Prepared dish cold chain logistics temperature and humidity traceability system and method based on digital twinning

Abstract

The present application relates to the technical field of intelligent monitoring and digital twin traceability of cold chain logistics, in particular to a prefabricated meal cold chain logistics temperature and humidity traceability system and method based on digital twin, the system is composed of modeling module, synchronization module, judgment module and control module, first, build a cold chain full-scene digital twin model and complete virtual-real unit binding, real-time collection of synchronous cold chain temperature and humidity and equipment operation data; then, eliminate invalid data, distinguish true and false temperature control abnormalities, locate abnormal causes and complete quality risk level division; finally, verify the traceability result through precision and integrity, complete data evidence and implement differentiated logistics control. The present application completes the whole-process traceability research and judgment relying on the virtual-real linkage of digital twin, the judgment standard is unified and standardized, can accurately identify the cold chain temperature control hidden danger, effectively control the prefabricated meal circulation quality, and improve the intelligent level of cold chain logistics traceability supervision.

Description

Technical Field

[0001] This invention relates to the field of intelligent monitoring and digital twin traceability technology for cold chain logistics, and more specifically, to a temperature and humidity traceability system and method for pre-prepared dishes in cold chain logistics based on digital twins. Background Technology

[0002] With the rapid development of the prepared food industry, an integrated cold chain logistics system encompassing cross-regional warehousing, transportation, and distribution is gradually taking shape. The temperature and humidity environment throughout the cold chain directly determines the preservation effect and food safety of prepared foods, making the industry's need for traceability and supervision of the entire cold chain increasingly urgent. Currently, the cold chain for prepared foods involves many links and spans a large distance, and fluctuations in temperature and humidity can easily cause food spoilage. Therefore, building an efficient and accurate traceability and control system has become a necessity for the industry's development.

[0003] Existing cold chain traceability for pre-prepared food mostly adopts traditional data recording and single temperature monitoring modes. Related traceability technologies only focus on the collection and retention of basic environmental data, without introducing the concept of digital twin virtual-real mapping control. Various cold chain operation data are relatively scattered, lacking multi-dimensional data collaborative analysis capabilities. Data transmission is lagging, and there is a large amount of invalid data interference, making it difficult to achieve linkage and judgment of the cold chain status in all scenarios.

[0004] The core technical problem with existing traceability solutions is that they cannot effectively distinguish between false and true temperature control anomalies during cold chain operations, making it difficult to accurately pinpoint the root cause of the anomalies. Furthermore, they cannot combine the magnitude of temperature and humidity deviations with the duration of the anomalies to classify the quality risks of food products, making it difficult to verify traceability results and impossible to implement targeted logistics control based on risk levels. Summary of the Invention

[0005] In view of this, the present invention proposes a temperature and humidity traceability system and method for cold chain logistics of pre-prepared dishes based on digital twins. It aims to solve the problems in the existing technology that cannot effectively distinguish between false temperature control anomalies and real temperature control anomalies in the cold chain operation process, make it difficult to accurately locate the root cause of the anomaly, and cannot combine the temperature and humidity deviation range and the duration of the anomaly to complete the risk classification of the food quality. The traceability results are difficult to verify and cannot implement targeted logistics control based on the risk level.

[0006] In a first aspect, the present invention provides a temperature and humidity traceability system for cold chain logistics of pre-prepared dishes based on digital twins, including: a modeling module, used to build a digital twin model of the entire cold chain scenario of the target pre-prepared dishes, and to bind all physical entity units in the cold chain scenario with corresponding virtual twin units to construct a batch-specific traceability carrier; The synchronization module is used to collect temperature, humidity and cold chain operation status data in real time throughout the entire process of cold chain storage, transportation and distribution of the target pre-prepared dishes, and synchronize the collected data to the digital twin model. The judgment module is used to remove various invalid data from the collected data, and to distinguish between real and fake temperature control anomalies based on the preset temperature control standard and the duration of the anomaly. It determines the cause and time interval of the anomaly through digital twin virtual-real comparison, and finally determines the impact on the quality of the dish and classifies the risk level by combining the degree of temperature and humidity deviation and the duration of the anomaly. The control module is used to verify the anomaly identification results, cause location information and level classification content by using accurate verification and completeness verification. After verification, the complete traceability data is entered into the digital twin exclusive traceability ledger to complete the solidification and evidence storage. At the same time, the corresponding pre-made food logistics flow control measures are implemented according to the determined risk level.

[0007] In some embodiments, the modeling module is used to build a digital twin model of the entire cold chain scenario for the target pre-prepared dish, and to bind all physical entity units within the cold chain scenario to their corresponding virtual twin units. When constructing a batch-specific traceability carrier, it includes: Determine whether the unique identifier of each physical entity unit in the cold chain scenario of the target pre-prepared dish is completely consistent with the identity identifier of the corresponding virtual twin unit; When the unique identifier of the physical entity does not match the identity identifier of the virtual twin unit, the unit binding is determined to be abnormal, all subsequent tracing processes are suspended and the binding relationship is awaited to be manually corrected. When the unique identifier of the physical entity is completely consistent with the identity identifier of the virtual twin unit, it is further determined whether the scene space mapping deviation value between the physical entity and the virtual twin unit exceeds the preset mapping matching threshold. When the scene space mapping deviation between the physical entity and the virtual twin unit exceeds the preset mapping matching threshold, the binding compliance is determined to be substandard, the twin binding relationship is reset and the binding matching process is re-executed. When the scene space mapping deviation between the physical entity and the virtual twin unit does not exceed the preset mapping matching threshold, the virtual and physical unit binding is deemed valid, and the basic carrier for batch traceability is established.

[0008] In some embodiments, the synchronization module is used to collect temperature and humidity data and cold chain operation status data in real time throughout the entire process of cold chain storage, transportation, and distribution of the target pre-prepared dish, and to synchronize the collected data to the digital twin model, including: Determine whether the transmission delay of real-time cold chain temperature and humidity and equipment status data exceeds the preset timeliness threshold for digital twin scenario synchronization; When the data transmission delay exceeds the preset time threshold, the data transmission of this group is determined to be abnormal, the data is marked as missing and the group of data is discarded and will not participate in the virtual twin scene state update. If the data transmission delay does not exceed the preset timeliness threshold, it is further determined whether the number of missing fields in the data group exceeds the preset data integrity threshold. When the number of missing fields in the data exceeds the preset data integrity threshold, the data set is deemed invalid, and the twin scenario synchronization update process for that data set is stopped. When the data transmission latency and data integrity both meet the corresponding preset threshold requirements, the data set is determined to be valid, and the virtual twin model is driven to complete the synchronous replication of the physical scene state.

[0009] In some embodiments, the judgment module is used to remove various invalid data from the collected data, and to distinguish between true and false temperature control anomalies based on a preset temperature control standard and the duration of the anomaly. It also determines the cause and time interval of the anomaly through digital twin comparison, and finally, when determining the degree of impact on food quality and classifying the risk level by combining the degree of temperature and humidity deviation with the duration of the anomaly, it includes: Determine whether the real-time collected cold chain temperature and humidity values ​​exceed the preset temperature control compliance range of the pre-prepared dishes; When the temperature and humidity values ​​are within the compliant range, the cold chain temperature control status is determined to be normal, the twin model is maintained in a normal monitoring state, and the traceability process is not triggered. When the temperature and humidity values ​​exceed the compliant range, it is further determined whether the duration of the abnormality reaches the preset abnormality judgment threshold, and at the same time, it is determined whether the difference between the real-time data and the twin normal simulation steady-state data exceeds the preset steady-state deviation threshold. If the duration of the anomaly does not reach the preset anomaly judgment threshold and the data difference does not exceed the preset steady-state deviation threshold, it is judged as a false anomaly caused by instantaneous environmental disturbance. Only the data record is retained and the twin source tracing and deduction process is not initiated. When the duration of the anomaly is greater than or equal to the preset anomaly judgment threshold, it is determined to be a real cold chain temperature control anomaly, and the digital twin virtual-real traceability judgment process is immediately activated.

