Electronic tag-based production logistics full-link ai intelligent empowerment method and system

Abstract

The application provides an electronic tag-based production logistics full-link AI intelligent enabling method and system, relates to the technical field of data processing, and comprises the following steps: extracting a node section as a suspended section after a logistics object leaves a previous node and no entry record is generated in a subsequent process corresponding node, identifying the blocking strength of the suspended section on a continuous feeding link to obtain a retention compression value, establishing a accompanying reference relationship for the logistics objects in the same transfer area, time interval and process batch as the suspended section, identifying the process receiving capacity of the logistics objects in the suspended section after entering a target work station to obtain a demand receiving value, identifying a real in-place state, an occupying state to be supplemented and a blocking state to be released, and adjusting the material entry sequence, work station waiting sequence and transfer release sequence of the production logistics. The application can identify the actual flow state of the logistics object and avoid the problem of distorted logistics state.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to an AI-enabled method and system for the entire production logistics chain based on electronic tags. Background Technology

[0002] Existing AI-enabled methods and systems for end-to-end production logistics typically bind electronic tags such as RFID, QR codes, or barcodes to materials, turnover boxes, pallets, semi-finished products, or finished products. Tag information is collected at various business nodes, including warehousing, warehouse transfer, material requisition, online delivery, process flow, quality inspection, and finished product warehousing. The system uploads the collected material codes, batch numbers, quantities, workstations, times, and flow status to the MES or ERP platform. Combined with production plans, bills of materials, process routes, and inventory data, it generates material tracking, delivery reminders, inventory warnings, and production logistics scheduling results through rule-based models or AI analysis models.

[0003] However, existing technologies for judging the status of the entire logistics chain typically rely primarily on the data collected by electronic tags at fixed nodes, which may lack business-related judgments regarding the actual retention status of materials between adjacent processes. For example, in the automotive parts assembly scenario, a batch of key connectors with electronic tags has been identified at the warehouse outbound gate, and the system marks them as having been delivered to the production line. However, if this batch of materials fails to reach the target workstation for an extended period in the transit buffer area due to congestion at the preceding workstations, the system may generate a judgment that the materials for subsequent processes are sufficient based on the outbound records, resulting in the inability to identify the risk of subsequent material shortages in advance. Summary of the Invention

[0004] The purpose of this invention is to provide an AI-enabled method and system for the entire production logistics chain based on electronic tags, aiming to solve the problems mentioned in the background art.

[0005] To solve the above-mentioned technical problems, the technical solution of the present invention is as follows:

[0006] Firstly, a method for AI-enabled intelligent empowerment of the entire production logistics chain based on electronic tags, the method comprising:

[0007] Obtain the label flow data and process task data of logistics objects, and extract node entry records, node departure records and process succession relationships to construct a node advancement sequence;

[0008] Based on the node progression sequence, the node segments in which the logistics object has completed its departure from the preceding node and has not generated an entry record in the corresponding node of the subsequent process are extracted as suspended segments to obtain suspended associated data.

[0009] Based on the suspension correlation data, the blocking intensity of the suspension section on the continuous feeding link is identified, and the retention pressure value is obtained.

[0010] Based on the suspension association data, establish accompanying reference relationships with logistics objects that are in the same transit area, time interval and process batch as the suspension section, identify abnormal replacement objects, and obtain accompanying diffusion data;

[0011] Based on the accompanying diffusion data, the process acceptance capacity of logistics objects in the suspended section after entering the target workstation is identified, and the demand acceptance value is obtained.

[0012] Based on the demand acceptance value and the stagnation pressure value, the original production logistics generated the delivered status, and the real arrival status, the occupied waiting status, and the blocked waiting release status are identified to obtain the penetrating status data.

[0013] Based on the penetration status data, the logistics objects in the blocked and waiting-to-be-released state are generated into a dynamic replacement chain according to the target workstation gap order, the transit area aggregation order, and the previous node release order. The material entry order, workstation waiting order, and transit release order of the production logistics are adjusted to obtain scheduling execution data.

[0014] Furthermore, based on the node progression sequence, node segments where the logistics object leaves a preceding node but does not generate an entry record in the corresponding node of a subsequent process are extracted as suspended segments, yielding suspended associated data, including:

[0015] Based on the node advancement sequence, extract the node departure record of the extraction flow object and the process succession relationship corresponding to the node departure record to obtain the succession relationship data;

[0016] Based on the acceptance relationship data, determine the node corresponding to the subsequent process of the node departure record, and obtain the node entry record of the logistics object in the corresponding node of the subsequent process to obtain the node verification data.

[0017] Based on the node verification data, the node segments with records of node departures but no corresponding records of node entry are identified as suspended segments, thus obtaining suspended segment data;

[0018] Based on the suspended section data, the logistics objects, nodes corresponding to node departure records, nodes corresponding to subsequent processes, and related processes of the suspended section are associated to obtain suspended associated data.

[0019] Furthermore, based on the suspension correlation data, the blockage intensity of the suspension section on the continuous feeding link is identified, and the retention pressure value is obtained, including:

[0020] Based on the suspension association data, extract the suspension duration of the current suspension segment and the transfer duration that has been completed between the same preceding node and the subsequent process node, identify the degree of deviation of the current logistics object from the normal acceptance state, and obtain the duration deviation item.

[0021] Count the number of logistics objects in the suspended section between the same preceding node and the subsequent process node, and the number of logistics objects that have been completed and accepted, identify the backlog in the current acceptance relationship, and obtain the backlog items.

[0022] The number of logistics objects in the current suspended section and the total number of logistics objects participating in the node advancement sequence are counted to identify the degree of suspension impact on the current associated process and obtain the process impact item;

[0023] Extract the dwell time of the current logistics object in the preceding node, identify the degree of transformation of the logistics object from the internal flow state of the node to the inter-node stagnation state, and obtain the state transformation item;

[0024] By integrating the duration deviation, backlog, process impact, and state transition items, the blockage intensity of the suspended section on the continuous material supply chain is identified, and the retention pressure value is obtained.

[0025] Furthermore, based on the suspension association data, accompanying reference relationships are established with logistics objects that are in the same transit area, time interval, and process batch as the suspension section, identifying abnormal replacement objects and obtaining accompanying diffusion data, including:

[0026] Based on the suspension association data, the transit area, time interval and process batch of the suspension section are extracted, and logistics objects with the same transit area, time interval and process batch are filtered to obtain the accompanying object data;

[0027] Based on the accompanying object data, the node advancement sequence of each logistics object is extracted, and the advancement position of each logistics object in the node advancement sequence is identified to obtain advancement position data;

[0028] Based on the advancement position data, the advancement position of the logistics object in the suspended section is compared with the advancement position of the accompanying object. The accompanying object that has entered the subsequent process node and whose advancement position is ahead of the logistics object in the suspended section is identified, and the advancement difference data is obtained.

[0029] Based on the advance difference data, the accompanying objects with advanced advance positions are associated with the logistics objects in the suspension section, the process occupancy relationship is identified and the abnormal replacement objects are determined, and the accompanying diffusion data is obtained.

[0030] Furthermore, based on the accompanying diffusion data, the process acceptance capacity of the logistics object within the suspended section after entering the target workstation is identified, and the demand acceptance value is obtained, including:

[0031] Based on the accompanying diffusion data, the number of abnormal replacement objects and the number of logistics objects in the suspended section are counted, the degree to which the logistics objects in the suspended section are replaced and taken over is identified, and the replacement occupancy items are obtained.

[0032] Extract the advancement positions of abnormal replacement objects and logistics objects within the suspended section, identify the degree of compensation of logistics objects within the suspended section for the current advancement gap, and obtain the advancement compensation item;

[0033] Count the number of accompanying objects that have entered subsequent process nodes in the same process batch and the total number of accompanying objects, identify the degree of completeness of the same process batch in subsequent processes, and obtain the batch inheritance items;

[0034] The number of process acceptance positions already occupied by abnormal replacement objects and the number of unoccupied process acceptance positions that can still be corresponding to logistics objects in the suspended section are counted. The retention ratio of unoccupied process acceptance positions relative to occupied process acceptance positions is calculated to obtain the vacancy retention items.

[0035] By integrating the replacement occupancy item, the advancement compensation item, the batch acceptance item, and the vacancy retention item, the process acceptance capacity of the logistics object in the suspended section after entering the target workstation is identified, and the demand acceptance value is obtained.

[0036] Furthermore, based on the demand acceptance value and the congestion pressure value, the original production logistics generated the delivered status, identifying the actual arrival status, the occupied and pending replenishment status, and the blocked and pending release status, to obtain penetrating status data, including:

[0037] Based on the demand acceptance value and the retention pressure value, the logistics objects in the delivered status are extracted, and the degree of deviation between the process acceptance capacity and the link blockage intensity of the logistics objects is identified to obtain status verification data.

[0038] Based on the status verification data, cross-identification is performed on the process acceptance capacity and link blockage intensity to identify the actual acceptance status of the logistics object in the target workstation and obtain status mapping data.

[0039] Based on the state mapping data, logistics objects with node entry records and process acceptance capacity higher than the link blockage strength are identified as truly in place; logistics objects without node entry records and process acceptance capacity higher than the link blockage strength are identified as occupied and waiting to be filled; and logistics objects without node entry records and link blockage strength higher than the process acceptance capacity are identified as blocked and waiting to be released, thus obtaining state splitting data.

[0040] Based on the state-segmented data, the logistics object, actual arrival status, occupied and pending replenishment status, and blocked and pending release status are associated, and the original delivered status generated by the production logistics is replaced to obtain penetrating state data.

[0041] Furthermore, based on the penetration status data, a dynamic replacement chain is generated for the logistics objects in the blocked and pending release state according to the target workstation gap order, the transit area aggregation order, and the preceding node release order. The material entry order, workstation waiting order, and transit release order of the production logistics are adjusted to obtain scheduling execution data, including:

[0042] Based on the penetration status data, extract the logistics objects that are in the blocked and waiting-to-be-released state, and obtain their target workstation, transit area and preceding node to obtain the data of the objects to be released;

[0043] Based on the data of objects to be released, the number of logistics objects in the occupied and replenished state and the number of logistics objects in the actual arrival state of each target workstation are counted, the degree of acceptance gap of each target workstation is identified, and gap correlation data is obtained.

[0044] Based on the gap association data, the degree of gap acceptance of the target workstation of the object to be released, the degree of object aggregation in the transfer area, and the degree of object release of the preceding node are associated and matched to determine the order of filling the gap of the object to be released and obtain the filling sorting data.

