Port logistics and city industry linkage supply chain optimization model construction method

Abstract

The invention discloses a port logistics and urban industry linkage supply chain optimization model construction method, and relates to the technical field of supply chain collaborative optimization, and the method comprises the steps: collecting port logistics data, urban industry data and urban consumption data, carrying out the cleaning and fusion processing, and forming a port logistics and urban industry supply chain data lake; based on the urban consumption data in the port logistics and urban industry supply chain data lake, consumption demand prediction is carried out and is inversely converted into a supply chain demand instruction set for industrial production and port operation; and according to the supply chain demand instruction set and the real-time data in the port logistics and urban industry supply chain data lake, calculating and monitoring the port logistics and urban industry linkage performance index. According to the method, iterative optimization of the model is realized by executing feedback, a closed-loop collaborative decision of data driving, causal sensing and continuous evolution is formed, and the accuracy, dynamic nature and overall efficiency of port and industry linkage are effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of supply chain collaborative optimization, and in particular to a supply chain optimization model construction method for port logistics and city industry linkage. BACKGROUND

[0002] Under the dual driving of globalization economy and regional integration development, modern supply chain management has shifted from single-link optimization to multi-system collaborative decision-making. As an international logistics hub, the operation efficiency of a port directly affects the supply of raw materials and the circulation of finished products for the industries in the hinterland. Meanwhile, the dynamic demand of city industries also shapes the operation rhythm and resource allocation strategy of the port. In order to improve the competitiveness of the regional economy, the academia and industry gradually pay attention to the linkage between the port and the industry, and try to build a collaborative model through digital means. In the prior art, a representative scheme is a supply chain collaborative framework based on a multi-agent system. In this kind of framework, the port operation subjects and the industry subjects are modeled as autonomous agents, and through defining negotiation rules and objective functions, a contract net protocol or an auction mechanism is used to realize distributed task allocation and resource scheduling.

[0003] However, although the multi-agent system has advantages in heterogeneous subject collaboration, it still has limitations in dealing with the high dynamicity and deep coupling relationship of the port-industry complex system. The existing MAS framework usually relies on pre-defined rules and local objectives for interaction, lacks global perception and dynamic optimization capability for the overall state of the system, and now it is difficult to quantify the causal relationship strength between the port operation indicators and the industry operation indicators, resulting in collaborative decision-making based on correlation rather than causality, which cannot accurately identify and prioritize the key bottleneck links. SUMMARY

[0004] In view of the above existing problems, the present application is proposed.

[0005] Therefore, the present application provides a supply chain optimization model construction method for port logistics and city industry linkage, which solves the problem that the prior art cannot focus on key contradictions for deep collaborative optimization due to relying on correlation decision-making.

[0006] To solve the above technical problems, the present application provides the following technical solutions:

[0007] In a first aspect, the present application provides a supply chain optimization model construction method for port logistics and city industry linkage, which comprises collecting port logistics data, city industry data and city consumption data, performing cleaning and fusion processing to form a port logistics and city industry supply chain data lake;

[0008] Based on the city consumption data in the port logistics and city industry supply chain data lake, the consumption demand is predicted and inversely transformed into a supply chain demand instruction set for industry production and port operation.

[0009] According to the real-time data in the port logistics and urban industry supply chain data lake, the performance indicators of the port logistics and urban industry linkage are calculated and monitored;

[0010] Based on the performance indicators, the bottleneck link and root cause diagnosis report of the port logistics and urban industry linkage are diagnosed by using the causal inference analysis technology;

[0011] The supply chain demand instruction set is taken as the optimization target, the resource data in the port logistics and urban industry supply chain data lake is taken as the constraint, and the bottleneck link and root cause are taken as the optimization focus. A multi-objective optimization model is constructed, the multi-objective optimization model is solved, and a supply chain optimization execution scheme is generated;

[0012] The supply chain optimization execution scheme is executed, and the execution effect data is fed back to the port logistics and urban industry supply chain data lake, and the multi-objective optimization model is iteratively updated.

