Digitized animal health supervision method and system based on big data
By integrating data from the entire animal health chain through big data and blockchain technology, dividing regulatory zones and calculating risk values, and generating tamper-proof evidence records, the problem of data fragmentation and delayed risk identification in the traditional regulatory model has been solved, achieving precise and efficient regulation throughout the entire life cycle.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-19
- Publication Date
- 2026-03-20
AI Technical Summary
The existing animal health supervision model relies on manual inspections and paper records, resulting in unreal-time data collection, delayed risk identification, difficulties in cross-link traceability, low accuracy of risk assessment, poor timeliness of early warning, and difficulty in achieving full-cycle supervision.
By adopting a big data-based digital supervision method, animal identification is bound to passive sensor tags with RFID chips, integrating data from the entire chain, dividing the area into regulatory zones, calculating comprehensive and in-depth risk values, and using blockchain technology to generate tamper-proof evidence records, a closed-loop supervision is formed.
It has achieved standardized data management throughout the entire lifecycle, improved the accuracy and foresight of risk identification, ensured the security and traceability of data, reduced the cost of manual verification, and achieved precise and efficient supervision.
Smart Images
Figure CN121707345A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of industrial internet technology, and in particular to a method and system for digital supervision of animal health based on big data. Background Technology
[0002] Animal health supervision is a core link in ensuring public health security and the healthy development of animal husbandry. Existing supervision models largely rely on manual inspections and paper-based records, which suffer from problems such as unreal-time data collection, delayed risk identification, difficulties in cross-chain traceability, and insufficient prediction of risk transmission between regions. Some digital supervision systems focus only on data collection from a single stage, failing to integrate data from the entire chain of breeding, distribution, and slaughter, and neglecting to consider risk interference between different regions and different livestock species. This results in low accuracy of risk assessment and poor timeliness of early warnings, making it difficult to achieve precise, full-cycle animal health supervision. Summary of the Invention
[0003] This invention provides a big data-based digital supervision method for animal health, which addresses the shortcomings of existing technologies such as insufficient data integration across the entire animal health supervision chain, low risk identification accuracy, and slow early warning response.
[0004] The present invention provides a big data-based digital animal health supervision method, comprising: S1: Collect data from the entire animal health chain, customize passive sensor tags with RFID chips, assign unique physical fingerprint ear tags to animals for identification, and obtain fingerprint ear tag information.
[0005] S2: Preprocess the fingerprint ear tag information and divide it into regulatory zones. Then, collect the processed data into the corresponding zones to obtain a dedicated dataset.
[0006] S3: Calculate the comprehensive risk value of each partition from the risk value of the dedicated dataset for immune compliance and physiological abnormality identification, and record the risk tracing information associated with the fingerprint ear tag.
[0007] S4: Calculate the depth risk value for each zone based on the comprehensive risk value, the degree of risk hazard, and the interference coefficient between zones.
[0008] S5: Synchronizes the raw data containing comprehensive risk value and deep risk value to the blockchain mini node, hashes and encrypts it, binds it with the physical fingerprint of the tag to generate an immutable evidence record, and caches offline data.
[0009] S6: Compare the fingerprint and ear tag information with the risk value stored on the blockchain to determine if any abnormality has occurred. If so, issue an alarm and generate control instructions based on the deep risk value. Regulatory personnel then retrieve the stored evidence to complete the traceability verification, thus forming a regulatory closed loop.
[0010] According to the big data-based digital animal health supervision method provided by the present invention, the specific steps for obtaining the tag ear tag information in step S1 are as follows: S11: Collect big data from the entire animal health chain, classify and archive the data to form a structured raw animal health dataset.
[0011] S12: Based on the category and batch characteristics of the original animal health dataset, customize passive sensor tags with integrated RFID chips, write the chips, and generate ear tag hardware carriers with unique physical fingerprints.
[0012] S13: Match the ear tag hardware carrier with the batch information of each animal in the original animal health dataset one by one to form a matching list.
[0013] S14: Based on the matching list, write the basic information of the animals and the breeding registration information of the corresponding batch into the RFID chip, complete the deep binding of the physical fingerprint of the tag and the animal identity information, and output the tagged animal ledger with the binding completed.
[0014] S15: Verify the consistency between the physical fingerprint of the tag, the animal identification information and the original dataset according to the tagged animal ledger. After the verification is passed, obtain the fingerprint ear tag information.
[0015] According to the big data-based digital animal health supervision method provided by the present invention, the specific steps for obtaining the dedicated dataset in step S2 are as follows: S21: Filter out incorrect and duplicate fingerprint ear tag information, supplement missing breeding / immunization information, and form standardized fingerprint ear tag information.
[0016] S22: Based on the breeding type, administrative region, and circulation node in the fingerprint ear tag information, the regulatory scope is divided into sub-exclusive regulatory zones, zone codes are compiled, and the regulatory boundaries and animal batches covered by each zone are clearly defined.
[0017] S23: Match the standardized fingerprint ear tag information to the sub-dedicated regulatory zone according to the zone code corresponding to the animal batch, and record the tag physical fingerprint and animal health related data list under the zone.
[0018] S24: Based on the matched tag and ear tag data and animal health-related data, establish a dedicated dataset for each regulatory zone, label the data source and update time, and form a dedicated dataset.
