Inspection sample data tracking identification method and system based on Internet of Things

Abstract

The invention belongs to the technical field of data management, and discloses an inspection sample data tracking identification method and system based on the Internet of Things. The method comprises the following steps: a cloud data center constructs a sample tracking identification model and a sample data analysis model, and deploys a block chain network; the Internet of Things gateway is used for collecting real-time handover records and sending the real-time handover records to the cloud data center; the cloud data center performs tampering verification and generates real-time test sample data; the cloud data center is used for performing sample tracking and identification by using the sample tracking and identification model; the cloud data center is used for performing sample data analysis by using a sample data analysis model; and the cloud data center is used for storing the real-time test sample data, the real-time sample tracking identification result and the real-time sample data analysis result of the detection sample by using a block chain network. According to the invention, the problems of easy data tampering, difficult tracking, inaccurate analysis, low management efficiency and low storage reliability in the prior art are solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of data management, and particularly relates to a method and system for tracking and identifying inspection sample data based on the Internet of Things. Background Art

[0002] The laboratory department of a hospital is responsible for examining the blood, urine, body fluids, etc. of patients to obtain information such as the biochemical indicators, immunological indicators, and hematological indicators of the patients. Through these examination results, doctors can understand the physical condition of the patients, judge the type and severity of diseases, and formulate corresponding treatment plans. Or it is responsible for examining the tissues, cells, etc. of patients to obtain pathological information. Through microscopic observation and analysis of tissue specimens, doctors can determine the pathological type, lesion range and degree of diseases, providing accurate diagnostic basis for clinicians. An inspection sample refers to a substance collected from the human body for laboratory testing and analysis. These samples can provide information about an individual's health status, disease state, physiological function, etc.

[0003] With the continuous development of medical technology, the volume of inspection sample data in the laboratory department shows exponential growth, and the inspection sample data involves patients' privacy information. Therefore, the management of inspection sample data has become increasingly important. However, the existing inspection sample data management technologies have exposed many defects in practical applications, specifically including: 1) Easy data tampering: Traditional sample data management often relies on a centralized database, and the data is easily tampered with maliciously during transmission and storage, resulting in the inability to guarantee the authenticity of the data; 2) Difficult tracking: In the existing technology, the tracking of samples mainly relies on manual records or simple barcode systems, making it difficult to achieve real-time and accurate tracking, and easily causing the loss or confusion of samples; 3) Inaccurate analysis: Traditional data analysis methods often rely on manual experience or simple statistical tools, lacking the ability of deep learning and big data analysis, resulting in inaccurate and incomplete analysis results; 4) Low management efficiency: In the existing technology, the processes of sample collection, recording, transmission and analysis often require a large amount of manual intervention, with low efficiency and difficult to meet the needs of large-scale and rapid inspections; 5) Low storage reliability: The existing data storage methods are often limited to local servers or centralized databases, lacking reliable storage and disaster recovery capabilities, and are easily affected by hardware failures or natural disasters. Summary of the Invention

[0004] In order to solve the problems of easy data tampering, difficult tracking, inaccurate analysis, low management efficiency and low storage reliability existing in the prior art, the purpose of the present invention is to provide a method and system for tracking and identifying inspection sample data based on the Internet of Things.

[0005] The technical solution adopted by the present invention is as follows: A method for tracking and identifying inspection sample data based on the Internet of Things, comprising the following steps: The cloud data center uses artificial intelligence algorithms to construct a sample tracking and identification model and a sample data analysis model, and uses blockchain technology to deploy a blockchain network; The Internet of Things gateway collects the real-time handover records of the inspection samples at the current inspection sample storage points and uploads the real-time handover records to the cloud data center; The cloud data center verifies the tampering of the real-time handover records of the same inspection sample at all inspection sample storage points. After the tampering verification passes, it combines all the real-time handover records and the corresponding real-time sample component data to obtain the real-time inspection sample data of the inspection sample; The cloud data center uses the sample tracking and identification model to perform sample tracking and identification on several real-time handover records of the real-time inspection sample data to obtain real-time sample tracking and identification results; The cloud data center uses the sample data analysis model to perform sample data analysis on the real-time sample component data of the real-time inspection sample data to obtain real-time sample data analysis results; The cloud data center uses the blockchain network to store the real-time inspection sample data, real-time sample tracking and identification results, and real-time sample data analysis results of the inspection sample.

[0006] Further, the cloud data center uses artificial intelligence algorithms to construct a sample tracking and identification model and a sample data analysis model, and uses blockchain technology to deploy a blockchain network, including the following steps: The cloud data center uses artificial intelligence algorithms to construct an initial sample tracking and identification model and an initial sample data analysis model; Use swarm intelligence optimization algorithms to optimize the initial sample tracking and identification model and the initial sample data analysis model to obtain an optimized sample tracking and identification model and an optimized sample data analysis model; Collect a number of historical inspection sample data and preprocess the number of historical inspection sample data to obtain a number of preprocessed historical inspection sample data; According to a number of preprocessed historical inspection sample data, train the optimized sample tracking and identification model to obtain a final sample tracking and identification model, and generate a number of historical sample tracking and identification results; According to a number of preprocessed historical inspection sample data, train the optimized sample data analysis model to obtain a final sample data analysis model; Use blockchain technology to distributively connect all data servers in the cloud data center as data nodes to obtain a blockchain network; According to the identity allocation mechanism, a number of data nodes in the blockchain network are divided into a number of consensus nodes and a number of storage nodes, obtaining a data storage sub-network and a blockchain consensus sub-network.