[0010] In some embodiments, the judgment module is used to remove various invalid data from the collected data, and to distinguish between true and false temperature control anomalies based on a preset temperature control standard and the duration of the anomaly. It also determines the cause and time interval of the anomaly through digital twin comparison, and finally, when determining the degree of impact on food quality and classifying the risk level by combining the degree of temperature and humidity deviation with the duration of the anomaly, it further includes: Call the operating data of the sensing terminal twin to determine whether the abnormal temperature and humidity are caused by sensor terminal drift or malfunction; When it is determined that the sensing terminal has an abnormal operating condition, the sensing and acquisition terminal is identified as the root cause of the abnormality, and the location of the source node in this round of tracing is completed. When the sensor terminal is determined to be operating normally, the operating condition data of the cold chain equipment twin is called to determine whether there is any abnormality in the operation of the refrigeration temperature control equipment. When it is determined that the cold chain temperature control equipment is in abnormal condition, the cold chain equipment end is identified as the root cause of the abnormality, and the source tracing node is located in this round. When it is determined that the cold chain equipment is operating normally, the behavior data of the logistics scenario twin is called to determine whether there are any behaviors such as human-made unauthorized door opening or unauthorized operation. When it is determined that there is human error, the logistics operation end is identified as the root cause of the anomaly, and the source node for this round of tracing is located. When it is determined that there is no human error, the environmental twin simulation data is called to determine whether the temperature control abnormality is caused by the influence of external extreme environment, and finally the cause of the abnormality and the source node are identified.

[0011] In some embodiments, the judgment module is used to remove various invalid data from the collected data, and to distinguish between true and false temperature control anomalies based on a preset temperature control standard and the duration of the anomaly. It also determines the cause and time interval of the anomaly through digital twin comparison, and finally, when determining the degree of impact on food quality and classifying the risk level by combining the degree of temperature and humidity deviation with the duration of the anomaly, it further includes: Determine whether the numerical deviation of abnormal temperature and humidity in the cold chain reaches the preset deviation classification threshold for each level, and classify different deviation risk levels. Determine whether the duration of abnormal temperature and humidity in the cold chain reaches the preset time threshold for each level, and classify different time-risk levels. The quality twin model is invoked, and the preset quality degradation judgment threshold is matched based on the offset grading threshold and the duration grading threshold. If the temperature and humidity deviation does not exceed the slight deviation threshold and the abnormal duration does not exceed the short-term abnormal threshold, and the matching result does not reach the preset quality degradation judgment threshold, then the batch of cold chain abnormality is judged to be of low risk level. When the temperature and humidity deviation is in the slight deviation range and the abnormal duration is in the medium time range, or the deviation is in the medium range and the duration is in the short time range, and the matching result reaches the preset primary quality degradation judgment threshold, the batch of cold chain abnormality is judged to be of medium risk level. When the temperature and humidity deviation reaches the moderate deviation threshold and the abnormal duration reaches the long-term abnormal threshold, or the deviation reaches the severe deviation threshold and the matching result reaches the preset severe quality degradation judgment threshold, the batch of cold chain is judged to be at a high-risk level.

[0012] In some embodiments, the judgment module is used to remove various invalid data from the collected data, and to distinguish between true and false temperature control anomalies based on a preset temperature control standard and the duration of the anomaly. It also determines the cause and time interval of the anomaly through digital twin comparison, and finally, when determining the degree of impact on food quality and classifying the risk level by combining the degree of temperature and humidity deviation with the duration of the anomaly, it further includes: Configure independent virtual twins of goods, virtual twins of cold chain equipment, and virtual twins of logistics route scenarios. Each type of twin has a built-in basic status judgment program for self-checking whether its own operating status and the parameters of its environment meet the corresponding preset basic thresholds. Determine whether the independent discrimination results of various types of twins are synchronously uploaded to the digital twin collaborative platform; If any type of twin fails to upload discrimination data, the source tracing and fusion operation will be paused until all twin data is synchronized. When all types of twin identification data are synchronized, the twin platform is used to complete the fusion of multi-source data and multi-level logical collaborative operation, and jointly output a complete traceability judgment result.

[0013] In some embodiments, the control module is used to verify the anomaly identification results, cause location information, and level classification content using accuracy verification and completeness verification. After verification, the complete traceability data is entered into the digital twin-specific traceability ledger for solidification and evidence storage. Simultaneously, when implementing corresponding pre-prepared food logistics flow control measures based on the determined risk level, the module includes: Extract the identified causes of anomalies and abnormal operating parameters, and import them into the digital twin virtual cold chain scenario to complete the state replication and simulation. Retrieve the full-time-series virtual-real mapping historical data stored in the twin model to determine whether the matching degree between the temperature and humidity change curve generated by the scene replication and the actual collected data reaches the preset accurate matching threshold. When the matching degree between the replicated data and the actual collected data does not reach the preset accurate matching threshold, it is determined that there is a deviation in the current source tracing and positioning, the source tracing logic is reset and the twin simulation source tracing and deduction is restarted. When the matching degree between the replicated data and the actual collected data reaches or exceeds the preset accurate matching threshold, the source tracing and positioning result is determined to be accurate and passes the accuracy verification.

[0014] In some embodiments, the control module is used to verify the anomaly identification results, cause location information, and level classification content using accuracy verification and completeness verification. After verification, the complete traceability data is entered into the digital twin dedicated traceability ledger for solidification and evidence storage. Simultaneously, when implementing corresponding pre-prepared food logistics flow control measures based on the determined risk level, the module also includes: Verify that the core traceability elements in the traceability results are complete, including abnormal time, abnormal location, abnormal cause, risk level, quality impact, and handling recommendations. When core traceability elements are missing, the traceability data is determined to be incomplete, and the twin model is driven to automatically fill in the missing data and regenerate a complete traceability result. When the core traceability elements are complete, it is further determined whether all traceability data format parameters conform to the preset twin storage format threshold specification; When the data format does not conform to the preset storage format threshold specification, it will be automatically corrected and adapted to the twin storage format before entering the archiving and evidence preservation process. When the data elements are complete and the format meets the preset storage format threshold specifications, the traceability results are determined to be complete and compliant, and the twin ledger is solidified and stored as evidence. The batch risk levels obtained from the completed hierarchical classification will be mapped in real time to the digital twin virtual model for logistics management; When the control model identifies that the risk level of a batch meets the preset low-risk judgment threshold, the filing control logic is triggered, only the twin ledger information is retained, and normal circulation is allowed. When the control model identifies that the risk level of a batch meets the preset medium risk judgment threshold, the sampling control logic is triggered, the batch is locked and the food is forcibly sampled and re-inspected. The control can only be lifted after the re-inspection is qualified. When the control model identifies that the risk level of a batch meets the preset high-risk judgment threshold, it triggers the circulation restriction logic, which locks the market circulation channels of the batch of pre-made dishes through twin virtual permissions, prohibiting their sale and circulation.