[0019] According to the big data-based digital supervision method for animal health provided by the present invention, the specific steps for establishing the animal health-related data list in step S23 are as follows: A mapping table between animal batches and zoning codes is constructed. Based on the batch attributes in the standardized fingerprint ear tag information, the corresponding sub-specific regulatory zoning codes are automatically matched, and a matching relationship log is generated.
[0020] Based on the matching relationship log, the physical fingerprints of the tags and basic animal information for each batch are collected into the temporary database of the corresponding sub-dedicated regulatory zone.
[0021] The data in the temporary database is sorted out and categorized by fingerprint number, animal batch, and data type to generate a list of physical fingerprints and animal health-related data for each sub-exclusive regulatory zone, and the data ownership is marked.
[0022] According to the big data-based digital animal health supervision method provided by the present invention, the specific steps for calculating the comprehensive risk value in step S3 are as follows: S31: Retrieve the dedicated datasets of each regulatory zone, extract the tag fingerprint association information, verify the compliance of immunization coverage and withdrawal period, calculate the immunization compliance risk value of each zone according to the proportion of violations, and associate the tag fingerprint record with the violation tracing information.
[0023] S32: Identify the proportion of animals with abnormal body temperature and behavior based on the dedicated dataset, calculate the physiological abnormality risk value for each partition, and supplement it to the risk tracing information associated with fingerprints and ear tags.
[0024] S33: Calculate the comprehensive risk value based on the immune compliance risk value and the physiological abnormality risk value, and bind the calculation result with the tag fingerprint to improve the core data dimension of risk traceability information.
[0025] S34: Summarize the comprehensive risk value, individual risk value, and traceability clues associated with tag fingerprints for each partition, and archive them by partition code, tag fingerprint, and risk type to form a risk traceability information database.
[0026] According to the big data-based digital animal health supervision method provided by the present invention, the specific steps for calculating the deep risk value in step S4 are as follows: S41: Retrieve the comprehensive risk value and corresponding tag fingerprint from the risk tracing information database, match them with the preset risk hazard mapping table, calculate the degree of hazard R of each partition risk to other partitions, and form a hazard degree list.
[0027] S42: Based on the spacing between each zone, the frequency of transportation and circulation, and climate data, the interference coefficient kj between each zone is calculated by substituting it into the interference coefficient formula, and the interference coefficient of the corresponding zone is marked on the list of associated hazard levels.
[0028] S43: Integrate the comprehensive risk value, hazard level R, and interference coefficient kj of each zone, substitute them into the deep risk value formula to calculate the deep risk value of each zone, and synchronously associate the tag fingerprint record calculation basis.
[0029] S44: Compare the calculated deep risk value with historical data and the current epidemic situation, calibrate the value, verify the rationality of the value, and add the final deep risk value to the risk traceability information database after calibration.
[0030] According to the big data-based digital animal health supervision method provided by the present invention, the specific steps for generating tamper-proof evidence records in step S5 are as follows: S51: Based on the original data of each partition and the physical fingerprint information of the tag, the data is synchronized to the blockchain mini node through an encrypted transmission protocol to form a synchronization log.
[0031] S52: Hash and encrypt the raw data received by the blockchain mini-node according to the synchronization log, generate a unique encrypted hash value, and deeply bind the encrypted hash value with the tag's physical fingerprint.
[0032] S53: Generate an immutable blockchain evidence record based on the bound encrypted hash value and the tag physical fingerprint. Offline cache the synchronized data in the absence of network, mark the cache time, and automatically re-enter it into the evidence record after the network is restored.
[0033] According to the big data-based digital animal health supervision method provided by the present invention, the specific steps in step S52 of deeply binding the encrypted hash value with the tag's physical fingerprint are as follows: Based on the synchronization logs, the original data successfully received by the nodes and their corresponding physical fingerprints are filtered out, while data that failed to be received or had incorrect formats are excluded, forming an encrypted dataset to be processed.
[0034] The SHA-256 algorithm is used to hash and encrypt the original data in the dataset to be processed, generating a unique encrypted hash value. The original data batch and tag fingerprint corresponding to each hash value are recorded.
[0035] Establish a one-to-one mapping relationship between the physical fingerprint of the tag and the encrypted hash value, and write the binding information into the distributed ledger of the blockchain node to ensure that each tag fingerprint corresponds to only one hash value, thus preventing data tampering.
[0036] According to the big data-based digital animal health supervision method provided by the present invention, the specific steps for forming a supervision closed loop in step S6 are as follows: S61: Use an RFID reader to read the physical fingerprint and associated data of the tag, and automatically compare the local data with the comprehensive risk value and deep risk value in the evidence storage based on the blockchain evidence storage record, and record the comparison results.
[0037] S62: Determine whether the data is consistent based on the comparison results. If it is, keep it unchanged; otherwise, it is determined to be abnormal. The card reader immediately triggers an audible and visual alarm and simultaneously pushes the abnormal label fingerprint and risk value difference information to the regulatory terminal, marking the abnormal type.
[0038] S63: Based on the abnormal information and the deep risk value of the blockchain evidence, generate corresponding control instructions according to the risk level.
[0039] S64: By combining blockchain-stored data with information from all stages of the label process, we can complete the tracing of the source of the epidemic and the verification of data fraud. After the verification is completed, the disposal records are archived to form a regulatory closed loop of identification-early warning-disposal-verification.
[0040] This invention also provides a big data-based digital animal health monitoring system, comprising: The ear tag binding module is used to collect data from the entire animal health chain, and to customize passive sensor tags with RFID chips to assign unique physical fingerprint ear tags to animals for identification and obtain fingerprint ear tag information.
