Production task collaborative scheduling optimization method and system for storage and transportation whole chain

Abstract

This invention relates to the field of storage and transportation management technology, and discloses a method and system for collaborative scheduling optimization of production tasks across the entire storage and transportation chain. The method includes: constructing a causal structure based on historical operation records and domain rules of the entire storage and transportation chain; injecting real-time operation data of the entire storage and transportation chain into the causal structure; analyzing the interdependence of performance coupling relationships to obtain a collaborative state baseline; conducting counterfactual strategy simulations on key coupling bottlenecks of the collaborative state baseline to obtain a causal effect graph; mapping scheduling parameters to the causal effect graph to obtain candidate scheduling strategies; evaluating the collaborative effectiveness of the candidate scheduling strategy set based on multi-objective optimization criteria of the entire storage and transportation chain to obtain a preferred collaborative scheduling strategy; matching the real-time operation status of the entire storage and transportation chain with the conditions of the preferred collaborative scheduling strategy; and encoding the matching result as a collaborative scheduling instruction. This invention can improve the efficiency of collaborative scheduling optimization of production tasks across the entire storage and transportation chain.

Description

Technical Field

[0001] This invention relates to the field of storage and transportation management technology, and in particular to a method and system for collaborative scheduling optimization of production tasks across the entire storage and transportation chain. Background Technology

[0002] The entire storage and transportation chain is a core component of the logistics industry system, encompassing multi-dimensional operational processes such as transportation, warehousing, loading and unloading, and distribution. Its operational efficiency and collaborative scheduling level directly determine the overall service capacity and operational benefits of the logistics system. With the acceleration of the digital and intelligent development of the logistics industry, the application of various data collection technologies and Internet of Things (IoT) sensing technologies in the storage and transportation field is becoming increasingly widespread. This enables the comprehensive retention of historical operational records for the entire storage and transportation chain, and the accurate collection of real-time operational data for all aspects, including vehicle movement, changes in warehouse inventory, loading and unloading operations, and delivery route execution.

[0003] Existing collaborative scheduling technologies for the entire storage and transportation chain lack systematic methods for correlation mining of the multi-dimensional characteristics of historical operational data and the constraints of domain rules. This makes it impossible to effectively construct a structured system that reflects the inherent logical connections between various operational elements throughout the chain, resulting in a lack of precise element correlation support for scheduling analysis. Furthermore, existing technologies lack quantitative interdependence analysis logic that combines real-time operational data to understand the interaction relationships between various performance dimensions in the entire storage and transportation chain. This makes it difficult to accurately grasp the coupling patterns of various performance elements from a holistic perspective of the entire chain, and fails to provide a benchmark basis that fits the actual operational status for the scientific formulation of scheduling strategies. Therefore, how to improve the efficiency of collaborative scheduling optimization of production tasks throughout the entire storage and transportation chain has become an urgent problem to be solved. Summary of the Invention

[0004] This invention provides a method and system for collaborative scheduling optimization of production tasks across the entire storage and transportation chain, in order to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides a collaborative scheduling optimization method for production tasks across the entire storage and transportation chain, comprising: S1. Construct the causal structure of the entire storage and transportation chain based on the historical operation records and domain rules of the entire chain; S2. Inject the real-time operation data of the entire storage and transportation chain into the causal structure, perform interdependence analysis on the performance coupling relationship of the entire storage and transportation chain, and obtain the collaborative state baseline of the entire storage and transportation chain; S3. Perform counterfactual strategy simulation on the key coupling bottlenecks in the collaborative state baseline to obtain the causal effect map of the entire storage and transportation chain; S4. Map scheduling parameters to the causal effect map to obtain candidate scheduling strategies for the entire storage and transportation chain; S5. Based on the multi-objective optimization criteria of the entire storage and transportation chain, evaluate the collaborative effectiveness of the candidate scheduling strategy set to obtain the preferred collaborative scheduling strategy for the entire storage and transportation chain. S6. Match the real-time operating status of the entire storage and transportation chain with the strategies in the preferred collaborative scheduling strategy, and encode the matching result as a collaborative scheduling instruction for the entire storage and transportation chain.

[0006] In a preferred embodiment, the process of constructing the causal structure of the entire storage and transportation chain is as follows: The key operational characteristics of the historical operation records of the entire storage and transportation chain are obtained by multi-dimensional extraction. Constraints are extracted from the domain rules involved in the entire storage and transportation chain to obtain the constraints of the entire storage and transportation chain. By performing dependency mining on the key operational characteristics and the constraints, the causal relationships of the entire storage and transportation chain can be obtained; The causal relationships are topologically reconstructed to obtain the causal structure of the entire storage and transportation chain.

[0007] In a preferred embodiment, the process of obtaining the baseline of the coordinated state of the entire storage and transportation chain is as follows: The real-time operation data of the entire storage and transportation chain is injected into the causal structure to obtain a real-time status instance of the entire storage and transportation chain. Based on the real-time status instance, the interaction impact between performance dimensions in the entire storage and transportation chain is evaluated to obtain the interaction strength of performance indicators in the entire storage and transportation chain. Based on the interaction strength of the performance indicators, the density of performance nodes in the real-time status instance is identified to obtain the performance association cluster of the entire storage and transportation chain; The performance association clusters and the causal paths corresponding to the performance association clusters are topologically fused to obtain the panoramic coupling structure of the entire storage and transportation chain; The steady-state baseline of the operating state characterized by the panoramic coupling structure is condensed to obtain the collaborative state baseline of the entire storage and transportation chain.

[0008] In a preferred embodiment, the process of obtaining the causal effect map of the entire storage and transportation chain is as follows: Bottleneck identification is performed on the cooperative state baseline to obtain the key constraint nodes of the cooperative state baseline; Based on the key constraint nodes, hypothetical scheduling actions are derived for the entire storage and transportation chain to obtain a set of hypothetical scheduling operations for the entire storage and transportation chain. Using the collaborative state baseline as the fact benchmark, counterfactual scenario deduction is performed on the hypothetical scheduling operation set to obtain the simulated state trajectory of the entire storage and transportation chain; The intensity of the operational causal impact of the entire storage and transportation chain is obtained by measuring the difference between the simulated state trajectory and the cooperative state baseline. A knowledge structure is constructed to assess the causal impact strength of the aforementioned operations, thereby obtaining a causal effect map of the entire storage and transportation chain.

[0009] In a preferred embodiment, the process of obtaining the hypothetical scheduling operation set for the entire storage and transportation chain is as follows: Attribute analysis is performed on the key constraint nodes to obtain attribute descriptions of the key constraint nodes; Based on the attribute description, the scheduling action prototypes in the preset scheduling knowledge base are called according to the adaptation rules to obtain the scheduling action template of the key constraint node. The scheduling action template is extended with parameters to obtain the candidate operation sequence for the entire storage and transportation chain; Based on the environmental and resource constraints of the entire storage and transportation chain, the candidate operation sequences are screened for compliance to obtain a hypothetical scheduling operation set for the entire storage and transportation chain.

[0010] In a preferred embodiment, the process of obtaining the simulated state trajectory of the entire storage and transportation chain is as follows: The collaborative state baseline is set as the projection benchmark state for the entire storage and transportation chain; Based on the aforementioned baseline state, counterfactual effects are injected into the operations in the hypothetical scheduling operation set to obtain the single-step disturbance state of the entire storage and transportation chain. Using the causal structure of the entire storage and transportation chain as the transmission path, the initial impact represented by the single-step disturbance state is transmitted and deduced to obtain the state evolution sequence of the entire storage and transportation chain; The state evolution sequence is encapsulated with trajectory features to obtain the simulated state trajectory of the entire storage and transportation chain.

[0011] In a preferred embodiment, the process of obtaining candidate scheduling strategies for the entire storage and transportation chain is as follows: The coupling relationships of the causal effect map are deeply deconstructed to obtain the key performance elements of the causal effect map. Based on the aforementioned key performance elements, the control parameters of the entire storage and transportation chain are obtained by traversing the historical operation records and current process rules of the entire storage and transportation chain. By strategically associating the key performance elements with the control parameters, the parameter mapping relationship of the entire storage and transportation chain is obtained; Based on the parameter mapping relationship, the real-time operation status of the entire storage and transportation chain is integrated with the preset scheduling target to obtain the control parameter configuration scheme of the entire storage and transportation chain; The control parameter configuration scheme is structured and encapsulated to obtain the candidate scheduling strategy for the entire storage and transportation chain.

