Intelligent food safety information tracing method and system

Abstract

The invention discloses an intelligent food safety information tracing method and system. The intelligent food safety information tracing method comprises the steps of S110, performing fusion coding on multi-source data, and generating a unique fingerprint of food data; s120, performing dynamic risk assessment on the food after fusion coding; s130, performing block chain credible evidence storage on the unique fingerprint and the risk assessment result of the food; s140, constructing a food safety tracing path for the food subjected to block chain credible evidence storage; s150, carrying out dynamic adjustment and intelligent decision making on the optimized tracing path; real-time monitoring and efficient management are provided for food safety information tracing, the safety of food in the whole supply chain process is ensured, and potential safety accidents are avoided.

Description

Technical Field

[0001] The present invention relates to blockchain technology, and in particular to an intelligent food safety information tracing method. Background Art

[0002] Intelligent food safety information traceability methods aim to achieve traceability and safety assurance throughout the entire food supply chain, from production to consumption, through advanced technologies. With the growing global food safety crisis, traditional food traceability methods are no longer sufficient to meet the demands of real-time monitoring and efficient management. Therefore, leveraging technologies such as the Internet of Things (IoT), blockchain, data fusion, and artificial intelligence, intelligent food safety traceability systems are being developed. These systems can collect and monitor data from food production, processing, transportation, storage, and other stages in real time. Through multi-source data fusion, dynamic risk assessment, and path optimization, these systems can enhance food safety management. Furthermore, intelligent early warning systems can quickly identify potential risks and automatically initiate emergency response measures, minimizing food safety risks and ensuring transparency and traceability throughout the food supply chain. This approach not only improves food safety assurance capabilities but also enhances consumer trust and satisfaction with food quality. Summary of the Invention

[0003] The present invention provides an intelligent food safety information tracing method, comprising:

[0004] S110, fusing and encoding multi-source data to generate a unique fingerprint of food data;

[0005] S120. Conduct dynamic risk assessment on foods after integrated coding;

[0006] S130. Use blockchain to store the unique fingerprint and risk assessment results of food;

[0007] S140. For foods that have completed blockchain-based trusted evidence storage, establish a food safety traceability path;

[0008] S150. Dynamically adjust and make intelligent decisions on the optimized traceability path.

[0009] In the above-mentioned intelligent food safety information traceability method, the method of fusion encoding of multi-source data specifically includes the following sub-steps:

[0010] Collect microscopic feature data;

[0011] Collect behavior and interaction data;

[0012] Define a unified data fingerprint encoding.

[0013] As described above, an intelligent food safety information traceability method utilizes blockchain technology to securely store and verify the unique fingerprint of food and risk assessment results. Each block is encrypted and stored using the hash value of the previous block, the fingerprint of the current food, and the risk assessment results, forming a secure and continuous data chain, and encrypting and storing this information through the blockchain.

[0014] The intelligent food safety information traceability method described above, wherein the method for constructing a food safety traceability path for food that has completed blockchain trusted evidence, is specifically divided into the following sub-steps:

[0015] Establish food safety traceability pathways;

[0016] The optimal path is selected by optimizing the cost function of the tracing path.

[0017] The intelligent food safety information traceability method described above, wherein the method for dynamically adjusting and intelligently making decisions on the optimized traceability path, specifically comprises the following sub-steps:

[0018] Real-time data monitoring and feedback;

[0019] Dynamic path adjustment;

[0020] Intelligent early warning and emergency response.

[0021] The present invention also provides an intelligent food safety information traceability system, including: a fusion coding module, a dynamic risk assessment module, a blockchain trusted evidence module, a traceability path construction module, and a dynamic adjustment and intelligent decision-making module.

[0022] Fusion coding module: Fusion coding of multi-source data to generate a unique fingerprint of food data;

[0023] Dynamic risk assessment module: conduct dynamic risk assessment on the fused coded food;

[0024] Blockchain trusted evidence module: Blockchain trusted evidence storage of food’s unique fingerprint and risk assessment results;

[0025] Traceability path construction module: Build a food safety traceability path for food that has completed blockchain trusted evidence storage;

[0026] Dynamic adjustment and intelligent decision-making module: Dynamically adjust and make intelligent decisions on the optimized traceability path.