[0045] Based on the filler sorting data, objects to be released that have continuous filler relationships are linked together into a dynamic filler chain;

[0046] Based on the replacement chain, adjust the material entry order of the blocked logistics objects to be released, and adjust the waiting order of the target workstation and the transfer release order of the preceding nodes to obtain the scheduling execution data.

[0047] Secondly, an AI-powered intelligent system for the entire production and logistics chain based on electronic tags, the system comprising:

[0048] The sequence module is used to acquire the label flow data and process task data of logistics objects, and extract node entry records, node departure records and process succession relationships to construct a node advancement sequence;

[0049] The suspension module is used to extract the node segments of logistics objects that have left the preceding node but have not generated an entry record in the corresponding node of the subsequent process, based on the node advancement sequence, and obtain the suspension association data.

[0050] The retention and compression module is used to identify the blockage intensity of the suspension section on the continuous feeding link based on the suspension correlation data, and obtain the retention and compression value.

[0051] The diffusion module is used to establish accompanying reference relationships for logistics objects that are in the same transit area, time interval and process batch as the suspended section based on the suspended association data, identify abnormal replacement objects, and obtain accompanying diffusion data.

[0052] The demand acceptance module is used to identify the process acceptance capacity of logistics objects in the suspended section after they enter the target workstation based on the accompanying diffusion data, and to obtain the demand acceptance value.

[0053] The status module is used to break down the delivered status generated by the original production logistics based on the demand acceptance value and the stagnation pressure value, identify the actual delivery status, the occupied waiting status, and the blocked waiting release status, and obtain the penetrating status data.

[0054] The scheduling module is used to generate a dynamic replacement chain based on the penetration status data, which divides the logistics objects in the blocked and waiting-to-be-released state into target workstation gap order, transit area aggregation order and preceding node release order, and adjusts the material entry order, workstation waiting order and transit release order of production logistics to obtain scheduling execution data.

[0055] The above-described solution of the present invention has at least the following beneficial effects:

[0056] This invention extracts the node segment where a logistics object leaves a preceding node but does not generate an entry record at the corresponding node in a subsequent process as a suspended segment. This enables the structured representation of data states in production logistics data that were originally located between two collection nodes and lacked independent data expression. It transforms the logistics process between preceding and subsequent nodes that has not yet been completed into storable, associative, and computable data objects. This incorporates the blank areas between nodes into the business data system, forming information associations that include logistics objects, preceding nodes, subsequent nodes, and related processes. It provides an independent data carrier for the transitional states between nodes that were originally impossible to express directly. This data carrier expands the data expression range of production logistics states and forms a data description system that covers the complete flow process.

[0057] This invention generates a stagnation pressure value by identifying the obstruction intensity of suspended sections on the continuous material supply chain. This transforms the suspended sections from simple state records into data results that can participate in subsequent business calculations. The stagnation pressure value enables each suspended section to represent its impact on the continuous material supply chain in a unified data format, forming a data foundation that can be used for sorting, filtering, matching, and state mapping. It transforms the stagnant states between nodes, which originally existed only as events, into data results with quantifiable attributes. This allows abnormal states in the production logistics chain to enter the subsequent data processing flow. At the same time, the stagnation pressure value establishes a data mapping relationship between logistics objects and the continuous material supply chain, so that the state of logistics objects is no longer limited to their own flow records, but can be associated with the data expression at the material supply chain level.

[0058] This invention generates a demand acceptance value by identifying the process acceptance capacity of a logistics object after it enters the target workstation within a suspended section. This enables the production logistics system to generate data results related to the acceptance status of the target workstation. The demand acceptance value transforms the acceptance relationship between the logistics object and the target workstation into a data object that can participate in subsequent processing. The logistics object not only corresponds to the flow status data but also to the workstation acceptance status data, establishing a mapping relationship between logistics data and workstation demand data. This data result can reflect the process acceptance status corresponding to the logistics object after entering the target workstation and serves as the data basis for subsequent status breakdown processing, adding a data dimension oriented towards workstation acceptance relationships to the production logistics data system.

[0059] This invention identifies three states: "True Delivery," "Pending Replacement," and "Blocked and Pending Release." This transforms the original single "Delivered" status into multiple data status categories with distinct business characteristics. By penetrating the status data, the data objects corresponding to the "Delivered" status are reclassified according to different process acceptance statuses and link states, forming a multi-level status system. This expands the logistics object status data from a one-dimensional classification to a multi-dimensional classification structure. Different logistics objects can correspond to different status labels, establishing a one-to-one mapping relationship between status and logistics objects. This achieves fine-grained classification of production logistics status data, enabling subsequent scheduling data generation to be directly based on the classification results.

[0060] This invention generates a dynamic replacement chain for logistics objects in a blocked, pending-release state, based on the order of gaps at target workstations, the aggregation order in transit areas, and the release order of preceding nodes. It also adjusts the material entry order, workstation waiting order, and transit release order of production logistics. This organizes logistics objects scattered across different nodes, areas, and workstations into a data chain structure with sequential relationships. Within this data chain structure, each logistics object forms a sequential relationship according to predetermined association rules, transforming originally independent data records into a data set with chain-like organizational characteristics, forming a data sequence directly used for scheduling execution. This data sequence simultaneously associates logistics objects, workstations, and node information, establishing data organization relationships between different business objects and reflecting the release order, entry order, and waiting order of logistics objects. This results in data execution outcomes oriented towards production logistics scheduling, realizing the conversion of status data into scheduling data. Attached Figure Description

[0061] Figure 1 This is a flowchart of an AI-enabled production logistics end-to-end method based on electronic tags, provided by an embodiment of the present invention. Detailed Implementation

[0062] 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 so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0063] like Figure 1 As shown, embodiments of the present invention propose an AI-enabled intelligent empowerment method for the entire production logistics chain based on electronic tags, the method comprising:

[0064] Obtain the label flow data and process task data of logistics objects, and extract node entry records, node departure records and process succession relationships to construct a node advancement sequence;

[0065] Based on the node progression sequence, the node segments in which the logistics object has completed its departure from the preceding node and has not generated an entry record in the corresponding node of the subsequent process are extracted as suspended segments to obtain suspended associated data.

[0066] Based on the suspension correlation data, the blocking intensity of the suspension section on the continuous feeding link is identified, and the retention pressure value is obtained.

[0067] Based on the suspension association data, establish accompanying reference relationships with logistics objects that are in the same transit area, time interval and process batch as the suspension section, identify abnormal replacement objects, and obtain accompanying diffusion data;

[0068] Based on the accompanying diffusion data, the process acceptance capacity of logistics objects in the suspended section after entering the target workstation is identified, and the demand acceptance value is obtained.

[0069] Based on the demand acceptance value and the stagnation pressure value, the original production logistics generated the delivered status, and the real arrival status, the occupied waiting status, and the blocked waiting release status are identified to obtain the penetrating status data.

[0070] Based on the penetration status data, the logistics objects in the blocked and waiting-to-be-released state are generated into a dynamic replacement chain according to the target workstation gap order, the transit area aggregation order, and the previous node release order. The material entry order, workstation waiting order, and transit release order of the production logistics are adjusted to obtain scheduling execution data.

[0071] In this embodiment of the invention, the label flow data and process task data of the logistics object are acquired, and node entry records, node departure records, and process succession relationships are extracted to construct a node advancement sequence, establishing a data foundation for subsequent logistics status identification. Based on the node advancement sequence, the node segments where the logistics object has completed its departure from the preceding node but has not generated an entry record in the corresponding node of the subsequent process are extracted as suspended segments, obtaining suspended association data. This can detect logistics anomalies hidden in the flow process between nodes in advance, providing a basis for subsequent risk identification. Based on the suspended association data, the blocking intensity of the suspended segment on the continuous material supply link is identified, obtaining the stagnation pressure value, and identifying whether the anomaly exists, its importance, and its scope of influence. Based on the suspended association data, the logistics objects in the same transit area, time interval, and process batch as the suspended segment are established with accompanying reference relationships, identifying the anomaly replacement object and obtaining accompanying diffusion data. This can identify whether the logistics object itself is abnormal and identify the mutual influence relationship between logistics objects in the same batch.

[0072] Based on the accompanying diffusion data, the process acceptance capacity of logistics objects within the suspended section after entering the target workstation is identified, and the demand acceptance value is obtained, effectively avoiding problems such as invalid delivery, duplicate delivery, and delayed delivery. Based on the demand acceptance value and the stagnation pressure value, the delivered status generated by the original production logistics is broken down, and the actual arrival status, the occupied waiting status, and the blocked waiting release status are identified, resulting in penetrating status data. This enables in-depth verification and fine-grained expression of the logistics status, which can truly reflect the actual business location and process value of the logistics objects. Based on the penetrating status data, the logistics objects in the blocked waiting release status are dynamically replenished according to the target workstation gap sequence, the transit area aggregation sequence, and the previous node release sequence. The material entry sequence, workstation waiting sequence, and transit release sequence of the production logistics are adjusted to obtain scheduling execution data, realizing closed-loop processing from anomaly detection to scheduling optimization. This enables logistics resources to flow to the most needed workstations first, improving the real-time response capability of logistics scheduling.

[0073] This involves acquiring the tag flow data and process task data of logistics objects, extracting node entry records, node departure records, and process succession relationships, and constructing a node progression sequence, specifically including:

[0074] The system implements unified identification and management for logistics objects throughout the entire production logistics chain. These logistics objects include raw materials, semi-finished products, finished products, turnover boxes, pallets, and carriers associated with production tasks. The system pre-establishes a binding relationship between unique electronic tags and logistics object codes, storing this binding relationship in a basic logistics data table. Electronic tag identification devices, installed in warehouse receiving and dispatching areas, material buffer areas, transfer channels, delivery routes, production workstations, process handover areas, and finished product storage areas, continuously collect data on the location changes of logistics objects during the production logistics process, forming tag flow data. This tag flow data includes at least the tag identifier, logistics object identifier, identification node identifier, identification device identifier, identification time, node status information, and node's region information. The system retrieves process task data corresponding to the logistics objects from the production execution system, production planning system, or process management system. This process task data includes the production order number, product number, process route number, process number, process sequence, target workstation, task start time, task completion time, and the relationship between processes. The system matches and associates the process task data with the logistics object identifiers, ensuring that each logistics object corresponds to its respective production task and process route.