[0013] As a preferred scheme of the port logistics and urban industry linkage supply chain optimization model construction method, the port logistics data, the urban industry data and the urban consumption data are collected, cleaned and fused to form a port logistics and urban industry supply chain data lake, which includes the following steps,

[0014] The port logistics data, the urban industry data and the urban consumption data are obtained by acquiring the port logistics data, the urban industry data and the urban consumption data through sensing devices and data interfaces, and performing de-duplication, error correction and abnormal value processing on the port logistics data, the urban industry data and the urban consumption data;

[0015] The cleaned port logistics data, the urban industry data and the urban consumption data are converted into a unified space-time format and measurement unit to obtain standardized port logistics data, urban industry data and urban consumption data;

[0016] The standardized port logistics data, the urban industry data and the urban consumption data are aligned and associated according to entities and time to obtain fused port logistics data, urban industry data and urban consumption data;

[0017] The fused port logistics data, the urban industry data and the urban consumption data are persistently stored to form a port logistics and urban industry supply chain data lake.

[0018] As a preferred scheme of the port logistics and urban industry linkage supply chain optimization model construction method, based on the urban consumption data in the port logistics and urban industry supply chain data lake, the consumption demand is predicted and inversely transformed into a supply chain demand instruction set for industrial production and port operation, which includes the following steps,

[0019] extracting city consumption data in a one-year time range from the port logistics and city industry supply chain data lake;

[0020] Based on the city consumption data, using the association rule mining method to construct the derived features, using the long short-term memory network model to train the derived features, and generating the city consumption demand prediction report;

[0021] Through collecting the maximum operating rate of port equipment, the saturation capacity of the yard, the upper limit of road traffic capacity, the maximum load of enterprise production line and the scale of transport vehicle fleet data, and after cleaning and standardization processing, form the capacity and transport capacity constraints in the port logistics and city industry supply chain data lake;

[0022] Taking the city consumption demand prediction report as the optimization target, combining the capacity and transport capacity constraints in the port logistics and city industry supply chain data lake, and solving the industrial production instruction set and the port operation instruction set through mathematical programming;

[0023] The industrial production instruction set and the port operation instruction set are combined to form the supply chain demand instruction set.

[0024] As a preferred scheme of the port logistics and city industry supply chain optimization model construction method, according to the supply chain demand instruction set, the real-time data in the port logistics and city industry supply chain data lake, the performance indicators of the port logistics and city industry linkage are calculated and monitored, including the following steps,

[0025] Extracting port logistics real-time data and city industry real-time data from the port logistics and city industry supply chain data lake, based on historical operation cycle data, real-time ship AIS forecast data, enterprise production rhythm data and road traffic prediction data in the port logistics and city industry supply chain data lake, the planning timeline in the supply chain demand instruction set is obtained through operational research;

[0026] The planning timeline in the supply chain demand instruction set is accurately aligned with the time stamp of the port logistics real-time data and the city industry real-time data to form the plan-actual comparison data set;

[0027] Based on the plan-actual comparison data set, using time series pattern recognition and association rule mining technology to extract port indicators, industry indicators and linkage indicators, and combining the port indicators, industry indicators and linkage indicators to form the linkage performance index set;

[0028] The entropy weight method is used to assign weights to the indicators in the linkage performance index set, and the port-industry linkage comprehensive index is calculated;

[0029] By analyzing the historical linkage performance index set data in the port logistics and city industry supply chain data lake, the linkage threshold is set.

[0030] Monitor the values ​​of the linkage performance indicator set and the port-production linkage comprehensive index. When the value of the linkage comprehensive index exceeds the linkage threshold, an early warning signal is triggered.

[0031] As a preferred embodiment of the supply chain optimization model construction method for port logistics and urban industry linkage described in this invention, the method includes the following steps: based on performance indicators, a causal inference analysis technique is used to diagnose the bottlenecks and root causes of port logistics and urban industry linkage, and a diagnostic report is generated.

[0032] A convergent cross-mapping analysis was conducted on the average port time of port vessels and the number of days of raw material inventory of enterprises in the port-production linkage comprehensive index and the linkage performance index set. The causal strength and direction between the average port time of port vessels and the number of days of raw material inventory of enterprises were quantified. The convergent cross-mapping algorithm was used to calculate the causal contribution between the average port time of port vessels and the number of days of raw material inventory of enterprises.