[0007] Furthermore, the sample tracking and recognition model is constructed based on the LSTM-DBN algorithm, and the sample tracking and recognition model includes a sample handover trajectory feature extraction module constructed based on the LSTM algorithm and a sample tracking and recognition module constructed based on the DBN algorithm, which are connected in sequence; The sample data analysis model is constructed based on the RF-Atteniton-MLP algorithm, and the sample data analysis model includes a key feature extraction module constructed based on the RF algorithm, an attention weight module constructed based on the Attention mechanism, and a sample data analysis module constructed based on the MLP algorithm, which are connected in sequence; The swarm intelligence optimization algorithm is the ICPO algorithm.

[0008] Furthermore, using the swarm intelligence optimization algorithm, the initial sample tracking and recognition model and the initial sample data analysis model are optimized to obtain an optimized sample tracking and recognition model and an optimized sample data analysis model, including the following steps: Encode the initial model parameters of the initial sample tracking and recognition model and the initial sample data analysis model into the individual vectors of the ICPO algorithm; Taking the minimization of the model error value as the optimization goal, use the optimization goal as the fitness function of the ICPO algorithm, and set the algorithm parameters and the maximum number of iterations of the ICPO algorithm; According to the algorithm parameters and individual vectors of the ICPO algorithm, perform initialization to obtain an initial ICPO population; Use the fitness function to obtain the fitness value of each initial ICPO individual in the initial ICPO population, and retain the optimal individual; According to the fitness value, use the ICPO algorithm to iteratively update the initial ICPO population to obtain an updated ICPO population; Use the dynamic reverse mechanism to perform dynamic reverse on the initial ICPO population to obtain a dynamically reversed ICPO population; Use the fitness function to obtain the fitness value of each ICPO individual in the updated ICPO population and the dynamically reversed ICPO population; According to the fitness value, update the optimal individual to obtain an updated optimal individual. If the current number of iterations is greater than the maximum number of iterations, output the updated optimal individual; Decode the individual vector of the updated optimal individual to obtain the optimal initial model parameters of the initial sample tracking and recognition model and the initial sample data analysis model; Optimize the initial sample tracking and recognition model and the initial sample data analysis model according to the optimal initial model parameters to obtain an optimized sample tracking and recognition model and an optimized sample data analysis model.

[0009] Furthermore, the real-time handover record includes the location data of the detection sample storage point, the IP address of the IoT gateway, and the real-time inbound record and real-time outbound record of the detection sample at the detection sample storage point.

[0010] Furthermore, the cloud data center performs tampering verification on the real-time handover records of the same detection sample at all detection sample storage points. After the tampering verification passes, combine all the real-time handover records and the corresponding real-time sample component data to obtain the real-time inspection sample data of the detection sample, including the following steps: The cloud data center sends the real-time handover record of the same detection sample at each detection sample storage point to the corresponding IoT gateway for integrity comparison at the IoT gateway; Receive the integrity comparison success information returned by the IoT gateway. If the cloud data center receives the integrity comparison success information returned by the IoT gateways corresponding to all real-time handover records, the tampering verification passes; After the tampering verification passes, obtain the real-time inspection sample data of the detection sample according to the time sequence of all real-time handover records and the corresponding real-time sample component data.

[0011] Furthermore, the cloud data center uses the sample tracking and recognition model to perform sample tracking and recognition on several real-time handover records of the real-time inspection sample data to obtain a real-time sample tracking and recognition result, including the following steps: The cloud data center combines several real-time handover records of the real-time inspection sample data into a real-time handover record sequence according to the time sequence and inputs the real-time handover record sequence into the sample tracking and recognition model; Use the sample handover trajectory feature extraction module of the sample tracking and recognition model to extract the real-time sample handover trajectory features of the real-time handover record sequence; Use the sample tracking and recognition module of the sample tracking and recognition model to perform sample tracking and recognition according to the real-time sample handover trajectory features to obtain a real-time sample tracking and recognition result.

[0012] Furthermore, the cloud data center uses the sample data analysis model to perform sample data analysis on the real-time sample component data of the real-time inspection sample data to obtain a real-time sample data analysis result, including the following steps: The cloud data center inputs the real-time sample component data of the real-time inspection sample data into the sample data analysis model; Use the key feature extraction module of the sample data analysis model to extract several real-time key features of the real-time sample component data; The attention weight module of the sample data analysis model weights and fuses a number of real-time key features according to a preset attention weight value to obtain real-time weighted fusion features; The sample data analysis module of the sample data analysis model performs sample data analysis based on the real-time weighted fusion features to obtain real-time sample data analysis results.

[0013] Furthermore, the cloud data center uses a blockchain network to store the real-time inspection sample data, real-time sample tracking and identification results, and real-time sample data analysis results of the test samples, including the following steps: The cloud data center shards the real-time inspection sample data of the test samples according to the replica sharding mechanism to obtain a number of real-time data shards including replica shards; Use a random encryption algorithm to encrypt a number of real-time data shards to obtain a number of encrypted real-time data shards, and generate a real-time data storage request; Use the blockchain consensus sub-network of the blockchain network to conduct consensus on the real-time data storage request. After successful consensus, use the data storage sub-network of the blockchain network to store a number of real-time data shards, real-time sample tracking and identification results, and real-time sample data analysis results of the test samples.