[0075] The system preprocesses the tag flow data, aggregates the collected records according to the logistics object identifier, and sorts them according to the identification time to form time-series data for the corresponding logistics object. Duplicate collection records, abnormal jump records, and invalid collection records are then removed. The identification results are corrected based on the node's region and equipment deployment location to eliminate data interference caused by continuous scanning, signal reflection, or repeated tag identification, thus obtaining stable logistics flow trajectory data. The system identifies node entry and exit behaviors based on the order in which logistics objects appear at each node. When a logistics object is first collected by the identification device corresponding to a node, the system records the time the logistics object enters the node and generates a node entry record. When a logistics object leaves the coverage area of ​​the current node and is no longer identified by the current node device within a preset time window, but is simultaneously identified by downstream nodes or adjacent area devices, the system records the time the logistics object leaves the current node and generates a node exit record. The node entry record includes the logistics object identifier, the entering node identifier, and the entry time; the node exit record includes the logistics object identifier, the leaving node identifier, and the departure time.

[0076] The system extracts process succession relationships based on the process route information in the process task data. It establishes process mapping relationships according to the sequence of processes in the process route, associating the current process with the next process, and further mapping the corresponding execution station of each process with logistics nodes, thus forming node-level succession relationship data. These process succession relationships characterize the target node that a logistics object should enter after completing its current node task, as well as the corresponding process flow direction between different nodes. The system performs node advancement analysis on a per-logistics-object basis. The system uses node entry records as the node start state and corresponding node departure records as the node completion state, and determines the next target node based on the process succession relationships. Subsequently, it continuously associates the entry, dwell, and departure states of each node with the target node information in chronological order, forming the advancement trajectory of the logistics object in the production logistics chain. The system sequentially connects the advancement relationships between nodes according to the process route sequence, linking the entire process flow status of the logistics object from warehousing nodes, distribution nodes, transfer nodes to production station nodes, forming a node advancement sequence that reflects the actual advancement process of the logistics object. The node advancement sequence records the nodes that the logistics object has completed, the nodes it is currently staying at, the nodes it has left, and the subsequent nodes that it should theoretically reach, and maintains a continuous correlation in the time dimension.

[0077] In a preferred embodiment of the present invention, based on the node progression sequence, node segments in which the logistics object has not generated an entry record in the corresponding node of the subsequent process after leaving the preceding node are extracted as suspended segments, thereby obtaining suspended associated data, including:

[0078] Based on the node advancement sequence, extract the node departure record of the extraction flow object and the process succession relationship corresponding to the node departure record to obtain the succession relationship data;

[0079] Based on the acceptance relationship data, determine the node corresponding to the subsequent process of the node departure record, and obtain the node entry record of the logistics object in the corresponding node of the subsequent process to obtain the node verification data.

[0080] Based on the node verification data, the node segments with records of node departures but no corresponding records of node entry are identified as suspended segments, thus obtaining suspended segment data;

[0081] Based on the suspended section data, the logistics objects, nodes corresponding to node departure records, nodes corresponding to subsequent processes, and related processes of the suspended section are associated to obtain suspended associated data.

[0082] In this embodiment of the invention, based on the node progression sequence, the node departure record of the extracted logistics object and the corresponding process acceptance relationship are obtained to obtain acceptance relationship data. This allows the system to determine the destination of the logistics object after departure based on process logic, providing a clear basis for subsequent judgment on whether a suspended state between nodes has been formed. Based on the acceptance relationship data, the corresponding node of the subsequent process of the node departure record is determined, and the node entry record of the logistics object at the corresponding node of the subsequent process is obtained to obtain node verification data. This achieves closed-loop confirmation of the flow status between logistics object nodes, avoiding the problem of determining that the logistics object has completed delivery based solely on the outbound, material issuance, or departure records of the preceding node. Based on the node verification data, the node segment with node departure records but no corresponding node entry records is determined as a suspended segment to obtain suspended segment data. This allows for accurate identification of the breakpoint status of the logistics object between adjacent nodes. Based on the suspended segment data, the logistics object, the node corresponding to the node departure record, the node corresponding to the subsequent process, and the related process of the suspended segment are associated to obtain suspended association data. This enables the system to analyze the impact of the suspended state on process acceptance, material supply, and production cycle.

[0083] Specifically, based on node verification data, node segments with records of node departures but no corresponding records of node arrivals are identified as suspended segments, resulting in suspended segment data, which includes:

[0084] The system uses logistics objects as processing units to parse node verification data item by item. The node verification data includes the logistics object identifier, the identifier of the preceding node, the departure time of the preceding node, the identifier of the corresponding node in the subsequent process, the verification result of the subsequent node, and the corresponding process succession relationship. The system aggregates the node verification data according to the logistics object identifier and establishes a verification mapping relationship between the current node and the subsequent process nodes according to the process route sequence, forming a succession verification link between adjacent nodes of the logistics object. The system reads the node departure records in the node verification data and uses the node departure record as the starting event to establish a set of objects to be verified. For each node departure record in the set of objects to be verified, the system extracts the corresponding subsequent process node identifier and searches the tag flow database to see if the same logistics object has already generated a node entry record corresponding to that subsequent process node. During the search process, the system uses the node departure time as the time benchmark, retaining only entry records whose occurrence time is later than the node departure time as valid succession records to avoid data interference caused by historical duplicate flow, rework flow, or duplicate tag identification.

[0085] When the system finds a valid node entry record in the corresponding node of a subsequent process, it determines that the current logistics object has completed the node transfer and marks the corresponding segment as a completed transfer segment. When the system does not find a valid node entry record, it further verifies the logistics object continuously. The system establishes a verification time window starting from the node departure time. Within the verification time window, it continuously monitors the tag identification information uploaded by the identification devices corresponding to the nodes of subsequent processes and determines in real time whether a new node entry record is generated. If no corresponding node entry record is found by the end of the verification time window, the system determines that the logistics object has not completed the subsequent node transfer after leaving the preceding node. The system further determines the current node flow status of the logistics object. Based on the process transfer relationship, the system takes the node corresponding to the node departure record as the segment start node and the node corresponding to the subsequent process as the segment target node, and uses the node departure time as the segment start time. Since the logistics object has left the coverage area of ​​the start node and has not yet entered the coverage area of ​​the target node, the system determines the node segment between the start node and the target node as a suspended segment. This node segment does not represent the state of a logistics object staying at a fixed node, but rather the intermediate state of the logistics object during the flow between nodes, where it has not been effectively received by any target node.

[0086] The system defines the time boundaries of the suspended section, using the node departure time as the suspension start time and the current system time or the time of subsequent entry record generation as the suspension end time. When no subsequent entry record has been generated, the system uses the current system time as the dynamic calculation endpoint and continuously updates the suspension duration. Once a subsequent entry record is generated, the time corresponding to the entry record is used as the suspension end time, and the suspended section status is changed from active to terminated. The system identifies the spatial information corresponding to the suspended section. Based on the area where the node corresponding to the node departure record is located, the area where the subsequent process node is located, and the logistics transportation path information, the system determines the flow range between nodes covered by the suspended section and extracts the corresponding transit area information, buffer area information, and logistics channel information. If the logistics object has auxiliary positioning records, area identification records, or buffer area identification records within the transit area, the system associates the relevant area information with the suspended section to improve the positioning accuracy of subsequent suspended status. The system generates a unique suspension identifier for each suspended section and establishes a suspended status data structure, forming suspended section data.

[0087] In a preferred embodiment of the present invention, based on suspension correlation data, the blocking intensity of the suspension section on the continuous feeding link is identified to obtain the retention pressure value, including:

[0088] Based on the suspension association data, extract the suspension duration of the current suspension segment and the transfer duration that has been completed between the same preceding node and the subsequent process node, identify the degree of deviation of the current logistics object from the normal acceptance state, and obtain the duration deviation item.

[0089] Count the number of logistics objects in the suspended section between the same preceding node and the subsequent process node, and the number of logistics objects that have been completed and accepted, identify the backlog in the current acceptance relationship, and obtain the backlog items.

[0090] The number of logistics objects in the current suspended section and the total number of logistics objects participating in the node advancement sequence are counted to identify the degree of suspension impact on the current associated process and obtain the process impact item;

[0091] Extract the dwell time of the current logistics object in the preceding node, identify the degree of transformation of the logistics object from the internal flow state of the node to the inter-node stagnation state, and obtain the state transformation item;

[0092] By integrating the duration deviation, backlog, process impact, and state transition items, the blockage intensity of the suspended section on the continuous material supply chain is identified, and the retention pressure value is obtained.

[0093] In this embodiment of the invention, based on the suspension association data, the suspension duration of the current suspension segment and the completed transfer duration between the same preceding node and subsequent process node are extracted. The degree of deviation of the current logistics object from the normal transfer state is identified, resulting in a duration deviation item. This avoids judging stagnation anomalies solely based on fixed time thresholds, making duration anomaly identification more aligned with the current production rhythm and on-site logistics conditions. The number of logistics objects in the suspension segment and the number of completed transfers between the same preceding node and subsequent process node are counted to identify the backlog degree in the current transfer relationship, resulting in a transfer backlog item. This identifies whether the transfer capacity of the logistics channel, buffer area, or target workstation has systematically decreased. The current associated workstations are counted. The system identifies the number of logistics objects in the suspended section and the total number of logistics objects participating in the node advancement sequence. It then identifies the degree of suspension impact on the current associated process, obtaining a process impact item that reflects the degree of impact of the suspension state on specific production processes. The system also extracts the dwell time of the current logistics object within the preceding node, identifies the degree of transformation of the logistics object from an internal node flow state to an inter-node stagnation state, and obtains a state transformation item. This allows the system to determine whether logistics anomalies have accumulated in the preceding node stage. Finally, it integrates the duration deviation item, the backlog item, the process impact item, and the state transformation item to identify the blocking intensity of the suspended section on the continuous material supply chain, obtaining a stagnation pressure value that represents the blocking impact of the suspended section on the material supply chain.

[0094] The formula for calculating the retention pressure value is as follows: ,

[0095] in, The value of stagnation and compression. This represents the duration of the current suspended segment, which is the current analysis time minus the time when the node left the record. This refers to the average transfer time between the same preceding node and the corresponding node in the subsequent process, that is, the average transfer time for logistics objects where a node has left the record and the corresponding node has entered the record. This represents the duration the current logistics object spends within the preceding node, which is the departure time of the preceding node minus the entry time of the preceding node. This refers to the number of logistics objects that are in a suspended segment between the same preceding node and the corresponding node of the subsequent process. This refers to the number of logistics objects that have been successfully transferred between the same preceding node and the corresponding node in the subsequent process. This represents the number of logistics objects currently in the pending section under the related process. This represents the total number of logistics objects participating in the node advancement sequence under the current associated process.