[0012] In a preferred embodiment, the process of obtaining the preferred collaborative scheduling strategy for the entire storage and transportation chain is as follows: The multi-objective optimization criteria for the entire storage and transportation chain are quantitatively analyzed to obtain the evaluation dimensions of the multi-objective optimization criteria; Based on the evaluation dimensions, the candidate scheduling strategy set is deconstructed for collaborative effectiveness to obtain the strategy effectiveness of the candidate scheduling strategy set; Based on the effectiveness of the strategy, a comprehensive comparison of the merits of the candidate scheduling strategy set is performed to obtain the strategy priority sequence for the entire storage and transportation chain. The optimal strategy is selected from the priority sequence of the strategies to obtain the preferred collaborative scheduling strategy for the entire storage and transportation chain.

[0013] In a preferred embodiment, the real-time operating status of the entire storage and transportation chain is conditionally matched with the strategies in the preferred collaborative scheduling strategy, and the matching result is encoded into a collaborative scheduling instruction for the entire storage and transportation chain, including: The key indicators of the real-time operation status of the entire storage and transportation chain are analyzed to obtain the operation characteristics of the real-time operation status; Based on the aforementioned operational characteristics, the strategy triggering conditions in the preferred collaborative scheduling strategy are subjected to adaptability screening to obtain the matching strategy for the entire storage and transportation chain. Based on the real-time resource constraints and work procedures, the adaptability of the matching strategy is verified to obtain the adapted scheduling strategy of the matching strategy. The adaptive scheduling strategy is encoded into a collaborative scheduling instruction for the entire storage and transportation chain.

[0014] To address the aforementioned problems, this invention also provides a collaborative scheduling and optimization system for production tasks across the entire storage and transportation chain, the system comprising: The causal structure construction module is used to construct the causal structure of the entire storage and transportation chain based on the historical operation records and domain rules of the entire chain. The coupling analysis baseline generation module is used to inject real-time operation data of the entire storage and transportation chain into the causal structure, perform interdependence analysis on the performance coupling relationship of the entire storage and transportation chain, and obtain the collaborative state baseline of the entire storage and transportation chain. The bottleneck simulation causal effect module is used to perform counterfactual strategy simulation on the key coupling bottlenecks in the collaborative state baseline to obtain the causal effect map of the entire storage and transportation chain. The parameter mapping strategy candidate module is used to perform scheduling parameter mapping on the causal effect spectrum to obtain candidate scheduling strategies for the entire storage and transportation chain; The efficiency evaluation strategy optimization module is used to evaluate the collaborative efficiency of the candidate scheduling strategy set based on the multi-objective optimization criteria of the entire storage and transportation chain, and obtain the optimal collaborative scheduling strategy for the entire storage and transportation chain. The status matching instruction encoding module is used to match the real-time operating status of the entire storage and transportation chain with the strategies in the preferred collaborative scheduling strategy, and encode the matching result into the collaborative scheduling instruction of the entire storage and transportation chain.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention achieves its goal by systematically mining the dependencies between historical operational features and domain rules. The method first extracts key operational features from historical data and extracts constraints from domain rules. Then, it conducts in-depth dependency mining on the two, analyzes the logic of their mutual influence and constraints, and finally integrates these scattered elements and relationships into a hierarchical and clearly related causal structure network through topological reconstruction. This solves the problem of isolated data and rules and lack of internal connection in the prior art, and provides scheduling analysis with accurate and reliable structured basis.

[0016] 2. This invention achieves its goal by injecting real-time data into a pre-constructed causal structure and performing dynamic interdependence analysis. The method involves matching and injecting real-time operational data to form real-time state instances, and then evaluating the interaction effects between various performance dimensions to quantify their strength. By identifying closely related performance nodes to form association clusters, and further topologically fusing them into a panoramic structure that shows the global coupling state, the method finally condenses the baseline of the collaborative state under steady state. This process, combined with real-time data, dynamically reveals the quantitative interdependence between performance elements, thereby providing a realistic, accurate, and reliable benchmark for the formulation of scheduling strategies. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating a production task collaborative scheduling optimization method for the entire storage and transportation chain provided in an embodiment of the present invention. Figure 2 This is a functional block diagram of a production task collaborative scheduling and optimization system for the entire storage and transportation chain provided in an embodiment of the present invention; The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0018] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0019] This application provides a method for collaborative scheduling and optimization of production tasks across the entire storage and transportation chain. The executing entity of this method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the method can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0020] Reference Figure 1 As shown, this is an embodiment of the production task collaborative scheduling optimization method for the entire storage and transportation chain provided by the present invention. In this embodiment, the production task collaborative scheduling optimization method for the entire storage and transportation chain includes: S1, constructing the causal structure of the entire storage and transportation chain based on the historical operation records and domain rules of the entire storage and transportation chain; In this embodiment of the invention, the process of constructing the causal structure of the entire storage and transportation chain is as follows: The key operational characteristics of the historical operation records of the entire storage and transportation chain are obtained by multi-dimensional extraction. Constraints are extracted from the domain rules involved in the entire storage and transportation chain to obtain the constraints of the entire storage and transportation chain. By performing dependency mining on the key operational characteristics and the constraints, the causal relationships of the entire storage and transportation chain can be obtained; The causal relationships are topologically reconstructed to obtain the causal structure of the entire storage and transportation chain.

[0021] Multi-dimensional extraction was performed on the historical operation records of the entire storage and transportation chain to obtain key operational characteristics. These historical operation records refer to complete records generated during all past operations, including transportation, storage, loading / unloading, and distribution. They encompass various information such as vehicle travel time, stops, cargo weight and type, warehouse inventory changes, cargo inbound and outbound times, loading / unloading times, and delivery routes and completion times. The multi-dimensional extraction was conducted according to four fixed dimensions: time, operational stages, resource consumption, and performance. The time dimension selected daily operational data within a continuous period, while the operational stage dimension comprehensively covered each sub-stage of transportation, warehousing, loading / unloading, and distribution. Operational records are available. The resource consumption dimension focuses on the amount of manpower input, the utilization of transportation vehicle capacity, and warehouse space occupancy data. The performance dimension revolves around data related to operation completion efficiency, operation cost expenditure, and cargo integrity rate. For the specific data under each dimension, data cleaning is performed first to remove obviously abnormal data. The standard for judging abnormal data is that the data exceeds the average value of all data under the corresponding dimension by a certain percentage or more. Then, the frequency of occurrence and influence weight of each data item under the corresponding dimension are counted. Data items with a high frequency of occurrence and a high influence weight are selected. These selected data items, which can directly reflect the core operating status of the entire storage and transportation chain in the past, together constitute the key operational characteristics of the historical operation record.

[0022] Constraints are extracted from the domain rules involved in the entire storage and transportation chain to obtain the constraints of the entire storage and transportation chain. Domain rules refer to various established requirements and standards that guide and regulate the operation of transportation, warehousing, loading and unloading, and distribution in the storage and transportation industry. These include relevant industry-issued specifications, internal enterprise operating systems, and safety operation guidelines. During constraint extraction, all domain rule texts related to the entire storage and transportation chain are first collected comprehensively. Then, professional personnel are organized to study these rules one by one to identify the content that is mandatory, restrictive, and directly affects the scheduling results. This content is then transformed into clear and specific executable requirements. All such transformed executable requirements together constitute the constraints of the entire storage and transportation chain.

[0023] Dependency mining is performed on the key operational features and constraints to obtain the causal relationships of the entire storage and transportation chain. Key operational features are data sets that reflect the core operational status of the entire storage and transportation chain in the past, while constraints are specific boundary requirements that limit the formulation and execution of scheduling strategies. Dependency mining involves systematically analyzing the mutual influence and constraints between these two. For each key operational feature, all constraints are matched one by one to determine whether the key operational feature is restricted by the constraints and whether changes in the constraints will cause changes in the key operational feature. At the same time, it is analyzed whether changes in the key operational feature will affect the enforcement of the constraints. Following the above method, all key operational features and constraints are matched and analyzed one by one to identify all existing interaction relationships. These relationships together constitute the causal relationships of the entire storage and transportation chain.