[0014] An inspection sample data tracking and identification system based on the Internet of Things is used to implement the inspection sample data tracking and identification method. The system includes a cloud data center, a number of Internet of Things gateways, a number of tag sensing devices, and a number of smart tags. Each Internet of Things gateway and each tag sensing device are set at the corresponding test sample storage point, and the Internet of Things gateway is communicatively connected to the tag sensing device at the test sample storage point. Each smart tag is set on the outer shell of the corresponding test sample. The cloud data center is communicatively connected to the Internet of Things gateways at all test sample storage points, and the cloud data center includes an initialization unit, a tampering verification unit, a sample tracking and identification unit, a sample data analysis unit, and a data storage unit connected in sequence.

[0015] The beneficial effects of the present invention are: The present invention discloses a method and system for tracking and identifying inspection sample data based on the Internet of Things. Through a blockchain network constructed by blockchain technology, data tampering is prevented, and real-time data is verified for tampering to ensure the authenticity and integrity of inspection sample data. The Internet of Things gateway is used to collect sample handover records in real time, and a sample tracking and identification model constructed in combination with artificial intelligence algorithms is used to achieve precise tracking and positioning of samples and standardize the management process of inspection sample data. A sample data analysis model is constructed, and deep learning and data analysis are carried out using artificial intelligence technology to be able to mine the deep information of real-time sample component data and improve the accuracy and comprehensiveness of data analysis. The automated collection, verification, analysis, and storage processes reduce manual intervention and significantly improve the efficiency of inspection sample management, being applicable to large-scale data scenarios. By combining the advantages of cloud storage and blockchain storage, the reliability of data storage is improved, data loss is prevented, and the impact of hardware failures or natural disasters is avoided.

[0016] Other beneficial effects of the present invention will be further described in the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a flowchart of the method for tracking and identifying inspection sample data based on the Internet of Things in the present invention.

[0018] Figure 2 is a structural block diagram of the system for tracking and identifying inspection sample data based on the Internet of Things in the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0019] The present invention will be further explained below with reference to the accompanying drawings and specific embodiments.

[0020] Embodiment 1: As Figure 1 shown, this embodiment provides a method for tracking and identifying inspection sample data based on the Internet of Things, including the following steps: S1: In the cloud data center, using artificial intelligence algorithms, construct a sample tracking and identification model and a sample data analysis model, and use blockchain technology to deploy a blockchain network, including the following steps: S1-1: In the cloud data center, using artificial intelligence algorithms, construct an initial sample tracking and identification model and an initial sample data analysis model; S1-2: Use the swarm intelligence optimization algorithm to optimize the initial sample tracking and identification model and the initial sample data analysis model to obtain an optimized sample tracking and identification model and an optimized sample data analysis model; The swarm intelligence optimization algorithm is an Improved Crested Porcupine Optimizer (ICPO) algorithm; Using the swarm intelligence optimization algorithm, optimize the initial sample tracking and recognition model and the initial sample data analysis model to obtain the optimized sample tracking and recognition model and the optimized sample data analysis model, including the following steps: S1-2-1: Encode the initial model parameters of the initial sample tracking and recognition model and the initial sample data analysis model as individual vectors of the ICPO algorithm; S1-2-2: Taking the minimization of the model error value as the optimization goal, use the optimization goal as the fitness function of the ICPO algorithm, and set the algorithm parameters and the maximum number of iterations of the ICPO algorithm; The formula is:

[0021] In the formula, is the fitness function of the ICPO individual ; is the model error value; is the ICPO individual variable; is the ICPO individual indicator; S1-2-3: According to the algorithm parameters and individual vectors of the ICPO algorithm, use the Circle chaotic mapping sequence for initialization to obtain the initial ICPO population; The formula is:

[0022] In the formula, is the initial ICPO individual of the Circle chaotic mapping; is the randomly generated initial ICPO individual; is the ICPO individual indicator; is the remainder function; S1-2-4: Use the fitness function to obtain the fitness value of each initial ICPO individual in the initial ICPO population and retain the optimal individual; S1-2-5: According to the fitness value, use the ICPO algorithm to iteratively update the initial ICPO population to obtain the updated ICPO population, including the following steps: S1-2-5-1: Introduce a cyclic population reduction mechanism to limit the number of individuals in the algorithm parameters to obtain the updated algorithm parameters for the next iteration; The formula is:

[0023] In the formula, is the number of individuals in the ICPO population parameters at the -th iteration; is the The number of individuals in the ICPO population parameters of the current iteration; Is the minimum number of individuals in the ICPO population parameters; Is the function evaluation parameter; Is the function evaluation loop parameter; Is the maximum function evaluation loop parameter; t Is the iteration number indicator; S1-2-5-2: Calculate the initial fitness values of the initial ICPO individuals in the initial ICPO population according to the fitness function; S1-2-5-3: Update the initial ICPO population using the first defense strategy, the second defense strategy, the third defense strategy, and the fourth defense strategy according to the initial fitness values and the updated ICPO population parameters to obtain the updated ICPO population; The formula for the first defense strategy is:

[0024] In the formula, Is the updated ICPO individual within the first defense range; Is the initial ICPO individual within the first defense range; Is a random number based on the normal distribution; Is a random value in the interval [0,1]; Is the optimal solution within the first defense range; Is the vector generated between the true optimal solution and the randomly selected optimal solution from the ICPO population within the first defense range; Is the ICPO individual indicator; Is the iteration indicator; The formula for the second defense strategy is:

[0025] In the formula, Is the updated ICPO individual within the second defense range; Is the initial ICPO individual within the second defense range; Is the search upper limit vector of the second defense range; Is a random value in the interval [0,1]; Are respectively the th initial ICPO individuals; Are both two random integers between [1, ; Is the vector generated between the true optimal solution and the randomly selected optimal solution from the ICPO population within the second defense range; The formula for the third defense strategy is:

[0026] Wherein, is the updated ICPO individual within the third defense range; is the initial ICPO individual within the third defense range; is the search upper limit vector of the third defense range; are respectively the th initial ICPO individuals; is a random integer between [1, ; is the odor diffusion factor defined by the fitness function; is the defense factor; is the search direction control parameter; The formula for the fourth defense strategy is:

[0027] Wherein, is the updated ICPO individual within the fourth defense range; is the initial ICPO individual within the fourth defense range; is the optimal solution within the fourth defense range; are all random values in the interval [0, 1]; is the defense factor; is the search direction control parameter; is the average force affecting the search direction; is the convergence speed factor; S1-2-6: Use the dynamic reverse mechanism to perform dynamic reverse on the initial ICPO population to obtain the dynamically reversed ICPO population; The formula is:

[0028] Wherein, is the dynamically reversed ICPO individual; is the decreasing inertia coefficient; are respectively the maximum and minimum values of the vector space; is the updated ICPO individual; S1-2-7: Use the fitness function to obtain the fitness values of each ICPO individual in the updated ICPO population and the dynamically reversed ICPO population; S1-2-8: Update the optimal individual according to the fitness value to obtain the updated optimal individual. If the current iteration number is greater than the maximum iteration number, output the updated optimal individual; S1-2-9: Decode the individual vector of the updated optimal individual to obtain the optimal initial model parameters of the initial sample tracking and recognition model and the initial sample data analysis model; S1-2-10: Optimize the initial sample tracking and recognition model and the initial sample data analysis model according to the optimal initial model parameters to obtain an optimized sample tracking and recognition model and an optimized sample data analysis model; S1-3: Collect a number of historical test sample data and preprocess the number of historical test sample data to obtain a number of preprocessed historical test sample data; S1-4: Train the optimized sample tracking and recognition model according to a number of preprocessed historical test sample data to obtain a final sample tracking and recognition model, and generate a number of historical sample tracking and recognition results; The sample tracking and recognition model is constructed based on the Long Short-Term Memory (LSTM)-Deep Belief Network (DBN) algorithm, and the sample tracking and recognition model includes a sample handover trajectory feature extraction module constructed based on the LSTM algorithm and a sample tracking and recognition module constructed based on the DBN algorithm, which are connected in sequence; The sample handover trajectory feature extraction module extracts the sample handover trajectory features in the test sample data that are combined into a handover record sequence in chronological order; the sample tracking and recognition module performs sample tracking and recognition according to the sample handover trajectory features, and identifies abnormal sample handover records and paths, including abnormal handover times, abnormal handover frequencies, and abnormal handover paths, etc.; S1-5: Train the optimized sample data analysis model according to a number of preprocessed historical test sample data to obtain a final sample data analysis model; The sample data analysis model is constructed based on the Random Forest (RF)-Attention-Multilayer Perceptron (MLP) algorithm, and the sample data analysis model includes a key feature extraction module constructed based on the RF algorithm, an attention weight module constructed based on the Attention mechanism, and a sample data analysis module constructed based on the MLP algorithm, which are connected in sequence; The key feature extraction module selects several important features of the sample component data through the ensemble learning of multiple decision trees, and selects the key features related to the analysis and prediction of the sample data from these important features as the feature basis for subsequent data analysis. For example, the sample data analysis includes the deep features of all index parameters and detection items for predicting the detection items, the important component parameter features of the detection items for accurately classifying the detection results, and the range features of each important component parameter for detecting abnormal component parameters; the attention weight module assigns different weights to different types of features through the Attention mechanism, enabling the model to pay more attention to the features that have a greater impact on the analysis results, thereby improving the accuracy of the analysis; the sample data analysis module is used to perform sample data analysis based on the weighted fusion features output by the attention weight module, including detection item analysis and prediction, detection result classification, abnormal component prediction, etc. S1-6: Use blockchain technology to distributively connect all data servers in the cloud data center as data nodes to obtain a blockchain network; S1-7: According to the identity assignment mechanism, divide several data nodes of the blockchain network into several consensus nodes and several storage nodes to obtain a data storage sub-network and a blockchain consensus sub-network, including the following steps: S1-7-1: Obtain the honest behaviors and malicious behaviors of each data node in the historical consensus process, and obtain the corresponding reputation values; Honest behaviors include correct transaction review behaviors, accurate identity verification behaviors, and compliance with laws, and malicious behaviors include incorrect transaction review behaviors, incorrect identity verification behaviors, and violations of laws; The formula is:

[0029] In the formula, is the reputation value of node at the iteration number ; is the reward value of the honest behavior level ; is the count of the honest behavior level L ; is the penalty value of the malicious behavior level ; is the count of the malicious behavior level ; is the data node indicator; is the iteration number indicator; is the honest behavior level; is the malicious behavior level; S1-7-2: Sort several data nodes in descending order according to their reputation values, and use the top M data nodes as consensus nodes, and the remaining data nodes as storage nodes; S1-7-3: Obtain a blockchain consensus sub-network based on several consensus nodes connected distributively, and obtain a data storage sub-network based on the storage nodes connected distributively; S2: The IoT gateway collects the real-time handover records of the detection samples at the current detection sample storage point and uploads the real-time handover records to the cloud data center, including the following steps: S2-1: The IoT gateway collects the real-time handover records of the detection samples at the current detection sample storage point, and encrypts the real-time handover records of the detection samples according to the private key of the IoT gateway to obtain encrypted real-time handover records; S2-2: Generate public key application information according to the IoT gateway information of the IoT gateway; The private key of the IoT gateway is generated by a trusted institution according to the IoT gateway information of the IoT gateway using a non-docking encryption algorithm, including a pair of public-private key pairs. The private key of the public-private key pair is sent to the corresponding IoT gateway, and the public key of the public-private key pair is stored inside the trusted institution; S2-3: Upload the encrypted real-time handover records and public key application information to the cloud data center; S3: The cloud data center verifies the tampering of the real-time handover records of the same detection sample at all detection sample storage points. After the tampering verification passes, it combines all the real-time handover records and the corresponding real sample component data to obtain the real-time inspection sample data of the detection sample; The real-time handover records include the location data of the detection sample storage point, the IP address of the IoT gateway, and the real-time inbound record and real-time outbound record of the detection sample at the detection sample storage point; The real-time inbound record is generated by the label sensing device set at the detection sample storage point sensing the information of the smart label on the outer shell of the inbound detection sample. The real-time inbound record includes the inbound timestamp and the basic information of the detection sample stored in the smart label. The real-time outbound record is generated by the label sensing device set at the detection sample storage point sensing the information of the smart label on the outer shell of the outbound detection sample. The real-time outbound record includes the outbound timestamp and the basic information of the detection sample stored in the smart label. The handover time information of the detection sample is reflected by the inbound timestamp and the outbound timestamp. The location data of several detection sample storage points constitutes the handover path information of the detection sample. The IP address of the IoT gateway is used for subsequent tampering verification; The cloud data center needs to perform a decryption operation after receiving the encrypted real-time handover records and public key application information uploaded by the IoT gateway to restore the encrypted real-time handover records to plaintext data, including the following steps: S3-1-1: The cloud data center invokes a trusted institution and sends the public key application information uploaded by the IoT gateway to the trusted institution. S3-1-2: If the legal verification of the public key application information by the trusted institution passes, accept the public key corresponding to the IoT gateway returned by the trusted institution. S3-1-3: Decrypt the corresponding encrypted real-time handover record according to the public key to obtain the decrypted real-time handover record. The cloud data center performs tampering verification on the real-time handover records of the same test sample at all test sample storage points. After the tampering verification passes, combine all the real-time handover records and the corresponding real-time sample component data to obtain the real-time test sample data of the test sample, including the following steps: S3-2-1: The cloud data center sends the real-time handover record of the same test sample at each test sample storage point to the corresponding IoT gateway for integrity comparison, including the following steps: S3-2-1-1: The cloud data center parses the real-time handover record to obtain the IP address of the IoT gateway at the corresponding test sample storage point. S3-2-1-2: According to the IP address of the IoT gateway, send the real-time handover record of each test sample storage point to the corresponding IoT gateway. S3-2-1-2: If the comparison verification of the received real-time handover record by the corresponding IoT gateway passes, return a comparison verification passed signal to the cloud data center. The IoT gateway receives the real-time handover record sent by the cloud data center and compares it with the corresponding real-time handover record stored locally. If they are the same, the comparison verification passes. S3-2-1-3: If the cloud data center receives the comparison verification passed signals returned by the IoT gateways at all test sample storage points of the same test sample, the tampering verification passes. The tampering verification is used to ensure that the records received by the cloud data center have not been tampered with a second time, improving the authenticity and reliability of the data. S3-2-1-4: After the tampering verification passes, combine all the real-time handover records and the corresponding real-time sample component data to obtain the real-time test sample data of the test sample. S3-2-2: Receive the integrity comparison success information returned by the IoT gateway. If the cloud data center receives the integrity comparison success information returned by the IoT gateways corresponding to all the real-time handover records, the tampering verification passes. S3-2-3: After the tampering verification passes, arrange all the real-time handover records in chronological order and the corresponding real-time sample component data to obtain the real-time test sample data of the test sample. S4: The cloud data center uses the sample tracking and identification model to perform sample tracking and identification on several real-time handover records of the real-time inspection sample data, and obtains the real-time sample tracking and identification results, including the following steps: S4-1: The cloud data center combines several real-time handover records of the real-time inspection sample data into a real-time handover record sequence in chronological order, and inputs the real-time handover record sequence into the sample tracking and identification model; S4-2: Use the sample handover trajectory feature extraction module of the sample tracking and identification model to extract the real-time sample handover trajectory features of the real-time handover record sequence; S4-3: Use the sample tracking and identification module of the sample tracking and identification model to perform sample tracking and identification according to the real-time sample handover trajectory features, and obtain the real-time sample tracking and identification results; The real-time sample tracking and identification results include the real-time abnormal handover time identification result, the real-time abnormal handover frequency identification result, and the real-time abnormal handover path identification result; S5: The cloud data center uses the sample data analysis model to perform sample data analysis on the real-time sample component data of the real-time inspection sample data, and obtains the real-time sample data analysis results, including the following steps: The cloud data center inputs the real-time sample component data of the real-time inspection sample data into the sample data analysis model; S5-1: Use the key feature extraction module of the sample data analysis model to extract several real-time key features of the real-time sample component data; S5-2: Use the attention weight module of the sample data analysis model to perform weighted fusion on several real-time key features according to the preset attention weight values to obtain real-time weighted fusion features; S5-3: Use the sample data analysis module of the sample data analysis model to perform sample data analysis according to the real-time weighted fusion features, and obtain the real-time sample data analysis results; The real-time sample data analysis results include the real-time detection item analysis and prediction results, the real-time detection result classification results, and the real-time abnormal component prediction results; S6: The cloud data center uses the blockchain network to store the real-time inspection sample data, the real-time sample tracking and identification results, and the real-time sample data analysis results of the detection sample, including the following steps: S6-1: The cloud data center performs data sharding on the real-time inspection sample data of the detection sample according to the replica sharding mechanism to obtain several real-time data shards including replicas; S6-2: Use the random encryption algorithm to encrypt several real-time data shards to obtain several encrypted real-time data shards, and generate a real-time data storage request; S6-3: Use the blockchain consensus sub-network of the blockchain network to conduct consensus on the real-time data storage request. After successful consensus, use the data storage sub-network of the blockchain network to store several real-time data shards of the detection sample, the real-time sample tracking and identification results, and the real-time sample data analysis results, including the following steps: S6-3-1: Take the consensus node that receives the real-time storage request in the blockchain consensus sub-network as the primary node, and use the primary node to send the real-time storage request to other consensus nodes; S6-3-2: According to the Byzantine Fault Tolerance (IPBFT) consensus algorithm, use the primary node to broadcast a pre-prepare message to other consensus nodes and verify the legality of the real-time storage request; S6-3-3: If the legality verification passes, use the primary node to broadcast a prepare message containing the voting information of the primary node to other consensus nodes and write the prepare message into the message log; S6-3-4: Based on all consensus nodes, exchange confirmation messages. If the primary node receives more than the quantity threshold of confirmation messages, the consensus is successful. Use the primary node to convert the real-time storage request and the consensus timestamp into a data block and chain the data block. Otherwise, the consensus fails; S6-3-5: After successful consensus, send several real-time data shards of the detection sample to several storage nodes of the data storage sub-network; S6-3-6: Use all storage nodes to locally store the received real-time data shards to obtain the real-time storage address and send real-time storage success information to other storage nodes; S6-3-7: Write the real-time storage address of the real-time data shard, the corresponding real-time sample tracking and identification results, and the real-time sample data analysis results into the distributed ledger of the data storage sub-network; S6-3-8: If each storage node receives more than the preset quantity threshold of several real-time storage success messages, end the storage step. Otherwise, continue the storage.