[0027] In the intelligent food safety information traceability system described above, the method for fusion encoding of multi-source data specifically includes the following sub-steps:

[0028] Collect microscopic feature data;

[0029] Collect behavior and interaction data;

[0030] Define a unified data fingerprint encoding.

[0031] As described above, an intelligent food safety information traceability system utilizes blockchain technology to securely store and verify the unique fingerprint of food and risk assessment results. Each block is encrypted and stored using the hash value of the previous block, the fingerprint of the current food, and the risk assessment results, forming a secure and continuous data chain, and encrypting and storing this information through the blockchain.

[0032] In the intelligent food safety information traceability system described above, a method for constructing a food safety traceability path for food that has completed blockchain trusted evidence is specifically divided into the following sub-steps:

[0033] Establish food safety traceability pathways;

[0034] The optimal path is selected by optimizing the cost function of the tracing path.

[0035] In the intelligent food safety information traceability system described above, the method for dynamically adjusting and intelligently deciding the optimized traceability path specifically includes the following sub-steps:

[0036] Real-time data monitoring and feedback;

[0037] Dynamic path adjustment;

[0038] Intelligent early warning and emergency response.

[0039] The beneficial effects achieved by the present invention are as follows: This application provides real-time monitoring and efficient management for food safety information traceability, ensuring the safety of food throughout the entire supply chain and avoiding potential safety accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments described in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0041] Figure 1 This is a flow chart of an intelligent food safety information traceability method provided in Example 1 of the present application;

[0042] Figure 2 This is a schematic diagram of an intelligent food safety information traceability system provided in Example 2 of this application. DETAILED DESCRIPTION

[0043] The following is a clear and complete description of the technical solutions in the embodiments of the present invention, in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0044] Example 1

[0045] like Figure 1 As shown, the first embodiment of the present application provides an intelligent food safety information traceability method

[0046] Step S110: Fusion-encode the multi-source data to generate a unique fingerprint of the food data;

[0047] Food safety information involves multiple aspects. By integrating heterogeneous data from production, transportation, testing, and other links to ensure the authenticity and credibility of the data, the method of fusion coding of multi-source data specifically includes the following sub-steps:

[0048] Step S111, collecting microscopic feature data;

[0049] At the source of food production, in addition to traditional environmental parameter collection, advanced gene sequencing technology is used to collect genetic information from crop seeds or livestock embryos. For crops, recording their variety-specific genetic markers not only allows for precise tracing of their origins but also links genetic information to their potential disease and pest resistance and adaptability to specific environments, providing in-depth insights into subsequent growth processes and product quality.

[0050] Nanosensor technology is used to collect real-time data on changes in material composition at the microscopic level during food processing. These nanosensors can be embedded in processing equipment or attached to food packaging materials, and can sense the content and changes of trace elements and additive molecules in food.

[0051] Step S112: collecting behavior and interaction data;

[0052] At every stage of the food supply chain, IoT technology combined with blockchain-based smart contracts records the behavioral data of all parties involved. When food is transported from the manufacturer to the wholesaler, the vehicle's departure time, route, stops along the way, and the identity authentication information of both parties are automatically recorded.

[0053] Step S113: define a unified data fingerprint code;

[0054] Unified data fingerprinting refers to converting data or data sets into a unique, fixed-length code through a specific algorithm, thereby achieving data identification and authentication. The core goal of this process is to ensure the integrity and authenticity of data through the "fingerprint" of the data, and to facilitate rapid detection and comparison during data transmission, storage, and verification. Specifically, the formula is used: Calculate the data fingerprint of the food, where FP i Represents the unique fingerprint of the i-th data, ω k represents the weight of the k-th category data, k represents temperature, humidity, etc., D ik represents the kth category of data in the i-th data, δ represents a constant used to prevent zero values or instability in the calculation, σ represents the Sigmoid function, which maps the input value to the range of 0 to 1 to ensure that the generated fingerprint value remains in a reasonable range, and n represents the total number of data categories.