[0024] The causal relationships are topologically reconstructed to obtain the causal structure of the entire storage and transportation chain. Topological reconstruction refers to constructing a clear and orderly structured framework according to the interaction logic of each element in the causal relationship. First, each key operational feature and each constraint is treated as an independent node, and the name of the node is directly adopted from the specific description of the key operational feature or constraint. Then, according to the interaction direction determined in the causal relationship, the nodes with dependencies are connected by lines, and the direction of the lines represents the direction of influence. At the same time, the nodes are arranged according to the closeness of the influence between them. Nodes with an influence degree that reaches a set standard are placed in adjacent positions, and finally, a hierarchical and clearly related network structure is formed. This network structure is the causal structure of the entire storage and transportation chain.

[0025] The beneficial effects include ensuring comprehensive and accurate key operational characteristics, providing a high-quality and targeted data foundation for causal structure construction, improving the accuracy of causal structure construction, clearly defining the boundary requirements of scheduling operations, avoiding violations or infeasible situations, improving the compliance and feasibility of scheduling strategies, sorting out the dependency logic of key operational characteristics and constraints, clarifying the correlation relationships, providing a reliable basis for topology reconstruction, enhancing the logic and rationality of causal structures, forming an intuitive and orderly causal structure, facilitating the understanding of the overall correlation of operational elements, providing a clear analytical framework, and improving the efficiency of subsequent data processing and analysis.

[0026] S2. Inject the real-time operation data of the entire storage and transportation chain into the causal structure, perform interdependence analysis on the performance coupling relationship of the entire storage and transportation chain, and obtain the collaborative state baseline of the entire storage and transportation chain; In this embodiment of the invention, the process of obtaining the baseline of the coordinated state of the entire storage and transportation chain is as follows: The real-time operation data of the entire storage and transportation chain is injected into the causal structure to obtain a real-time status instance of the entire storage and transportation chain. Based on the real-time status instance, the interaction impact between performance dimensions in the entire storage and transportation chain is evaluated to obtain the interaction strength of performance indicators in the entire storage and transportation chain. Based on the interaction strength of the performance indicators, the density of performance nodes in the real-time status instance is identified to obtain the performance association cluster of the entire storage and transportation chain; The performance association clusters and the causal paths corresponding to the performance association clusters are topologically fused to obtain the panoramic coupling structure of the entire storage and transportation chain; The steady-state baseline of the operating state characterized by the panoramic coupling structure is condensed to obtain the collaborative state baseline of the entire storage and transportation chain.

[0027] The real-time operational data of the entire storage and transportation chain is injected into the causal structure to obtain a real-time state instance of the entire storage and transportation chain. The causal structure is a topological structure that includes key operational features and constraint dependencies, previously constructed based on the historical operation records and domain rules of the entire storage and transportation chain. The real-time operational data covers the instantaneous data of each link in the storage and transportation chain, such as transportation, warehousing, loading and unloading, and distribution. Specifically, it includes the real-time location and loading capacity of transport vehicles, the real-time inventory of warehouses, the real-time progress of loading and unloading operations, the real-time operating parameters of equipment, the real-time flow of materials, and the environmental parameters on site. According to the correspondence of each node in the causal structure, these real-time data are matched and injected into the corresponding positions of the causal structure one by one, so that each node in the causal structure has the support of the actual operation data at the current moment. The final real-time state instance is the specific presentation of the causal structure at the current moment, including the specific values ​​and status information of each link, each piece of equipment, and each parameter in real-time operation, and fully reflects the current operation of the entire storage and transportation chain.

[0028] Based on the real-time status instance, the interaction impact assessment of the performance dimensions in the entire storage and transportation chain is conducted to obtain the interaction strength of the performance indicators of the entire storage and transportation chain. The performance dimensions are key aspects for measuring the operational effectiveness of the entire storage and transportation chain, including operational efficiency, operational costs, cargo integrity rate, resource utilization rate, etc. Relying on the real-time data of each performance dimension in the real-time status instance, the degree of influence of each performance dimension on all other performance dimensions is analyzed one by one. At the same time, the counter-effect of other performance dimensions on this dimension is analyzed. For example, whether the improvement of operational efficiency will lead to the change of operational costs, and whether the change of cargo integrity rate will affect resource utilization rate, etc. Through a comprehensive review and quantitative assessment of this interaction, the interaction strength of the performance indicators is finally obtained, which is a specific representation of the degree of mutual influence between the performance dimensions. The higher the value, the more significant the mutual influence.

[0029] Based on the interaction strength of the performance indicators, the density of performance nodes in the real-time state instance is identified to obtain the performance association clusters of the entire storage and transportation chain. The performance node is a specific data node in the real-time state instance corresponding to each performance dimension. Each node carries the real-time operation data of the corresponding performance dimension. According to the magnitude of the interaction strength of the performance indicators, a clear judgment standard is set. That is, if the interaction strength value is higher than a preset threshold, it is judged as high density. According to this standard, all performance nodes are screened and classified. Performance nodes with high interaction strength and close mutual influence are grouped together to form a performance association cluster. It is a set of performance nodes with significant interaction. The nodes within each association cluster are closely connected and jointly affect a specific operational efficiency of the entire storage and transportation chain.

[0030] The performance-related clusters and their corresponding causal paths are topologically fused to obtain a panoramic coupled structure for the entire storage and transportation chain. Topological fusion constructs a hierarchical and clearly structured framework based on the connection relationships of nodes within each performance-related cluster and the logical order of the causal paths corresponding to each cluster. First, the causal path corresponding to each performance-related cluster is clarified, that is, the transmission path of causal influence between nodes in the cluster. Then, the performance-related clusters are treated as whole nodes, and these whole nodes are connected and integrated according to the order and interrelationship of their corresponding causal paths, while retaining the connection relationships of nodes within each cluster. The resulting panoramic coupled structure is a global network structure that can fully display all performance nodes, related clusters, and their causal relationships and interactions in the entire storage and transportation chain, clearly presenting the coupling state between each link and dimension.

[0031] The steady-state baseline of the storage and transportation chain is obtained by refining the operating state represented by the panoramic coupling structure. The steady-state baseline involves long-term monitoring and data statistics of the operating state represented by the panoramic coupling structure, screening out the stable and efficient state data intervals, and analyzing the operating data of the panoramic coupling structure at different time periods to eliminate unstable data caused by sudden failures, abnormal interference, etc. The core data features and parameter ranges that can represent the normal and efficient operation of the entire storage and transportation chain are extracted. The resulting collaborative state baseline is the benchmark standard of the entire storage and transportation chain under stable operating conditions, providing a reference for subsequent bottleneck identification and strategy optimization.

[0032] The beneficial effects include: accurately matching real-time data with causal structures, making real-time state instances authentic and comprehensive, providing reliable data for subsequent analysis, improving analytical accuracy, quantifying the mutual influence of performance dimensions, clarifying the relationships between them, providing a basis for node clustering and coupling structure construction, deepening the understanding of operational rules, clustering dispersed performance nodes by density to form logically clear association clusters, simplifying the difficulty of analysis, focusing on core nodes, improving analytical efficiency, and forming a panoramic coupling structure through topological fusion, intuitively presenting the global coupling state, clarifying causal relationships and interactions, providing structured objects for steady-state benchmark condensation, and providing a clear and stable benchmark for collaborative state baselines, making subsequent bottleneck identification and strategy optimization systematic, helping the entire chain to operate stably and efficiently, and improving the level of collaborative management and control.