[0033] Based on the causal contribution, the indicators that have a concentrated impact on the port-industry linkage performance index, namely the average port vessel time in port, the average speed of port access roads, and the inventory turnover days of industrial raw materials, are identified as bottleneck links.

[0034] By performing correlation analysis between the bottleneck process and the planned-actual comparison dataset, the specific operational events of the bottleneck process can be located, and the root cause analysis results can be obtained.

[0035] The bottleneck links, causal strength, and root cause analysis results are integrated to form a bottleneck link and root cause diagnosis report for the linkage between port logistics and urban industries.

[0036] As a preferred embodiment of the supply chain optimization model construction method for port logistics and urban industry linkage described in this invention, the multi-objective optimization model is constructed by taking the supply chain demand instruction set as the optimization objective, the resource data in the port logistics and urban industry supply chain data lake as constraints, and the bottleneck links and root causes as the optimization focus, including the following steps.

[0037] Based on the supply chain demand instruction set and the bottleneck and root cause diagnosis report of the linkage between port logistics and urban industries, resource data is extracted from the port logistics and urban industrial supply chain data lake.

[0038] By taking the supply chain demand instruction set as the target and resource data as the constraint, the bottleneck links in the linkage between port logistics and urban industries and the bottlenecks in the root cause diagnosis report are mathematically compressed into enhanced constraints, and a multi-objective optimization model is constructed.

[0039] As a preferred embodiment of the supply chain optimization model construction method for port logistics and urban industry linkage described in this invention, the method includes the following steps: solving the multi-objective optimization model to generate a supply chain optimization execution plan.

[0040] Elite strategies are obtained by performing a non-dominated ranking between the population in the current generation and the set of elite individuals produced in the previous generation.

[0041] A fast non-dominated sorting genetic algorithm using an elite strategy is used to solve a multi-objective optimization model, yielding a Pareto optimal solution set.

[0042] The criterion-based decision analysis method selects the final solution from the Pareto optimal solution set based on the preference weights of cost, timeliness, and bottleneck relief, thus forming a supply chain optimization execution plan.

[0043] 9. As a preferred embodiment of the supply chain optimization model construction method for port logistics and urban industry linkage described in this invention, the method includes: executing the supply chain optimization execution plan and feeding back the execution effect data to the port logistics and urban industry supply chain data lake; and iteratively updating the multi-objective optimization model, comprising the following steps:

[0044] The supply chain optimization implementation plan is distributed to port operation terminals, transportation scheduling terminals and enterprise production terminals to drive actual operation, and new port logistics data and new urban industrial data generated by the actual operation of the supply chain optimization implementation plan are collected.

[0045] New port logistics data and new urban industry data are transmitted back to the port logistics and urban industry supply chain data lake for storage.

[0046] Based on historical and new data from the port logistics and urban industrial supply chain data lake, the parameters and weights of the multi-objective optimization model are recalibrated.

[0047] By utilizing the updated multi-objective optimization model, a new generation of supply chain optimization execution solutions is generated, initiating a new round of optimization cycles.

[0048] In a second aspect, the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, it implements any step of the method for constructing a supply chain optimization model for port logistics and urban industry linkage as described in the first aspect of the present invention.

[0049] Thirdly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the method for constructing a supply chain optimization model linking port logistics and urban industries as described in the first aspect of the present invention.

[0050] The beneficial effects of this invention are as follows: by collecting and integrating multi-source data to construct a supply chain data lake, generating demand instruction sets based on consumption data prediction, calculating and monitoring linkage performance indicators in real time, accurately diagnosing bottlenecks and root causes using causal inference technology, constructing a multi-objective optimization model with instruction sets as the target, resource data as the constraint, and bottlenecks as the focus, and solving to generate execution solutions, and achieving iterative optimization of the model through execution feedback, a data-driven, causally-aware, and continuously evolving closed-loop collaborative decision-making system is formed, effectively improving the accuracy, dynamism, and overall efficiency of port-industry linkage. Attached Figure Description

[0051] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0052] Fig. 1 This is a flowchart illustrating a method for constructing a supply chain optimization model that links port logistics with urban industries.