[0030] Example 2: As Figure 2As shown in the figure, this embodiment provides an inspection sample data tracking and identification system based on the Internet of Things, which is used to implement the inspection sample data tracking and identification method. The system includes a cloud data center, several Internet of Things gateways, several tag sensing devices, and several smart tags. Each Internet of Things gateway and each tag sensing device are set at the corresponding inspection sample storage point, and the Internet of Things gateway is communicatively connected to the tag sensing device at the inspection sample storage point. Each smart tag is set on the outer shell of the corresponding inspection sample. The cloud data center is communicatively connected to the Internet of Things gateways at all inspection sample storage points, and the cloud data center includes an initialization unit, a tampering verification unit, a sample tracking and identification unit, a sample data analysis unit, and a data storage unit that are connected in sequence.

[0031] The tag sensing device is used to sense the smart tags on the outer shells of the incoming and outgoing inspection samples, generate real-time inbound records and real-time outbound records, and send the real-time inbound records and real-time outbound records to the Internet of Things gateway at the corresponding inspection sample storage point. The Internet of Things gateway is used to generate real-time handover records of the inspection samples according to the location data of the inspection sample storage point, the IP address of the Internet of Things gateway, and the real-time inbound records and real-time outbound records of the inspection samples at the inspection sample storage point, and upload the real-time handover records to the cloud data center. The initialization unit is used to build a sample tracking and identification model and a sample data analysis model using artificial intelligence algorithms, and deploy a blockchain network using blockchain technology. The tampering verification unit is used to perform tampering verification on the real-time handover records of the same inspection sample at all inspection sample storage points. After the tampering verification passes, all the real-time handover records and the corresponding real-time sample component data are combined to obtain the real-time inspection sample data of the inspection sample. The sample tracking and identification unit is used to perform sample tracking and identification on several real-time handover records of the real-time inspection sample data using the sample tracking and identification model to obtain real-time sample tracking and identification results. The sample data analysis unit is used to perform sample data analysis on the real-time sample component data of the real-time inspection sample data using the sample data analysis model to obtain real-time sample data analysis results. The data storage unit is used to store the real-time inspection sample data, real-time sample tracking and identification results, and real-time sample data analysis results of the inspection samples using the blockchain network.