[0033] S3. Perform counterfactual strategy simulation on the key coupling bottlenecks in the collaborative state baseline to obtain the causal effect map of the entire storage and transportation chain; In this embodiment of the invention, the process of obtaining the causal effect map of the entire storage and transportation chain is as follows: Bottleneck identification is performed on the cooperative state baseline to obtain the key constraint nodes of the cooperative state baseline; Based on the key constraint nodes, hypothetical scheduling actions are derived for the entire storage and transportation chain to obtain a set of hypothetical scheduling operations for the entire storage and transportation chain. Using the collaborative state baseline as the fact benchmark, counterfactual scenario deduction is performed on the hypothetical scheduling operation set to obtain the simulated state trajectory of the entire storage and transportation chain; The intensity of the operational causal impact of the entire storage and transportation chain is obtained by measuring the difference between the simulated state trajectory and the cooperative state baseline. A knowledge structure is constructed to assess the causal impact strength of the aforementioned operations, thereby obtaining a causal effect map of the entire storage and transportation chain.

[0034] The process of obtaining the hypothetical scheduling operation set for the entire storage and transportation chain is as follows: Attribute analysis is performed on the key constraint nodes to obtain attribute descriptions of the key constraint nodes; Based on the attribute description, the scheduling action prototypes in the preset scheduling knowledge base are called according to the adaptation rules to obtain the scheduling action template of the key constraint node. The scheduling action template is extended with parameters to obtain the candidate operation sequence for the entire storage and transportation chain; Based on the environmental and resource constraints of the entire storage and transportation chain, the candidate operation sequences are screened for compliance to obtain a hypothetical scheduling operation set for the entire storage and transportation chain.

[0035] The process of obtaining the simulated state trajectory of the entire storage and transportation chain is as follows: The collaborative state baseline is set as the projection benchmark state for the entire storage and transportation chain; Based on the aforementioned baseline state, counterfactual effects are injected into the operations in the hypothetical scheduling operation set to obtain the single-step disturbance state of the entire storage and transportation chain. Using the causal structure of the entire storage and transportation chain as the transmission path, the initial impact represented by the single-step disturbance state is transmitted and deduced to obtain the state evolution sequence of the entire storage and transportation chain; The state evolution sequence is encapsulated with trajectory features to obtain the simulated state trajectory of the entire storage and transportation chain.

[0036] The causal effect map is a structured knowledge system that records the relationship between hypothetical operations and the entire chain of influence. It includes the influence nodes, influence intensity, and related logic of each operation. When conducting in-depth deconstruction of coupling relationships, the connection relationship between all nodes in the map is first sorted out to clarify the influence path and mode of each node on other nodes. Then, the weight ratio of each node in the entire chain performance system is analyzed. Nodes with a weight ratio that reaches the set standard are marked as core nodes. Then, the influence transmission range of the core nodes is tracked to screen out the core elements that play a decisive role in the overall performance of the entire chain and can be changed through scheduling operations. These elements are the key performance elements, which are directly related to the core operational efficiency of the entire storage and transportation chain.

[0037] Key performance elements (KPIs) are the core elements that determine the core effectiveness of the entire chain. Historical operation records are a complete set of operational data from past operations across the entire storage and transportation chain. Current process rules are the standards and requirements for current standardized operations. During the process, all operation items in the historical operation records are comprehensively reviewed, and the operational steps and parameter settings that are allowed to be adjusted in the current process rules are identified. Parameters that can be adjusted through human intervention and are directly related to KPIs are selected. These parameters must be able to directly affect KPIs after adjustment and meet the basic requirements of the current process rules. The parameters selected in this way are the control parameters.

[0038] Key performance elements (KPIs) are the elements that affect the core effectiveness of the entire chain. Control parameters are related parameters that can be adjusted manually. When performing targeted correlation, for each KPI, the direction and degree of influence of all control parameter adjustments on the KPI are analyzed one by one. The direction of influence is divided into three categories: positive influence, negative influence, and no influence. The degree of influence is determined by comparing the changes in the KPIs before and after parameter adjustments. If the change reaches a set threshold, it is judged as having a significant influence. Each KPI is mapped one-to-one with the control parameters that have a significant positive influence on it, clarifying the correspondence between parameter adjustment methods and changes in performance elements. The resulting systematic correlation system is the parameter-performance mapping relationship.

[0039] The parameter-effect mapping relationship clarifies the influence relationship between control parameters and key performance elements. Real-time operation status is the current actual operation of the entire storage and transportation chain, including the operation progress, resource occupancy, and connection status of each node. The preset scheduling goal is the pre-set optimization direction of the entire chain, such as improving operation efficiency, reducing operation costs, and improving resource utilization. During integrated planning, the current key performance elements are first judged based on the real-time operation status. For performance elements that have not met the standards, the corresponding control parameters are selected according to the parameter-effect mapping relationship. The adjustment direction and adjustment range of the parameters are determined in combination with the preset scheduling goal. At the same time, the mutual influence between control parameters is taken into account to avoid conflicts in parameter adjustment. The final complete plan that covers all parameters that need to be adjusted, adjustment schemes, and implementation logic is the control parameter configuration scheme.

[0040] A control parameter configuration scheme is a complete plan that includes parameter adjustment details and implementation logic. When encapsulated in a structured manner, all contents in the configuration scheme are organized and standardized according to a fixed framework of parameter category, adjustment goal, adjustment method, implementation steps, applicable scenarios, and precautions. The parameter category clarifies the work link or management dimension to which the parameter belongs, the adjustment goal corresponds to the specific key performance element optimization direction, the adjustment method describes the specific adjustment operation of the parameter, the implementation steps clarify the order of operations and the timing of execution, the applicable scenarios define the applicable operating state of the scheme, and the precautions list the risks to be avoided and the norms to be followed during the execution process. The standardized scheme set after being organized is the candidate scheduling strategy.

[0041] The multi-objective optimization criteria are a set of pre-defined optimization directions across the entire chain, covering core optimization dimensions such as operational efficiency, resource utilization, operational costs, and seamless integration. During quantitative analysis, each optimization criterion is decomposed into multiple measurable specific evaluation dimensions. Each evaluation dimension has clearly defined measurement standards and judgment criteria. For example, the operational efficiency criterion can be decomposed into evaluation dimensions such as operational completion cycle, workload per unit time, and node connection waiting time. Each dimension has clearly defined specific content to be measured and achievement requirements. All the decomposed specific dimensions together constitute the evaluation dimension system of the multi-objective optimization criteria.

[0042] The evaluation dimension system is a specific standard for measuring strategy effectiveness. The candidate scheduling strategy set is a collection of multiple standardized scheduling schemes. During collaborative effectiveness deconstruction, for each candidate scheduling strategy, each dimension in the evaluation dimension system is compared one by one, and the operational data of the strategy under that dimension is collected. According to the measurement standard of the evaluation dimension, the performance level of the strategy in that dimension is analyzed. For example, in the job completion cycle dimension, the changes in job completion cycle after the strategy is implemented are analyzed; in the job cost dimension, the changes in job cost after the strategy is implemented are analyzed. By combining the performance levels of all evaluation dimensions, a comprehensive description of the overall effectiveness of the strategy is formed, which is the strategy effectiveness.

[0043] Strategy effectiveness is the comprehensive performance of each candidate strategy across all evaluation dimensions. In a panoramic comparison of strengths and weaknesses, a corresponding weight is first assigned to each evaluation dimension. The weight is determined based on the importance of each dimension to the core effectiveness of the entire chain. The higher the importance, the greater the weight. Then, the comprehensive effectiveness score of each candidate strategy is calculated by multiplying the performance score of each evaluation dimension by the corresponding weight, and then adding all the weighted scores together. Based on the comprehensive effectiveness score, all candidate scheduling strategies are ranked, with the strategy with the higher score ranked higher. The resulting ordered strategy list is the strategy priority sequence.

[0044] The strategy priority sequence is a list of strategies sorted by comprehensive performance score. When selecting the optimal strategy, we first check whether the strategies ranked at the top in the sequence meet the basic operational requirements of the entire chain, including whether they comply with current process rules, whether they are within the resource constraints, and whether there are potential operational risks. The strategy that meets all the basic requirements and has the highest comprehensive performance score is selected as the preferred collaborative scheduling strategy, which can achieve the optimal balance of the entire chain's operational performance across multiple optimization dimensions.