[0041] The data partitioning module is used to preprocess fingerprint ear tag information, divide it into regulatory partitions, and collect the processed data into the corresponding partitions to obtain a dedicated dataset.
[0042] The risk tracing module is used to identify risk values from a dedicated dataset based on immune compliance and physiological abnormalities, calculate the comprehensive risk value for each partition, and record risk tracing information associated with fingerprint ear tags.
[0043] The in-depth risk control module is used to calculate the in-depth risk value for each zone based on the comprehensive risk value, the degree of risk severity, and the interference coefficient between zones.
[0044] The on-chain evidence storage module is used to synchronize the original data containing comprehensive risk value and deep risk value to the blockchain mini node, hash and encrypt it, and bind it with the physical fingerprint of the tag to generate an immutable evidence storage record, and cache offline data.
[0045] The closed-loop control module compares the fingerprint ear tag information with the risk value stored on the blockchain to determine if any anomalies have occurred. If so, an alarm is issued, and control instructions are generated based on the deep risk value. Regulatory personnel then retrieve the stored evidence to complete the traceability verification, thus forming a closed-loop control system.
[0046] The big data-based digital animal health supervision method provided by this invention solves the core pain points of traditional animal health supervision, such as fragmented data, delayed risk identification, and difficulty in traceability, through the technical logic of full-chain data integration, multi-dimensional risk identification, blockchain evidence storage, and closed-loop management. It has significant advantages in multiple dimensions and achieves the following beneficial effects: This invention achieves standardized management and control of animal health data throughout its entire lifecycle. The data collection phase covers four major categories of data across the entire chain: basic information, dynamic monitoring, environment, and distribution / slaughter. Combined with the unique physical fingerprint binding of RFID passive sensor tags, it ensures precise association between data and individual animals / batch from the source, avoiding the problem of data disconnect between traditional ledger records and the regulated entities. The data preprocessing stage uses error removal, missing data completion, and partitioned aggregation to form a dedicated dataset. Regulatory zones are divided according to farming type, administrative region, and distribution node, enabling structured and partitioned management of scattered regulatory data, significantly improving data accessibility and laying a precise data foundation for subsequent risk analysis.
[0047] This invention constructs a two-tiered risk assessment system consisting of a comprehensive risk value and a deep risk value, significantly improving the accuracy and foresight of risk identification. The comprehensive risk value is calculated from two core dimensions: immune compliance and physiological abnormalities. This comprehensive risk value is then calibrated by combining the type of livestock and the level of disease. This system covers both basic compliance risks and captures early signs of disease at the physiological level in animals. The calculation of the deep risk value incorporates the degree of hazard and interference coefficients across different zones, fully considering the interference of disease transmission between different zones. This overcomes the limitations of traditional single-zone risk assessment, enabling the prediction of cross-regional disease transmission risks and shifting risk warning from post-event response to pre-event prediction.
[0048] The integration of blockchain technology in this invention enables the immutability and full-process traceability of regulatory data. After the original data containing risk values is synchronized to the blockchain mini-node, it is encrypted with SHA-256 hash and bound to the physical fingerprint of the tag to generate a storage record. This not only eliminates the possibility of data tampering and forgery, but also ensures the integrity of data in remote areas and scenarios without network access through an offline caching mechanism.
[0049] This invention automatically generates tiered control instructions based on deep risk values and accurately pushes them to the corresponding area managers, avoiding the problems of inaccurate instruction issuance and delayed response in traditional supervision. Areas that have not completed control measures will be continuously monitored until the risk is eliminated, ensuring that regulatory instructions are effectively implemented. The entire process uses data-linked tags and physical fingerprints, allowing regulators to quickly locate the source of risk, significantly reducing manual verification costs and improving regulatory efficiency.
[0050] In summary, this invention deeply integrates big data, IoT, and blockchain technologies with animal health supervision, achieving standardized and precise management of regulatory data, enhancing the foresight of risk identification and data security, and ensuring the implementation of regulatory measures through closed-loop management, thus providing a precise, efficient, and traceable digital solution for animal health supervision. Attached Figure Description
[0051] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0052] Figure 1 This is a flowchart illustrating the steps of the big data-based digital animal health supervision method provided in this embodiment of the invention. Figure 2 This is a flowchart of the big data-based digital animal health supervision method provided in an embodiment of the present invention; Figure 3 This is a module diagram of the big data-based digital animal health supervision system provided in this embodiment of the invention. Detailed Implementation
[0053] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.
[0054] The following is combined with Figures 1-3 This invention describes a big data-based digital animal health supervision method and system.
[0055] like Figures 1-3 As shown in the figure, the big data-based digital animal health supervision method provided in this embodiment of the invention mainly includes the following steps: S1: Collect data from the entire animal health chain, customize passive sensor tags with integrated RFID chips, assign each batch of animals an ear tag with a unique physical fingerprint, bind their identity, and obtain tag ear tag information.
[0056] S11: Collect big data covering the entire animal health chain, including basic information, dynamic monitoring, environment, circulation and slaughter, complete data classification and archiving, and form a structured raw animal health dataset to provide a data foundation for subsequent tag binding.
[0057] Animal health big data includes basic information data, dynamic monitoring data, environmental data, and circulation and slaughter data: Basic information data: covering information on the registration of breeding entities, animal species / batch information, compulsory immunization records, veterinary drug / feed usage ledgers, and livestock and poultry identification (ear tags / QR codes).