[0055] Step S120: Perform dynamic risk assessment on the fused coded food;

[0056] The purpose of dynamic risk assessment is to evaluate the risk level of food in different environments through real-time monitoring data, so that timely intervention measures can be taken to ensure food safety. During the dynamic assessment process, the system continuously receives data from different environments and sensors, and updates the input of the risk assessment model in real time. Using a threat assessment formula based on time decay, the risk level of food is predicted by comparing the current state with historical data. Specifically, the formula is used: Calculate the risk assessment value of food, where R(t) represents the risk assessment value of food at time t, S current Indicates the abnormal standard value measured at the current moment, S max It represents the maximum abnormal standard value measured in the past historical data of the food. λ represents the attenuation coefficient of historical data, which is used to control the influence of historical data in the model. The larger the attenuation coefficient, the smaller the influence of historical data; conversely, the greater the influence of historical data. α and β represent weight values, which control the relative influence of the current value and historical attenuation data in the overall risk assessment.

[0057] Step S130: credibly store the unique fingerprint and risk assessment results of the food on the blockchain;

[0058] Blockchain technology is used to securely store and verify the unique fingerprint of food and risk assessment results. Each block is encrypted and stored using the hash value of the previous block, the fingerprint of the current food, and the risk assessment results, forming a secure and continuous data chain. This information is encrypted and stored on the blockchain to ensure the data is tamper-proof and authentic. Specifically, the formula is used: Calculate the hash value of each block, where Hj Represents the hash value of the jth block. The hash value of each block is unique and represents the identity of the block. j-1 Indicates the hash value of the previous block, Hash represents the hash function, FP i represents the fingerprint of the i-th food, represents the risk change rate at the jth moment.

[0059] Step S140: Construct a food safety traceability path for the food that has completed blockchain trusted evidence storage;

[0060] The method for building a food safety traceability path for food that has completed blockchain trusted evidence is divided into the following sub-steps:

[0061] Step S141: Establishing a food safety traceability path;

[0062] The food safety traceability path refers to the movement path of food throughout the entire supply chain, from raw material production, processing, packaging, transportation, to the hands of final consumers. Each link in this process involves specific environmental factors and quality monitoring data, which directly affect the safety and quality of food.

[0063] Based on information about food production, processing, and transportation, multiple complete pathways from production to consumer delivery are constructed. Data for each link is associated with specific time nodes and spatial locations (such as geographic coordinates) along the pathway. By integrating spatiotemporal information, traceability analysis can be effectively performed at every stage of the food chain, providing reliable pathway information.

[0064] Step S142: Selecting the optimal path by optimizing the cost function of the tracing path;

[0065] Based on the established food safety traceability path, an optimization goal is set to optimize the traceability path to ensure the accuracy and consistency of data during the traceability process. The present invention selects the optimal path by optimizing the cost function of the traceability path. Specifically, the formula is used:

[0066] To achieve the selection of the optimal path, C represents the minimized cost of the path, ▽FP(x,y,t) represents the gradient in space x,y and time t, and refers to the rate of change of the traceability path. By calculating the change of the food fingerprint (FP) over time and space, the change trend of the path can be obtained. ||▽FP(x,y,t)||2 represents the L2 norm, which is usually used to measure the smoothness of the path to avoid excessive fluctuations. Indicates integration over the time interval [t1, t2].

[0067] Step S150: Dynamically adjust and intelligently decide on the optimized tracing path;

[0068] The method for dynamically adjusting and intelligently deciding the optimized traceability path includes the following sub-steps:

[0069] Step S151: real-time data monitoring and feedback;

[0070] IoT technology and smart sensors collect real-time data on food status at every stage of the process, including environmental factors such as temperature, humidity, light intensity, and gas concentrations, which directly impact food quality and safety. Sensors are embedded in production, processing, and packaging equipment and transmit data via wireless networks to a central database for storage and analysis. This data is fed back to the traceability system in real time, automatically identifying anomalies based on pre-set thresholds. If an anomaly occurs, the system immediately provides early warning feedback to relevant personnel and systems, enabling prompt response.

[0071] Step S152: dynamic path adjustment;

[0072] By monitoring food status data in real time, the traceability system can automatically adjust the traceability path based on environmental changes or abnormal situations. For example, if the system detects that the temperature at a certain stage in food transportation exceeds the safe range, it will automatically calculate a new optimal path, selecting more suitable storage conditions or transportation routes to reduce risk exposure. During this process, the system dynamically adjusts the path based on historical data, food fingerprints, and their changing trends over time and space to ensure that the food is in optimal storage and transportation conditions. Furthermore, the system evaluates the costs and risks of multiple paths in real time and automatically selects the safest and most efficient option.