[0045] Real-time operational status is the immediate operational condition of the entire storage and transportation chain, including information on the progress of each link, resource occupancy status, equipment operation status, and node connection status. When analyzing key indicators, key indicators that reflect the core operational status of the entire chain are extracted from the real-time operational status, including indicators related to operational efficiency, resource utilization, connection and coordination, and cost control. The current status of each key indicator is described, such as whether resource occupancy is high or low, whether the operation progress is ahead of schedule or behind schedule, and whether the connection status is smooth or congested. These organized key indicator status descriptions are the operational characteristics.

[0046] Operational characteristics are the core indicators describing the real-time operational status. Each strategy in the optimized collaborative scheduling strategy has a predefined trigger condition. The trigger condition is an applicable operational status description in which the strategy can achieve the best effect. During the adaptability screening, the operational characteristics are compared with the trigger conditions of each strategy one by one to analyze the degree of fit. The criterion for judging the degree of fit is whether the key indicator status in the operational characteristics is consistent with the indicator requirements in the trigger conditions. Strategies that are completely consistent or whose core indicators are consistent are judged to meet the fit standard. All strategies that meet the fit standard are the matching strategies.

[0047] Matching strategies are a set of strategies that fit the current operating state. Real-time resource constraints are the upper limit of resources that can be called up in the entire chain, including restrictions on manpower, equipment, space, time, etc. Operation procedures are mandatory requirements and operational standards for standardizing the operation. During adaptability verification, each matching strategy is checked one by one to see if its execution is within the range of real-time resource constraints. For example, whether the number of manpower required by the strategy does not exceed the total number of currently available manpower, and whether the required equipment is within the range of currently callable equipment. At the same time, the operation steps of the strategy are checked to see if they meet the requirements of the operation procedures. There are no operations that violate the standards. After verification, the strategy that meets both resource constraints and operation procedures is the adaptive scheduling strategy.

[0048] Adaptive scheduling strategies are standardized strategies with executable conditions. During coding, the specific content of the strategy is transformed into a standardized instruction format recognizable by the execution end. The instruction content must clearly specify key information such as the executing entity, execution time, operation steps, parameter requirements, expected goals, and emergency handling methods. The executing entity clearly specifies the specific work team or equipment; the execution time clearly specifies the time range for strategy initiation and completion; the operation steps clearly specify the sequence and specific actions of each operation; the parameter requirements clearly specify the key parameter standards in the operation process; the expected goals clearly specify the direction of efficiency improvement after strategy execution; and the emergency handling methods clearly specify the response measures when anomalies occur during execution. The instructions after standardization are the collaborative scheduling instructions.

[0049] The beneficial effects of this invention are as follows: By deconstructing the causal effect map, it accurately locates key performance elements and clarifies parameter mapping objectives, thereby enhancing the focus of scheduling optimization; it screens compliant control parameters, providing a legal basis for adjustment and improving the executability of scheduling strategies; it establishes clear correlations and logical interactions between parameters, improving the scientific rigor and accuracy of scheduling strategy formulation; it integrates real-time status with preset objectives to formulate plans, avoiding blind adjustments and improving strategy adaptability and optimization effectiveness; it structures and encapsulates standardized candidate strategies, facilitating evaluation and screening and improving the efficiency of strategy management and application; it quantitatively analyzes multi-objective criteria and constructs a unified evaluation system, improving the objectivity and accuracy of performance evaluation; and it deconstructs the performance of candidate strategies to comprehensively assess their effectiveness. By understanding strategy performance, we can provide detailed evidence for comparing superior and inferior strategies; by forming a strategy priority sequence and clearly presenting comprehensive effectiveness, we can improve the efficiency and rationality of screening; by selecting the optimal strategy to achieve a multi-dimensional performance balance, we can maximize the optimization effect of the entire chain operation and scheduling; by analyzing real-time key indicators and extracting core features, we can provide accurate evidence for strategy matching and improve matching accuracy; by screening suitable strategies, we can avoid redundant evaluation, improve screening efficiency, and lay the foundation for verification; by eliminating non-compliant strategies through adaptability verification, we can ensure execution conditions, improve scheduling success rate, and avoid resource waste; by encoding feasible strategies into standardized scheduling instructions, we can clarify requirements and formats, improve execution efficiency and accuracy, and ensure that optimization effects are implemented.

[0050] S4. Map scheduling parameters to the causal effect map to obtain candidate scheduling strategies for the entire storage and transportation chain; In this embodiment of the invention, the process of obtaining the candidate scheduling strategy for the entire storage and transportation chain is as follows: The coupling relationships of the causal effect map are deeply deconstructed to obtain the key performance elements of the causal effect map. Based on the aforementioned key performance elements, the control parameters of the entire storage and transportation chain are obtained by traversing the historical operation records and current process rules of the entire storage and transportation chain. By strategically associating the key performance elements with the control parameters, the parameter mapping relationship of the entire storage and transportation chain is obtained; Based on the parameter mapping relationship, the real-time operation status of the entire storage and transportation chain is integrated with the preset scheduling target to obtain the control parameter configuration scheme of the entire storage and transportation chain; The control parameter configuration scheme is structured and encapsulated to obtain the candidate scheduling strategy for the entire storage and transportation chain.

[0051] A deep deconstruction of the causal effect map is performed. The causal effect map is a knowledge structure formed by simulating the key coupling bottlenecks in the collaborative state baseline using counterfactual strategies. It contains information on the causal relationships and degree of influence between various links and elements in the entire storage and transportation chain. During the deep deconstruction, the association paths of all performance nodes in the map are first sorted out to clarify the direction and scope of influence of each node on other nodes. Then, the core elements that play a decisive role in the overall operation effect of the entire storage and transportation chain are selected. These core elements are the key performance elements, which specifically include operation completion efficiency, operation cost, cargo integrity rate, resource utilization rate, etc. Each element can directly reflect the operation quality and scheduling effect of the entire storage and transportation chain.

[0052] Based on key performance indicators (KPIs), we thoroughly reviewed historical operational records and current process rules across the entire storage and transportation chain. Historical operational records encompass complete data generated during past transportation, warehousing, loading / unloading, and distribution operations, including vehicle dispatch frequency, warehouse space allocation, loading / unloading equipment runtime, and delivery route selection. Current process rules are industry-standard operating procedures and internal company-defined operational standards, clearly defining the operational requirements and limitations for each stage. During this review, we comprehensively examined these historical data and rule documents to identify parameters that can be adjusted manually or systematically to influence KPIs. These parameters are the control parameters, such as vehicle dispatch intervals, warehouse area allocation ratios, loading / unloading equipment start / stop times, and delivery route planning schemes.

[0053] By establishing targeted correlations between key performance elements (KPIs) and control parameters, and analyzing the impact of all control parameters on each KPI, the positive and negative correlations and the degree of correlation are determined. For example, the KPI of operational efficiency is negatively correlated with the dispatch interval of transport vehicles and the running time of loading and unloading equipment, but positively correlated with the delivery route planning scheme; the KPI of operational cost is positively correlated with the warehouse space allocation ratio and the fuel consumption control parameters of transport vehicles. Through this targeted analysis, a clear correspondence is established between each KPI and its corresponding control parameter, forming a parameter-effect mapping relationship. This relationship clearly shows which control parameters can affect which KPIs, and the specific logic of the influence.

[0054] Based on the parameter-effect mapping relationship, the real-time operation status of the entire storage and transportation chain is integrated with the preset scheduling goals for planning. The real-time operation status is the operational data of each link in the storage and transportation process obtained through sensors and data acquisition equipment, including the current location distribution of transport vehicles, the occupancy of warehouse space, the operating status of loading and unloading equipment, and the real-time flow of goods. The preset scheduling goals are set by the enterprise according to business needs, such as completing a predetermined transportation volume within a specified time, controlling operating costs within a certain range, and ensuring that the integrity rate of goods is not lower than a specific standard. During the integration planning, the gap between the current real-time operation status and the preset scheduling goals is analyzed with reference to the parameter-effect mapping relationship. For each key performance element, the corresponding control parameters are adjusted so that the adjusted parameter combination can narrow the gap between the actual status and the goal, and finally a control parameter configuration scheme is formed. This scheme clarifies the specific adjustment direction and value of each control parameter, such as shortening the dispatch interval of transport vehicles, increasing the allocation ratio of warehouse area A, and specifying a certain optimized delivery route.