[0058] Dynamic monitoring data: Animal surface temperature, activity status, physiological signs data collected through passive sensor tags, as well as dynamic video footage of the breeding / transportation / slaughtering process.
[0059] Environmental data: Environmental parameters such as temperature and humidity, ammonia concentration, disinfection records, and ventilation conditions at farms / transport vehicles / slaughterhouses.
[0060] Slaughter data in circulation: animal quarantine certificate information, transportation route / duration, slaughter entry inspection record, synchronous quarantine results, and harmless treatment record.
[0061] S12: Based on the category and batch characteristics of the original animal health dataset, customize passive sensing tags that integrate RFID chips and temperature / humidity / body temperature sensitive materials to generate ear tag hardware carriers with unique physical fingerprints.
[0062] S13: Match the ear tag hardware carrier with a unique physical fingerprint with the batch information of each animal in the original animal health dataset, record the correspondence between the batch code and the physical fingerprint of the tag, and form a matching list.
[0063] S14: Based on the matching list of batch and tag physical fingerprint, write the basic animal information and breeding registration information of the corresponding batch into the RFID chip, complete the deep binding of tag physical fingerprint and animal identity information, and output the tagged animal ledger with binding completed.
[0064] S15: Retrieve the tagged animal register, verify the consistency between the tag's physical fingerprint, animal identification information and the original dataset. After verification, synchronize the bound data to the temporary database to provide accurate tag-animal association data for subsequent data preprocessing.
[0065] S2: Preprocess the tag ear tag information and divide it into regulatory partitions. Then, collect the processed data into the corresponding partitions to obtain a dedicated dataset.
[0066] S21: Filter and remove erroneous and duplicate fingerprint ear tag information, supplement missing breeding information, and form standardized fingerprint ear tag information. Retrieve tag-animal association data, and use algorithms to compare the uniqueness of the tag's physical fingerprint and the correspondence between the ear tag code and the animal batch to identify erroneous data. Deduplicate by fingerprint + batch dimension, and remove duplicate ear tag information uploaded from the same batch. For ear tag data with missing breeding information, link it to the breeding registration ledger and immunization record database to automatically fill in the missing fields. If no matching data is found, mark it as pending verification and push it to grassroots personnel for manual entry. Organize the verified ear tag data into a unified format, standardize the naming and numerical units of fields such as fingerprint code, breeding type, and immunization time, and generate a structured standardized fingerprint ear tag information table.
[0067] S22: Based on the breeding type, administrative region, and distribution node in the fingerprint ear tag information, the regulatory scope is divided into sub-exclusive regulatory zones, and zone codes are assigned to clarify the regulatory boundaries and the range of animal batches covered by each zone. The three core dimensions of breeding type, administrative region, and distribution node are extracted from the standardized fingerprint ear tag information to determine the hierarchy and basis for zone division. Following the logic of combining administrative region + breeding type + distribution node, the regulatory scope is divided into sub-exclusive regulatory zones, and the geographical boundaries of each zone are clarified. A unique code is assigned to each sub-exclusive regulatory zone, and a list of animal batches covered by each zone is compiled to establish a correspondence between codes and batches.
[0068] S23: Match the standardized fingerprint ear tag information to the sub-dedicated regulatory zone according to the zone code corresponding to the animal batch, and record the tag physical fingerprint and animal health related data list under the zone.
[0069] A mapping table between animal batches and zoning codes is constructed. Based on the batch attributes in the standardized fingerprint and ear tag information, the corresponding sub-specific regulatory zoning code is automatically matched, generating a matching relationship log. Based on the matching relationship log, the physical fingerprints of each batch's tags and basic animal information are collected into a temporary database for the corresponding sub-specific regulatory zoning. The data in the temporary database is then organized and categorized by fingerprint number, animal batch, and data type to generate a list of physical fingerprints of tags and a list of animal health-related data for each sub-specific regulatory zoning, with data attribution clearly marked.
[0070] S24: Based on the matched tag and ear tag data and animal health-related data, establish a dedicated dataset for each regulatory zone, label the data source and update time, and form a dedicated dataset.
[0071] A dedicated dataset framework is built for each sub-dedicated regulatory zone, setting up data modules such as basic information, dynamic monitoring, and compliance records. The data storage format and association rules of each module are defined. The matched tag and ear tag data and animal health-related data are entered into the corresponding modules. The collection source, first entry time, and latest update time of each data are marked. The integrity of each zone's dataset and the logical consistency between data are verified. The datasets that pass the verification are encapsulated to generate a dedicated dataset file for the sub-dedicated regulatory zone that can be directly called.
[0072] S3: Identify risk values from a dedicated dataset based on immune compliance and physiological abnormalities, calculate the comprehensive risk value for each partition, and record the risk tracing information associated with the tag fingerprint.
[0073] S31: Retrieve the dedicated datasets for each regulatory zone, extract information such as immunization records and vaccine batch numbers associated with tag fingerprints, verify the immunization coverage rate and withdrawal period compliance, calculate the immunization compliance risk value for each zone based on the violation ratio, and associate the tag fingerprint records with violation tracing information. Retrieve the dedicated datasets for each regulatory zone, extract information such as immunization records, vaccine batch numbers, and immunization times associated with tag fingerprints, verify the completeness of immunization categories against the mandatory immunization list, calculate the immunization coverage rate based on the number of breeding batches, and simultaneously verify the compliance of veterinary drug withdrawal period records.
