An intelligent logistics supply chain whole-process tracing method and system based on identification resolution

Abstract

The present application relates to the technical field of logistics management, in particular to a smart logistics supply chain whole-process tracing method and system based on identification analysis. The present application generates independent association event records for each association establishment, change and cancellation between target goods and carriers, and appends them to the association relationship time axis sequence in chronological order, and registers the association ID as an independent identification object in the secondary node of the industrial internet identification analysis system, so that in the multi-modal transport and dynamic carpooling or single disassembly scenarios, even if the goods frequently change carriers in the transit link, the tracing platform can still trace the carrier and its running track of the target goods in each transport stage through the association relationship time axis, avoiding the problem of broken tracing information caused by the disassociation of goods and carrier identification.

Description

Technical Field

[0001] This invention belongs to the field of logistics management technology, specifically relating to a smart logistics supply chain traceability method and system based on identifier resolution. Background Technology

[0002] With the rapid development of smart logistics, multimodal transport and dynamic carpooling / order splitting are becoming increasingly common, leading to frequent merging and separation operations between goods and vehicles in the logistics supply chain. Currently, some solutions achieve traceability by assigning identification codes to both goods and vehicles and recording the scanned information at transit nodes. However, these solutions typically only record the identification codes for goods and vehicles independently at different transport nodes, lacking a systematic maintenance of the dynamic binding relationship between the two.

[0003] Specifically, in multimodal transport and dynamic carpooling / order splitting scenarios, the lack of an effective management mechanism for establishing, changing, deregulating, and historically reviewing the association between item identification and vehicle identification leads to frequent breaks in traceability information during logistics transfer, making it impossible to form a complete and continuous traceability data chain. Based on the above, existing traceability systems can only provide passive query and playback of historical information, making it difficult to automatically identify and provide real-time warnings for abnormal events hidden in the traceability data, such as transportation timeouts, temperature control violations, route deviations, and fraudulent signing. They also cannot proactively push disposal suggestions to relevant responsible parties and trigger intervention processes when abnormalities occur.

[0004] To address the aforementioned issues, this invention proposes a method and system for end-to-end traceability of intelligent logistics supply chains based on identifier resolution. Summary of the Invention

[0005] To address the aforementioned problems in the existing technology, the present invention aims to provide a method and system for end-to-end traceability of intelligent logistics supply chain based on identifier resolution.

[0006] To achieve the above-mentioned objectives, the technical solution adopted by this invention is as follows: A smart logistics supply chain end-to-end traceability method based on identifier resolution includes: When the target item enters the first circulation node of the supply chain, the item identification code of the target item and the vehicle identification code of the currently associated vehicle are read to generate an initial association event record, and the association ID in the initial association event record is registered in the industrial internet identification resolution system as an independent identification object; When the target item arrives at any subsequent flow node in the supply chain, the identification information of that node is obtained. Based on the identification information, it is determined whether the association between the target item and the current vehicle has changed. If there is no change, the transit information is added. If there is a change, an association removal event record and a new association establishment event record are generated. The two event records are appended to the end of the association timeline sequence in sequence, and an association update request is sent to the Industrial Internet Identifier Resolution System. During the logistics and transportation of the target goods, real-time supply chain process data is acquired, and the supply chain process data is bound with currently valid related event records to generate traceability data blocks; Anomaly detection is performed on traceable data blocks based on a pre-defined anomaly rule base to determine whether any abnormal events exist. When an abnormal event is detected, the responsible party is determined based on the currently valid related event records, a tiered early warning is pushed out, and the handling measures information fed back by the responsible party is received and stored in association. In response to a traceability query request initiated by a user terminal, complete traceability information is extracted from the associated timeline and traceability data blocks based on the item identification code of the target item, and traceability results are generated and fed back to the user terminal.

[0007] Preferably, generating an initial association event record includes: bidirectionally associating the item identifier code and the vehicle identifier code to generate an initial association event record. The initial association event record includes at least the association ID, item identifier code, vehicle identifier code, association type, association establishment time, and association establishment location. The association type includes master-slave association and temporary association.

[0008] Preferably, determining whether the association between the target item and the current vehicle has changed includes: verifying the consistency between the item identification code carried in the reading information and the item identification code in the previous associated event record; if the verification passes, determining whether the vehicle identification code at the transfer node is the same as the vehicle identification code in the previous associated event record; if they are the same, it is determined that no change has occurred; if they are different, it is determined that a change has occurred.

[0009] Preferably, the association termination event record includes at least the original association ID, item identification code, original vehicle identification code, termination time, and termination location; the new association establishment event record includes at least the new association ID, item identification code, new vehicle identification code, association type, and association establishment time; the association relationship timeline is an ordered sequence of events with the item identification code as the primary key and the association event occurrence time as the sorting basis, which fully records the history of the vehicles that the target item has traveled on and the establishment, modification, and termination of its association relationships in each circulation stage since entering the supply chain.

[0010] Preferably, the process involves acquiring supply chain process data in real time and binding the supply chain process data with currently valid associated event records to generate traceability data blocks. This includes: acquiring supply chain process data from multiple data sources in real time through a data interface, including vehicle positioning terminals, environmental monitoring sensors, access control systems, warehouse management systems, transportation management systems, and handheld terminals; binding each set of acquired supply chain process data with currently valid associated event records to generate traceability data blocks. Each traceability data block includes at least a data block ID, item identification code, association ID, vehicle identification code, data type, data content, data timestamp, and data hash value.