[0053] Fig. 2 This is a schematic diagram of a data lake for port logistics and urban industrial supply chains.

[0054] Fig. 3 This is a diagram illustrating the triggering of a warning signal.

[0055] Fig. 4 This is a schematic diagram of the supply chain demand instruction set. Detailed Implementation

[0056] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0057] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0058] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0059] Reference Figs. 1-4As an embodiment of the present invention, this embodiment provides a method for constructing a supply chain optimization model that links port logistics with urban industries, including the following steps:

[0060] S1. Collect port logistics data, urban industry data, and urban consumption data, clean and integrate them to form a port logistics and urban industry supply chain data lake.

[0061] S1.1. Obtain port logistics data, urban industry data, and urban consumption data through sensing devices and data interfaces. Perform deduplication, error correction, and outlier processing on the port logistics data, urban industry data, and urban consumption data to obtain cleaned port logistics data, urban industry data, and urban consumption data.

[0062] Furthermore, by deploying IoT sensors on port cranes, yards, trucks, and warehouses, real-time data on equipment status, container displacement, and storage information is captured. Simultaneously, through application programming interfaces (APIs), the system connects to enterprise resource planning systems, warehouse management units, e-commerce platform databases, and sales terminals to obtain production plans, inventory levels, sales records, and consumption trend information. Redundant records are removed, logical errors are corrected, and abnormal values ​​exceeding reasonable ranges are filtered from the acquired port logistics data, urban industry data, and urban consumption data, ultimately resulting in cleaned port logistics data, urban industry data, and urban consumption data.

[0063] S1.2. Convert the cleaned port logistics data, urban industry data, and urban consumption data into a unified spatiotemporal format and unit of measurement to obtain standardized port logistics data, urban industry data, and urban consumption data.

[0064] Furthermore, the timestamps in the cleaned port logistics data, urban industry data, and urban consumption data are uniformly converted to Coordinated Universal Time (UTC) format. Geographic coordinates are mapped to a standard latitude and longitude coordinate system, and units of measurement such as cargo weight, volume, and value are uniformly converted to international standard units or industry-standard units, resulting in standardized port logistics data, urban industry data, and urban consumption data.

[0065] S1.3 Align and correlate the standardized port logistics data, urban industry data, and urban consumption data according to entities and time to obtain the integrated port logistics data, urban industry data, and urban consumption data.

[0066] Furthermore, based on unique entity identifiers such as container numbers, order numbers, and vehicle identification, standardized port logistics data, urban industry data, and urban consumption data are aligned sequentially at the same time granularity. Data links between port operation events, industrial production activities, and consumer orders are established through association rules to obtain integrated port logistics data, urban industry data, and urban consumption data.

[0067] S1.4. Persistently store the integrated port logistics data, urban industry data, and urban consumption data to form a port logistics and urban industry supply chain data lake.

[0068] Furthermore, a distributed columnar storage database is used to persistently store the integrated port logistics data, urban industry data, and urban consumption data by theme partitioning. The theme partitioning includes port operation partitioning, industry inventory partitioning, and consumption transaction partitioning, forming a port logistics and urban industry supply chain data lake.

[0069] S2. Based on urban consumption data in the port logistics and urban industrial supply chain data lake, conduct consumption demand forecasting and reverse-engineer it into a supply chain demand instruction set for industrial production and port operations.

[0070] S2.1 Extract urban consumption data for a one-year time frame from the port logistics and urban industrial supply chain data lake.

[0071] Furthermore, by using structured query language, complete historical records within the most recent year are extracted from the urban consumption data partitions of the port logistics and urban industrial supply chain data lake. These records include product categories, sales volume, transaction time, and geographical location information, thus completing the extraction of urban consumption data for the specified time range.

[0072] S2.2. Based on urban consumption data, construct derived features using association rule mining methods, train the derived features using a long short-term memory network model, and generate an urban consumption demand forecast report.