[0055] The control parameter configuration scheme is structured and encapsulated. According to the preset standard format, the contents of the control parameter configuration scheme are organized and the name of each control parameter, the adjusted value or range, the applicable operation scenario, the execution order and other information are clearly listed to ensure that the scheme is clear, easy to understand and execute. The standard document formed after structured encapsulation is the candidate scheduling strategy for the entire storage and transportation chain. Each candidate scheduling strategy corresponds to a complete parameter adjustment scheme, which can be directly applied to the scheduling operation of the entire storage and transportation chain.

[0056] The beneficial effects include: accurately extracting key performance elements, clarifying core indicators, focusing on core issues, improving the pertinence and effectiveness of scheduling optimization, ensuring the comprehensiveness and compliance of control parameters, avoiding invalid or non-compliant parameters, enhancing the feasibility of subsequent configuration schemes, revealing the intrinsic relationship between parameters and performance, clarifying the impact logic, providing solid support for parameter configuration, reducing blind adjustments, aligning with actual operating conditions and business objectives, ensuring the pertinence and practicality of the schemes, narrowing performance gaps, improving scheduling effectiveness, making scheduling schemes clear, standardized, and unified, facilitating evaluation, selection, understanding, and execution, and improving the efficiency and accuracy of scheduling strategy implementation.

[0057] S5. Based on the multi-objective optimization criteria of the entire storage and transportation chain, evaluate the collaborative effectiveness of the candidate scheduling strategy set to obtain the preferred collaborative scheduling strategy for the entire storage and transportation chain. In this embodiment of the invention, the process of obtaining the preferred collaborative scheduling strategy for the entire storage and transportation chain is as follows: The multi-objective optimization criteria for the entire storage and transportation chain are quantitatively analyzed to obtain the evaluation dimensions of the multi-objective optimization criteria; Based on the evaluation dimensions, the candidate scheduling strategy set is deconstructed for collaborative effectiveness to obtain the strategy effectiveness of the candidate scheduling strategy set; Based on the effectiveness of the strategy, a comprehensive comparison of the merits of the candidate scheduling strategy set is performed to obtain the strategy priority sequence for the entire storage and transportation chain. The optimal strategy is selected from the priority sequence of the strategies to obtain the preferred collaborative scheduling strategy for the entire storage and transportation chain.

[0058] The core objectives that need to be achieved in the actual operation of the entire collection, storage, and transportation chain are all directly related to collaborative scheduling. These include completing transportation and storage tasks as quickly as possible, controlling human and material costs, ensuring that goods are not damaged, and ensuring that resources such as vehicles and warehouses are not idle. For each core objective, specific aspects that can directly reflect the achievement of the objective are broken down. The operational efficiency objective is broken down into task completion time and the amount of goods processed per unit time; the operational cost objective is broken down into human input costs, vehicle fuel consumption, and warehouse maintenance expenses; the goods integrity rate objective is broken down into the number of damaged goods and the proportion of spoilage; and the resource utilization rate objective is broken down into vehicle load rate, warehouse space occupancy rate, and equipment operating time percentage. These specific aspects constitute the evaluation dimensions of the multi-objective optimization criterion, and each evaluation dimension corresponds to a specific measurement direction of a core objective.

[0059] Take a scheduling strategy from the candidate scheduling strategy set, and collect the actual operation data of the strategy in simulated execution or similar historical scenarios for each evaluation dimension. For the task completion time dimension, collect all time data from the start to the end of the task after the strategy is executed. For the quantity of goods processed per unit time dimension, collect the total quantity of goods actually processed per unit time during the execution of the strategy. For the human resource input cost dimension, calculate the total salary of all participants during the execution of the strategy. For the quantity of damaged goods dimension, record the specific number of damaged goods after the execution of the strategy. Complete the data collection for the strategy on all evaluation dimensions in the same way. Organize the data under each evaluation dimension to form the specific performance result of the strategy on each dimension. The combined performance results of all evaluation dimensions is the strategy effectiveness. Repeat the above operation for each strategy in the candidate scheduling strategy set to obtain the strategy effectiveness corresponding to each strategy.

[0060] Based on the actual business needs of the entire storage and transportation chain, the importance of each evaluation dimension is ranked. In the fresh food storage and transportation scenario, the importance of cargo integrity rate is higher than other dimensions. In the storage and transportation of general fast-moving consumer goods, the importance of operational efficiency and cost is even higher. Once the ranking is determined, it will not be changed. The strategy effectiveness of all candidate scheduling strategies is placed under the same comparison framework. First, the most important evaluation dimension is compared. The strategy with the best performance in that dimension is classified into the first tier, the next best performance into the second tier, and so on. Strategies in the same tier are then compared with the less important evaluation dimensions to further subdivide the tiers. The above comparison process is repeated in order of importance of the evaluation dimensions until all strategies are distinguished in order. The resulting strategy list arranged in descending order is the strategy priority sequence. The earlier a strategy appears in the sequence, the stronger its ability to comprehensively meet the multi-objective optimization criteria.

[0061] Starting from the first strategy in the priority sequence, check whether the strategy meets the current real-time resource conditions of the entire storage and transportation chain, including whether there are sufficient vehicles, warehouse space, and staff to support the strategy's execution, and whether it complies with industry standards and internal company operating procedures. If the first strategy meets all constraints, it is directly determined as the preferred collaborative scheduling strategy. If the first strategy does not meet any constraint, it is removed, and the next strategy in the sequence is checked, and its compliance with all constraints is verified. Each strategy in the sequence is checked in the above order until the first strategy that fully meets all constraints and is located at the beginning of the sequence is found. This strategy is the preferred collaborative scheduling strategy for the entire storage and transportation chain.

[0062] The beneficial effects include: clarifying the measurement direction of multi-objective optimization criteria, providing clear and unified judgment basis, meeting actual needs, laying the foundation for accurate evaluation of strategy effectiveness, comprehensively grasping the effectiveness of candidate strategies in each dimension, clarifying strategy differences, avoiding evaluation bias, providing detailed data support for comparison of superior and inferior strategies, comparing strategies in layers according to the importance of evaluation dimensions, taking into account both comprehensiveness and business focus, avoiding one-sidedness, and intuitively reflecting comprehensive competitiveness in the strategy priority sequence, providing an orderly reference for the selection of the optimal strategy, ensuring that the selected strategy is comprehensively optimal and feasible and compliant, improving the practicality and execution success rate of collaborative scheduling strategies, and providing a reliable guarantee for the efficient collaborative operation of the entire storage and transportation chain.

[0063] S6. Match the real-time operating status of the entire storage and transportation chain with the strategies in the preferred collaborative scheduling strategy, and encode the matching result as a collaborative scheduling instruction for the entire storage and transportation chain.

[0064] In this embodiment of the invention, the real-time operating status of the entire storage and transportation chain is conditionally matched with the strategies in the preferred collaborative scheduling strategy, and the matching result is encoded into a collaborative scheduling instruction for the entire storage and transportation chain, including: The key indicators of the real-time operation status of the entire storage and transportation chain are analyzed to obtain the operation characteristics of the real-time operation status; Based on the aforementioned operational characteristics, the strategy triggering conditions in the preferred collaborative scheduling strategy are subjected to adaptability screening to obtain the matching strategy for the entire storage and transportation chain. Based on the real-time resource constraints and work procedures, the adaptability of the matching strategy is verified to obtain the adapted scheduling strategy of the matching strategy. The adaptive scheduling strategy is encoded into a collaborative scheduling instruction for the entire storage and transportation chain.