[0011] Preferably, anomaly detection is performed on the traceability data block based on a preset anomaly rule base, including: extracting the data type and associated ID of the current traceability data block, and filtering a subset of candidate rules from the anomaly rule base according to the data type; for each rule in the subset of candidate rules, extracting the feature data required for the triggering condition from the traceability data block, and matching the feature data with the triggering condition; if the match is successful, it is determined that an anomaly event has been triggered, and an anomaly event record is generated; the anomaly rule base includes at least the following rule types: transportation timeout anomaly, route deviation anomaly, temperature control exceeding standard anomaly, delay anomaly, association breakage anomaly, and recipient identity anomaly.

[0012] Preferably, it also includes self-learning of exception rules: Using records of abnormal events that have been manually confirmed within a preset time period as the training sample set, the temporal feature value sequence of each sample within a preset time window before the occurrence of the abnormality is extracted. An abnormal pattern recognition model is constructed using the isolated forest algorithm. The model is retrained based on newly confirmed samples at a preset period and the trigger condition parameters are updated by weighted fusion.

[0013] Preferably, tiered early warning push notifications are implemented, including: The alert push strategy is determined based on the anomaly level. If the anomaly level is Level 1, an anomaly event log is recorded in the system backend. If the anomaly level is Level 2, the operating entity information is queried based on the vehicle identification code in the currently valid associated event record to determine the current responsible party, and an alert notification and handling suggestions are sent to the current responsible party. If the anomaly level is Level 3, an alert notification is sent to both the current responsible party and the next higher level responsible party, and an emergency notification is sent to the administrator account. If no feedback is received within the preset handling time limit, a reminder notification is automatically pushed to the next higher level responsible party.

[0014] Preferably, extracting complete traceability information from the association timeline and traceability data blocks includes: using the item identification code as an index, retrieving all related event records from the association timeline and sorting them to generate an association event timeline sequence; using the item identification code and each associated ID as a combined index, retrieving process data for each stage of the related event from the traceability data blocks and sorting them to generate a process data sequence; and merging the association event timeline sequence and the process data sequence to generate structured complete traceability information.

[0015] This invention also discloses a smart logistics supply chain end-to-end traceability system based on identifier resolution, comprising: The initial association construction module is used to read the item identification code of the target item and the vehicle identification code of the currently associated vehicle when the target item enters the first circulation node of the supply chain, generate an initial association event record, and register the association ID in the initial association event record as an independent identification object in the industrial internet identification resolution system. The association change management module is used to obtain the identification information of any subsequent circulation node in the supply chain when the target item arrives at that node, and to determine whether the association relationship has changed based on the identification information: if no change has occurred, the transit information is added; if a change has occurred, an association termination event record and a new association establishment event record are generated and added to the association relationship timeline sequence, and an association relationship update request is sent to the Industrial Internet Identifier Resolution System. The traceability data acquisition module is used to acquire supply chain process data in real time during the logistics and transportation of target items, bind the supply chain process data with currently valid related event records, and generate traceability data blocks. The anomaly detection module is used to perform anomaly detection on traceable data blocks based on a preset anomaly rule base to determine whether there are any abnormal events. The tiered early warning push module is used to determine the responsible party based on the currently valid related event records when an abnormal event is detected, and to execute tiered early warning push. It also receives and stores the handling measures information fed back by the responsible party. The traceability query response module is used to respond to traceability query requests initiated by user terminals. It extracts complete traceability information from the associated timeline and traceability data blocks based on the item identification code of the target item, generates traceability results, and feeds them back to the user terminal. Beneficial effects

[0016] 1. This invention generates independent association event records for each establishment, modification, and disassociation of the association between the target item and the means of transport, and adds them to the association relationship timeline sequence in chronological order. At the same time, the association ID is registered as an independent identifier at the secondary node of the industrial internet identifier resolution system. Thus, in multimodal transport and dynamic carpooling or splitting scenarios, even if the goods frequently change means of transport during transit, the traceability platform can still completely trace back the means of transport and their operating trajectory of the target goods in each stage of transportation through the association relationship timeline, avoiding the problem of broken traceability information caused by the unbinding of the goods and means of transport identifiers.

[0017] 2. This invention constructs a detection engine that includes multi-dimensional anomaly rules such as transportation timeouts, route deviations, temperature control violations, delays, broken connections, and abnormal recipient identities. The trigger condition parameters for each rule are determined based on the statistical analysis results of historical operating data. The isolated forest algorithm is used to perform weighted fusion updates on a weekly basis based on newly confirmed samples, thereby achieving objective determination and continuous optimization of the detection threshold. This enables the traceability platform to automatically match and identify anomalies in supply chain process data, solving the problem that traditional traceability systems can only provide historical information for passive querying and cannot actively detect anomalies.

[0018] 3. When an abnormal event is detected, the present invention executes a differentiated early warning push strategy based on the level of abnormality. It automatically queries the operating entity information based on the vehicle identification code in the current associated event record to determine the current responsible party, and associates and stores the abnormal event with the handling measures reported by the responsible party to form a closed loop record. If no feedback is received within the preset handling time limit, it automatically pushes a reminder notice to the next higher level of responsible party. In this way, when an abnormality occurs, it can proactively push handling suggestions to relevant responsible parties and trigger the intervention process, thereby shortening the abnormality response time and improving the efficiency of supply chain collaborative management. Attached Figure Description

[0019] Figure 1 This is a flowchart of the method of the present invention; Figure 2 This is a system module diagram of the present invention. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments. It should be understood that the specific embodiments described herein are merely for explaining the invention and are not intended to limit the scope of protection of the invention. Example 1

[0021] Please see Figure 1 As shown, this embodiment provides a method for end-to-end traceability of smart logistics supply chains based on identifier resolution, including the following steps: When a target item enters the first circulation node of the supply chain, the traceability platform obtains the item identification code and the vehicle identification code of the currently associated vehicle through identification reading devices, and constructs an initial association event record.

