the verification is successful, it calls the dynamic Bayesian network probability parameters corresponding to the current base wine in the pre-built feature library of the cloud trusted data space to infer the state type of the real-time data. The dynamic Bayesian network probability parameters are encrypted and stored through a pre-uploaded client public key and can only be temporarily decrypted and called. The client public key corresponds to the client's private key. The early warning module is used to perform zero-knowledge proof verification on the state type, issue graded early warnings based on the verification results, and write the hash value of the early warning log into the customer equity block in the blockchain. Specifically, the inference module is used to calculate the observation probability of the real-time data by utilizing the observation probability distribution parameters in the dynamic Bayesian network probability parameters, and to calculate the posterior probability of each state of the real-time data by combining the state transition probability matrix in the dynamic Bayesian network probability parameters and the state probability of the real-time data at the previous moment, and to take the state type with the highest posterior probability as the state type of the real-time data. Specifically, the early warning module is used to generate a proof file containing mathematical constraint solutions corresponding to the state type based on the ZK-SNARKs protocol, and send the proof file to the client so that the client can verify the validity of the proof file through a discrete logarithm algorithm. The mathematical constraint solutions are constructed based on the early warning threshold and the observation probability distribution parameters in the dynamic Bayesian network probability parameters corresponding to the current base wine. The module also receives feedback results from the client and corrects the state type based on the feedback results.

7. An electronic device, characterized in that, The electronic device includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, code set, or instruction set, and the instruction, program, code set, or instruction set is loaded and executed by the processor to implement the steps of the data processing method for the base liquor of Maotai-flavor liquor according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores one or more programs, which can be executed by one or more processors to implement the steps of the data processing method for the base liquor of Maotai-flavor liquor according to any one of claims 1 to 5.

Images