[0015] Secondly, the present invention provides a method for tracing the temperature and humidity of pre-prepared dishes in cold chain logistics based on digital twins, comprising the following steps: A digital twin model of the entire cold chain scenario for the target pre-prepared dishes is built, and all physical entities in the cold chain scenario are bound to the corresponding virtual twin units to construct a batch-specific traceability carrier. The system collects temperature, humidity, and cold chain operation status data in real time throughout the entire process of cold chain storage, transportation, and distribution of the target pre-prepared dishes, and synchronizes the collected data to the digital twin model. Remove all invalid data from the collected data, and distinguish between real and fake temperature control anomalies based on the preset temperature control standard and the duration of the anomaly. Determine the cause and time interval of the anomaly through digital twin comparison. Finally, determine the impact on the quality of the dish and classify the risk level by combining the degree of temperature and humidity deviation and the duration of the anomaly. Accurate and complete verification are used to review and verify the anomaly identification results, cause location information and level classification content. After verification, the complete traceability data is entered into the digital twin exclusive traceability ledger to complete the solidification and evidence storage. At the same time, the corresponding pre-prepared food logistics flow control measures are implemented according to the determined risk level.

[0016] Compared with existing technologies, the beneficial effects of this invention are as follows: This application, based on the collaborative cooperation of a modeling module, a synchronization module, a judgment module, and a control module, effectively improves upon the core shortcomings of existing pre-prepared food cold chain traceability, namely low accuracy and poor control targeting. Firstly, this application constructs a digital twin virtual-physical binding architecture for the entire cold chain scenario through the modeling module, and relies on the synchronization module to achieve real-time synchronous replication of temperature, humidity, and equipment status data throughout the cold chain process. This effectively solves the problems of scattered data, delayed transmission, and poor scenario adaptability in traditional traceability methods, thus constructing a complete digital traceability infrastructure.

[0017] Secondly, this application completes invalid data removal, genuine and fake temperature control anomalies, anomaly root cause location and quality risk classification through the judgment module. It relies on multi-twin collaborative operation to realize multi-source data fusion and judgment, which completely solves the technical shortcomings of traditional technology in accurately identifying anomaly types, locking anomaly causes and quantifying quality risks.

[0018] Finally, the control module verifies the traceability results through dual logic and solidifies the evidence. It implements differentiated logistics control based on risk level, which greatly improves the accuracy and completeness of the traceability results. This enables the cold chain temperature control anomalies of pre-prepared dishes to be traceable, risks to be assessed, and control to be managed, effectively ensuring the quality and food safety of pre-prepared dishes in the cold chain.

[0019] The above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure.

[0020] Other features and aspects of the present invention will become clearer from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0021] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0022] Figure 1 Functional block diagram of a temperature and humidity traceability system for cold chain logistics of pre-prepared dishes based on digital twins provided in an embodiment of the present invention; Figure 2 A flowchart illustrating the temperature and humidity traceability method for cold chain logistics of pre-prepared dishes based on digital twins, provided in an embodiment of the present invention. Detailed Implementation

[0023] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the disclosure to those skilled in the art. It should be noted that, unless otherwise specified, embodiments and features in the embodiments of the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0024] See Figures 1-2 As shown in the first embodiment, a temperature and humidity traceability system for pre-prepared dishes based on digital twins according to an embodiment of this application includes: The modeling module is used to build a digital twin model of the entire cold chain scenario of the target pre-prepared dishes, and to bind all physical entity units in the cold chain scenario with the corresponding virtual twin units to construct a batch-specific traceability carrier. The synchronization module is used to collect temperature, humidity and cold chain operation status data in real time throughout the entire process of cold chain storage, transportation and distribution of the target pre-prepared dishes, and synchronize the collected data to the digital twin model. The judgment module is used to remove various invalid data from the collected data, and to distinguish between real and fake temperature control anomalies based on the preset temperature control standard and the duration of the anomaly. It determines the cause and time interval of the anomaly through digital twin virtual-real comparison, and finally determines the impact on the quality of the dish and classifies the risk level by combining the degree of temperature and humidity deviation and the duration of the anomaly. The control module is used to verify the anomaly identification results, cause location information and level classification content by using accurate verification and completeness verification. After verification, the complete traceability data is entered into the digital twin exclusive traceability ledger to complete the solidification and evidence storage. At the same time, the corresponding pre-made food logistics flow control measures are implemented according to the determined risk level.

[0025] It should be understood that the overall operating principle is to first complete the digital replication of the physical scene, then synchronize the on-site operating parameters in real time, rely on the built-in multi-level logic judgment program to complete the data analysis and judgment, and finally verify the judgment results for compliance and implement the corresponding control strategies. The entire process relies on various preset quantitative thresholds as the sole basis for judgment, abandoning subjective experience judgment, so that the traceability operation has a unified execution standard.

[0026] In practical applications of cold chain logistics for pre-prepared dishes, this system can be comprehensively deployed across all scenarios, including cold storage facilities for pre-prepared dish production, long-haul cold chain transport vehicles, and terminal distribution warehouses, covering all stages of the process from warehousing to long-distance transportation and short-distance delivery. This system enables full-process digital implementation of cold chain traceability, effectively integrating various operational data within the cold chain environment and overcoming the drawbacks of fragmented data and disjointed processes inherent in traditional traceability models. Its four clearly defined modules significantly simplify the cold chain traceability process and reduce the workload of manual traceability analysis. By relying on systematic logical judgment to replace manual inspection, it fundamentally improves the overall accuracy of identifying and tracing abnormalities in cold chain temperature and humidity. Simultaneously, it enables permanent storage and preservation of traceability data, facilitating subsequent food safety traceability and liability determination. This comprehensively enhances the intelligent and standardized traceability supervision level of pre-prepared dish cold chain logistics, effectively reducing spoilage and loss of pre-prepared dishes due to abnormal temperature control and ensuring the safety of pre-prepared dish distribution.

[0027] In some specific embodiments, the modeling module is used to build a digital twin model of the entire cold chain scenario for the target pre-prepared dish, and to bind all physical entity units within the cold chain scenario to their corresponding virtual twin units. When constructing a batch-specific traceability carrier, this includes: Determine whether the unique identifier of each physical entity unit in the cold chain scenario of the target pre-prepared dish is completely consistent with the identity identifier of the corresponding virtual twin unit; When the unique identifier of the physical entity does not match the identity identifier of the virtual twin unit, the unit binding is determined to be abnormal, all subsequent tracing processes are suspended and the binding relationship is awaited to be manually corrected. When the unique identifier of the physical entity is completely consistent with the identity identifier of the virtual twin unit, it is further determined whether the scene space mapping deviation value between the physical entity and the virtual twin unit exceeds the preset mapping matching threshold. When the scene space mapping deviation between the physical entity and the virtual twin unit exceeds the preset mapping matching threshold, the binding compliance is determined to be substandard, the twin binding relationship is reset and the binding matching process is re-executed. When the scene space mapping deviation between the physical entity and the virtual twin unit does not exceed the preset mapping matching threshold, the virtual and physical unit binding is deemed valid, and the basic carrier for batch traceability is established.