[0022] Specifically, the traceability platform uses identification and recognition devices such as handheld scanning terminals, RFID readers or fixed channel scanning devices to read the first identification carrier set on the target item and the second identification carrier set on the current vehicle.

[0023] The first identification carrier stores the item identification code of the target item. This item identification code is generated according to the coding rules of the Industrial Internet Identifier Resolution System and includes at least item category information, batch information and single item serial number.

[0024] The second identification carrier stores the vehicle identification code of the vehicle. This vehicle identification code is also generated according to the coding rules of the Industrial Internet Identifier Resolution System and includes at least vehicle type information, operating entity information, and license plate or container number information.

[0025] The traceability platform will bidirectionally associate the read item identification code and vehicle identification code to generate an initial association event record. This initial association event record will include at least the association ID, item identification code, vehicle identification code, association type, association establishment time, association establishment location, operator information, and association validity period.

[0026] Preferably, the association types are divided into two categories based on the different transportation organization models: master-slave association and temporary association. Master-slave association is suitable for long-term stable binding relationships, such as the binding between containers and ships, or between full trucks and trailers; temporary association is suitable for short-term binding relationships in carpooling or splitting scenarios, such as the binding between multiple parcels and the same urban delivery vehicle.

[0027] Even better, while constructing the initial associated event record, the traceability platform initiates an identifier registration request to the Industrial Internet Identifier Resolution System, registering the associated ID in the initial associated event record as an independent identifier object at the secondary node, so that the corresponding associated relationship details can be queried through the associated ID later.

[0028] The items mentioned include, but are not limited to, physical entities that need to be traced in the logistics supply chain, such as goods, parcels, pallets, and turnover boxes; the means of transport mentioned include, but are not limited to, vehicles, ships, airplanes, trains, containers, cage cars, and transfer carts, and other equipment or containers that carry items for spatial movement.

[0029] S2. Obtain the identification information reported by the identification reading device of the transit node, generate the association change event record and update the association relationship timeline; When the target item arrives at any subsequent transfer node in the supply chain, the traceability platform obtains the identification information reported by the identification device of that transfer node, generates a related change event record based on this information, and updates the timeline of the related relationships.

[0030] Specifically, when the target item arrives at the transit node, the identification reading device at the transit node reads the item identification code of the target item and the vehicle identification code of the current vehicle simultaneously or sequentially, and reports the reading information to the traceability platform. After receiving the identification information, the traceability platform checks the consistency between the item identification code carried in the identification information and the item identification code in the previous associated event record. If they match, the platform continues to execute the subsequent steps. If they do not match, the platform generates the first abnormal signal and reports it to the abnormal event handling module.

[0031] After the consistency check passes, the traceability platform determines whether the vehicle identification code at the transit node is the same as the vehicle identification code in the previous associated event record.

[0032] If they are the same, it is determined that the relationship between the target item and the vehicle has not changed. The traceability platform only adds the transit information of the current transit node to the associated event record, including arrival time, arrival location and transit operation type, and does not generate a new associated event record.

[0033] If the differences are not observed, it is determined that the target item underwent a change of transportation at the transit node, i.e., a change in the association relationship. The traceability platform then performs association deregulation and reconstruction operations. For the original association relationship, the traceability platform generates an association deregulation event record. This record includes at least the original association ID, item identification code, original transportation identification code, deregulation time, deregulation location, and deregulation reason. Reasons for deregulation include, but are not limited to, transit transfer, carpooling splitting, and vehicle malfunction. This association deregulation event record is appended to the end of the timeline sequence corresponding to the item identification code in the association relationship timeline.

[0034] For new associations, the traceability platform generates a new association establishment event record. This new record includes at least the new association ID, item identification code, new vehicle identification code, association type, association establishment time, association establishment location, and association validity period. This new record is also appended to the end of the timeline sequence corresponding to the item identification code in the association timeline. The traceability platform sends an association update request to the Industrial Internet Identifier Resolution System, registering the association termination event record and the new association establishment event record at the secondary node, enabling the complete association timeline to be retrieved using the item identification code.

[0035] Furthermore, when a change in association occurs at a transit node, the traceability platform automatically verifies whether the current physical state of the target item meets the switching conditions; if the target item is a cold chain item and the current temperature data exceeds the preset safety threshold, the change in association is temporarily suspended, a second abnormal signal is generated and pushed to the current responsible party; The preset safety threshold is determined based on the temperature control requirements in the industry standards for the product category. Specifically, for cold chain pharmaceuticals, it is based on the temperature range specified in Appendix III, "Management Specifications for Automatic Monitoring of Temperature and Humidity in Pharmaceutical Storage," of the Good Supply Practice for Pharmaceutical Products (GSP); for cold chain food, it is based on the temperature control requirements for that food category in the National Food Safety Standard for Hygienic Standards of Cold Chain Logistics for Food (GB 31605). This threshold can be adjusted synchronously through the traceability platform's management interface according to updates to national standards.

[0036] The association timeline refers to an ordered sequence of events with the item identification code as the primary key and the occurrence time of the associated events as the sorting basis. It fully records the history of the means of transport that the target item has taken in each circulation stage since entering the supply chain system, as well as the establishment, modification and termination of its associations.

[0037] Through the above process, in multimodal transport and dynamic carpooling or splitting scenarios, every establishment, change and termination of the association between the target goods and the means of transport can be fully recorded, forming a complete, continuous and traceable traceability data chain, fundamentally solving the problem of traceability failure caused by information breaks in the transit links.