[0073] Step S153: Intelligent early warning and emergency response;

[0074] The intelligent early warning and emergency response system is the last line of defense for ensuring food safety traceability. By monitoring changes in food status, it can promptly identify potential risks, trigger early warning mechanisms, and implement appropriate emergency measures. The degree of food anomaly is assessed by calculating the information entropy of the food fingerprint (FP). Information entropy represents the randomness or uncertainty of data. If the food fingerprint data changes dramatically, the information entropy value will increase, indicating a high degree of uncertainty and potential risk in the food. Specifically, the formula used is:

[0075] Entropy(FP)=-∑p(FP i )logp(FP i ) calculates the information entropy of food fingerprints, where Entropy(FP) represents the information entropy of food fingerprints, p(FP i) represents the probability distribution of the i-th fingerprint state.

[0076] Combine the dynamic risk assessment value and information entropy to make early warning decisions. When the product of the risk assessment value and information entropy is greater than a certain set threshold, the system will trigger an alarm, indicating that the current food has a high risk. Specifically, the formula is used:

[0077] Represents early warning judgment, where Alert represents the early warning judgment result, R(t) represents the risk assessment value of food at time t, Entropy(FP) represents information entropy, and θ represents the threshold for triggering the early warning.

[0078] Example 2

[0079] like Figure 2 As shown, the second embodiment of the present application provides an intelligent food safety information traceability system, including:

[0080] Fusion coding module 21: performs fusion coding on multi-source data to generate a unique fingerprint of food data;

[0081] Food safety information involves multiple aspects. By integrating heterogeneous data from production, transportation, testing, and other links to ensure the authenticity and credibility of the data, the method of fusion coding of multi-source data specifically includes the following sub-steps:

[0082] Microscopic data collection module: collects microscopic feature data;

[0083] At the source of food production, in addition to traditional environmental parameter collection, advanced gene sequencing technology is used to collect genetic information from crop seeds or livestock embryos. For crops, recording their variety-specific genetic markers not only allows for precise tracing of their origins but also links genetic information to their potential disease and pest resistance and adaptability to specific environments, providing in-depth insights into subsequent growth processes and product quality.

[0084] Nanosensor technology is used to collect real-time data on changes in material composition at the microscopic level during food processing. These nanosensors can be embedded in processing equipment or attached to food packaging materials, and can sense the content and changes of trace elements and additive molecules in food.

[0085] Behavior and interaction data collection module: collects behavior and interaction data;

[0086] At every stage of the food supply chain, IoT technology combined with blockchain-based smart contracts records the behavioral data of all parties involved. When food is transported from the manufacturer to the wholesaler, the vehicle's departure time, route, stops along the way, and the identity authentication information of both parties are automatically recorded.

[0087] Fingerprint coding module: defines unified data fingerprint coding;

[0088] Unified data fingerprinting refers to converting data or data sets into a unique, fixed-length code through a specific algorithm, thereby achieving data identification and authentication. The core goal of this process is to ensure the integrity and authenticity of data through the "fingerprint" of the data, and to facilitate rapid detection and comparison during data transmission, storage, and verification. Specifically, the formula is used: Calculate the data fingerprint of the food, where FP i Represents the unique fingerprint of the i-th data, ω k represents the weight of the k-th category data, k represents temperature, humidity, etc., D ik represents the kth category of data in the i-th data, δ represents a constant used to prevent zero values or instability in the calculation, σ represents the Sigmoid function, which maps the input value to the range of 0 to 1 to ensure that the generated fingerprint value remains in a reasonable range, and n represents the total number of data categories.

[0089] Dynamic risk assessment module 22: dynamic risk assessment of the fused coded food;

[0090] The purpose of dynamic risk assessment is to evaluate the risk level of food in different environments through real-time monitoring data, so that timely intervention measures can be taken to ensure food safety. During the dynamic assessment process, the system continuously receives data from different environments and sensors, and updates the input of the risk assessment model in real time. Using a threat assessment formula based on time decay, the risk level of food is predicted by comparing the current state with historical data. Specifically, the formula is used: Calculate the risk assessment value of food, where R(t) represents the risk assessment value of food at time t, S current Indicates the abnormal standard value measured at the current moment, S max It represents the maximum abnormal standard value measured in the past historical data of the food. λ represents the attenuation coefficient of historical data, which is used to control the influence of historical data in the model. The larger the attenuation coefficient, the smaller the influence of historical data; conversely, the greater the influence of historical data. α and β represent weight values, which control the relative influence of the current value and historical attenuation data in the overall risk assessment.