[0028] It should be understood that in actual operation, the system prioritizes retrieving the unique identification codes built into the two types of units to complete the comparison. The preset mapping matching threshold is the maximum allowable spatial coordinate deviation set in advance based on the cold chain scenario layout and equipment installation location. Only when both the identity identification is consistent and the spatial mapping deviation value does not exceed the corresponding threshold can the binding be deemed qualified. If either condition is not met, the binding process will be automatically terminated and corrected, ensuring the accurate correspondence between virtual and real scenarios from the source and avoiding deviations in subsequent traceability data due to binding misalignment.

[0029] In the actual construction of a digital twin scenario for cold storage and cold chain, staff batch-enter the identity information and spatial coordinates of all cold chain equipment and goods storage areas within the cold storage. The system automatically completes the matching and binding of virtual units. If errors occur, such as incorrect equipment number entry or deviations in the virtual scene layout, the system can immediately identify and prompt for correction. This binding verification method effectively avoids errors in the correspondence between virtual and real data during the construction of the digital twin model, ensuring that subsequent data synchronization and anomaly analysis are based on accurate mapping. The standardized binding judgment process reduces the operational difficulty of model construction and is adaptable to pre-prepared food cold chain storage scenarios of different sizes and layouts. Simultaneously, accurate virtual-real binding significantly improves the matching accuracy of subsequent temperature and humidity data, laying a solid foundation for accurate traceability throughout the entire process and reducing traceability analysis errors caused by model binding mistakes.

[0030] In some specific embodiments, the synchronization module is used to collect temperature and humidity data and cold chain operation status data in real time throughout the entire process of cold chain storage, transportation, and distribution of the target pre-prepared dish. When synchronizing the collected data to the digital twin model, it includes: Determine whether the transmission delay of real-time cold chain temperature and humidity and equipment status data exceeds the preset timeliness threshold for digital twin scenario synchronization; When the data transmission delay exceeds the preset time threshold, the data transmission of this group is determined to be abnormal, the data is marked as missing and the group of data is discarded and will not participate in the virtual twin scene state update. If the data transmission delay does not exceed the preset timeliness threshold, it is further determined whether the number of missing fields in the data group exceeds the preset data integrity threshold. When the number of missing fields in the data exceeds the preset data integrity threshold, the data set is deemed invalid, and the twin scenario synchronization update process for that data set is stopped. When the data transmission latency and data integrity both meet the corresponding preset threshold requirements, the data set is determined to be valid, and the virtual twin model is driven to complete the synchronous replication of the physical scene state.

[0031] It should be understood that the core technical means in this part is a front-end data dual-layer screening mechanism. During system operation, the raw data is collected by temperature and humidity sensors and equipment operation monitoring terminals deployed on site. The preset timeliness threshold is the maximum allowable transmission delay time of cold chain data, and the preset data integrity threshold is the maximum allowable limit of the number of missing data fields. The system has a built-in data sorting program in the background, which automatically compares the real-time transmission parameters with the two preset thresholds. Data with timeout delays is directly marked as discarded, and data with too many missing fields is judged as invalid data and synchronization is stopped. Only compliant and valid data can complete the synchronous replication of the virtual and real scene status. The data source is purified and traced from the source to ensure that the data participating in the analysis has authenticity and validity.

[0032] In cold chain trunk transportation scenarios, on-board data collection terminals collect real-time data on temperature and humidity inside the vehicle, operating power of refrigeration equipment, and start / stop status. This data is transmitted to a digital twin cloud model via wireless network. Issues such as network lag causing data transmission delays and data field loss due to terminal malfunctions can be quickly identified and filtered by the system. Pre-processing data filtering significantly reduces the interference of invalid, delayed, and incomplete data on subsequent traceability and analysis, improving the reliability of overall traceability results. Real-time compliant data synchronization enables seamless display of the physical cold chain site status and the virtual simulation scenario, allowing managers to remotely and intuitively grasp the actual cold chain operation. Simultaneously, a unified data filtering standard adapts to data collection in different communication environments and with different collection devices, improving the system's overall data compatibility and reducing the probability of errors in data collection throughout the cold chain process.

[0033] In some specific embodiments, the judgment module is used to remove various invalid data from the collected data, and to distinguish between true and false temperature control anomalies based on preset temperature control standards and the duration of the anomaly. It also determines the cause and time interval of the anomaly through digital twin comparison, and finally, when determining the degree of impact on food quality and classifying the risk level by combining the degree of temperature and humidity deviation with the duration of the anomaly, it includes: Determine whether the real-time collected cold chain temperature and humidity values ​​exceed the preset temperature control compliance range of the pre-prepared dishes; When the temperature and humidity values ​​are within the compliant range, the cold chain temperature control status is determined to be normal, the twin model is maintained in a normal monitoring state, and the traceability process is not triggered. When the temperature and humidity values ​​exceed the compliant range, it is further determined whether the duration of the abnormality reaches the preset abnormality judgment threshold, and at the same time, it is determined whether the difference between the real-time data and the twin normal simulation steady-state data exceeds the preset steady-state deviation threshold. If the duration of the anomaly does not reach the preset anomaly judgment threshold and the data difference does not exceed the preset steady-state deviation threshold, it is judged as a false anomaly caused by instantaneous environmental disturbance. Only the data record is retained and the twin source tracing and deduction process is not initiated. When the duration of the anomaly is greater than or equal to the preset anomaly judgment threshold, it is determined to be a real cold chain temperature control anomaly, and the digital twin virtual-real traceability judgment process is immediately activated.

[0034] It should be understood that the core operating principle of this part is a multi-parameter joint anomaly identification logic. The temperature control compliance range of pre-prepared dishes is set in advance according to the preservation requirements of different types of pre-prepared dishes. The preset anomaly judgment threshold is the shortest duration of anomaly required to determine a real anomaly. The preset steady-state deviation threshold is the allowable fluctuation difference of temperature and humidity data under normal and stable cold chain operation. The system retrieves the cold chain normal simulation steady-state data stored in the digital twin model as the benchmark reference data and compares it with the real-time operating data. Only when the dual conditions of the anomaly duration reaching the standard and the data difference exceeding the standard are met can it be identified as a real temperature control anomaly. Single instantaneous and small-amplitude data fluctuations are uniformly classified as false anomalies caused by environmental disturbances, which do not occupy traceability computing resources.

[0035] In the daily monitoring of pre-prepared food cold storage, short-term fluctuations in temperature and humidity caused by frequent opening and closing of the cold storage door, and brief data deviations caused by instantaneous changes in outdoor temperature, are all judged by the system as false anomalies and only recorded. However, long-term, large-scale temperature and humidity deviations caused by refrigeration equipment failures are judged as genuine anomalies, and the traceability process is quickly initiated. This identification method effectively solves the industry pain point of misjudging instantaneous environmental disturbances as equipment failures in traditional cold chain monitoring, significantly reducing the frequency of anomaly misjudgments and reducing unnecessary traceability workload. Accurate anomaly classification allows for the rational allocation of system computing resources, prioritizing traceability analysis for genuine temperature control anomalies, and improving the overall operational efficiency of the system. At the same time, relying on fixed quantitative thresholds to complete anomaly differentiation ensures standardized judgment results, eliminating the judgment bias caused by manual analysis, and further improving the standardization and accuracy of cold chain anomaly identification.