[0032] The present invention discloses a method and system for tracking and identifying inspection sample data based on the Internet of Things. Through a blockchain network constructed by blockchain technology, data tampering is prevented, and real-time data tampering verification is performed to ensure the authenticity and integrity of inspection sample data. The Internet of Things gateway is used to collect sample handover records in real time, and a sample tracking and identification model constructed in combination with artificial intelligence algorithms is used to achieve precise tracking and positioning of samples and standardize the management process of inspection sample data. A sample data analysis model is constructed, and deep learning and data analysis are performed using artificial intelligence technology to be able to mine the deep information of real-time sample component data and improve the accuracy and comprehensiveness of data analysis. The automated collection, verification, analysis, and storage processes reduce manual intervention and significantly improve the efficiency of inspection sample management, and are applicable to large-scale data scenarios. By combining the advantages of cloud storage and blockchain storage, the reliability of data storage is improved, data loss is prevented, and the impact of hardware failures or natural disasters is avoided.

[0033] The present invention is not limited to the above optional embodiments, and anyone can obtain other various forms of products under the inspiration of the present invention. The above specific embodiments should not be construed as limiting the protection scope of the present invention, and the protection scope of the present invention should be defined by the claims, and the description can be used to interpret the claims.

Claims

1. An inspection sample data tracking and identification method based on the Internet of Things, characterized in that: Including the following steps: The cloud data center uses artificial intelligence algorithms to build a sample tracking and recognition model and a sample data analysis model, and uses blockchain technology to deploy a blockchain network; The Internet of Things gateway collects the real-time handover records of the detection samples at the current detection sample storage points and uploads the real-time handover records to the cloud data center; The cloud data center verifies the tampering of the real-time handover records of the same detection sample at all detection sample storage points. After the tampering verification passes, it combines all the real-time handover records and the corresponding real-time sample composition data to obtain the real-time inspection sample data of the detection sample; The cloud data center uses the sample tracking and recognition model to perform sample tracking and recognition on several real-time handover records of the real-time inspection sample data to obtain real-time sample tracking and recognition results; The cloud data center uses the sample data analysis model to perform sample data analysis on the real-time sample composition data of the real-time inspection sample data to obtain real-time sample data analysis results; The cloud data center uses the blockchain network to store the real-time inspection sample data, real-time sample tracking and recognition results, and real-time sample data analysis results of the detection sample; 2. The method for tracking and identifying inspection sample data based on the Internet of Things according to claim 1, wherein: The cloud data center uses artificial intelligence algorithms to build a sample tracking and recognition model and a sample data analysis model, and uses blockchain technology to deploy a blockchain network, including the following steps: The cloud data center uses artificial intelligence algorithms to build an initial sample tracking and recognition model and an initial sample data analysis model; Use the swarm intelligence optimization algorithm to optimize the initial sample tracking and recognition model and the initial sample data analysis model to obtain an optimized sample tracking and recognition model and an optimized sample data analysis model; Collect several historical inspection sample data and preprocess the several historical inspection sample data to obtain several preprocessed historical inspection sample data; According to the several preprocessed historical inspection sample data, train the optimized sample tracking and recognition model to obtain the final sample tracking and recognition model and generate several historical sample tracking and recognition results; According to the several preprocessed historical inspection sample data, train the optimized sample data analysis model to obtain the final sample data analysis model; Use blockchain technology to distributively connect all the data servers in the cloud data center as data nodes to obtain a blockchain network; According to the identity allocation mechanism, divide several data nodes of the blockchain network into several consensus nodes and several storage nodes to obtain a data storage sub-network and a blockchain consensus sub-network; 3. The method for tracking and identifying inspection sample data based on the Internet of Things according to claim 2, characterized in that: The sample tracking and recognition model is built based on the LSTM-DBN algorithm, and the sample tracking and recognition model includes a sample handover trajectory feature extraction module built based on the LSTM algorithm and a sample tracking and recognition module built based on the DBN algorithm, which are connected in sequence; The sample data analysis model is built based on the RF-Atteniton-MLP algorithm, and the sample data analysis model includes a key feature extraction module built based on the RF algorithm, an attention weight module built based on the Attention mechanism, and a sample data analysis module built based on the MLP algorithm, which are connected in sequence; The swarm intelligence optimization algorithm described above is the ICPO algorithm.