[0096] Specifically, based on the suspension correlation data, the blocking intensity of the suspension section on the continuous feeding link is identified, and the retention pressure value is obtained, including:

[0097] The system reads the logistics object identifier, the preceding node identifier, the subsequent process node identifier, and the suspension start time corresponding to the current suspended segment. Using the suspension start time as the calculation start time and the current analysis time as the calculation end time, it calculates the duration for which the current logistics object is in a suspended state. The current analysis time can be either the system's real-time analysis time or the time when the scheduled analysis task is triggered. By subtracting the occurrence time corresponding to the node departure record from the current analysis time, the duration for which the current logistics object has not completed its transfer between nodes is obtained, forming the suspension duration of the current suspension segment. The system extracts completed logistics objects from the historical node progression sequence that share the same preceding node and the same subsequent process node as the current logistics object. For each completed logistics object, the system extracts its node departure time and corresponding node entry time, and calculates the actual handling time from the departure node to the entry into the subsequent node. The system statistically calculates the handling time of all completed objects to obtain the average handling time for that node segment. , This reflects the average time required for normal logistics objects to complete the transfer between nodes. The system will... and The system performs correlation comparisons to characterize the degree to which the current logistics object deviates from the normal handling rhythm. and Construct a duration deviation relationship. When continuously increasing and significantly exceeding When this occurs, it indicates that the current logistics object has deviated from the normal receiving rhythm; when near If this is the case, it indicates that the current logistics object is still within the normal circulation range. Therefore, the system utilizes... Construct a duration deviation term so that it can reflect the degree of deviation of the current suspension state from the normal acceptance state.

[0098] The system performs statistical analysis on all logistics objects between the current preceding node and subsequent process nodes. Within the current analysis period, the system counts the number of logistics objects in the suspended segment between the same preceding node and subsequent process node. At the same time, it counts the number of logistics objects that have been accepted and recorded as nodes in the same section. .in, Reflects the scale of unfinished projects in the current node segment. It reflects the normal flow scale in the current node segment. The system utilizes... Establish a ratio for handling backlogged inventory. When... When the proportion continues to increase, it indicates that a large number of logistics items are stuck in that node segment, the node's handling efficiency is declining, and the backlog is continuously increasing; when A high percentage indicates that the node connection is functioning normally. The system utilizes... Construct a backlog item to characterize the degree of logistics backlog in the current node's supply chain and quantify the impact of blockages on the material supply chain between nodes.

[0099] Based on the associated process number in the suspended associated data, the system counts all logistics objects participating in the node advancement sequence under the current process, and obtains the total number of logistics objects participating in the node advancement sequence. At the same time, count the number of logistics objects currently in the pending section under the related process. System calculation The corresponding process suspension impact ratio. When exist When the proportion of [something] is high, it indicates that there is a significant amount of material flow suspension in the current process, and the continuous material supply capacity of the process is significantly affected; when [something] A low percentage indicates that the suspension phenomenon is limited to a small number of logistics items and has little impact on the overall operation of the process. The system utilizes... Construct process impact terms to characterize the extent and intensity of the impact of the suspension state on the entire associated process.

[0100] The system extracts the entry time and exit time of the current logistics object from its preceding nodes, and calculates the duration of the logistics object's stay within the preceding nodes. .in, This indicates the length of time a logistics object spends completing its task, waiting for release, or queuing for processing within a node. The system will display the current suspension duration. Duration of stay with the preceding node Perform correlation analysis. If Greater than This indicates that the main problem with the logistics object arises in the connection process between nodes; if and A higher value indicates that the logistics object already has a release delay within the preceding node, which further evolves into a state of inter-node stagnation. System Construction As a state transition ratio, it describes the degree to which a logistics object transitions from an internal node operational state to an inter-node suspended state. To ensure that the state transition process simultaneously reflects the impact of node backlog, the system correlates and integrates the state transition ratio with the backlog acceptance ratio, i.e., constructs... As a state transition item, the state transition item can not only reflect the degree of evolution of logistics objects from internal dwelling to external stagnation, but also reflect the overall node backlog environment in which the evolution process takes place.

[0101] The system integrates the time deviation, backlog, process impact, and state transition items, and calculates the retention pressure value according to the above formula. The first item This reflects the degree to which the current logistics object deviates from the normal receiving rhythm; the second item Used to reflect the backlog level in the current node's connection links; the third item Used to reflect the overall impact of the suspension status on related processes; Item 4 It is used to reflect the intensity of the transformation of logistics objects from internal node delays to inter-node stagnation, as well as the backlog amplification effect of this transformation process.

[0102] As the duration of suspension increases, the number of nodes backlogs increases, the scope of processes affected expands, and the degree of state transformation intensifies, the retention pressure value increases. The pressure will increase synchronously; conversely, when the logistics object is close to normal receiving status and the node links are running smoothly, the congestion pressure value will decrease. The level will remain low. The system uses the stagnation pressure value as a quantitative indicator to represent the intensity of the blockage in the continuous material supply chain caused by the current suspended section, and outputs it to subsequent modules to provide basic data support for subsequent judgment of the actual logistics status.

[0103] In a preferred embodiment of the present invention, based on the suspension association data, a companion reference relationship is established for logistics objects that are in the same transit area, time interval, and process batch as the suspension segment, abnormal replacement objects are identified, and companion diffusion data is obtained, including:

[0104] Based on the suspension association data, the transit area, time interval and process batch of the suspension section are extracted, and logistics objects with the same transit area, time interval and process batch are filtered to obtain the accompanying object data;

[0105] Based on the accompanying object data, the node advancement sequence of each logistics object is extracted, and the advancement position of each logistics object in the node advancement sequence is identified to obtain advancement position data;

[0106] Based on the advancement position data, the advancement position of the logistics object in the suspended section is compared with the advancement position of the accompanying object. The accompanying object that has entered the subsequent process node and whose advancement position is ahead of the logistics object in the suspended section is identified, and the advancement difference data is obtained.

[0107] Based on the advance difference data, the accompanying objects with advanced advance positions are associated with the logistics objects in the suspension section, the process occupancy relationship is identified and the abnormal replacement objects are determined, and the accompanying diffusion data is obtained.

[0108] In this embodiment of the invention, based on the suspended correlation data, the transit area, time interval, and process batch of the suspended section are extracted, and logistics objects with the same transit area, time interval, and process batch are screened to obtain accompanying object data, avoiding mutual interference between data from different processes, different areas, or different time periods; based on the accompanying object data, the node advancement sequence of each logistics object is extracted, and the advancement position of each logistics object in the node advancement sequence is identified to obtain advancement position data, enabling a unified comparison of the advancement status between different logistics objects; based on the advancement position data, the advancement position of the logistics object in the suspended section is compared with the advancement position of the accompanying object, identifying the accompanying object that has entered the subsequent process node and whose advancement position is ahead of the logistics object in the suspended section, obtaining advancement difference data, accurately identifying the object that has bypassed the current suspended logistics object and completed the acceptance first in the same production environment; based on the advancement difference data, the accompanying object with the advanced advancement position is associated with the logistics object in the suspended section, identifying the process occupancy relationship and determining the abnormal replacement object, obtaining accompanying diffusion data, identifying the subsequent replacement acceptance behavior caused by its failure to arrive, and revealing the chain effect of logistics anomalies on the production chain.

[0109] Specifically, based on the advancement position data, the advancement position of the logistics object within the suspended section is compared with the advancement position of accompanying objects to identify accompanying objects that have entered subsequent process nodes and whose advancement position is ahead of the logistics object within the suspended section, thus obtaining advancement difference data, which specifically includes:

[0110] The system identifies the suspended logistics object corresponding to the current suspended section and reads its advancement position in the node advancement sequence. The advancement position characterizes the degree of advancement of the logistics object in the process route, and can be established based on the arrangement order of nodes in the process route to create an advancement index. For example, incremental position numbers can be assigned according to the order of raw material warehouse nodes, distribution nodes, transfer nodes, pre-assembly stations, main assembly stations, inspection stations, and finished product nodes, forming a node advancement mapping relationship. The system determines the corresponding advancement position number based on the currently completed node advancement status of the suspended logistics object and uses it as the baseline advancement position. The system traverses all accompanying objects in the accompanying object data, reads the node advancement sequence corresponding to each accompanying object, and extracts the current node and corresponding advancement position of each accompanying object. For accompanying objects that have completed multiple node flows, the system extracts the position number corresponding to the latest node as the current advancement position; for accompanying objects in the internal operation state of a node, the system extracts the position number corresponding to the current workstation node as the advancement position.

[0111] The system establishes a progress position comparison model, using the progress position of the suspended logistics object as the baseline position P0 and the progress position of the accompanying object as the comparison position Pi, and calculates the progress difference ΔPi = Pi - P0. If the progress difference is greater than zero, it indicates that the progress of the accompanying object has surpassed that of the suspended logistics object; if the progress difference is equal to zero, it indicates that both are at the same progress stage; if the progress difference is less than zero, it indicates that the progress of the accompanying object lags behind that of the suspended logistics object. The system verifies the validity of the progress difference based on the process succession relationship, extracts the subsequent process node corresponding to the suspended logistics object, and verifies whether the accompanying object has generated a node entry record for that subsequent process node. Only when the accompanying object has entered the subsequent process node corresponding to the suspended logistics object, and the progress difference is greater than the preset progress difference threshold, does the system recognize the accompanying object as a valid advanced object.

[0112] The system further analyzes the time difference between the advanced object and the suspended logistics object, extracting the entry time of the accompanying object into the subsequent process node and the start time of the suspended logistics object forming a suspended state, and calculating the time interval between the two. If the time of the accompanying object entering the subsequent process node occurs after the suspended logistics object forms a suspended state, it indicates that the accompanying object continues to advance to the subsequent process before the suspended logistics object has completed its acceptance. The system associates the advanced accompanying object identifier, the suspended logistics object identifier, the advancement difference, the advanced node, the entry time difference, the process number, and the target workstation information to generate advancement difference data. The advancement difference data is used to describe the degree of advancement of the accompanying object relative to the suspended logistics object and the process advancement relationship during the advancement process.