[0036] In some specific embodiments, the judgment module is used to remove various invalid data from the collected data, and to distinguish between true and false temperature control anomalies based on preset temperature control standards and the duration of the anomaly. It also determines the cause and time interval of the anomaly through digital twin comparison, and finally, when determining the degree of impact on food quality and classifying the risk level by combining the degree of temperature and humidity deviation with the duration of the anomaly, it further includes: Call the operating data of the sensing terminal twin to determine whether the abnormal temperature and humidity are caused by sensor terminal drift or malfunction; When it is determined that the sensing terminal has an abnormal operating condition, the sensing and acquisition terminal is identified as the root cause of the abnormality, and the location of the source node in this round of tracing is completed. When the sensor terminal is determined to be operating normally, the operating condition data of the cold chain equipment twin is called to determine whether there is any abnormality in the operation of the refrigeration temperature control equipment. When it is determined that the cold chain temperature control equipment is in abnormal condition, the cold chain equipment end is identified as the root cause of the abnormality, and the source tracing node is located in this round. When it is determined that the cold chain equipment is operating normally, the behavior data of the logistics scenario twin is called to determine whether there are any behaviors such as human-made unauthorized door opening or unauthorized operation. When it is determined that there is human error, the logistics operation end is identified as the root cause of the anomaly, and the source node for this round of tracing is located. When it is determined that there is no human error, the environmental twin simulation data is called to determine whether the temperature control abnormality is caused by the influence of external extreme environment, and finally the cause of the abnormality and the source node are identified.

[0037] It should be understood that the core technical principle of this part is a hierarchical traceability and investigation logic. The overall investigation sequence follows the priority order of data acquisition end → equipment end → human operation end → external environment end. The sensing terminal twin is responsible for monitoring the operating status of the sensors themselves and can identify data acquisition end faults such as sensor drift and component damage. The cold chain equipment twin monitors the operating status of the core refrigeration and temperature control equipment and identifies equipment faults such as equipment shutdown and insufficient power. The logistics scenario twin monitors human operations such as opening and closing of cold chain boxes and transfer of goods. The environmental twin monitors external natural environmental factors such as temperature and climate. By eliminating non-problematic causes layer by layer, the unique root cause of the anomaly can be accurately located. The entire investigation process is procedural and fixed, and there is no need for manual sorting of the investigation ideas.

[0038] When abnormal temperature and humidity occur in the cold chain container of pre-prepared food delivery within the city, the system first checks whether the temperature and humidity sensors inside the container are experiencing data drift. If the sensors are normal, the system checks the operating status of the onboard refrigeration equipment. If the equipment is operating normally, the system checks whether the delivery personnel have been operating the container door for an extended period of time, thus ultimately pinpointing the root cause of the anomaly. The hierarchical traceability and investigation model is clear and organized, which can quickly narrow down the scope of anomaly investigation and shorten the time required to locate the source of cold chain temperature control anomalies. It comprehensively covers four major categories of common anomaly causes: data collection equipment, refrigeration equipment, human operation, and external environment, achieving a thorough investigation of the causes of anomalies. The programmed automatic traceability replaces manual on-site investigation, significantly reducing the labor and time costs of cold chain anomaly tracing and making it easier for maintenance personnel to formulate anomaly rectification plans as soon as possible.

[0039] In some specific embodiments, the judgment module is used to remove various invalid data from the collected data, and to distinguish between true and false temperature control anomalies based on preset temperature control standards and the duration of the anomaly. It also determines the cause and time interval of the anomaly through digital twin comparison, and finally, when determining the degree of impact on food quality and classifying the risk level by combining the degree of temperature and humidity deviation with the duration of the anomaly, it further includes: Determine whether the numerical deviation of abnormal temperature and humidity in the cold chain reaches the preset deviation classification threshold for each level, and classify different deviation risk levels. Determine whether the duration of abnormal temperature and humidity in the cold chain reaches the preset time threshold for each level, and classify different time-risk levels. The quality twin model is invoked, and the preset quality degradation judgment threshold is matched based on the offset grading threshold and the duration grading threshold. If the temperature and humidity deviation does not exceed the slight deviation threshold and the abnormal duration does not exceed the short-term abnormal threshold, and the matching result does not reach the preset quality degradation judgment threshold, then the batch of cold chain abnormality is judged to be of low risk level. When the temperature and humidity deviation is in the slight deviation range and the abnormal duration is in the medium time range, or the deviation is in the medium range and the duration is in the short time range, and the matching result reaches the preset primary quality degradation judgment threshold, the batch of cold chain abnormality is judged to be of medium risk level. When the temperature and humidity deviation reaches the moderate deviation threshold and the abnormal duration reaches the long-term abnormal threshold, or the deviation reaches the severe deviation threshold and the matching result reaches the preset severe quality degradation judgment threshold, the batch of cold chain is judged to be at a high-risk level.

[0040] It should be understood that the basic status judgment program in this solution is a lightweight self-checking program built into various twins. It is only used to autonomously detect whether its own operating parameters and environmental parameters meet the corresponding preset basic thresholds. It does not participate in in-depth traceability analysis. The virtual twin of goods self-checks the storage environment parameters of goods, the virtual twin of cold chain equipment self-checks the rated operating conditions of the equipment, and the virtual twin of logistics route scenarios self-checks the logistics movement and container control status. The digital twin collaborative platform is the core of data aggregation and fusion calculation for the entire system. It is responsible for integrating all twin self-checking data, eliminating the one-sidedness of single twin analysis, and realizing global data coordination and analysis.

[0041] In large-scale cross-regional cold chain transportation of pre-prepared vegetables, all virtual twins corresponding to the transport vehicles synchronously complete self-inspections and upload data to the collaborative platform. The platform then aggregates the entire cold chain operation data to complete an overall situation analysis. This multi-twin independent self-inspection followed by centralized fusion operation mode enables comprehensive data collection from different monitoring dimensions of the cold chain, overcoming the limitations of single-dimensional data analysis. The distributed self-inspection combined with centralized computing architecture effectively distributes the overall system's computational load, improving the stability of traceability operations under large data volume scenarios. Simultaneously, a unified data upload verification mechanism ensures the integrity of the data participating in the fusion operation, preventing gaps in the overall traceability analysis results due to missing local data, and further solidifying the data foundation for subsequent risk level classification.

[0042] In some specific embodiments, the judgment module is used to remove various invalid data from the collected data, and to distinguish between true and false temperature control anomalies based on preset temperature control standards and the duration of the anomaly. It also determines the cause and time interval of the anomaly through digital twin comparison, and finally, when determining the degree of impact on food quality and classifying the risk level by combining the degree of temperature and humidity deviation with the duration of the anomaly, it further includes: Configure independent virtual twins of goods, virtual twins of cold chain equipment, and virtual twins of logistics route scenarios. Each type of twin has a built-in basic status judgment program for self-checking whether its own operating status and the parameters of its environment meet the corresponding preset basic thresholds. Determine whether the independent discrimination results of various types of twins are synchronously uploaded to the digital twin collaborative platform; If any type of twin fails to upload discrimination data, the source tracing and fusion operation will be paused until all twin data is synchronized. When all types of twin identification data are synchronized, the twin platform is used to complete the fusion of multi-source data and multi-level logical collaborative operation, and jointly output a complete traceability judgment result.