[0038] S3. Acquire supply chain process data in real time and bind it with current related event records to form traceability data blocks; The traceability platform acquires supply chain process data in real time and binds it with current related event records to form traceability data blocks.

[0039] Specifically, during the logistics and transportation of the target goods, the traceability platform obtains supply chain process data from multiple data sources in real time through data interfaces.

[0040] Data sources include, but are not limited to, vehicle-mounted positioning terminals installed on the transport vehicle, environmental monitoring sensors installed in the cargo compartment of the transport vehicle, access control systems or electronic fence systems at each transit node, WMS warehouse management system at each transit node, TMS transportation management system, handheld terminals of last-mile delivery personnel, and supply chain management system.

[0041] Among them, vehicle-mounted positioning terminals provide real-time location data and operating trajectories; environmental monitoring sensors provide environmental data such as temperature, humidity, and vibration, which are especially suitable for temperature monitoring of cold chain goods; access control systems or electronic fence systems provide entry and exit timestamps and regional location information; WMS warehouse management systems provide operation records such as inbound shelving and picking and outbound; TMS transportation management systems provide planning information such as electronic waybills and estimated arrival times; handheld terminals provide delivery information such as signing time, signatory identity, and signing images; and supply chain management systems provide source information such as purchase orders, production batches, and quality inspection reports.

[0042] The traceability platform binds each set of supply chain process data it acquires to a currently valid associated event record, generating a traceability data block. The currently valid associated event record refers to the latest association establishment event record corresponding to the item's identification code that has not yet been terminated. A traceability data block includes at least the following fields: data block ID, item identification code, association ID, vehicle identification code, data type, data content, data timestamp, data source, and data hash value. The data hash value is a verification value obtained by hashing the data content and is used to verify data integrity.

[0043] Preferably, when generating each traceability data block, the traceability platform simultaneously registers the key fields within it with the secondary nodes in the Industrial Internet Identifier Resolution System.

[0044] Key fields include at least the item identification code, associated ID, data type, data timestamp, and data hash value, enabling direct retrieval of index information for each traceability data block related to the item through identifier resolution queries using the item identification code. Furthermore, The traceability platform stores the generated traceability data blocks in a blockchain system or distributed database to ensure that the data is tamper-proof.

[0045] S4. Based on at least one exception rule base, perform anomaly detection on the traceability data block to determine whether there is an abnormal event.

[0046] The traceability platform performs anomaly detection on traceability data blocks based on at least one anomaly rule base to determine whether there are any abnormal events.

[0047] Specifically, the traceability platform has at least one pre-configured or dynamically loaded exception rule library. This exception rule library contains preset exception detection rules, and each exception detection rule includes at least a rule type, triggering conditions, and exception level. The traceability platform inputs each traceability data block generated in step S3 into the exception detection engine, which then matches each exception detection rule to determine whether an exception event exists.

[0048] The exception rule base includes at least the following rule types: transportation timeout exception, route deviation exception, temperature control exceedance exception, delay exception, association break exception, and recipient identity exception.

[0049] Among them, the triggering condition for the transportation timeout anomaly is that the actual elapsed time between any two consecutive nodes under the same associated event record exceeds the sum of the preset standard transportation time and the allowable deviation coefficient, and its anomaly level is level two or three. The trigger condition for path deviation anomaly is that the shortest distance between the real-time location of the vehicle and the preset transportation route exceeds the preset deviation threshold and the duration exceeds the preset time window, and its anomaly level is level two; The trigger condition for the temperature control failure is that the temperature or humidity data reported by the environmental monitoring sensor exceeds the preset safety threshold range corresponding to the product category and the duration exceeds the preset tolerance time. Its failure level is level three. The trigger condition for the delay anomaly is that the time an item stays at a certain transfer node exceeds the preset delay threshold, and its anomaly level is level two; The trigger condition for the association breakage anomaly is that after the item is unbound, no new association event record is established with any new vehicle within the preset maximum allowable unbinding time. Its anomaly level is level two. The trigger condition for abnormal recipient identity is that the recipient identity information collected during the signing process is inconsistent with the recipient identity information reserved in the order system, and the abnormality level is level three. The initial values ​​for the triggering conditions of the above anomaly detection rules are determined based on statistical analysis of historical operational data from the supply chain node or transportation route. Specifically: For abnormally long transportation times, the preset standard transportation time is taken as the 85th percentile of the normal transportation time data of the same origin to the same destination, the same mode of transportation, and the same type of goods in the past 90 days. The allowable deviation coefficient is the ratio of this percentile to the mean, which is rounded to one decimal place.

[0050] The preset deviation threshold for abnormal path deviation is the 95th percentile of the vertical distance between the GPS trajectory points of the transportation route that have been operating normally over the past 180 days and the planned route.

[0051] For the preset safety threshold range of temperature control exceeding the standard, it is determined according to the temperature or humidity limit specified in the industry standard of the product category. The preset tolerance time is taken as 80% of the longest allowable time for the product category to not undergo irreversible changes in quality under over-temperature conditions.

[0052] For the preset delay threshold of abnormal delay, take the average time taken from arrival to completion of the transfer operation of the same type of goods at the transfer node in the past 90 days, multiplied by 1.5.

[0053] The preset maximum allowable unbinding time for associated breakage anomalies is taken as twice the average transshipment time of the historical transfer links of the transportation route.

[0054] The preset error threshold for abnormal recipient identity is the maximum edit distance allowed when comparing the recipient's identity information. The default value is 1, which means that an input error of one character is allowed.