[0113] Specifically, based on the advancement difference data, the accompanying objects with advanced advancement positions are associated with logistics objects within the suspension section to identify process occupancy relationships and determine abnormal replacement objects, thus obtaining accompanying diffusion data, which specifically includes:

[0114] The system extracts the advanced accompanying objects and their corresponding suspended logistics objects from the progress difference data, and establishes a one-to-one or one-to-many association analysis set. The system reads the workstation resource data, process acceptance resource data, and workstation operation status data corresponding to the advanced accompanying object when it enters the subsequent process node to identify the process acceptance resources occupied by the subsequent process node when the advanced accompanying object enters. The system extracts the workstation number, workstation slot number, workstation buffer number, tooling number, or process processing window number corresponding to the subsequent process node, and determines the actual acceptance position occupied by the advanced accompanying object when it enters the subsequent process node. Based on the process route data, the system determines the target workstation and corresponding acceptance position that the suspended logistics object should theoretically enter. The system performs a matching analysis between the acceptance position occupied by the advanced accompanying object and the theoretical acceptance position of the suspended logistics object. When both correspond to the same workstation resource, the same process acceptance position, or the same process processing window, the system determines that the advanced accompanying object has occupied the process acceptance resource that should originally be occupied by the suspended logistics object, forming a process occupancy relationship. The process occupancy relationship is used to characterize the business status where a suspended logistics object fails to enter the subsequent process as planned, and its process undertaking opportunity is occupied by other logistics objects in advance.

[0115] The system statistically analyzes the occupancy relationships of all processes corresponding to the same suspended logistics object, and calculates the number of occupancy times, occupancy duration, and the amount of resources occupied. When multiple preceding accompanying objects occupy different receiving positions, the system establishes a multi-layered occupancy mapping link to reflect the diffusion of the suspended state in subsequent processes. The system identifies abnormal replacement objects based on process occupancy relationships. An accompanying object is identified as an abnormal replacement object when it meets the following conditions: its advancement position is ahead of the suspended logistics object; it has entered the subsequent process node corresponding to the suspended logistics object; it occupies the theoretical receiving position of the suspended logistics object; and its entry occurs during the period when the suspended logistics object has not completed its receiving. Accompanying objects that meet the above conditions are identified as alternative receiving objects formed due to the suspended logistics object's failure to arrive in time, i.e., abnormal replacement objects. The system establishes accompanying reference relationships between suspended logistics objects and abnormal replacement objects, and constructs a diffusion association network centered on the suspended logistics object. The diffusion association network records the number of abnormal replacement objects, corresponding workstation resources, occupancy time sequence, advancement difference, and process occupancy level to characterize the impact process of the suspended state spreading to subsequent processes. The system will uniformly associate and store the suspended logistics object identifier, abnormal replacement object identifier, process occupancy relationship identifier, progress difference, occupied resource information, occupied time information, workstation information, and diffusion level information to form accompanying diffusion data.

[0116] In a preferred embodiment of the present invention, based on accompanying diffusion data, the process acceptance capacity of the logistics object within the suspended section after entering the target workstation is identified to obtain the required acceptance value, including:

[0117] Based on the accompanying diffusion data, the number of abnormal replacement objects and the number of logistics objects in the suspended section are counted, the degree to which the logistics objects in the suspended section are replaced and taken over is identified, and the replacement occupancy items are obtained.

[0118] Extract the advancement positions of abnormal replacement objects and logistics objects within the suspended section, identify the degree of compensation of logistics objects within the suspended section for the current advancement gap, and obtain the advancement compensation item;

[0119] Count the number of accompanying objects that have entered subsequent process nodes in the same process batch and the total number of accompanying objects, identify the degree of completeness of the same process batch in subsequent processes, and obtain the batch inheritance items;

[0120] The number of process acceptance positions already occupied by abnormal replacement objects and the number of unoccupied process acceptance positions that can still be corresponding to logistics objects in the suspended section are counted. The retention ratio of unoccupied process acceptance positions relative to occupied process acceptance positions is calculated to obtain the vacancy retention items.

[0121] By integrating the replacement occupancy item, the advancement compensation item, the batch acceptance item, and the vacancy retention item, the process acceptance capacity of the logistics object in the suspended section after entering the target workstation is identified, and the demand acceptance value is obtained.

[0122] In this embodiment of the invention, based on accompanying diffusion data, the number of abnormal replacement objects and the number of logistics objects within the suspended section are counted. The degree to which logistics objects within the suspended section are replaced is identified to obtain a replacement occupancy item. The degree to which suspended logistics objects are replaced is also identified to determine whether the target workstation's receiving resources have been occupied by other objects. The advancement positions of abnormal replacement objects and logistics objects within the suspended section are extracted to identify the degree to which logistics objects within the suspended section compensate for the current advancement gap, resulting in an advancement compensation item. This avoids misjudging logistics objects that are already seriously behind the process cycle as still having effective receiving capacity. The number of accompanying objects that have entered subsequent process nodes in the same process batch and the total number of accompanying objects are counted to identify the degree of receiving completeness of the same process batch in subsequent processes. By obtaining batch acceptance items, we can determine whether suspended objects are still needed by combining the batch-level process progress. We can count the number of process acceptance positions occupied by abnormal replacement objects and the number of unoccupied process acceptance positions that can still be corresponding to logistics objects in the suspended section. We can calculate the retention ratio of unoccupied process acceptance positions relative to occupied process acceptance positions to obtain vacancy retention items. This allows us to determine whether suspended logistics objects still have actual acceptance space, so that the demand acceptance capacity analysis is no longer limited to the level of object quantity and progress position. By integrating replacement occupancy items, progress compensation items, batch acceptance items, and vacancy retention items, we can identify the process acceptance capacity of logistics objects in the suspended section after they enter the target workstation and obtain the demand acceptance value. This can accurately determine whether suspended logistics objects still have actual process value after they arrive.

[0123] The formula for calculating the demand acceptance value is as follows: ,

[0124] in, This is the value that can be accepted by the demand. The number of abnormal replacement objects that form a process occupancy relationship with logistics objects within the suspended section. The number of logistics objects within the suspension section. , This refers to the advancement position of the abnormal replacement object in the node advancement sequence. This refers to the position of the logistics object within the suspended section in the node advancement sequence. This is the difference in advancement position between the abnormal replacement object and the logistics object within the suspended section. The length of the node progression sequence corresponding to the same batch of processes. This refers to the number of accompanying objects in the same batch of processes that have already entered subsequent process nodes. This represents the total number of accompanying objects selected within the same batch of processes. This represents the number of process positions already occupied by the abnormal replacement object. This refers to the number of unoccupied process acceptance positions that can still be corresponding to logistics objects within the suspended section.

[0125] Specifically, based on the accompanying diffusion data, the process acceptance capacity of logistics objects within the suspended section after entering the target workstation is identified, and the demand acceptance value is obtained, including:

[0126] The system uses the suspended section identifier, target workstation identifier, and process batch identifier as search criteria to determine the set of suspended logistics objects for which demand acceptance values ​​need to be calculated, as well as the set of abnormal replacement objects that have accompanying diffusion relationships with them. It also counts the number of abnormal replacement objects that form process occupancy relationships with logistics objects within the suspended section. And count the number of logistics objects in the current suspension section that have not yet completed subsequent process nodes. Number of abnormal replacement objects This represents the size of objects that have replaced suspended logistics objects and entered subsequent process nodes, forming process occupancy relationships; the number of logistics objects within the suspended segment. This is used to represent the size of objects that are currently suspended between nodes and have not yet entered the target workstation. The system utilizes... Calculate the filler occupancy ratio, and use it as... This is used as a filler item. It characterizes the degree to which a logistics object within a suspended section is replaced or taken over by another object. Setting a constant 1 in the denominator allows for... and To avoid a zero denominator when the number is small, and to keep the padding occupancy term stable in low-sample scenarios. Number of abnormal padding objects. The larger the value, the more receiving positions have been occupied by other objects in subsequent processes, and the more likely the original receiving opportunity of the suspended logistics object after arriving at the target workstation is to be weakened, resulting in a larger replacement occupancy item. When the number of abnormal replacement objects is small, it indicates that the degree of substitution is low, and the replacement occupancy item is correspondingly small.

[0127] The system extracts the advancement position of the abnormal replacement object in the node advancement sequence. And extract the advancement position of logistics objects in the node advancement sequence within the suspended section. The advancement positions can be numbered according to the arrangement order of nodes or processes in the process route, indicating the actual advancement stage of the logistics object in the production logistics chain. The system will advance the abnormal replacement object to the correct position. Position of suspended logistics object Subtracting them gives the difference in propulsion position. ,Right now This difference is used to represent the degree of advancement of the abnormal replacement object relative to the suspended logistics object. The system further obtains the node advancement sequence length corresponding to the same process batch. The length of the node advancement sequence. This indicates the number of nodes or processes from the start node of the current batch to subsequent process nodes that can be used to measure progress. The system utilizes... Construct and promote compensation items, that is, with This term represents the difficulty for the suspended logistics object to compensate for the current progress gap. Since the further ahead the abnormal replacement object is in progress, the greater the progress gap the suspended logistics object needs to catch up with, this term reflects the ease with which the suspended logistics object can recover to the rhythm of subsequent processes. Setting a constant of 1 in the denominator avoids calculation instability when the node progress sequence is short.

[0128] The system analyzes the accompanying diffusion data and node progression sequence to determine the acceptance status of accompanying objects within the same process batch. It identifies all logistics objects belonging to the same process batch as the current suspended section and included in the accompanying object set, and counts the number of accompanying objects that have already entered subsequent process nodes. And count the total number of accompanying objects selected in the same batch of processes. . This indicates the size of objects in the batch that have actually been received by subsequent process nodes. This is used to represent the overall size of the objects participating in this co-diffusion analysis within the batch. The system utilizes... A batch succession term is constructed to represent the completeness of the succession of a batch in subsequent processes. Setting a constant of 1 avoids calculation anomalies when the number of accompanying objects is empty or the sample size is extremely small, and ensures that the batch succession term remains stable across different batch sizes. near When this occurs, it indicates that most accompanying objects in the same batch of processes have entered subsequent process nodes, the target workstation's acceptance of the batch is nearing completion, and the remaining acceptance demand after the suspended logistics objects continue to enter may decrease; when much smaller If this occurs, it indicates that there are still many objects in this batch that have not yet entered the subsequent process nodes, and the suspended logistics objects may still have high acceptance value after arrival.

[0129] The system counts the number of process takeover positions already occupied by abnormal replacement objects from the accompanying diffusion data. Based on the target workstation's receiving location configuration data, workstation waiting queue data, and the theoretical receiving relationship of suspended logistics objects, the number of unoccupied process receiving locations that can still correspond to logistics objects within the suspended section is counted. Among them, the number of process acceptance positions already occupied. This indicates the number of workstation slots, process windows, cache slots, or task assignment positions actually occupied by the abnormal replacement object; and the number of unoccupied process assignment positions. This indicates the number of available receiving resources that can still be matched after a suspended logistics object arrives at its target workstation. The system utilizes... Construct a vacancy reservation item, which indicates the degree to which space is still reserved in the target workstation for suspended logistics objects. If Larger and A smaller number indicates that a large number of receiving positions have already been occupied by abnormal replacement objects. After the suspended logistics object enters the target workstation, the number of available receiving positions decreases, and the number of vacancy reservations decreases; if Larger and A lower value indicates that there are still many unoccupied positions at the target workstation, and that suspended logistics objects still have a high capacity for receiving tasks, resulting in a relatively high vacancy rate. This value allows the system to specifically map the process's capacity to the occupied and remaining resources at the target workstation.