[0074] The violation rate is calculated by statistically analyzing the number of unimmunized animals in each zone and the percentage of animal batches that illegally used veterinary drugs during the withdrawal period. This violation rate is then mapped to the initial value of immunization compliance risk.
[0075] The initial value of immunization compliance risk is calibrated based on the type of livestock and the level of disease prevention and control to obtain the final immunization compliance risk value. The risk value, violation details, and corresponding tag fingerprints are then linked to record violation tracing information.
[0076] S32: Based on the animal surface temperature, activity status, and other data corresponding to the tag fingerprints centrally labeled in the dedicated dataset, identify the proportion of animals with abnormal body temperature and behavior, calculate the physiological abnormality risk value for each partition, and supplement it to the risk tracing information associated with the tag fingerprints. Based on the animal surface temperature and activity status sensor data corresponding to the tag fingerprints centrally labeled in the dedicated dataset, set the normal body temperature range and the threshold for judging abnormal behavior, and screen out individual animals with excessive body temperature and batches of animals with sudden drops / increases in activity.
[0077] The proportion of animals with abnormal body temperature / behavior in each zone to the total number of animals in that zone is statistically analyzed, and the physiological abnormality risk value is calculated by multiplying the abnormality proportion by the weighting coefficient.
[0078] The physiological abnormality risk value, the tag fingerprint of the abnormal animal, and the abnormal data timestamp are added to the tag fingerprint-related risk tracing information to improve the tracing dimension of abnormal risks.
[0079] S33: Integrate the immune compliance risk values and physiological abnormality risk values from each zone, calculate the comprehensive risk value using preset weights, and bind the calculation results to tag fingerprints to improve the core data dimensions of risk tracing information. Preset the weights for immune compliance risk values and physiological abnormality risk values, and integrate them by zone to form the basic data for risk value calculation. Calculate the comprehensive risk value for each regulatory zone using a weighted summation formula, retaining two decimal places to ensure accuracy. Batch bind the comprehensive risk value to the tag fingerprints of the corresponding zone and update it to the risk tracing information, supplementing the comprehensive risk level dimension and improving the core data system of risk tracing information.
[0080] S34: Summarize the overall risk value, individual risk value, and traceability clues associated with tag fingerprints for each partition, and archive them by partition code, tag fingerprint, and risk type to form a structured risk traceability information database. Collect the overall risk value, individual risk value for immune compliance / physiological abnormality, and all traceability clues for violations and abnormalities associated with tag fingerprints for each partition, and initially classify them by partition code.
[0081] The collected data is broken down according to the dimensions of partition coding, tag fingerprint, and risk type, and the source and discovery time of each traceability clue are marked. The structured and classified data is entered into the database, an index is created, and a searchable and traceable risk traceability information database is generated, providing complete data support for in-depth risk value calculation.
[0082] S4: Calculate the depth risk value for each zone based on the comprehensive risk value, the degree of risk hazard, and the interference coefficient between zones.
[0083] S41: Retrieve the comprehensive risk value and corresponding tag fingerprint from the risk traceability information database and match them against a pre-defined risk hazard mapping table. Calculate the degree of harm (R) of each zone's risk to other zones, forming a hazard level list. Retrieve the comprehensive risk value of each zone, the animal species associated with the tag fingerprint, and the risk type from the risk traceability information database, and organize them into a structured risk baseline data list according to zone codes. Match the risk baseline data list with the pre-defined risk hazard mapping table to determine the baseline hazard value of each zone's risk to other zones. Combine the baseline hazard value with the disease transmission characteristics to obtain the final hazard level (R), and organize it in the format of source zone-target zone-R value to form a hazard level list labeled with tag fingerprint traceability information.
[0084] S42: Based on the distance between each zone, the frequency of animal transport and circulation, and climate data, the interference coefficient kj between each zone is calculated by substituting it into the interference coefficient formula. The interference coefficient of the corresponding zone is marked on the list of associated hazard levels. Geographical distance, animal transport and circulation frequency, and climate data of each regulatory zone are collected and organized into an interference coefficient calculation parameter table by zone. The data in the parameter table is then substituted into the interference coefficient formula (…). ), calculate the interference coefficient k between each pair of partitions. j The calculated interference coefficient k j The source partition and target partition dimensions are linked to the hazard level list, and an interference coefficient field is added to the list to complete the labeling.
[0085] S43: Integrate the overall risk value, hazard level R, and interference coefficient k of each zone. j The deep risk value for each partition is calculated using the deep risk value formula, and the calculation is based on the associated tag fingerprint records. The comprehensive risk value, hazard level R, and interference coefficient k of each partition are then collected. jThe dataset is integrated according to the dimensions of target partition, source partition, and risk parameter to form a deep risk value calculation dataset.
[0086] Substitute the calculated dataset into the depth risk value formula. Each regulatory zone was individually calculated for its deep risk value, generating a preliminary deep risk value result table.
[0087] The initial deep risk value is bound to the physical fingerprint of the corresponding partition label, and the calculation basis is added to the result table to form a deep risk value data table with traceability information.
[0088] S44: Compare the calculated deep risk value with historical data and the current epidemic situation to verify its rationality. After calibration, add the final deep risk value to the risk traceability information database to improve the data dimensions. Retrieve historical deep risk value data for the same region and product category from the risk traceability information database and compare it with the deep risk value data table to analyze the differences and reasons for fluctuations.