[0055] After the system starts running, the above initial values ​​will be continuously and dynamically adjusted and optimized by the following exception rule self-learning module based on actual running data.

[0056] The specific process of anomaly detection performed by the traceability platform on each traceability data block is as follows: extract the data type and associated ID of the current traceability data block; based on the data type, filter the subset of candidate rules related to the data type from the anomaly rule library. For example, if the data type is location data, filter the path deviation anomaly rule; if the data type is environmental data, filter the temperature control exceedance anomaly rule; for each rule in the subset of candidate rules, extract the feature data required for the triggering condition of the rule from the traceability data block, and match and judge the feature data with the triggering condition.

[0057] If a match is successful, the traceability data block is determined to have triggered an abnormal event, and an abnormal event record is generated. This abnormal event record includes at least the abnormal ID, item identification code, the data block ID that triggered the abnormality, rule type, abnormality level, time of occurrence of the abnormality, location of occurrence of the abnormality, and the original data that triggered the abnormality.

[0058] Furthermore, the traceability platform employs different detection frequencies for different anomaly levels. Level 1 anomalies are detected using timed batch detection with a preset detection cycle, such as once every 30 minutes; Level 2 anomalies are detected using near real-time detection with a preset detection interval, such as once every 5 minutes; and Level 3 anomalies are detected using real-time streaming detection, meaning that anomaly detection is triggered immediately after each traceability data block is generated.

[0059] Furthermore, the traceability platform also includes self-learning of exception rules. The specific implementation method of exception rule self-learning is as follows: The training sample set is composed of records of abnormal events manually confirmed within the past 90 days and their subsequent handling results. Positive samples are confirmed valid abnormal events, while negative samples are events marked as abnormal but verified by humans as false alarms. For each training sample, the temporal feature value sequence of each data dimension within the 30 minutes prior to the occurrence of the abnormal event is extracted, including but not limited to the rate of change of the number of queued vehicles at that node, the deviation of the cumulative operation time at that node, the real-time speed of the current vehicle associated with the item and its deviation from the planned speed, and the real-time readings and rate of change of environmental monitoring sensors. The Isolation Forest algorithm is used to train the above temporal feature values ​​in unsupervised learning to construct an abnormal pattern recognition model. This model outputs an abnormal score for each sample; the higher the score, the more the feature pattern of the sample deviates from the normal baseline. The abnormal score output by the model is compared with the results of manual confirmation, and the model is fine-tuned using the F1-score as the evaluation metric. Regarding the parameter update strategy, a weekly update cycle is used. The model is retrained based on newly added confirmed abnormal events and false alarm events. The feature boundary thresholds for judging abnormalities in the new model are extracted. The new boundary thresholds are then weighted and fused with the trigger condition parameters in the existing rules. The weight coefficients are taken as the harmonic average of the precision and recall of the new model on the validation set, so that the new thresholds with high confidence receive higher update weights. The updated parameters are automatically synchronized to the anomaly detection engine.

[0060] S5: When an abnormal event is detected, the responsible party is automatically matched based on the currently valid related event records, and a tiered early warning push is executed. When an abnormal event is detected, the tracing platform automatically matches the responsible party based on the currently valid related event records and sends out tiered early warnings.

[0061] Specifically, after step S4 detects an abnormal event and generates an abnormal event record, the tracing platform executes a tiered early warning push based on the abnormality level in the abnormal event record and the currently valid related event records. The execution process of the tiered early warning push is as follows: The warning push strategy is determined based on the anomaly level in the abnormal event log. If the anomaly level is Level 1 (Alert Level), the traceability platform only records the abnormal event log in the system backend and displays an alert icon in the abnormal event list on the management dashboard, without actively pushing notifications. If the anomaly level is Level 2 (Attention Level), the traceability platform queries the operating entity information of the vehicle based on the vehicle identification code in the currently valid related event log, determines the current responsible party, and sends an early warning notification to the current responsible party via SMS, application push, or instant messaging, along with preset handling suggestions. If the anomaly level is Level 3 (Emergency Level), the traceability platform determines the current responsible party and the superior responsible party based on the currently valid related event log and the two most recent related event logs in the related relationship timeline, sends an early warning notification to both the current responsible party and the superior responsible party simultaneously via SMS, application push, or instant messaging, along with preset handling suggestions, and also sends an emergency notification to the administrator account of the supply chain management platform.

[0062] The traceability platform also generates handling suggestions for abnormal events and pushes these suggestions along with the early warning notification.

[0063] Pre-defined handling suggestions for different types of abnormal events are stored in a handling suggestion knowledge base. For example, the handling suggestion for a transportation timeout is to contact the carrier to confirm the current vehicle location and estimated arrival time, and coordinate with the transfer node to adjust the subsequent schedule if necessary; the handling suggestion for a route deviation is to contact the driver to confirm whether the detour is due to road closures or traffic control, and verify whether there is any unauthorized route change; the handling suggestion for a temperature control exceedance is to immediately check the operating status of the refrigeration equipment, and arrange for a nearby cold chain repair point or change of transport vehicle if necessary; the handling suggestion for a delay is to contact the transfer node to confirm whether the goods have been unloaded but have not been scanned and unbound in time, and verify whether there is any missed scanning; the handling suggestion for a broken association is to contact the transfer node operator to supplement the associated event, or verify whether the goods have been misassigned to other transport vehicles; the handling suggestion for an abnormal signatory identity is to have the delivery person verify the signatory's identity information in person, and contact the recipient's phone number reserved in the order for confirmation if necessary.