[0130] The system calculates the required acceptance value according to the above formula. The system integrates the scale of abnormal replenishment, the gap in advancement position, the completeness of batch acceptance, and the retention status of process acceptance positions into a unified demand acceptance value. This demand acceptance value reflects whether the logistics object within the suspended section still has the ability to be effectively received, wait for, or continue to be used by the current process after entering the target workstation. The system associates and stores the calculated demand acceptance value with the suspended logistics object, the target workstation, the process batch, and subsequent process nodes, and outputs it to the subsequent penetration status identification process.

[0131] In a preferred embodiment of the present invention, based on the demand acceptance value and the congestion pressure value, the original production logistics generated by the delivered status is broken down to identify the actual delivery status, the occupied waiting-to-be-replenished status, and the blocked waiting-to-be-released status, thereby obtaining penetration status data, including:

[0132] Based on the demand acceptance value and the retention pressure value, the logistics objects in the delivered status are extracted, and the degree of deviation between the process acceptance capacity and the link blockage intensity of the logistics objects is identified to obtain status verification data.

[0133] Based on the status verification data, cross-identification is performed on the process acceptance capacity and link blockage intensity to identify the actual acceptance status of the logistics object in the target workstation and obtain status mapping data.

[0134] Based on the state mapping data, logistics objects with node entry records and process acceptance capacity higher than the link blockage strength are identified as truly in place; logistics objects without node entry records and process acceptance capacity higher than the link blockage strength are identified as occupied and waiting to be filled; and logistics objects without node entry records and link blockage strength higher than the process acceptance capacity are identified as blocked and waiting to be released, thus obtaining state splitting data.

[0135] Based on the state-segmented data, the logistics object, actual arrival status, occupied and pending replenishment status, and blocked and pending release status are associated, and the original delivered status generated by the production logistics is replaced to obtain penetrating state data.

[0136] In this embodiment of the invention, based on the demand acceptance value and the congestion pressure value, logistics objects in the delivered state are extracted. The degree of deviation between the process acceptance capacity and the link congestion strength of the logistics objects is identified to obtain state verification data. This data, combined with the process acceptance capacity and link congestion strength, is used to determine whether the delivery status is true and valid, thus improving the reliability of the logistics status data. Based on the state verification data, the process acceptance capacity and link congestion strength are cross-identified to identify the actual acceptance status of the logistics objects in the target workstation, obtaining state mapping data. This avoids misjudgments caused by relying solely on the demand acceptance value or the congestion pressure value. Based on the state mapping data, logistics objects with node entry records and process acceptance capacities higher than the link congestion strength are identified. Logistics objects with high congestion intensity are identified as truly arrived. Logistics objects without node entry records and whose process capacity exceeds the link congestion intensity are identified as occupying and awaiting replenishment. Logistics objects without node entry records and whose link congestion intensity exceeds the process capacity are identified as blocked and awaiting release. This results in state segmentation data, which can distinguish between different scenarios: truly arrived, not yet arrived but still needing replenishment, and not yet arrived and with the link congested. Based on the state segmentation data, logistics objects, truly arrived states, occupying and awaiting replenishment states, and blocked and awaiting release states are associated, and the original delivered states generated by production logistics are replaced to obtain penetrating state data. This avoids subsequent processes from misjudging material sufficiency due to false delivered states.

[0137] Specifically, based on demand acceptance value and congestion pressure value, logistics objects in the delivered state are extracted, and the degree of deviation between the process acceptance capacity and the link blockage intensity of the logistics objects is identified to obtain state verification data, which specifically includes:

[0138] The system extracts logistics objects currently marked as "delivered" from the production logistics status database. "Delivered" refers to a logistics object that has generated warehousing outbound records, delivery completion records, transit completion records, or system delivery task completion records, and is recognized by the production logistics system as having completed delivery. Based on the logistics object identifier, process batch identifier, target workstation identifier, and subsequent process node identifier, the system matches and associates the delivered logistics objects with demand acceptance values ​​and backlog pressure values.

[0139] The system extracts the demand acceptance value and the retention pressure value for each logistics object. The demand acceptance value characterizes the logistics object's ability to be effectively accepted by subsequent processes after arriving at the target workstation, while the retention pressure value characterizes the degree of blockage formed by the logistics object in the continuous supply chain during its flow between nodes. To eliminate the impact of differences in data dimensions across different batches, processes, and analysis periods, the system first standardizes the demand acceptance value and retention pressure value and converts them to a unified analysis interval. The system calculates the degree of difference between the demand acceptance value and the retention pressure value, using the difference as the baseline quantity for state deviation, and combines their ratio to form a state deviation index. When the demand acceptance value is significantly higher than the retention pressure value, it indicates that although the logistics object is suspended, its acceptance value after entering the target workstation is still high; when the retention pressure value is significantly higher than the demand acceptance value, it indicates that the logistics object is affected by strong chain blockage, and its actual usable value has decreased.

[0140] The system verifies the current node progress of logistics objects by extracting node entry records, node departure records, suspended section status, and workstation acceptance status for the corresponding logistics objects, and analyzes the actual progress of the logistics objects in the process route. When the demand acceptance value is high but the logistics object has not yet formed a target workstation entry record, the system judges that the logistics object has a state deviation where the business demand still exists but the physical location has not yet been reached. When the delay pressure value is high and the logistics object remains in the suspended section, the system judges that the logistics object has a state deviation where the delivery status is inconsistent with the actual availability status. The system associates and stores the logistics object identifier, demand acceptance value, delay pressure value, state deviation index, node progress status, and workstation acceptance status to form state verification data.

[0141] Specifically, based on the status verification data, the process acceptance capacity and link blockage strength are cross-identified to identify the actual acceptance status of the logistics object in the target workstation, thus obtaining status mapping data, which includes:

[0142] The system performs cross-analysis of demand acceptance value and congestion pressure value, using demand acceptance value as an indicator of process capacity and congestion pressure value as an indicator of link blockage intensity, and constructs a two-dimensional state recognition model of capacity and blockage intensity. Based on the demand acceptance value and congestion pressure value in the state verification data, the system locates the state interval of each logistics object, determining its position in the capacity dimension and its position in the blockage intensity dimension, and generating corresponding state coordinates. When the demand acceptance value is in a high range and the congestion pressure value is in a low range, the system determines that the logistics object has a strong process acceptance capacity and is not significantly affected by link blockage. When both the demand acceptance value and the congestion pressure value are in a high range, the system determines that although the logistics object has a high process demand, it has been significantly affected by link blockage. When both the demand acceptance value and the congestion pressure value are in a low range, the system determines that the logistics object not only has a reduced acceptance capacity but also suffers from severe logistics blockage. When both the demand acceptance value and the congestion pressure value are in a low range, it indicates that the actual acceptance value of the logistics object in the target workstation is already low.

[0143] The system performs cross-validation by combining node entry records in the node advancement sequence. This allows the system to extract information such as whether the logistics object has entered the target workstation, whether a subsequent process node entry record has been generated, and whether it is still in a suspended section. This information is then combined with the two-dimensional state recognition results for joint judgment. This ensures that process acceptance capacity and link congestion intensity not only reflect the business value of the logistics object but also its actual location status. Based on the cross-analysis results, the system establishes a state mapping relationship and maps the logistics object to the corresponding actual acceptance state area. The state mapping relationship includes the logistics object identifier, acceptance capacity level, congestion intensity level, node entry status, and corresponding state category, forming state mapping data.

[0144] Based on the state mapping data, logistics objects with node entry records and process acceptance capacity higher than the link blockage strength are identified as being in a true arrival state; logistics objects without node entry records and process acceptance capacity higher than the link blockage strength are identified as being in a placeholder state; and logistics objects without node entry records and link blockage strength higher than the process acceptance capacity are identified as being in a blockage state. This results in state decomposition data, specifically including:

[0145] The system first extracts the node entry status, demand acceptance value, and congestion pressure value corresponding to the logistics object, and classifies and judges them according to preset status splitting rules. The system determines whether the logistics object has formed a valid node entry record for the target workstation or subsequent process node. When the system detects that the logistics object already has a target workstation entry record, it further compares the demand acceptance value and the congestion pressure value. If the demand acceptance value is greater than the congestion pressure value, it means that the logistics object has actually entered the target workstation, and its process acceptance capacity is higher than the impact of link blockage. The logistics object can be effectively received and used by the current process, so the system determines it as a truly arrived state. When the system detects that the logistics object has not yet formed a target workstation entry record, it further analyzes the relationship between the demand acceptance value and the congestion pressure value. If the demand acceptance value is still higher than the congestion pressure value, it means that the target workstation still has an actual demand for the logistics object. Although the logistics object has not yet entered the target workstation, the corresponding process acceptance position has not been completely replaced by other objects, so the system determines it as a placeholder waiting to be filled. This state indicates that the logistics object should still enter the target workstation as a subsequent replacement object, and its corresponding process acceptance demand is still retained. If the system detects that a logistics object has not yet entered its target workstation and its congestion pressure value is higher than its demand acceptance value, it indicates that the logistics object has not only failed to enter its target workstation, but its logistics link has also experienced significant congestion, and the acceptance value of its corresponding process has been significantly weakened. In this case, the system classifies it as a blocked-out-of-flow-time state. This state means that the logistics object needs to have its link congestion cleared first and then re-participate in the subsequent scheduling process.

[0146] The system performs the aforementioned state decomposition process on all delivered logistics objects, generating sets of actual arrival status, occupied and pending replenishment status, and blocked and pending release status. The system associates and stores the logistics object identifier, original delivered status, new status type, demand acceptance value, delay pressure value, node entry status, status determination time, and target workstation information to form state decomposition data. This state decomposition data enables the accurate representation of the true business status of the logistics objects.

[0147] In a preferred embodiment of the present invention, based on the penetration status data, a dynamic replacement chain is generated for the logistics objects in the blocked and pending release state according to the target workstation gap sequence, the transit area aggregation sequence, and the preceding node release sequence. The material entry sequence, workstation waiting sequence, and transit release sequence of the production logistics are adjusted to obtain scheduling execution data, including:

[0148] Based on the penetration status data, extract the logistics objects that are in the blocked and waiting-to-be-released state, and obtain their target workstation, transit area and preceding node to obtain the data of the objects to be released;

[0149] Based on the data of objects to be released, the number of logistics objects in the occupied and replenished state and the number of logistics objects in the actual arrival state of each target workstation are counted, the degree of acceptance gap of each target workstation is identified, and gap correlation data is obtained.