[0089] Based on the current regional epidemic situation, coefficients are calibrated for deep risk values that exceed reasonable ranges to obtain the final deep risk value.
[0090] The final calibrated deep risk value and calibration basis are linked to the corresponding tag fingerprint and added to the risk tracing information database to improve the data dimensions of deep risk value, calibration coefficient and epidemic situation, and complete the data update.
[0091] S5: Synchronizes the raw data containing comprehensive risk value and deep risk value to the blockchain mini node, hashes and encrypts it, binds it with the physical fingerprint of the tag to generate an immutable evidence record, and caches offline data.
[0092] S51: Based on the original data of each partition and the physical fingerprint information of the tag, the data is synchronized to the blockchain mini node through an encrypted transmission protocol to form a synchronization log.
[0093] The system integrates the raw data from each partition, including the comprehensive risk value and the deep risk value, as well as the tag physical fingerprint information. It encapsulates the data according to the blockchain node data format, uses the TLS encrypted transmission protocol, and initiates a data synchronization request to the sub-blockchain mini-node.
[0094] The sub-blockchain mini-nodes receive transmitted data, verify data integrity and the uniqueness of the tag's physical fingerprint, remove data with incorrect format, and record the success / failure status of reception and the corresponding data batch.
[0095] The system summarizes information such as data transmission time, node reception status, data batches, and tag fingerprint list, sorts them by timestamp to generate a structured synchronization log, and marks the synchronization result of each data item, which serves as the basis for subsequent encryption operations.
[0096] S52: Hash and encrypt the raw data received by the blockchain mini-node according to the synchronization log, generate a unique encrypted hash value, and deeply bind the encrypted hash value with the tag's physical fingerprint.
[0097] Based on the synchronization logs, the original data successfully received by the nodes and their corresponding physical fingerprints are filtered out, while data that failed to be received or had incorrect formats are excluded, forming an encrypted dataset to be processed.
[0098] The SHA-256 algorithm is used to hash and encrypt the original data in the dataset to be processed, generating a unique encrypted hash value. The original data batch and tag fingerprint corresponding to each hash value are recorded.
[0099] Establish a one-to-one mapping relationship between the physical fingerprint of the tag and the encrypted hash value, and write the binding information into the distributed ledger of the blockchain node to ensure that each tag fingerprint corresponds to only one hash value, thus preventing data tampering.
[0100] S53: Generate an immutable blockchain evidence record based on the bound encrypted hash value and the tag physical fingerprint. Offline cache the synchronized data in the absence of network, mark the cache time, and automatically re-enter it into the evidence record after the network is restored.
[0101] S6: Reads the tag's physical fingerprint and associated data, automatically comparing it with the comprehensive risk value and deep risk value stored in the locally cached blockchain evidence. If the data is inconsistent, an audible and visual alarm is triggered to indicate data anomaly. The early warning module determines whether the deep risk value stored in the blockchain exceeds a preset threshold and generates corresponding control instructions. Regulatory personnel retrieve the blockchain evidence data through the provincial platform and combine it with information from all stages of the tag's lifecycle to complete disease tracing and counterfeiting verification, forming a complete regulatory closed loop.
[0102] S61: Use an RFID reader to read the physical fingerprint and associated data of the tag, and automatically compare the local data with the comprehensive risk value and deep risk value in the evidence storage based on the blockchain evidence storage record, and record the comparison results.
[0103] S62: Determine whether the data is consistent based on the comparison results. If it is, keep it unchanged; otherwise, it is determined to be abnormal. The card reader immediately triggers an audible and visual alarm and simultaneously pushes the abnormal label fingerprint and risk value difference information to the regulatory terminal, marking the abnormal type.
[0104] S63: Based on the abnormal information and the deep risk value of the blockchain evidence, determine whether the preset threshold is exceeded, and generate corresponding control instructions according to the risk level.
[0105] S64: By combining blockchain-stored data with information from all stages of the label process, we can complete the tracing of the source of the epidemic and the verification of data fraud. After the verification is completed, the disposal records are archived to form a regulatory closed loop of identification-early warning-disposal-verification.
[0106] like Figure 2 As shown, the present invention also provides a big data-based digital animal health supervision system, comprising: The ear tag binding module is used to collect data from the entire animal health chain, and to customize passive sensor tags with RFID chips to assign unique physical fingerprint ear tags to animals for identification and obtain fingerprint ear tag information.
[0107] The data partitioning module is used to preprocess fingerprint ear tag information, divide it into regulatory partitions, and collect the processed data into the corresponding partitions to obtain a dedicated dataset.
[0108] The risk tracing module is used to identify risk values from a dedicated dataset based on immune compliance and physiological abnormalities, calculate the comprehensive risk value for each partition, and record risk tracing information associated with fingerprint ear tags.
[0109] The in-depth risk control module is used to calculate the in-depth risk value for each zone based on the comprehensive risk value, the degree of risk severity, and the interference coefficient between zones.
[0110] The on-chain evidence storage module is used to synchronize the original data containing comprehensive risk value and deep risk value to the blockchain mini node, hash and encrypt it, and bind it with the physical fingerprint of the tag to generate an immutable evidence storage record, and cache offline data.
[0111] The closed-loop control module compares the fingerprint ear tag information with the risk value stored on the blockchain to determine if any anomalies have occurred. If so, an alarm is issued, and control instructions are generated based on the deep risk value. Regulatory personnel then retrieve the stored evidence to complete the traceability verification, thus forming a closed-loop control system.