[0064] The traceability platform receives information on handling measures from the current responsible party or the responsible party at the next higher level, and stores the handling measures information in association with the abnormal event records to form a closed-loop record of abnormal events.

[0065] Specifically, after receiving the warning notification, the responsible party provides feedback on the specific handling measures and results through their terminal device. The traceability platform adds the feedback information to the abnormal event record and updates the status of the abnormal event from pending handling to handled or in progress. If no feedback is received within the preset handling time limit, the traceability platform automatically sends a reminder notice to the next higher level of responsible party. The preset handling time limit is preferably 2 hours.

[0066] Furthermore, the traceability platform also includes closed-loop management of abnormal events, used to track all abnormal events throughout their entire lifecycle. The entire lifecycle includes at least the abnormal detection status, the early warning push status, the handling feedback status, and the closure and archiving status.

[0067] S6, in response to the traceability query request initiated by the user terminal, extracts complete traceability information from the associated timeline and traceability data block according to the target item identification code, generates traceability results and feeds them back to the user terminal; The traceability platform responds to traceability query requests initiated by user terminals by extracting complete traceability information from the associated timeline and traceability data blocks based on the target item identification code, generating traceability results and feeding them back to the user terminal.

[0068] Specifically, the user terminal initiates a traceability query request to the traceability platform by scanning the first identification carrier on the target item. The traceability query request carries at least the item identification code of the target item, and the user terminal includes, but is not limited to, the consumer's smartphone, the terminal device of the supply chain manager, or the terminal device of the regulatory agency.

[0069] Upon receiving a traceability query request, the system retrieves all associated event records related to the item identification code from the association timeline, indexed by the item identification code. These records are then sorted in ascending order by timestamp to generate a timeline sequence of associated events. All associated event records include association establishment events, association change events, and association termination events.

[0070] Using the item identification code and the associated IDs in the associated event records as a combined index, the traceability data blocks associated with each associated event record are retrieved from the traceability data blocks, arranged in ascending order according to the data timestamp, and the process data sequence of each associated event stage is generated.

[0071] The timeline sequence of related events and the process data sequence of each related event stage are merged to generate structured and complete traceability information. This structured and complete traceability information includes at least basic information, related trajectories, process data, and anomaly records. Basic information includes the item name, category, batch number, production date, and manufacturer; the related trajectories include information on each transportation stage arranged chronologically, with each stage including at least start and end times, start and end locations, vehicle information, and operating entity information; process data includes the location trajectory, environmental monitoring data, and transfer operation records corresponding to each stage; and anomaly records include all anomaly event records related to the item's identification code and their handling results.

[0072] The traceability platform encapsulates complete traceability information into a standard format message and sends it to the user terminal for display. Preferably, the standard format message is JSON-LD format conforming to the Industrial Internet Identifier Resolution System data exchange standard, or XML format message conforming to the EPCIS 2.0 standard, so that different user terminals can uniformly parse and display it.

[0073] Furthermore, before extracting traceability information, the traceability platform verifies the user's query permissions: it determines the user's role type based on their identity information, including ordinary consumers, supply chain managers, and regulatory agencies; it then determines the scope of data the user can view based on their role type, extracting only the traceability information within that scope for feedback. For example, ordinary consumers can only view basic information (item name, category, batch number, manufacturer) and delivery information at the signing point, but cannot view information about specific operators at transit points or the operating entity of the transportation vehicle; supply chain managers can view all related history and process data, but cannot view the exception handling records specific to regulatory agencies; regulatory agencies can view all traceability information and exception handling records, but cannot modify any data. Even better, when a traceability query request includes exception information filtering conditions, the traceability platform prioritizes extracting and highlighting exception event records related to the item's identification code and their handling results, for example, by highlighting or specially marking exception events in the traceability results display interface. Example 2

[0074] Please see Figure 2 As shown, this embodiment provides a smart logistics supply chain end-to-end traceability system based on identifier resolution, including a traceability platform. The traceability platform is communicatively connected to identifier reading devices set up at each node of the supply chain. The traceability platform is also communicatively connected to the industrial internet identifier resolution system and at least one abnormal rule base.

[0075] The traceability platform includes an initial association construction module, an association change management module, a traceability data collection module, an anomaly detection module, a tiered early warning push module, and a traceability query response module. Among these: The initial association construction module is used to read the item identification code stored on the first identification carrier of the target item and the vehicle identification code stored on the second identification carrier of the current vehicle when the target item enters the first circulation node of the supply chain. It then establishes a bidirectional association between the read item identification code and the vehicle identification code, generating an initial association event record. This initial association event record includes at least the association ID, item identification code, vehicle identification code, association type, association establishment time, association establishment location, operator information, and association validity period. The association type is divided into two types based on the transportation organization mode: master-slave association and temporary association.

[0076] Furthermore, while constructing the initial association event record, the initial association construction module initiates an identifier registration request to the Industrial Internet Identifier Resolution System, and registers the association ID in the initial association event record as an independent identifier object on the secondary node.

[0077] The association change management module is used to obtain the identification information reported by the identification reading device of any subsequent transfer node in the supply chain when the target item arrives at that node. Based on this, it generates an association change event record and updates the association relationship timeline. The association change management module performs a consistency check between the item identification code carried in the identification information and the previous association event record. If the check passes, it determines whether the vehicle identification code has changed. If no change has occurred, it only appends the transit information of the current transfer node; if a change has occurred, it generates an association termination event record and a new association establishment event record, and appends both to the end of the association relationship timeline sequence. At the same time, it sends an association relationship update request to the Industrial Internet Identifier Resolution System.