[0065] When analyzing key indicators of the real-time operational status of the entire storage and transportation chain, it is essential to first clarify that the real-time operational status encompasses instantaneous information from all operational stages, including transportation, warehousing, loading and unloading, and delivery. This includes the real-time location, current load, and speed of transport vehicles; the real-time inventory quantity and storage capacity occupancy in warehousing; the current progress and equipment operating status of loading and unloading operations; and the completed mileage and remaining route status of delivery. The determination of key indicators is based on the core operational needs and performance targets of the entire storage and transportation chain. Specifically, these include transportation progress and vehicle utilization rate in the transportation stage; inventory turnover rate and storage capacity occupancy rate in the warehousing stage; operational efficiency and equipment failure rate in the loading and unloading stage; and on-time delivery rate and cargo damage rate in the delivery stage. Real-time data corresponding to these key indicators should be collected. Next, the data is cleaned to remove abnormal data caused by equipment failure, signal interference, etc. The criterion for judging abnormal data is that the difference between the data and the adjacent data in the same time period exceeds three times the normal fluctuation range. The normal fluctuation range is obtained by statistically analyzing the operating data of the indicator over the past three months to obtain the average fluctuation amplitude. Then, feature extraction is performed on the cleaned effective data to statistically analyze the current value of each indicator, the trend of change in the recent period (e.g., rising, falling, or stable), and the stability of the value (e.g., frequent fluctuations or continuous stability). This information is integrated to form an operating feature that can comprehensively and accurately reflect the core situation of the current real-time operating status. The operating feature is a set of structured information containing the current status and changing trend of each key indicator.

[0066] When selecting matching strategies based on the obtained operational characteristics, the preferred collaborative scheduling strategies are the optimal set of strategies determined after evaluation by multi-objective optimization criteria. Each strategy has pre-defined trigger conditions, which are set according to the operational needs and objectives under different work scenarios. For example, the trigger condition for one strategy is that the transportation progress is lagging and the vehicle idle rate is high, while the trigger condition for another strategy is that the warehouse capacity occupancy rate exceeds the standard and the loading and unloading efficiency is insufficient. Following a fixed sequence of transportation, warehousing, loading and unloading, and delivery, the key indicator information of each link in the operational characteristics is compared one by one with the trigger conditions of each preferred collaborative scheduling strategy. During the comparison, the indicator values ​​and trends in the operational characteristics are checked to ensure they are completely consistent with the requirements of the trigger conditions. For example, if the trigger condition requires that the transportation progress is lagging by more than 10% and the vehicle idle rate is higher than 15%, then the trend of the transportation progress in the operational characteristics is checked to see if it meets the lag requirement, and whether the idle rate after converting the vehicle utilization rate meets the corresponding standard. After completing the comparison of all preferred collaborative scheduling strategies, all strategies whose trigger conditions perfectly match the operational characteristics are selected. These strategies together constitute the matching strategy for the entire storage and transportation chain.

[0067] Based on real-time resource constraints and operational procedures verification and adaptation scheduling strategies, real-time resource constraints are obtained in real time through resource monitoring systems at each stage. These constraints include the current available manpower, the available transport capacity of vehicles (e.g., load capacity, mileage), remaining warehouse space capacity, the number and operational capacity of loading and unloading equipment, and road conditions along delivery routes (e.g., congestion, passability). Operational procedures are standardized operational requirements developed over long-term operations across the entire storage and transportation chain. These procedures cover safety operating standards (e.g., safe weight limits for loading and unloading goods, safe driving speeds for transport vehicles), loading and unloading processes (e.g., the loading and unloading sequence and stacking height for fragile items), vehicle scheduling rules (e.g., priority order for vehicle scheduling), and warehouse management standards (e.g., temperature and humidity requirements for goods storage). Each matching strategy is checked one by one. First, it is determined whether the manpower, transport capacity, and warehouse space required for the strategy are within the current real-time resource constraints, i.e., the required resource quantity does not exceed the currently available resource quantity, and the required resource specifications match the current available resource configuration. Then, it is checked whether the operational process of the strategy fully complies with all requirements of the operational procedures, with no violations. A matching strategy that passes both of the above checks is determined to be an adaptive scheduling strategy.

[0068] When encoding adaptive scheduling strategies into collaborative scheduling instructions, the specific operational requirements within the adaptive scheduling strategy are first broken down and categorized according to the stages of transportation, warehousing, loading and unloading, and delivery. The operational objects for each stage are clearly defined, such as a specific transport vehicle, a specific warehousing area, or a specific loading and unloading equipment; the operational content includes vehicle routes, cargo entry locations, equipment operation steps, operation times (departure time, start time, completion deadline), and operational standards (cargo integrity requirements, delivery on-time requirements), etc. These details are then converted into standardized instruction formats that can be directly recognized and executed by each execution stage. The instruction formats are set according to the operational habits and receiving specifications of each execution unit, ensuring that the execution unit can understand the operational requirements without additional interpretation. The resulting collaborative scheduling instructions are a structured set of standardized instructions containing specific operational instructions for each stage, which can be directly sent to the corresponding execution units to guide the operation.

[0069] The beneficial effects include: clarifying key indicators, cleaning standards, and extraction logic to ensure the authenticity and comprehensiveness of operational characteristics; providing high-quality data for strategy selection and improving selection accuracy; comparing in a fixed order to ensure rigorous and orderly selection; accurately matching and adapting strategies to avoid omissions and misselections; improving the fit between strategies and actual scenarios; double verification to ensure that strategies have sufficient resource support and comply with specifications; avoiding scheduling failures; enhancing executability and operational safety; encoding into standardized instructions to reduce information loss and misunderstanding bias; improving execution efficiency; ensuring smooth collaboration among all links; and improving overall scheduling efficiency.

[0070] like Figure 2 The diagram shown is a functional block diagram of a production task collaborative scheduling optimization system for the entire storage and transportation chain provided by an embodiment of the present invention.

[0071] The production task collaborative scheduling optimization system 100 for the entire storage and transportation chain described in this invention can be installed in an electronic device. Depending on the functions implemented, the production task collaborative scheduling optimization system 100 for the entire storage and transportation chain may include a causal structure construction module 101, a coupling analysis baseline generation module 102, a bottleneck simulation causal effect module 103, a parameter mapping strategy candidate module 104, an efficiency evaluation strategy optimization module 105, and a state matching instruction encoding module 106. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and are stored in the memory of the electronic device.

[0072] In this embodiment, the functions of each module / unit are as follows: The causal structure construction module 101 is used to construct the causal structure of the entire storage and transportation chain based on the historical operation records and domain rules of the entire storage and transportation chain. The coupling analysis baseline generation module 102 is used to inject real-time operation data of the entire storage and transportation chain into the causal structure, perform interdependence analysis on the performance coupling relationship of the entire storage and transportation chain, and obtain the collaborative state baseline of the entire storage and transportation chain. The bottleneck simulation causal effect module 103 is used to perform counterfactual strategy simulation on the key coupling bottlenecks in the collaborative state baseline to obtain the causal effect map of the entire storage and transportation chain. The parameter mapping strategy candidate module 104 is used to perform scheduling parameter mapping on the causal effect spectrum to obtain candidate scheduling strategies for the entire storage and transportation chain. The efficiency evaluation strategy optimization module 105 is used to evaluate the collaborative efficiency of the candidate scheduling strategy set based on the multi-objective optimization criteria of the entire storage and transportation chain, so as to obtain the preferred collaborative scheduling strategy of the entire storage and transportation chain. The state matching instruction encoding module 106 is used to match the real-time operating status of the entire storage and transportation chain with the strategy in the preferred collaborative scheduling strategy, and encode the matching result into the collaborative scheduling instruction of the entire storage and transportation chain.

[0073] In the several embodiments provided by this invention, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0074] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0075] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0076] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0077] This application embodiment can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0078] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A collaborative scheduling optimization method for production tasks across the entire storage and transportation chain, characterized in that: The method includes: S1. Construct the causal structure of the entire storage and transportation chain based on the historical operation records and domain rules of the entire chain; S2. Inject the real-time operation data of the entire storage and transportation chain into the causal structure, perform interdependence analysis on the performance coupling relationship of the entire storage and transportation chain, and obtain the collaborative state baseline of the entire storage and transportation chain; S3. Perform counterfactual strategy simulation on the key coupling bottlenecks in the collaborative state baseline to obtain the causal effect map of the entire storage and transportation chain; S4. Map scheduling parameters to the causal effect map to obtain candidate scheduling strategies for the entire storage and transportation chain; S5. Based on the multi-objective optimization criteria of the entire storage and transportation chain, evaluate the collaborative effectiveness of the candidate scheduling strategy set to obtain the preferred collaborative scheduling strategy for the entire storage and transportation chain. S6. Match the real-time operating status of the entire storage and transportation chain with the strategies in the preferred collaborative scheduling strategy, and encode the matching result as a collaborative scheduling instruction for the entire storage and transportation chain.