[0112] The big data-based digital animal health supervision method provided by this invention solves the core pain points of traditional animal health supervision, such as fragmented data, delayed risk identification, and difficulty in traceability, through the technical logic of full-chain data integration, multi-dimensional risk identification, blockchain evidence storage, and closed-loop management. It has significant advantages in multiple dimensions and achieves the following beneficial effects: This invention achieves standardized management and control of animal health data throughout its entire lifecycle. The data collection phase covers four major categories of data across the entire chain: basic information, dynamic monitoring, environment, and distribution / slaughter. Combined with the unique physical fingerprint binding of RFID passive sensor tags, it ensures precise association between data and individual animals / batch from the source, avoiding the problem of data disconnect between traditional ledger records and the regulated entities. The data preprocessing stage uses error removal, missing data completion, and partitioned aggregation to form a dedicated dataset. Regulatory zones are divided according to farming type, administrative region, and distribution node, enabling structured and partitioned management of scattered regulatory data, significantly improving data accessibility and laying a precise data foundation for subsequent risk analysis.
[0113] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of various embodiments or some parts of embodiments.
[0114] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. These modifications or substitutions do not cause the essence of the corresponding technical solutions to depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A digital animal health supervision method based on big data, characterized in that, include: S1: Collect data from the entire animal health chain, customize passive sensor tags with RFID chips, assign unique physical fingerprint ear tags to animals for identification, and obtain fingerprint ear tag information; S2: Preprocess the fingerprint ear tag information and divide it into monitoring zones. Then, collect the processed data into the corresponding zones to obtain a dedicated dataset. S3: Identify the risk value of the dedicated dataset from the immune compliance and physiological abnormality data, calculate the comprehensive risk value of each partition, and record the risk tracing information associated with the fingerprint ear tag; S4: Calculate the depth risk value for each zone based on the comprehensive risk value, the degree of risk hazard, and the interference coefficient of each zone; S5: Synchronize the raw data containing comprehensive risk value and deep risk value to the blockchain mini node, hash and encrypt it, bind it with the physical fingerprint of the tag to generate an immutable evidence record, and cache offline data; S6: Compare the fingerprint and ear tag information with the risk value stored on the blockchain to determine if any abnormality has occurred. If so, issue an alarm and generate control instructions based on the deep risk value. Regulatory personnel then retrieve the stored evidence to complete the traceability verification, thus forming a regulatory closed loop.
2. The method for digital animal health supervision based on big data according to claim 1, characterized in that, In step S1, the specific steps for obtaining the tag ear tag information are as follows: S11: Collect big data from the entire animal health chain, classify and archive the data to form a structured raw animal health dataset; S12: Based on the category and batch characteristics of the original animal health dataset, customize a passive sensor tag with an integrated RFID chip to generate an ear tag hardware carrier with a unique physical fingerprint. S13: Match the ear tag hardware carrier with the batch information of each animal in the original animal health dataset one by one to form a matching list; S14: Based on the matching list, write the basic information of the animals and the breeding registration information of the corresponding batch into the RFID chip, complete the deep binding of the physical fingerprint of the tag and the animal identity information, and output the tagged animal ledger with the binding completed. S15: Verify the consistency between the physical fingerprint of the tag, the animal identification information and the original dataset according to the tagged animal ledger. After the verification is passed, obtain the fingerprint ear tag information.
3. The method for digital animal health supervision based on big data according to claim 1, characterized in that, In step S2, the specific steps to obtain the dedicated dataset are as follows: S21: Filter out incorrect and duplicate fingerprint ear tag information, supplement missing breeding or immunization information, and form standardized fingerprint ear tag information; S22: Based on the breeding type, administrative region, and circulation node in the fingerprint ear tag information, the regulatory scope is divided into sub-exclusive regulatory zones, zone codes are compiled, and the regulatory boundaries and animal batch coverage of each zone are clarified. S23: Match the standardized fingerprint ear tag information to the sub-exclusive supervision zone according to the zone code corresponding to the animal batch, and record the tag physical fingerprint and animal health related data list under the zone; S24: Based on the matched tag and ear tag data and animal health-related data, establish a dedicated dataset for each regulatory zone, label the data source and update time, and form a dedicated dataset.
4. The method for digital animal health supervision based on big data according to claim 1, characterized in that, In step S23, the specific steps for creating the animal health-related data list are as follows: Construct a mapping table between animal batches and zoning codes, and automatically match the corresponding sub-exclusive regulatory zoning codes based on the batch attributes in the standardized fingerprint ear tag information to generate a matching relationship log; Based on the matching relationship log, the physical fingerprint of the tag and the basic information of the animal for each batch are collected into the temporary database of the corresponding sub-exclusive regulatory zone; The data in the temporary database is sorted out and categorized by fingerprint number, animal batch, and data type to generate a list of physical fingerprints and animal health-related data for each sub-exclusive regulatory zone, and the data ownership is marked.