[0150] Based on the gap association data, the degree of gap acceptance of the target workstation of the object to be released, the degree of object aggregation in the transfer area, and the degree of object release of the preceding node are associated and matched to determine the order of filling the gap of the object to be released and obtain the filling sorting data.

[0151] Based on the filler sorting data, objects to be released that have continuous filler relationships are linked together into a dynamic filler chain;

[0152] Based on the replacement chain, adjust the material entry order of the blocked logistics objects to be released, and adjust the waiting order of the target workstation and the transfer release order of the preceding nodes to obtain the scheduling execution data.

[0153] In this embodiment of the invention, based on the penetration status data, logistics objects in a blocked and pending release state are extracted, and their target workstations, transit areas, and preceding nodes are obtained to obtain the data of objects to be released. This allows subsequent scheduling to no longer indiscriminately process all delivered objects, but to precisely process objects that truly need to be released and filled. Based on the data of objects to be released, the number of logistics objects in a occupied and pending state and the number of logistics objects in a truly arrived state at each target workstation are counted to identify the degree of gap in each target workstation and obtain gap correlation data. This accurately identifies the material gap priority of different target workstations, avoiding simple scheduling based on material outbound time or scanning time. Based on the gap correlation data, the degree of gap in the target workstation of the object to be released, the object aggregation degree in the transit area, and the preceding nodes are considered. The release status of objects at nodes is correlated and matched to determine the order of replacement of objects to be released, resulting in replacement sorting data. This ensures that the replacement order considers both downstream workstation demand and congestion in intermediate areas as well as upstream release capacity. Based on the replacement sorting data, objects to be released with continuous replacement relationships are linked together into a dynamic replacement chain, enabling the system to perform replacement scheduling in a chain-like manner, rather than processing objects one by one in isolation. Based on the replacement chain, the material entry order of logistics objects in the blocked and waiting-to-release state is adjusted, as well as the workstation waiting order of the target workstation and the transit release order of the preceding nodes, to obtain scheduling execution data. Dynamically adjusting the material entry order, workstation waiting order, and transit release order can reduce material shortage waiting at the target workstation, reduce backlog in the transit area, and improve the collaborative scheduling efficiency of the entire production logistics chain.

[0154] Specifically, based on the data of objects to be released, the number of logistics objects in the "occupied but waiting" state and the number of logistics objects in the "actually in place" state at each target workstation are counted, the degree of the gap in the acceptance of each target workstation is identified, and gap correlation data is obtained, including:

[0155] The system categorizes and aggregates all objects to be released according to the target workstation identifier and establishes a mapping relationship between target workstations and objects to be released. The system reads the penetration status data and extracts the actual in-situ logistics objects and the occupied-but-to-be-replenished logistics objects corresponding to each target workstation. For each target workstation, the system counts the number of logistics objects already in the actual in-situ state and the number of logistics objects in the occupied-but-be-replenished state to obtain the planned quantity required for the production task corresponding to the current target workstation. Based on the production task demand of the target workstation, the system performs a demand satisfaction analysis on the number of actually in-situ logistics objects, comparing the number of actually in-situ logistics objects with the planned quantity to identify the actual capacity already met by the current target workstation. Simultaneously, the system counts the number of occupied-but-be-replenished logistics objects as potential capacity to identify unfinished but still existing process requirements at the target workstation. The system establishes a workstation gap analysis model based on the planned quantity, the number of actually in-situ logistics objects, and the number of occupied-but-be-replenished logistics objects. For target workstations where the actual number of workers arriving is insufficient and the number of vacant positions awaiting replenishment is large, the system determines that the degree of gap is high; for target workstations where the actual number of workers arriving is close to the planned number of workers to be accommodated, the system determines that the degree of gap is low. The system associates and stores the target workstation identifier, planned number of workers to be accommodated, actual number of workers arriving, number of vacant positions awaiting replenishment, and degree of gap, forming gap-related data.

[0156] Specifically, based on gap correlation data, the degree of gap acceptance at the target workstation of the object to be released, the degree of object clustering in the transfer area, and the degree of object release at the preceding node are correlated and matched to determine the order of filling the gaps for the objects to be released, thus obtaining the filling ranking data, which specifically includes:

[0157] The system extracts the target workstation capacity gap for each object to be released. Taking the current transit area of ​​the object to be released as the analysis object, it counts the number of logistics objects in a blocked state awaiting release, the cumulative waiting time, and the proportion of regional buffer capacity occupied within that transit area. Based on the statistical results, it determines the object clustering degree of the transit area. The system reads the preceding node information corresponding to the object to be released and counts the number of logistics objects currently waiting to be released at that preceding node, the queue length of the preceding node, and the average release cycle of the preceding node. Based on the above data, the system calculates the object release degree of the preceding node, which reflects the release pressure of the preceding node and the subsequent release demand. The system standardizes the target workstation capacity gap, the transit area object clustering degree, and the preceding node object release degree, respectively, so that data from different dimensions can be compared under a unified evaluation system. Then, the system establishes a fill-in priority evaluation model to integrate and analyze the above three dimensions. The target workstation capacity gap reflects the urgency of downstream demand, the transit area object clustering degree reflects the congestion of intermediate links, and the preceding node object release degree reflects the upstream release pressure. The system generates a corresponding replacement priority value for each object to be released and sorts them from high to low priority. When the target workstation gap is large, the transit area has a high degree of clustering, and the release pressure of the preceding node is high, the replacement priority of the corresponding object to be released is increased; conversely, its replacement priority is decreased. The system associates the object to be released identifier, target workstation identifier, priority value, sorting position, and corresponding evaluation factors to form replacement sorting data.

[0158] Specifically, based on the padding sorting data, objects to be released that have continuous padding relationships are chained together into a dynamic padding chain, which includes:

[0159] The system arranges all objects to be released according to their priority, and uses the sorting result as the basis for constructing the replacement chain. It sequentially reads the target workstation, transfer area, process batch, and preceding node information of adjacent objects to be released, and analyzes whether they meet the continuous replacement conditions. When multiple objects to be released correspond to the same target workstation and can sequentially fill the continuous gaps in the same workstation, the system determines that they have a continuous workstation replacement relationship; when multiple objects to be released are located in the same transfer area and can be released to the target workstation through the same path, the system determines that they have a continuous area replacement relationship; when multiple objects to be released originate from the same preceding node and can continuously enter subsequent process nodes according to the release order, the system determines that they have a continuous release replacement relationship. The system connects the objects to be released that meet the continuous replacement conditions according to their replacement priority and establishes a sequential replacement reference relationship between objects. For example, the object with the highest priority is determined as the head object, and subsequent objects that meet the continuous replacement conditions are sequentially connected after the head object, forming a replacement chain structure with a continuous execution relationship. The system generates a link identifier for each replacement chain and records the order of objects within the chain, the target workstation, the area path, and the expected release order. When the target workstation gap, the status of the transit area, or the release status of the preceding node changes, the system recalculates the replacement priority and dynamically adjusts the order of objects within the chain to form a dynamic replacement chain.

[0160] Specifically, based on the replacement chain, the material entry order of the blocked logistics objects awaiting release is adjusted, and the waiting order of the target workstation and the transfer release order of the preceding nodes are adjusted to obtain scheduling execution data, which includes:

[0161] The system reads the object sequence information in the replenishment chain and uses this sequence as the new material entry order. Based on the target workstation gap status recorded in the replenishment chain, the system adjusts the waiting queues for target workstations. For replenishment objects at workstations with high gaps, the system increases their waiting priority, allowing them to enter the workstation waiting queue first. For workstations where the gap has eased or demand has decreased, the waiting priority of the corresponding replenishment objects is reduced. The system adjusts the transit area release plan according to the area release order in the replenishment chain. For objects located in high-concentration areas with high priority, the system generates area release instructions first, allowing them to leave the transit area first. For objects with lower priority, the release time is delayed to avoid creating new area congestion. The system adjusts the release order of preceding nodes according to the release relationship of preceding nodes in the replenishment chain. It generates preceding node release instructions according to the replenishment chain order and controls the corresponding logistics objects to leave the preceding nodes sequentially and enter the subsequent logistics chain, ensuring that downstream workstations can obtain the required materials according to the gap priority. The system integrates the adjusted material entry order, workstation waiting order, transit area release order, and preceding node release order into unified scheduling execution data. The scheduling execution data includes at least the logistics object identifier, dynamic replacement chain identifier, target workstation identifier, entry order, transit release order, preceding node release order, execution priority, and schedule generation time. The system sends the scheduling execution data to the logistics execution system, MES system, or scheduling control system to drive actual logistics release, material distribution, and workstation replacement execution, achieving orderly release and dynamic replacement of blocked, pending-release logistics objects towards actual workstation demand.

[0162] Embodiments of the present invention also provide an AI-enabled intelligent system for the entire production logistics chain based on electronic tags, the system comprising:

[0163] The sequence module is used to acquire the label flow data and process task data of logistics objects, and extract node entry records, node departure records and process succession relationships to construct a node advancement sequence;

[0164] The suspension module is used to extract the node segments of logistics objects that have left the preceding node but have not generated an entry record in the corresponding node of the subsequent process, based on the node advancement sequence, and obtain the suspension association data.

[0165] The retention and compression module is used to identify the blockage intensity of the suspension section on the continuous feeding link based on the suspension correlation data, and obtain the retention and compression value.

[0166] The diffusion module is used to establish accompanying reference relationships for logistics objects that are in the same transit area, time interval and process batch as the suspended section based on the suspended association data, identify abnormal replacement objects, and obtain accompanying diffusion data.

[0167] The demand acceptance module is used to identify the process acceptance capacity of logistics objects in the suspended section after they enter the target workstation based on the accompanying diffusion data, and to obtain the demand acceptance value.

[0168] The status module is used to break down the delivered status generated by the original production logistics based on the demand acceptance value and the stagnation pressure value, identify the actual delivery status, the occupied waiting status, and the blocked waiting release status, and obtain the penetrating status data.

[0169] The scheduling module is used to generate a dynamic replacement chain based on the penetration status data, which divides the logistics objects in the blocked and waiting-to-be-released state into target workstation gap order, transit area aggregation order and preceding node release order, and adjusts the material entry order, workstation waiting order and transit release order of production logistics to obtain scheduling execution data.