2. The collaborative scheduling optimization method for production tasks across the entire storage and transportation chain as described in claim 1, characterized in that, The process of constructing the causal structure of the entire storage and transportation chain is as follows: The key operational characteristics of the historical operation records of the entire storage and transportation chain are obtained by multi-dimensional extraction. Constraints are extracted from the domain rules involved in the entire storage and transportation chain to obtain the constraints of the entire storage and transportation chain. By performing dependency mining on the key operational characteristics and the constraints, the causal relationships of the entire storage and transportation chain can be obtained; The causal relationships are topologically reconstructed to obtain the causal structure of the entire storage and transportation chain.

3. The collaborative scheduling optimization method for production tasks across the entire storage and transportation chain as described in claim 1, characterized in that, The process of obtaining the baseline of the coordinated state of the entire storage and transportation chain is as follows: The real-time operation data of the entire storage and transportation chain is injected into the causal structure to obtain a real-time status instance of the entire storage and transportation chain. Based on the real-time status instance, the interaction impact between performance dimensions in the entire storage and transportation chain is evaluated to obtain the interaction strength of performance indicators in the entire storage and transportation chain. Based on the interaction strength of the performance indicators, the density of performance nodes in the real-time status instance is identified to obtain the performance association cluster of the entire storage and transportation chain; The performance association clusters and the causal paths corresponding to the performance association clusters are topologically fused to obtain the panoramic coupling structure of the entire storage and transportation chain; The steady-state baseline of the operating state characterized by the panoramic coupling structure is condensed to obtain the collaborative state baseline of the entire storage and transportation chain.

4. The collaborative scheduling optimization method for production tasks across the entire storage and transportation chain as described in claim 1, characterized in that, The process of obtaining the causal effect map of the entire storage and transportation chain is as follows: Bottleneck identification is performed on the cooperative state baseline to obtain the key constraint nodes of the cooperative state baseline; Based on the key constraint nodes, hypothetical scheduling actions are derived for the entire storage and transportation chain to obtain a set of hypothetical scheduling operations for the entire storage and transportation chain. Using the collaborative state baseline as the fact benchmark, counterfactual scenario deduction is performed on the hypothetical scheduling operation set to obtain the simulated state trajectory of the entire storage and transportation chain; The intensity of the operational causal impact of the entire storage and transportation chain is obtained by measuring the difference between the simulated state trajectory and the cooperative state baseline. A knowledge structure is constructed to assess the causal impact strength of the aforementioned operations, thereby obtaining a causal effect map of the entire storage and transportation chain.

5. The collaborative scheduling optimization method for production tasks across the entire storage and transportation chain as described in claim 4, characterized in that, The process of obtaining the hypothetical scheduling operation set for the entire storage and transportation chain is as follows: Attribute analysis is performed on the key constraint nodes to obtain attribute descriptions of the key constraint nodes; Based on the attribute description, the scheduling action prototypes in the preset scheduling knowledge base are called according to the adaptation rules to obtain the scheduling action template of the key constraint node. The scheduling action template is extended with parameters to obtain the candidate operation sequence for the entire storage and transportation chain; Based on the environmental and resource constraints of the entire storage and transportation chain, the candidate operation sequences are screened for compliance to obtain a hypothetical scheduling operation set for the entire storage and transportation chain.

6. The collaborative scheduling optimization method for production tasks across the entire storage and transportation chain as described in claim 4, characterized in that, The process of obtaining the simulated state trajectory of the entire storage and transportation chain is as follows: The collaborative state baseline is set as the projection benchmark state for the entire storage and transportation chain; Based on the aforementioned baseline state, counterfactual effects are injected into the operations in the hypothetical scheduling operation set to obtain the single-step disturbance state of the entire storage and transportation chain. Using the causal structure of the entire storage and transportation chain as the transmission path, the initial impact represented by the single-step disturbance state is transmitted and deduced to obtain the state evolution sequence of the entire storage and transportation chain; The state evolution sequence is encapsulated with trajectory features to obtain the simulated state trajectory of the entire storage and transportation chain.

7. The collaborative scheduling optimization method for production tasks across the entire storage and transportation chain as described in claim 1, characterized in that, The process of obtaining candidate scheduling strategies for the entire storage and transportation chain is as follows: The coupling relationships of the causal effect map are deeply deconstructed to obtain the key performance elements of the causal effect map. Based on the aforementioned key performance elements, the control parameters of the entire storage and transportation chain are obtained by traversing the historical operation records and current process rules of the entire storage and transportation chain. By strategically associating the key performance elements with the control parameters, the parameter mapping relationship of the entire storage and transportation chain is obtained; Based on the parameter mapping relationship, the real-time operation status of the entire storage and transportation chain is integrated with the preset scheduling target to obtain the control parameter configuration scheme of the entire storage and transportation chain; The control parameter configuration scheme is structured and encapsulated to obtain the candidate scheduling strategy for the entire storage and transportation chain.

8. The collaborative scheduling optimization method for production tasks across the entire storage and transportation chain as described in claim 1, characterized in that, The process of obtaining the optimal collaborative scheduling strategy for the entire storage and transportation chain is as follows: The multi-objective optimization criteria for the entire storage and transportation chain are quantitatively analyzed to obtain the evaluation dimensions of the multi-objective optimization criteria; Based on the evaluation dimensions, the candidate scheduling strategy set is deconstructed for collaborative effectiveness to obtain the strategy effectiveness of the candidate scheduling strategy set; Based on the effectiveness of the strategy, a comprehensive comparison of the merits of the candidate scheduling strategy set is performed to obtain the strategy priority sequence for the entire storage and transportation chain. The optimal strategy is selected from the priority sequence of the strategies to obtain the preferred collaborative scheduling strategy for the entire storage and transportation chain.

9. The collaborative scheduling optimization method for production tasks across the entire storage and transportation chain as described in claim 1, characterized in that, The real-time operating status of the entire storage and transportation chain is matched with the strategies in the preferred collaborative scheduling strategy, and the matching result is encoded into a collaborative scheduling instruction for the entire storage and transportation chain, including: The key indicators of the real-time operation status of the entire storage and transportation chain are analyzed to obtain the operation characteristics of the real-time operation status; Based on the aforementioned operational characteristics, the strategy triggering conditions in the preferred collaborative scheduling strategy are subjected to adaptability screening to obtain the matching strategy for the entire storage and transportation chain. Based on the real-time resource constraints and work procedures, the adaptability of the matching strategy is verified to obtain the adapted scheduling strategy of the matching strategy. The adaptive scheduling strategy is encoded into a collaborative scheduling instruction for the entire storage and transportation chain.

10. A collaborative scheduling and optimization system for production tasks across the entire storage and transportation chain, characterized in that: The system is used to implement the collaborative scheduling and optimization method for production tasks across the entire storage and transportation chain as described in any one of claims 1-9, the system comprising: The causal structure construction module is used to construct the causal structure of the entire storage and transportation chain based on the historical operation records and domain rules of the entire chain. The coupling analysis baseline generation module is used to inject real-time operation data of the entire storage and transportation chain into the causal structure, perform interdependence analysis on the performance coupling relationship of the entire storage and transportation chain, and obtain the collaborative state baseline of the entire storage and transportation chain. The bottleneck simulation causal effect module is used to perform counterfactual strategy simulation on the key coupling bottlenecks in the collaborative state baseline to obtain the causal effect map of the entire storage and transportation chain. The parameter mapping strategy candidate module is used to perform scheduling parameter mapping on the causal effect spectrum to obtain candidate scheduling strategies for the entire storage and transportation chain; The efficiency evaluation strategy optimization module is used to evaluate the collaborative efficiency of the candidate scheduling strategy set based on the multi-objective optimization criteria of the entire storage and transportation chain, and obtain the optimal collaborative scheduling strategy for the entire storage and transportation chain. The status matching instruction encoding module is used to match the real-time operating status of the entire storage and transportation chain with the strategies in the preferred collaborative scheduling strategy, and encode the matching result into the collaborative scheduling instruction of the entire storage and transportation chain.

Images