5. The method for digital animal health supervision based on big data according to claim 1, characterized in that, In step S3, the specific steps for calculating the comprehensive risk value are as follows: S31: Retrieve the dedicated datasets for each regulatory zone, extract the tag fingerprint association information, verify the compliance of immunization coverage and withdrawal period, calculate the immunization compliance risk value for each zone according to the proportion of violations, and associate the tag fingerprint records with violation tracing information; S32: Identify the proportion of animals with abnormal body temperature and abnormal behavior based on the exclusive dataset, calculate the physiological abnormality risk value for each partition, and supplement it to the risk tracing information associated with fingerprint ear tags; S33: Calculate the comprehensive risk value based on the immune compliance risk value and physiological abnormality risk value, and bind the calculation result with the tag fingerprint to improve the core data dimension of risk traceability information; S34: Summarize the comprehensive risk value, individual risk value, and traceability clues associated with tag fingerprints for each partition, and archive them by partition code, tag fingerprint, and risk type to form a risk traceability information database.
6. The method for digital animal health supervision based on big data according to claim 1, characterized in that, In step S4, the specific steps for calculating the depth risk value are as follows: S41: Retrieve the comprehensive risk value and corresponding tag fingerprint from the risk tracing information database, match them with the preset risk hazard mapping table, calculate the degree of hazard R of each partition risk to other partitions, and form a hazard degree list; S42: Based on the spacing between each zone, the frequency of transportation and circulation, and climate data, the interference coefficient kj between each zone is calculated by substituting into the interference coefficient formula, and the interference coefficient of the corresponding zone is marked on the list of associated hazard levels. S43: Integrate the comprehensive risk value, hazard level R, and interference coefficient kj of each zone, substitute them into the deep risk value formula to calculate the deep risk value of each zone, and synchronously associate the tag fingerprint record calculation basis; S44: Compare the calculated deep risk value with historical data and the current epidemic situation, calibrate the value, verify the rationality of the value, and add the final deep risk value to the risk traceability information database after calibration.
7. The method for digital animal health supervision based on big data according to claim 6, characterized in that, In step S5, the specific steps for generating an immutable evidence record are as follows: S51: Based on the original data of each partition and the physical fingerprint information of the tag, the data is synchronized to the blockchain mini node through an encrypted transmission protocol to form a synchronization log; S52: Hash and encrypt the raw data received by the blockchain mini node according to the synchronization log, generate a unique encrypted hash value, and deeply bind the encrypted hash value with the tag physical fingerprint. S53: Generate an immutable blockchain evidence record based on the bound encrypted hash value and the tag physical fingerprint. Offline cache the synchronized data in the absence of network, mark the cache time, and automatically re-enter it into the evidence record after the network is restored.
8. The method for digital animal health supervision based on big data according to claim 7, characterized in that, In step S52, the specific steps for deeply binding the encrypted hash value with the tag's physical fingerprint are as follows: Based on the synchronization log, the original data successfully received by the node and the corresponding tag physical fingerprint are filtered out, and data that failed to be received or had incorrect format is excluded, forming an encrypted dataset to be processed; The SHA-256 algorithm is used to hash and encrypt the original data in the dataset to be encrypted, generating a unique encrypted hash value, and recording the original data batch and tag fingerprint corresponding to each hash value; Establish a one-to-one mapping relationship between the physical fingerprint of the tag and the encrypted hash value, and write the binding information into the distributed ledger of the blockchain node to ensure that each tag fingerprint corresponds to only one hash value, thus preventing data tampering.
9. The method for digital animal health supervision based on big data according to claim 1, characterized in that, In step S6, the specific steps to form a regulatory closed loop are as follows: S61: Use an RFID reader to read the physical fingerprint and associated data of the tag, and automatically compare the local data with the comprehensive risk value and deep risk value in the blockchain evidence storage record, and record the comparison result; S62: Determine whether the data is consistent based on the comparison result. If it is, keep it unchanged; otherwise, it is determined to be abnormal. The card reader immediately triggers an audible and visual alarm and simultaneously pushes the abnormal label fingerprint and risk value difference information to the monitoring terminal, marking the abnormal type. S63: Based on the abnormal information and the deep risk value of the blockchain evidence, generate corresponding control instructions according to the risk level; S64: By combining blockchain-stored data with information from all stages of the label process, we can complete the tracing of the source of the epidemic and the verification of data fraud. After the verification is completed, the disposal records are archived to form a regulatory closed loop of identification-early warning-disposal-verification.
10. A big data-based digital animal health supervision system, which employs the big data-based digital animal health supervision method as described in any one of claims 1 to 9, characterized in that, The regulatory system includes: The ear tag binding module is used to collect data from the entire animal health chain, and is customized into a passive sensor tag with an RFID chip. It assigns a unique physical fingerprint ear tag to the animal for identification and obtains the fingerprint ear tag information. The data partitioning module is used to preprocess the fingerprint ear tag information, divide it into monitoring partitions, and collect the processed data into the corresponding partitions to obtain a dedicated dataset. The risk tracing module is used to identify the risk value of the dedicated dataset from the perspectives of immune compliance and physiological abnormalities, calculate the comprehensive risk value of each partition, and record the risk tracing information associated with the fingerprint ear tag; The deep risk control module is used to calculate the deep risk value of each partition based on the comprehensive risk value, the degree of risk hazard, and the interference coefficient of each partition. The on-chain evidence storage module is used to synchronize the original data containing the comprehensive risk value and deep risk value to the blockchain mini node, hash and encrypt it, and bind it with the physical fingerprint of the tag to generate an immutable evidence storage record, and cache offline data; The closed-loop control module compares the fingerprint ear tag information with the risk value stored on the blockchain to determine if any anomalies have occurred. If so, an alarm is issued, and control instructions are generated based on the deep risk value. Regulatory personnel then retrieve the stored evidence to complete the traceability verification, thus forming a closed-loop control system.