[0043] It should be understood that the various thresholds in this section are defined as follows: the offset grading thresholds include mild offset thresholds, moderate offset thresholds, and severe offset thresholds, used to classify the severity of temperature and humidity deviations from standard values; the duration grading thresholds include short-term abnormality thresholds, medium-term abnormality thresholds, and long-term abnormality thresholds, used to define the duration of abnormalities; the preset quality degradation judgment thresholds are divided into primary quality degradation judgment thresholds and severe quality degradation judgment thresholds, used to quantify the degree of quality loss of pre-prepared dishes due to abnormal temperature control. The system will input the offset parameters and duration parameters into the quality inference model, match the corresponding degradation thresholds, and then automatically classify the risk level according to the established judgment rules.

[0044] Short-term, minor deviations in temperature and humidity in cold chain batches are classified as low-risk, medium-to-long-term deviations are classified as medium-risk, and long-term, significant temperature and humidity anomalies are directly classified as high-risk. By leveraging multi-threshold linkage to classify risk levels, the system can quantify and grade the severity of hazard caused by abnormal temperature control in the cold chain of prepared dishes, overcoming the limitations of traditional methods that rely solely on experience for rough risk classification. Precise risk level classification results directly reflect the impact of abnormal temperature control on the freshness and quality of dishes, providing accurate data for subsequent differentiated management. Furthermore, standardized grading rules are adaptable to various prepared dishes with different shelf lives and storage requirements, broadening the applicability of the entire traceability system and improving its industry-wide versatility.

[0045] In some specific embodiments, the control module is used to verify the anomaly identification results, cause location information, and level classification content using accuracy verification and completeness verification. After verification, the complete traceability data is entered into the digital twin dedicated traceability ledger for solidification and evidence storage. Simultaneously, when implementing corresponding pre-prepared food logistics flow control measures based on the determined risk level, this includes: Extract the identified causes of anomalies and abnormal operating parameters, and import them into the digital twin virtual cold chain scenario to complete the state replication and simulation. Retrieve the full-time-series virtual-real mapping historical data stored in the twin model to determine whether the matching degree between the temperature and humidity change curve generated by the scene replication and the actual collected data reaches the preset accurate matching threshold. When the matching degree between the replicated data and the actual collected data does not reach the preset accurate matching threshold, it is determined that there is a deviation in the current source tracing and positioning, the source tracing logic is reset and the twin simulation source tracing and deduction is restarted. When the matching degree between the replicated data and the actual collected data reaches or exceeds the preset accurate matching threshold, the source tracing and positioning result is determined to be accurate and passes the accuracy verification.

[0046] It should be understood that the core working principle of this part is the virtual scene reproduction comparison and verification principle. The preset accurate matching threshold is the minimum qualified standard for the data overlap between two temperature and humidity change curves. The digital twin model has a complete cold chain working condition simulation and replication capability, which can reproduce the entire operating status of the cold chain site during the period of anomaly. By reproducing the entire process of the on-site anomaly through virtual simulation, it is then compared with the actual collected data change trend in a comprehensive manner. This is used to reverse verify whether there are any deviations in the previous anomaly root cause location, anomaly timing determination and other tracing results. If the matching degree does not meet the standard, the tracing logic is automatically reset and re-deduced to ensure that the tracing and positioning results are correct.

[0047] After completing the cold chain anomaly tracing and location work, the system can replicate the entire cold chain operation status during the anomaly with one click, and compare the simulation data with the on-site measured data to complete the accuracy verification. This verification method relies on virtual simulation reproduction technology to achieve reverse verification of the tracing results, which can effectively identify logical loopholes and positioning deviations in the previous tracing and judgment process, and significantly improve the accuracy of the final tracing conclusion. The full-time historical data retrieval and comparison mode can realize a thorough review of the entire anomaly process without blind spots, avoiding judgment errors in local periods. The automatic reset and re-deduction mechanism can promptly correct erroneous tracing results, further ensuring the rigor and reliability of the overall judgment results of the entire tracing scheme from the review level.

[0048] In some specific embodiments, the control module is used to verify the anomaly identification results, cause location information, and level classification content using accuracy verification and completeness verification. After verification, the complete traceability data is entered into the digital twin dedicated traceability ledger for solidification and evidence storage. Simultaneously, when implementing corresponding pre-prepared food logistics flow control measures based on the determined risk level, the module also includes: Verify that the core traceability elements in the traceability results are complete, including abnormal time, abnormal location, abnormal cause, risk level, quality impact, and handling recommendations. When core traceability elements are missing, the traceability data is determined to be incomplete, and the twin model is driven to automatically fill in the missing data and regenerate a complete traceability result. When the core traceability elements are complete, it is further determined whether all traceability data format parameters conform to the preset twin storage format threshold specification; When the data format does not conform to the preset storage format threshold specification, it will be automatically corrected and adapted to the twin storage format before entering the archiving and evidence preservation process. When the data elements are complete and the format meets the preset storage format threshold specifications, the traceability results are determined to be complete and compliant, and the twin ledger is solidified and stored as evidence. The batch risk levels obtained from the completed hierarchical classification will be mapped in real time to the digital twin virtual model for logistics management; When the control model identifies that the risk level of a batch meets the preset low-risk judgment threshold, the filing control logic is triggered, only the twin ledger information is retained, and normal circulation is allowed. When the control model identifies that the risk level of a batch meets the preset medium risk judgment threshold, the sampling control logic is triggered, the batch is locked and the food is forcibly sampled and re-inspected. The control can only be lifted after the re-inspection is qualified. When the control model identifies that the risk level of a batch meets the preset high-risk judgment threshold, it triggers the circulation restriction logic, which locks the market circulation channels of the batch of pre-made dishes through twin virtual permissions, prohibiting their sale and circulation.

[0049] It should be understood that the operating principle of this part is divided into two layers. The first layer is the principle of compliant archiving of traceability data. The system has a built-in complete checklist of traceability elements, which automatically checks whether the necessary information such as the time, location, cause, and risk level of the anomaly is complete. The preset storage format threshold uniformly specifies the data storage fields, layout format, and input specifications for traceability data, and automatically corrects non-standard data formats to ensure that the traceability ledger data is uniform and neat. The second layer is the principle of hierarchical control execution. It relies on the control virtual model to identify the risk level of the batch. The thresholds for low, medium, and high risks are consistent with the risk level classification standards mentioned above, and trigger different levels of logistics control strategies one by one to achieve precise matching between risk level and control measures.

[0050] For low-risk pre-prepared food cold chain batches, only traceability information is retained for normal circulation; medium-risk batches are subject to mandatory random sampling and re-inspection; and high-risk batches are directly restricted from market sales and circulation. Completeness verification ensures that traceability records are complete and formatted correctly, facilitating future food safety traceability reviews, regulatory department inspections, and internal quality assessments by enterprises. Standardized data archiving ensures long-term secure storage of traceability data, preventing data loss or tampering. A differentiated, tiered logistics management model enables precise control and tiered measures, ensuring the normal market circulation of low-risk, qualified pre-prepared food while strictly controlling cold chain batches with potential quality risks. This controls food safety from the distribution terminal, effectively reducing the probability of problematic food entering the market, balancing cold chain logistics efficiency with food safety supervision.