[0078] Furthermore, the association change management module automatically verifies whether the current physical state of the target item meets the switching conditions when the association relationship changes. If the target item is a cold chain item and the current temperature data exceeds the preset safety threshold, the association relationship change is temporarily suspended and an abnormal signal is generated. The preset safety threshold is determined based on the temperature control requirements in the industry standard to which the item belongs, and is synchronously adjusted through the management interface of the traceability platform according to updates to national standards.

[0079] The traceability data acquisition module is used to acquire supply chain process data in real time and bind it with currently valid related event records to generate traceability data blocks. A traceability data block includes at least a data block ID, item identification code, association ID, vehicle identification code, data type, data content, data timestamp, data source, and data hash value.

[0080] Furthermore, when generating each traceability data block, the traceability data acquisition module simultaneously registers its key fields with the secondary nodes in the Industrial Internet Identifier Resolution System and stores the generated traceability data block in a blockchain system or distributed database.

[0081] The anomaly detection module is used to detect anomalies in traceability data blocks based on at least one anomaly rule base. The anomaly rule base contains preset anomaly detection rules, each of which includes at least a rule type, triggering conditions, and anomaly level. The anomaly rule base includes at least the following rule types: transportation timeout anomaly, route deviation anomaly, temperature control exceeding anomaly, delay anomaly, association break anomaly, and recipient identity anomaly. The initial values ​​of the triggering condition parameters for each of the above anomaly detection rules are determined based on statistical analysis of historical operational data for that supply chain node or transportation route, and are continuously dynamically adjusted and optimized based on actual operational data by the anomaly rule self-learning unit built into the anomaly detection module after system operation.

[0082] The specific process of anomaly detection module performing anomaly detection on each traceable data block is as follows: extract the data type and associated ID of the current traceable data block, filter the candidate rule subset according to the data type, match and judge each candidate rule one by one, and generate an anomaly event record if the match is successful.

[0083] Furthermore, the anomaly detection module employs different detection frequencies for different anomaly levels. Specifically, the anomaly rule self-learning unit uses manually confirmed anomaly event records from the past 90 days as the training sample set, employs the Isolation Forest algorithm to construct an anomaly pattern recognition model, updates weekly, retrains the model based on new data, and performs weighted fusion updates on the trigger condition parameters.

[0084] The tiered early warning push module is used to automatically match the current responsible party and execute tiered early warning pushes when the anomaly detection module detects an abnormal event, based on currently valid related event records. If the anomaly level is Level 1, only logs are recorded in the system background; if it is Level 2, the current responsible party is determined by querying the operator's information based on the vehicle identification code, and an early warning notification and handling suggestions are sent to them; if it is Level 3, an early warning notification is sent to both the current responsible party and the next higher level responsible party, and an emergency notification is sent to the administrator account.

[0085] The tiered early warning push module also receives information on handling measures from the responsible party, associates and stores the handling measures with the abnormal event record to form a closed-loop record of the abnormal event, and automatically pushes a reminder notice to the next higher level responsible party if no feedback is received within the preset handling time limit.

[0086] The traceability query response module responds to traceability query requests initiated by the user terminal. Based on the target item identification code, it extracts complete traceability information from the associated timeline and traceability data blocks, generates traceability results, and sends them back to the user terminal. The module uses the item identification code as an index to retrieve all associated event records and sorts them to generate an associated event timeline sequence. Then, it uses each associated ID as an index to retrieve traceability data blocks for each stage and sorts them to generate a process data sequence. Finally, it merges these two data blocks to generate structured, complete traceability information, encapsulates it into a standard format message, and sends it back to the user terminal.

[0087] Furthermore, the standard format message is either JSON-LD format conforming to the Industrial Internet Identifier Resolution System data exchange standard, or XML format message conforming to the EPCIS 2.0 standard.

[0088] Furthermore, before extracting traceability information, the traceability query response module first verifies the user terminal's query permissions, determines the range of data that can be viewed based on the user's role type, and only extracts traceability information within that range for feedback.

[0089] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for end-to-end traceability of intelligent logistics supply chain based on identifier resolution, characterized in that, include: When the target item enters the first circulation node of the supply chain, the item identification code of the target item and the vehicle identification code of the currently associated vehicle are read to generate an initial association event record, and the association ID in the initial association event record is registered in the industrial internet identification resolution system as an independent identification object; When the target item arrives at any subsequent flow node in the supply chain, the identification information of that node is obtained, and the relationship between the target item and the current vehicle is determined based on the identification information: if there is no change, the transit information is added. If a change occurs, an event record for the termination of association and a new event record for the establishment of association are generated. The two event records are appended to the end of the timeline sequence of the association relationship, and an association relationship update request is sent to the Industrial Internet Identifier Resolution System. During the logistics and transportation of the target goods, real-time supply chain process data is acquired, and the supply chain process data is bound with currently valid related event records to generate traceability data blocks; Anomaly detection is performed on traceable data blocks based on a pre-defined anomaly rule base to determine whether any abnormal events exist. When an abnormal event is detected, the responsible party is determined based on the currently valid related event records, a tiered early warning is pushed out, and the handling measures information fed back by the responsible party is received and stored in association. In response to a traceability query request initiated by a user terminal, complete traceability information is extracted from the associated timeline and traceability data blocks based on the item identification code of the target item, and traceability results are generated and fed back to the user terminal.

2. The intelligent logistics supply chain end-to-end traceability method based on identifier resolution according to claim 1, characterized in that, Generate initial association event records, including: bidirectionally associating item identification codes and vehicle identification codes to generate initial association event records. Initial association event records include at least the association ID, item identification code, vehicle identification code, association type, association establishment time, and association establishment location; association types include master-slave association and temporary association.