[0170] It should be noted that this system is a system corresponding to the above method. All implementation methods in the above method embodiments are applicable to this embodiment and can achieve the same technical effect.

[0171] Embodiments of the present invention also provide a computing device, including: a processor and a memory storing a computer program, wherein the computer program, when executed by the processor, performs the method described above. All implementations in the above method embodiments are applicable to this embodiment and can achieve the same technical effects.

[0172] Embodiments of the present invention also provide a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the method described above. All implementations in the above method embodiments are applicable to this embodiment and can achieve the same technical effects.

[0173] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for AI-powered intelligent empowerment of the entire production logistics chain based on electronic tags, characterized in that: The method includes: Obtain the label flow data and process task data of logistics objects, and extract node entry records, node departure records and process succession relationships to construct a node advancement sequence; Based on the node progression sequence, the node segments in which the logistics object has completed its departure from the preceding node and has not generated an entry record in the corresponding node of the subsequent process are extracted as suspended segments to obtain suspended associated data. Based on the suspension correlation data, the blocking intensity of the suspension section on the continuous feeding link is identified, and the retention pressure value is obtained. Based on the suspension association data, establish accompanying reference relationships with logistics objects that are in the same transit area, time interval and process batch as the suspension section, identify abnormal replacement objects, and obtain accompanying diffusion data; Based on the accompanying diffusion data, the process acceptance capacity of logistics objects in the suspended section after entering the target workstation is identified, and the demand acceptance value is obtained. Based on the demand acceptance value and the stagnation pressure value, the original production logistics generated the delivered status, and the real arrival status, the occupied waiting status, and the blocked waiting release status are identified to obtain the penetrating status data. Based on the penetration status data, the logistics objects in the blocked and waiting-to-be-released state are generated into a dynamic replacement chain according to the target workstation gap order, the transit area aggregation order, and the previous node release order. The material entry order, workstation waiting order, and transit release order of the production logistics are adjusted to obtain scheduling execution data.

2. The AI-powered intelligent empowerment method for the entire production logistics chain based on electronic tags as described in claim 1, characterized in that, Based on the node progression sequence, node segments where a logistics object leaves a preceding node but does not generate an entry record in a subsequent process node are extracted as suspended segments, yielding suspended associated data, including: Based on the node advancement sequence, extract the node departure record of the extraction flow object and the process succession relationship corresponding to the node departure record to obtain the succession relationship data; Based on the acceptance relationship data, determine the node corresponding to the subsequent process of the node departure record, and obtain the node entry record of the logistics object in the corresponding node of the subsequent process to obtain the node verification data. Based on the node verification data, the node segments with records of node departures but no corresponding records of node entry are identified as suspended segments, thus obtaining suspended segment data; Based on the suspended section data, the logistics objects, nodes corresponding to node departure records, nodes corresponding to subsequent processes, and related processes of the suspended section are associated to obtain suspended associated data.

3. The AI-powered intelligent empowerment method for the entire production logistics chain based on electronic tags as described in claim 2, characterized in that, Based on the suspension correlation data, the blockage intensity of the suspension section on the continuous feeding link is identified, and the retention pressure value is obtained, including: Based on the suspension association data, extract the suspension duration of the current suspension segment and the transfer duration that has been completed between the same preceding node and the subsequent process node, identify the degree of deviation of the current logistics object from the normal acceptance state, and obtain the duration deviation item. Count the number of logistics objects in the suspended section between the same preceding node and the subsequent process node, and the number of logistics objects that have been completed and accepted, identify the backlog in the current acceptance relationship, and obtain the backlog items. The number of logistics objects in the current suspended section and the total number of logistics objects participating in the node advancement sequence are counted to identify the degree of suspension impact on the current associated process and obtain the process impact item; Extract the dwell time of the current logistics object in the preceding node, identify the degree of transformation of the logistics object from the internal flow state of the node to the inter-node stagnation state, and obtain the state transformation item; By integrating the duration deviation, backlog, process impact, and state transition items, the blockage intensity of the suspended section on the continuous material supply chain is identified, and the retention pressure value is obtained.

4. The AI-powered intelligent empowerment method for the entire production logistics chain based on electronic tags according to claim 3, characterized in that, Based on the suspension association data, a companion reference relationship is established with logistics objects that are in the same transit area, time interval, and process batch as the suspension segment. Abnormal replacement objects are identified, and companion diffusion data is obtained, including: Based on the suspension association data, the transit area, time interval and process batch of the suspension section are extracted, and logistics objects with the same transit area, time interval and process batch are filtered to obtain the accompanying object data; Based on the accompanying object data, the node advancement sequence of each logistics object is extracted, and the advancement position of each logistics object in the node advancement sequence is identified to obtain advancement position data; Based on the advancement position data, the advancement position of the logistics object in the suspended section is compared with the advancement position of the accompanying object. The accompanying object that has entered the subsequent process node and whose advancement position is ahead of the logistics object in the suspended section is identified, and the advancement difference data is obtained. Based on the advance difference data, the accompanying objects with advanced advance positions are associated with the logistics objects in the suspension section, the process occupancy relationship is identified and the abnormal replacement objects are determined, and the accompanying diffusion data is obtained.

5. The AI-powered intelligent empowerment method for the entire production logistics chain based on electronic tags according to claim 4, characterized in that, Based on the accompanying diffusion data, the process acceptance capacity of logistics objects within the suspended section after entering the target workstation is identified, and the demand acceptance value is obtained, including: Based on the accompanying diffusion data, the number of abnormal replacement objects and the number of logistics objects in the suspended section are counted, the degree to which the logistics objects in the suspended section are replaced and taken over is identified, and the replacement occupancy items are obtained. Extract the advancement positions of abnormal replacement objects and logistics objects within the suspended section, identify the degree of compensation of logistics objects within the suspended section for the current advancement gap, and obtain the advancement compensation item; Count the number of accompanying objects that have entered subsequent process nodes in the same process batch and the total number of accompanying objects, identify the degree of completeness of the same process batch in subsequent processes, and obtain the batch inheritance items; The number of process acceptance positions already occupied by abnormal replacement objects and the number of unoccupied process acceptance positions that can still be corresponding to logistics objects in the suspended section are counted. The retention ratio of unoccupied process acceptance positions relative to occupied process acceptance positions is calculated to obtain the vacancy retention items. By integrating the replacement occupancy item, the advancement compensation item, the batch acceptance item, and the vacancy retention item, the process acceptance capacity of the logistics object in the suspended section after entering the target workstation is identified, and the demand acceptance value is obtained.

6. The AI-powered intelligent empowerment method for the entire production logistics chain based on electronic tags according to claim 5, characterized in that, Based on demand acceptance and congestion pressure values, the original production logistics generated delivery status is broken down to identify the actual delivery status, the occupied and pending replenishment status, and the blocked and pending release status, resulting in penetrating status data, including: Based on the demand acceptance value and the retention pressure value, the logistics objects in the delivered status are extracted, and the degree of deviation between the process acceptance capacity and the link blockage intensity of the logistics objects is identified to obtain status verification data. Based on the status verification data, cross-identification is performed on the process acceptance capacity and link blockage intensity to identify the actual acceptance status of the logistics object in the target workstation and obtain status mapping data. Based on the state mapping data, logistics objects with node entry records and process acceptance capacity higher than the link blockage strength are identified as truly in place; logistics objects without node entry records and process acceptance capacity higher than the link blockage strength are identified as occupied and waiting to be filled; and logistics objects without node entry records and link blockage strength higher than the process acceptance capacity are identified as blocked and waiting to be released, thus obtaining state splitting data. Based on the state-segmented data, the logistics object, actual arrival status, occupied and pending replenishment status, and blocked and pending release status are associated, and the original delivered status generated by the production logistics is replaced to obtain penetrating state data.

7. The AI-powered intelligent empowerment method for the entire production logistics chain based on electronic tags according to claim 6, characterized in that, Based on the penetration status data, a dynamic replacement chain is generated for the logistics objects in the blocked and pending release state according to the target workstation gap order, the transit area aggregation order, and the preceding node release order. The material entry order, workstation waiting order, and transit release order of the production logistics are then adjusted to obtain scheduling execution data, including: Based on the penetration status data, extract the logistics objects that are in the blocked and waiting-to-be-released state, and obtain their target workstation, transit area and preceding node to obtain the data of the objects to be released; Based on the data of objects to be released, the number of logistics objects in the occupied and replenished state and the number of logistics objects in the actual arrival state of each target workstation are counted, the degree of acceptance gap of each target workstation is identified, and gap correlation data is obtained. Based on the gap association data, the degree of gap acceptance of the target workstation of the object to be released, the degree of object aggregation in the transfer area, and the degree of object release of the preceding node are associated and matched to determine the order of filling the gap of the object to be released and obtain the filling sorting data. Based on the filler sorting data, objects to be released that have continuous filler relationships are linked together into a dynamic filler chain; Based on the replacement chain, adjust the material entry order of the blocked logistics objects to be released, and adjust the waiting order of the target workstation and the transfer release order of the preceding nodes to obtain the scheduling execution data.

8. A production logistics end-to-end AI intelligent empowerment system based on electronic tags, characterized in that: The system is used to perform the method as described in any one of claims 1 to 7, the system comprising: The sequence module is used to acquire the label flow data and process task data of logistics objects, and extract node entry records, node departure records and process succession relationships to construct a node advancement sequence; The suspension module is used to extract the node segments of logistics objects that have left the preceding node but have not generated an entry record in the corresponding node of the subsequent process, based on the node advancement sequence, and obtain the suspension association data. The retention and compression module is used to identify the blockage intensity of the suspension section on the continuous feeding link based on the suspension correlation data, and obtain the retention and compression value. The diffusion module is used to establish accompanying reference relationships for logistics objects that are in the same transit area, time interval and process batch as the suspended section based on the suspended association data, identify abnormal replacement objects, and obtain accompanying diffusion data. The demand acceptance module is used to identify the process acceptance capacity of logistics objects in the suspended section after they enter the target workstation based on the accompanying diffusion data, and to obtain the demand acceptance value. The status module is used to break down the delivered status generated by the original production logistics based on the demand acceptance value and the stagnation pressure value, identify the actual delivery status, the occupied waiting status, and the blocked waiting release status, and obtain the penetrating status data. The scheduling module is used to generate a dynamic replacement chain based on the penetration status data, which divides the logistics objects in the blocked and waiting-to-be-released state into target workstation gap order, transit area aggregation order and preceding node release order, and adjusts the material entry order, workstation waiting order and transit release order of production logistics to obtain scheduling execution data.

9. A computing device, characterized in that, include: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program that, when executed by a processor, implements the method as described in any one of claims 1 to 7.

Images