[0051] The second embodiment, according to an embodiment of this application, a method for tracing the temperature and humidity of pre-prepared dishes in cold chain logistics based on digital twins, includes the following steps: A digital twin model of the entire cold chain scenario for the target pre-prepared dishes is built, and all physical entities in the cold chain scenario are bound to the corresponding virtual twin units to construct a batch-specific traceability carrier. The system collects temperature, humidity, and cold chain operation status data in real time throughout the entire process of cold chain storage, transportation, and distribution of the target pre-prepared dishes, and synchronizes the collected data to the digital twin model. Remove all invalid data from the collected data, and distinguish between real and fake temperature control anomalies based on the preset temperature control standard and the duration of the anomaly. Determine the cause and time interval of the anomaly through digital twin comparison. Finally, determine the impact on the quality of the dish and classify the risk level by combining the degree of temperature and humidity deviation and the duration of the anomaly. Accurate and complete verification are used to review and verify the anomaly identification results, cause location information and level classification content. After verification, the complete traceability data is entered into the digital twin exclusive traceability ledger to complete the solidification and evidence storage. At the same time, the corresponding pre-prepared food logistics flow control measures are implemented according to the determined risk level.

[0052] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program goods. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program goods embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0053] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program goods according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0054] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0055] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0056] 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 above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A temperature and humidity traceability system for cold chain logistics of pre-prepared dishes based on digital twins, characterized in that, include: The modeling module is used to build a digital twin model of the entire cold chain scenario of the target pre-prepared dishes, and to bind all physical entity units in the cold chain scenario with the corresponding virtual twin units to construct a batch-specific traceability carrier. The synchronization module is used to collect temperature, humidity and cold chain operation status data in real time throughout the entire process of cold chain storage, transportation and distribution of the target pre-prepared dishes, and synchronize the collected data to the digital twin model. The judgment module is used to remove various invalid data from the collected data, and to distinguish between real and fake temperature control anomalies based on the preset temperature control standard and the duration of the anomaly. It determines the cause and time interval of the anomaly through digital twin virtual-real comparison, and finally determines the impact on the quality of the dish and classifies the risk level by combining the degree of temperature and humidity deviation and the duration of the anomaly. The control module is used to verify the anomaly identification results, cause location information and level classification content by using accurate verification and completeness verification. After verification, the complete traceability data is entered into the digital twin exclusive traceability ledger to complete the solidification and evidence storage. At the same time, the corresponding pre-made food logistics flow control measures are implemented according to the determined risk level.

2. The temperature and humidity traceability system for pre-prepared dishes based on digital twins according to claim 1, characterized in that, The modeling module is used to build a digital twin model of the entire cold chain scenario for the target pre-prepared dishes, and to bind all physical entities within the cold chain scenario to their corresponding virtual twin units. When constructing a batch-specific traceability carrier, it includes: Determine whether the unique identifier of each physical entity unit in the cold chain scenario of the target pre-prepared dish is completely consistent with the identity identifier of the corresponding virtual twin unit; When the unique identifier of the physical entity does not match the identity identifier of the virtual twin unit, the unit binding is determined to be abnormal, all subsequent tracing processes are suspended and the binding relationship is awaited to be manually corrected. When the unique identifier of the physical entity is completely consistent with the identity identifier of the virtual twin unit, it is further determined whether the scene space mapping deviation value between the physical entity and the virtual twin unit exceeds the preset mapping matching threshold. When the scene space mapping deviation between the physical entity and the virtual twin unit exceeds the preset mapping matching threshold, the binding compliance is determined to be substandard, the twin binding relationship is reset and the binding matching process is re-executed. When the scene space mapping deviation between the physical entity and the virtual twin unit does not exceed the preset mapping matching threshold, the virtual and physical unit binding is deemed valid, and the basic carrier for batch traceability is established.

3. The temperature and humidity traceability system for pre-prepared dishes based on digital twins according to claim 2, characterized in that, The synchronization module is used to collect temperature, humidity, and cold chain operational status data in real time throughout the entire process of cold chain storage, transportation, and distribution of the target pre-prepared dish. When synchronizing the collected data to the digital twin model, it includes: Determine whether the transmission delay of real-time cold chain temperature and humidity and equipment status data exceeds the preset timeliness threshold for digital twin scenario synchronization; When the data transmission delay exceeds the preset time threshold, the data transmission of this group is determined to be abnormal, the data is marked as missing and the group of data is discarded and will not participate in the virtual twin scene state update. If the data transmission delay does not exceed the preset timeliness threshold, it is further determined whether the number of missing fields in the data group exceeds the preset data integrity threshold. When the number of missing fields in the data exceeds the preset data integrity threshold, the data set is deemed invalid, and the twin scenario synchronization update process for that data set is stopped. When the data transmission latency and data integrity both meet the corresponding preset threshold requirements, the data set is determined to be valid, and the virtual twin model is driven to complete the synchronous replication of the physical scene state.

4. The temperature and humidity traceability system for pre-prepared dishes based on digital twins according to claim 3, characterized in that, The judgment module is used to remove various invalid data from the collected data, and to distinguish between true and false temperature control anomalies based on preset temperature control standards and the duration of the anomaly. It determines the cause and time interval of the anomaly through digital twin comparison, and finally, when determining the degree of impact on food quality and classifying the risk level by combining the degree of temperature and humidity deviation with the duration of the anomaly, it includes: Determine whether the real-time collected cold chain temperature and humidity values ​​exceed the preset temperature control compliance range of the pre-prepared dishes; When the temperature and humidity values ​​are within the compliant range, the cold chain temperature control status is determined to be normal, the twin model is maintained in a normal monitoring state, and the traceability process is not triggered. When the temperature and humidity values ​​exceed the compliant range, it is further determined whether the duration of the abnormality reaches the preset abnormality judgment threshold, and at the same time, it is determined whether the difference between the real-time data and the twin normal simulation steady-state data exceeds the preset steady-state deviation threshold. If the duration of the anomaly does not reach the preset anomaly judgment threshold and the data difference does not exceed the preset steady-state deviation threshold, it is judged as a false anomaly caused by instantaneous environmental disturbance. Only the data record is retained and the twin source tracing and deduction process is not initiated. When the duration of the anomaly is greater than or equal to the preset anomaly judgment threshold, it is determined to be a real cold chain temperature control anomaly, and the digital twin virtual-real traceability judgment process is immediately activated.

5. A temperature and humidity traceability system for pre-prepared dishes based on digital twins according to claim 4, characterized in that, The judgment module is used to remove various invalid data from the collected data, and to distinguish between true and false temperature control anomalies based on preset temperature control standards and the duration of the anomaly. It also determines the cause and time interval of the anomaly through digital twin comparison, and finally, when determining the impact on food quality and classifying the risk level by combining the degree of temperature and humidity deviation with the duration of the anomaly, it further includes: Call the operating data of the sensing terminal twin to determine whether the abnormal temperature and humidity are caused by sensor terminal drift or malfunction; When it is determined that the sensing terminal has an abnormal operating condition, the sensing and acquisition terminal is identified as the root cause of the abnormality, and the location of the source node in this round of tracing is completed. When the sensor terminal is determined to be operating normally, the operating condition data of the cold chain equipment twin is called to determine whether there is any abnormality in the operation of the refrigeration temperature control equipment. When it is determined that the cold chain temperature control equipment is in abnormal condition, the cold chain equipment end is identified as the root cause of the abnormality, and the source tracing node is located in this round. When it is determined that the cold chain equipment is operating normally, the behavior data of the logistics scenario twin is called to determine whether there are any behaviors such as human-made unauthorized door opening or unauthorized operation. When it is determined that there is human error, the logistics operation end is identified as the root cause of the anomaly, and the source node for this round of tracing is located. When it is determined that there is no human error, the environmental twin simulation data is called to determine whether the temperature control abnormality is caused by the influence of external extreme environment, and finally the cause of the abnormality and the source node are identified.