[0091] Blockchain trusted evidence module 23: Blockchain trusted evidence storage of food’s unique fingerprint and risk assessment results;

[0092] Blockchain technology is used to securely store and verify the unique fingerprint of food and risk assessment results. Each block is encrypted and stored using the hash value of the previous block, the fingerprint of the current food, and the risk assessment results, forming a secure and continuous data chain. This information is encrypted and stored on the blockchain to ensure the data is tamper-proof and authentic. Specifically, the formula is used: Calculate the hash value of each block, where H j Represents the hash value of the jth block. The hash value of each block is unique and represents the identity of the block. j-1 Indicates the hash value of the previous block, Hash represents the hash function, FP i represents the fingerprint of the i-th food, represents the risk change rate at the jth moment.

[0093] Traceability path construction module 24: Constructing a food safety traceability path for food that has completed blockchain trusted evidence storage;

[0094] The method for building a food safety traceability path for food that has completed blockchain trusted evidence is divided into the following sub-steps:

[0095] Traceability path establishment module: establish food safety traceability path;

[0096] The food safety traceability path refers to the movement path of food throughout the entire supply chain, from raw material production, processing, packaging, transportation, to the hands of final consumers. Each link in this process involves specific environmental factors and quality monitoring data, which directly affect the safety and quality of food.

[0097] Based on information about food production, processing, and transportation, multiple complete pathways from production to consumer delivery are constructed. Data for each link is associated with specific time nodes and spatial locations (such as geographic coordinates) along the pathway. By integrating spatiotemporal information, traceability analysis can be effectively performed at every stage of the food chain, providing reliable pathway information.

[0098] Optimizing path module: It selects the optimal path by optimizing the cost function of the tracing path;

[0099] Based on the established food safety traceability path, an optimization goal is set to optimize the traceability path to ensure the accuracy and consistency of data during the traceability process. The present invention selects the optimal path by optimizing the cost function of the traceability path. Specifically, the formula is used: To achieve the selection of the optimal path, C represents the minimized cost of the path, ▽FP(x,y,t) represents the gradient in space x,y and time t, and refers to the rate of change of the traceability path. By calculating the change of the food fingerprint (FP) over time and space, the change trend of the path can be obtained. ||▽FP(x,y,t)||2 represents the L2 norm, which is usually used to measure the smoothness of the path to avoid excessive fluctuations. Indicates integration over the time interval [t1, t2].

[0100] Dynamic adjustment and intelligent decision-making module 25: Dynamic adjustment and intelligent decision-making of the optimized traceability path;

[0101] The method for dynamically adjusting and intelligently deciding the optimized traceability path includes the following sub-steps:

[0102] Real-time monitoring module: real-time data monitoring and feedback;

[0103] IoT technology and smart sensors collect real-time data on food status at every stage of the process, including environmental factors such as temperature, humidity, light intensity, and gas concentrations, which directly impact food quality and safety. Sensors are embedded in production, processing, and packaging equipment and transmit data via wireless networks to a central database for storage and analysis. This data is fed back to the traceability system in real time, automatically identifying anomalies based on pre-set thresholds. If an anomaly occurs, the system immediately provides early warning feedback to relevant personnel and systems, enabling prompt response.

[0104] Dynamic path adjustment module: dynamic path adjustment;

[0105] By monitoring food status data in real time, the traceability system can automatically adjust the traceability path based on environmental changes or abnormal situations. For example, if the system detects that the temperature at a certain stage in food transportation exceeds the safe range, it will automatically calculate a new optimal path, selecting more suitable storage conditions or transportation routes to reduce risk exposure. During this process, the system dynamically adjusts the path based on historical data, food fingerprints, and their changing trends over time and space to ensure that the food is in optimal storage and transportation conditions. Furthermore, the system evaluates the costs and risks of multiple paths in real time and automatically selects the safest and most efficient option.