3. The intelligent logistics supply chain end-to-end traceability method based on identifier resolution according to claim 1, characterized in that, Determining whether the association between the target item and the current vehicle has changed includes: verifying the consistency between the item identification code carried in the read information and the item identification code in the previous associated event record; if the verification passes, determining whether the vehicle identification code at the transfer node is the same as the vehicle identification code in the previous associated event record; if they are the same, it is determined that no change has occurred; if they are different, it is determined that a change has occurred.

4. The intelligent logistics supply chain end-to-end traceability method based on identifier resolution according to claim 1, characterized in that, The record of the termination of association includes at least the original association ID, item identification code, original vehicle identification code, termination time and termination location; the record of the establishment of a new association includes at least the new association ID, item identification code, new vehicle identification code, association type and association establishment time; the association timeline is an ordered sequence of events with the item identification code as the primary key and the occurrence time of the association event as the sorting basis, which fully records the history of the vehicles that the target item has taken and the establishment, modification and termination of its associations in each circulation stage since it entered the supply chain.

5. The intelligent logistics supply chain end-to-end traceability method based on identifier resolution according to claim 1, characterized in that, Real-time acquisition of supply chain process data, binding of supply chain process data with currently valid related event records, and generation of traceability data blocks, including: The system acquires supply chain process data in real time from multiple data sources, including vehicle positioning terminals, environmental monitoring sensors, access control systems, warehouse management systems, transportation management systems, and handheld terminals. Each set of acquired supply chain process data is bound to the currently valid associated event records to generate traceability data blocks; The traceability data block includes at least the data block ID, item identification code, association ID, vehicle identification code, data type, data content, data timestamp, and data hash value.

6. The intelligent logistics supply chain end-to-end traceability method based on identifier resolution according to claim 1, characterized in that, Anomaly detection is performed on traceable data blocks based on a pre-defined anomaly rule base, including: Extract the data type and associated ID of the current traceable data block, and filter the candidate rule subset from the anomaly rule base according to the data type; for each rule in the candidate rule subset, extract the feature data required for the triggering condition from the traceable data block, and match the feature data with the triggering condition for judgment; If a match is successful, an abnormal event is determined to have been triggered, and an abnormal event record is generated. The abnormal rule base includes at least the following rule types: transportation timeout abnormality, route deviation abnormality, temperature control exceeding standard abnormality, delay abnormality, association break abnormality, and recipient identity abnormality.

7. The intelligent logistics supply chain end-to-end traceability method based on identifier resolution according to claim 6, characterized in that, It also includes self-learning of exception rules: Using records of abnormal events that have been manually confirmed within a preset time period as the training sample set, the temporal feature value sequence of each sample within a preset time window before the occurrence of the abnormality is extracted. An abnormal pattern recognition model is constructed using the isolated forest algorithm. The model is retrained based on newly confirmed samples at a preset period and the trigger condition parameters are updated by weighted fusion.

8. The intelligent logistics supply chain end-to-end traceability method based on identifier resolution according to claim 1, characterized in that, Implement tiered early warning push notifications, including: The alert push strategy is determined based on the anomaly level. If the anomaly level is Level 1, an anomaly event log is recorded in the system backend. If the anomaly level is Level 2, the operating entity information is queried based on the vehicle identification code in the currently valid associated event record to determine the current responsible party, and an alert notification and handling suggestions are sent to the current responsible party. If the anomaly level is Level 3, an alert notification is sent to both the current responsible party and the next higher level responsible party, and an emergency notification is sent to the administrator account. If no feedback is received within the preset handling time limit, a reminder notification is automatically pushed to the next higher level responsible party.

9. The intelligent logistics supply chain end-to-end traceability method based on identifier resolution according to claim 1, characterized in that, Extract complete traceability information from the relationship timeline and traceability data blocks, including: using the item identification code as an index, retrieving all related event records from the relationship timeline and sorting them to generate a related event timeline sequence; using the item identification code and each related ID as a combined index, retrieving process data of each related event stage from the traceability data blocks and sorting them to generate a process data sequence; and merging the related event timeline sequence and the process data sequence to generate structured complete traceability information.

10. A smart logistics supply chain end-to-end traceability system based on identifier resolution, characterized in that, include: The initial association construction module is used to read the item identification code of the target item and the vehicle identification code of the currently associated vehicle when the target item enters the first circulation node of the supply chain, generate an initial association event record, and register the association ID in the initial association event record as an independent identification object in the industrial internet identification resolution system. The association change management module is used to obtain the identification information of any subsequent circulation node in the supply chain when the target item arrives at that node, and to determine whether the association relationship has changed based on the identification information: if no change has occurred, the transit information is added; if a change has occurred, an association termination event record and a new association establishment event record are generated and added to the association relationship timeline sequence, and an association relationship update request is sent to the Industrial Internet Identifier Resolution System. The traceability data acquisition module is used to acquire supply chain process data in real time during the logistics and transportation of target items, bind the supply chain process data with currently valid related event records, and generate traceability data blocks. The anomaly detection module is used to perform anomaly detection on traceable data blocks based on a preset anomaly rule base to determine whether there are any abnormal events. The tiered early warning push module is used to determine the responsible party based on the currently valid related event records when an abnormal event is detected, and to execute tiered early warning push. It also receives and stores the handling measures information fed back by the responsible party. The traceability query response module is used to respond to traceability query requests initiated by user terminals. It extracts complete traceability information from the associated timeline and traceability data blocks based on the item identification code of the target item, generates traceability results, and feeds them back to the user terminal.

Images