6. A temperature and humidity traceability system for pre-prepared dishes based on digital twins according to claim 5, characterized in that, The judgment module is used to remove various invalid data from the collected data, and to distinguish between true and false temperature control anomalies based on preset temperature control standards and the duration of the anomaly. It also determines the cause and time interval of the anomaly through digital twin comparison, and finally, when determining the impact on food quality and classifying the risk level by combining the degree of temperature and humidity deviation with the duration of the anomaly, it further includes: Determine whether the numerical deviation of abnormal temperature and humidity in the cold chain reaches the preset deviation classification threshold for each level, and classify different deviation risk levels. Determine whether the duration of abnormal temperature and humidity in the cold chain reaches the preset time threshold for each level, and classify different time-risk levels. The quality twin model is invoked, and the preset quality degradation judgment threshold is matched based on the offset grading threshold and the duration grading threshold. If the temperature and humidity deviation does not exceed the slight deviation threshold and the abnormal duration does not exceed the short-term abnormal threshold, and the matching result does not reach the preset quality degradation judgment threshold, then the batch of cold chain abnormality is judged to be of low risk level. When the temperature and humidity deviation is in the slight deviation range and the abnormal duration is in the medium time range, or the deviation is in the medium range and the duration is in the short time range, and the matching result reaches the preset primary quality degradation judgment threshold, the batch of cold chain abnormality is judged to be of medium risk level. When the temperature and humidity deviation reaches the moderate deviation threshold and the abnormal duration reaches the long-term abnormal threshold, or the deviation reaches the severe deviation threshold and the matching result reaches the preset severe quality degradation judgment threshold, the batch of cold chain is judged to be at a high-risk level.

7. A temperature and humidity traceability system for pre-prepared dishes based on digital twins according to claim 6, characterized in that, The judgment module is used to remove various invalid data from the collected data, and to distinguish between true and false temperature control anomalies based on preset temperature control standards and the duration of the anomaly. It also determines the cause and time interval of the anomaly through digital twin comparison, and finally, when determining the impact on food quality and classifying the risk level by combining the degree of temperature and humidity deviation with the duration of the anomaly, it further includes: Configure independent virtual twins of goods, virtual twins of cold chain equipment, and virtual twins of logistics route scenarios. Each type of twin has a built-in basic status judgment program for self-checking whether its own operating status and the parameters of its environment meet the corresponding preset basic thresholds. Determine whether the independent discrimination results of various types of twins are synchronously uploaded to the digital twin collaborative platform; If any type of twin fails to upload discrimination data, the source tracing and fusion operation will be paused until all twin data is synchronized. When all types of twin identification data are synchronized, the twin platform is used to complete the fusion of multi-source data and multi-level logical collaborative operation, and jointly output a complete traceability judgment result.

8. A temperature and humidity traceability system for pre-prepared dishes based on digital twins according to claim 7, characterized in that, The control module is used to verify the anomaly identification results, cause location information, and level classification content using accuracy and completeness verification. After verification, the complete traceability data is entered into the digital twin-specific traceability ledger for solidification and evidence storage. Simultaneously, when implementing corresponding pre-prepared food logistics flow control measures based on the determined risk level, the module includes: Extract the identified causes of anomalies and abnormal operating parameters, and import them into the digital twin virtual cold chain scenario to complete the state replication and simulation. Retrieve the full-time-series virtual-real mapping historical data stored in the twin model to determine whether the matching degree between the temperature and humidity change curve generated by the scene replication and the actual collected data reaches the preset accurate matching threshold. When the matching degree between the replicated data and the actual collected data does not reach the preset accurate matching threshold, it is determined that there is a deviation in the current source tracing and positioning, the source tracing logic is reset and the twin simulation source tracing and deduction is restarted. When the matching degree between the replicated data and the actual collected data reaches or exceeds the preset accurate matching threshold, the source tracing and positioning result is determined to be accurate and passes the accuracy verification.

9. A temperature and humidity traceability system for pre-prepared dishes based on digital twins according to claim 8, characterized in that, The control module is used to verify the anomaly identification results, cause location information, and level classification content using accurate and complete verification. After verification, the complete traceability data is entered into the digital twin-specific traceability ledger for solidification and evidence storage. Simultaneously, when implementing corresponding pre-prepared food logistics flow control measures based on the determined risk level, it also includes: Verify that the core traceability elements in the traceability results are complete, including abnormal time, abnormal location, abnormal cause, risk level, quality impact, and handling recommendations. When core traceability elements are missing, the traceability data is determined to be incomplete, and the twin model is driven to automatically fill in the missing data and regenerate a complete traceability result. When the core traceability elements are complete, it is further determined whether all traceability data format parameters conform to the preset twin storage format threshold specification; When the data format does not conform to the preset storage format threshold specification, it will be automatically corrected and adapted to the twin storage format before entering the archiving and evidence preservation process. When the data elements are complete and the format meets the preset storage format threshold specifications, the traceability results are determined to be complete and compliant, and the twin ledger is solidified and stored as evidence. The batch risk levels obtained from the completed hierarchical classification will be mapped in real time to the digital twin virtual model for logistics management; When the control model identifies that the risk level of a batch meets the preset low-risk judgment threshold, the filing control logic is triggered, only the twin ledger information is retained, and normal circulation is allowed. When the control model identifies that the risk level of a batch meets the preset medium risk judgment threshold, the sampling control logic is triggered, the batch is locked and the food is forcibly sampled and re-inspected. The control can only be lifted after the re-inspection is qualified. When the control model identifies that the risk level of a batch meets the preset high-risk judgment threshold, it triggers the circulation restriction logic, which locks the market circulation channels of the batch of pre-made dishes through twin virtual permissions, prohibiting their sale and circulation.

10. A method for tracing temperature and humidity in the cold chain logistics of pre-prepared dishes based on digital twins, characterized in that, The system for tracing the temperature and humidity of pre-prepared dishes in a cold chain logistics system based on digital twins, as described in any one of claims 1 to 9, comprises the following steps: A digital twin model of the entire cold chain scenario for the target pre-prepared dishes is built, and all physical entities in the cold chain scenario are bound to the corresponding virtual twin units to construct a batch-specific traceability carrier. The system collects temperature, humidity, and cold chain operation status data in real time throughout the entire process of cold chain storage, transportation, and distribution of the target pre-prepared dishes, and synchronizes the collected data to the digital twin model. Remove all invalid data from the collected data, and distinguish between real and fake temperature control anomalies based on the preset temperature control standard and the duration of the anomaly. Determine the cause and time interval of the anomaly through digital twin comparison. Finally, determine the impact on the quality of the dish and classify the risk level by combining the degree of temperature and humidity deviation and the duration of the anomaly. Accurate and complete verification are used to review and verify the anomaly identification results, cause location information and level classification content. After verification, the complete traceability data is entered into the digital twin exclusive traceability ledger to complete the solidification and evidence storage. At the same time, the corresponding pre-prepared food logistics flow control measures are implemented according to the determined risk level.

Images