[0106] Intelligent early warning module: intelligent early warning and emergency response;

[0107] The intelligent early warning and emergency response system is the last line of defense to ensure food safety traceability. By monitoring changes in food status, potential risks can be discovered in a timely manner, triggering early warning mechanisms and taking appropriate emergency measures. The degree of abnormality of food can be assessed by calculating the information entropy of the food fingerprint (FP). Information entropy represents the randomness or uncertainty of data. If the fingerprint data of a food changes dramatically, the information entropy value will increase, indicating that the food has a high degree of uncertainty and potential risk. Specifically, the formula is: Entropy (FP) = -∑p(FP i )logp(FP i ) calculates the information entropy of food fingerprints, where Entropy(FP) represents the information entropy of food fingerprints, p(FP i ) represents the probability distribution of the i-th fingerprint state.

[0108] Combine the dynamic risk assessment value and information entropy to make early warning decisions. When the product of the risk assessment value and information entropy is greater than a certain set threshold, the system will trigger an alarm, indicating that the current food has a high risk. Specifically, the formula is used:

[0109] Represents early warning judgment, where Alert represents the early warning judgment result, R(t) represents the risk assessment value of food at time t, Entropy(FP) represents information entropy, and θ represents the threshold for triggering the early warning.

[0110] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent replacements, improvements, etc. made on the basis of the technical solution of the present invention should be included in the scope of protection of the present invention.

Claims

1. An intelligent food safety information tracing method, characterized in that: include: S110, fusing and encoding multi-source data to generate a unique fingerprint of food data; S120. Conduct dynamic risk assessment on foods after integrated coding; S130. Use blockchain to store the unique fingerprint and risk assessment results of food; S140. For foods that have completed blockchain-based trusted evidence storage, establish a food safety traceability path; S150. Dynamically adjust and make intelligent decisions on the optimized traceability path.

2. An intelligent food safety information tracing method according to claim 1, characterized in that: The method for fusion encoding of multi-source data specifically includes the following sub-steps: Collect microscopic feature data; Collect behavior and interaction data; Define a unified data fingerprint encoding.

3. An intelligent food safety information tracing method according to claim 1, characterized in that: Blockchain technology is used to achieve secure storage and verification of food’s unique fingerprint and risk assessment results. Each block is encrypted and stored using the hash value of the previous block, the current food’s fingerprint and risk assessment results, forming a secure and continuous data chain, and this information is encrypted and stored through the blockchain.

4. The intelligent food safety information tracing method according to claim 1, wherein: The method for building a food safety traceability path for food that has completed blockchain trusted evidence is divided into the following sub-steps: Establish food safety traceability pathways; The optimal path is selected by optimizing the cost function of the tracing path.

5. The intelligent food safety information tracing method according to claim 1, characterized in that: The method for dynamically adjusting and intelligently deciding the optimized traceability path includes the following sub-steps: Real-time data monitoring and feedback; Dynamic path adjustment; Intelligent early warning and emergency response.

6. An intelligent food safety information traceability system, characterized in that: include: Fusion coding module: Fusion coding of multi-source data to generate a unique fingerprint of food data; Dynamic risk assessment module: conduct dynamic risk assessment on the fused coded food; Blockchain trusted evidence module: Blockchain trusted evidence storage of food’s unique fingerprint and risk assessment results; Traceability path construction module: Build a food safety traceability path for food that has completed blockchain trusted evidence storage; Dynamic adjustment and intelligent decision-making module: Dynamically adjust and make intelligent decisions on the optimized traceability path.

7. An intelligent food safety information traceability system according to claim 6, characterized in that: The method for fusion encoding of multi-source data specifically includes the following sub-steps: Collect microscopic feature data; Collect behavior and interaction data; Define a unified data fingerprint encoding.

8. An intelligent food safety information traceability system according to claim 6, characterized in that: Blockchain technology is used to achieve secure storage and verification of food’s unique fingerprint and risk assessment results. Each block is encrypted and stored using the hash value of the previous block, the current food’s fingerprint and risk assessment results, forming a secure and continuous data chain, and this information is encrypted and stored through the blockchain.

9. An intelligent food safety information traceability system according to claim 6, characterized in that: The method for building a food safety traceability path for food that has completed blockchain trusted evidence is divided into the following sub-steps: Establish food safety traceability pathways; The optimal path is selected by optimizing the cost function of the tracing path.

10. The intelligent food safety information tracing system according to claim 6, characterized in that: The method for dynamically adjusting and intelligently deciding the optimized traceability path includes the following sub-steps: Real-time data monitoring and feedback; Dynamic path adjustment; Intelligent early warning and emergency response.

Images