4. A method for tracking and identifying inspection sample data based on the Internet of Things according to claim 3, characterized in that: Using the swarm intelligence optimization algorithm to optimize the initial sample tracking and recognition model and the initial sample data analysis model to obtain an optimized sample tracking and recognition model and an optimized sample data analysis model, the steps are as follows: Encode the initial model parameters of the initial sample tracking and recognition model and the initial sample data analysis model as the individual vectors of the ICPO algorithm; Taking the minimization of the model error value as the optimization objective, use the optimization objective as the fitness function of the ICPO algorithm, and set the algorithm parameters and the maximum number of iterations of the ICPO algorithm; According to the algorithm parameters and individual vectors of the ICPO algorithm, perform initialization to obtain the initial ICPO population; Use the fitness function to obtain the fitness value of each initial ICPO individual in the initial ICPO population and retain the optimal individual; According to the fitness value, use the ICPO algorithm to iteratively update the initial ICPO population to obtain an updated ICPO population; Use the dynamic reverse mechanism to perform dynamic reverse on the initial ICPO population to obtain a dynamically reversed ICPO population; Use the fitness function to obtain the fitness value of each ICPO individual in the updated ICPO population and the dynamically reversed ICPO population; According to the fitness value, update the optimal individual to obtain an updated optimal individual. If the current number of iterations is greater than the maximum number of iterations, output the updated optimal individual; Decode the individual vector of the updated optimal individual to obtain the optimal initial model parameters of the initial sample tracking and recognition model and the initial sample data analysis model; According to the optimal initial model parameters, optimize the initial sample tracking and recognition model and the initial sample data analysis model to obtain an optimized sample tracking and recognition model and an optimized sample data analysis model.

5. The method for tracking and identifying inspection sample data based on the Internet of Things according to claim 4, wherein: The real-time handover record described above includes the location data of the detection sample storage point, the IP address of the Internet of Things gateway, and the real-time inbound record and real-time outbound record of the detection sample at the detection sample storage point.

6. The method for tracking and identifying inspection sample data based on the Internet of Things according to claim 5, characterized in that: The cloud data center performs tampering verification on the real-time handover records of the same detection sample at all detection sample storage points. After the tampering verification passes, combine all the real-time handover records and the corresponding real-time sample component data to obtain the real-time inspection sample data of the detection sample. The steps are as follows: The cloud data center sends the real-time handover record of the same detection sample at each detection sample storage point to the corresponding Internet of Things gateway for integrity comparison at the Internet of Things gateway; Receive the integrity comparison success information returned by the Internet of Things gateway. If the cloud data center receives the integrity comparison success information returned by the Internet of Things gateways corresponding to all real-time handover records, the tampering verification passes; After the tampering verification passes, arrange all the real-time handover records in chronological order and the corresponding real-time sample component data to obtain the real-time inspection sample data of the detection sample.

7. A method for tracking and identifying inspection sample data based on the Internet of Things according to claim 6, characterized in that: The cloud data center uses the sample tracking and recognition model to perform sample tracking and recognition on several real-time handover records of the real-time inspection sample data to obtain the real-time sample tracking and recognition result. The steps are as follows: The cloud data center combines a number of real-time handover records of real-time inspection sample data into a real-time handover record sequence in chronological order, and inputs the real-time handover record sequence into the sample tracking and identification model; Using the sample handover trajectory feature extraction module of the sample tracking and identification model, extract the real-time sample handover trajectory features of the real-time handover record sequence; Using the sample tracking and identification module of the sample tracking and identification model, perform sample tracking and identification according to the real-time sample handover trajectory features to obtain the real-time sample tracking and identification results.

8. The method for tracking and identifying inspection sample data based on the Internet of Things according to claim 7, wherein: The cloud data center uses the sample data analysis model to perform sample data analysis on the real-time sample component data of the real-time inspection sample data to obtain the real-time sample data analysis results, including the following steps: The cloud data center inputs the real-time sample component data of the real-time inspection sample data into the sample data analysis model; Using the key feature extraction module of the sample data analysis model, extract a number of real-time key features of the real-time sample component data; Using the attention weight module of the sample data analysis model, perform weighted fusion on a number of real-time key features according to the preset attention weight values to obtain real-time weighted fusion features; Using the sample data analysis module of the sample data analysis model, perform sample data analysis according to the real-time weighted fusion features to obtain the real-time sample data analysis results.

9. The method for tracking and identifying inspection sample data based on the Internet of Things according to claim 8, wherein: The cloud data center uses the blockchain network to store the real-time inspection sample data, real-time sample tracking and identification results, and real-time sample data analysis results of the detection samples, including the following steps: The cloud data center performs data sharding on the real-time inspection sample data of the detection samples according to the replica sharding mechanism to obtain a number of real-time data shards including replica shards; Use the random encryption algorithm to encrypt a number of real-time data shards to obtain a number of encrypted real-time data shards, and generate a real-time data storage request; Use the blockchain consensus sub-network of the blockchain network to perform consensus on the real-time data storage request. After successful consensus, use the data storage sub-network of the blockchain network to store a number of real-time data shards, real-time sample tracking and identification results, and real-time sample data analysis results of the detection samples.

10. An inspection sample data tracking and identification system based on the Internet of Things, which is used to implement the inspection sample data tracking and identification method as described in any one of claims 1-9, and is characterized in that: The described system includes a cloud data center, a number of Internet of Things gateways, a number of tag sensing devices, and a number of smart tags. Each of the Internet of Things gateways and each of the tag sensing devices are set at the corresponding detection sample storage points, and the Internet of Things gateway is communicatively connected to the tag sensing device at the detection sample storage point. Each of the smart tags is set on the outer shell of the corresponding detection sample. The cloud data center is communicatively connected to the Internet of Things gateways at all detection sample storage points, and the cloud data center includes an initialization unit, a tampering verification unit, a sample tracking and identification unit, a sample data analysis unit, and a data storage unit that are connected in sequence.

Images