[0073] Furthermore, based on the extracted urban consumption data, the Apriori algorithm is used to mine association rules and construct derived features such as weekly sales moving average and regional demand distribution coefficient. Then, a long short-term memory network model is used to supervise the training of urban consumption data containing derived features, generating an urban consumption demand forecast report containing future multi-period category and regional demand forecasts.

[0074] S2.3. By collecting data on the maximum operating rate of port equipment, saturated capacity of storage yards, upper limit of road traffic capacity, maximum load of enterprise production lines, and size of transportation fleets, and after cleaning and standardization, capacity and transportation constraints are formed in the port logistics and urban industrial supply chain data lake.

[0075] Furthermore, by collecting physical upper limit data such as the rated working efficiency of port quay cranes, the maximum design capacity of the yard, the design traffic capacity of port access roads, the theoretical maximum output of enterprise production lines, and the total number of registered vehicles in the transportation fleet, and after undergoing the same processing procedures as data cleaning and standardization, the data is persistently stored in the resource constraint partition of the port logistics and urban industrial supply chain data lake, forming the capacity and transportation constraints in the port logistics and urban industrial supply chain data lake.

[0076] S2.4. Using the city's consumption demand forecast report as the optimization target, and combining the capacity and transportation constraints in the port logistics and city industrial supply chain data lake, the industrial production instruction set and port operation instruction set are obtained through mathematical programming.

[0077] The industrial production instruction set expression is:

[0078]

[0079] Where Pr is the industrial production instruction set, p is the product category, f is the unique identifier of the production line, and t is the production time cycle. The plan is to produce a specified quantity of a specified product at a specified time and in a specified factory. P is the set of product categories, F is the set of unique identifiers for production lines, and T is the set of production time cycles.

[0080] The subset expression for loading / unloading instructions is:

[0081]

[0082] Where Ps is a subset of loading and unloading instructions, and b is a unique identifier for the loading and unloading berth. B represents the quantity of a specified cargo to be loaded or unloaded at a specified time and at a specified berth, where B is the set of berths for loading and unloading operations.

[0083] The subset expression of the evacuation instructions is:

[0084]

[0085] Where Pd is a subset of transport instructions, and r is the transport route. The quantity of a specified goods to be transported at a specified time and along a specified route.

[0086] The expression for the port operation instruction set is:

[0087] Pe = Pd∪Ps;

[0088] Among them, Pe is the port operation instruction set.

[0089] Furthermore, the projected demand from the city's consumption demand forecast report is used as the optimization objective of the mathematical programming model, while the capacity and transportation constraints in the port logistics and industrial supply chain data lake are used as the model's constraints. A linear programming solver is employed to solve the model, outputting an industrial production instruction set and a port operation instruction set. The industrial production instruction set specifically specifies the planned production quantity of different product categories on different production lines within a specific production time period. The port operation instruction set consists of a loading and unloading instruction subset and a transportation instruction subset. The loading and unloading instruction subset specifies the planned loading and unloading volume of different goods at a specific berth within a specific time window, while the transportation instruction subset specifies the planned transportation volume of different goods via a specific route within a specific time window.

[0090] S2.5 Merge the industrial production instruction set with the port operation instruction set to form a supply chain demand instruction set.

[0091] Furthermore, the industrial production instruction set and the port operation instruction set are merged to form a supply chain demand instruction set. The industrial production instruction set includes product categories, unique identifiers for production lines, production time cycles, and planned quantities of specific products to be produced at designated factories at specified times. The port operation instruction set consists of a loading / unloading instruction subset and a transport instruction subset. The loading / unloading instruction subset includes unique identifiers for loading / unloading berths and the planned quantities of specific goods to be loaded / unloaded at designated berths at specified times. The transport instruction subset includes transport routes and the planned quantities of specific goods to be transported along designated routes at specified times. The merging process uses data stitching technology to align and integrate the industrial production instruction set and the port operation instruction set according to a unified time sequence and entity identifiers to generate the supply chain demand instruction set.

[0092] S3. Calculate and monitor the performance indicators of port logistics and urban industry linkage based on the supply chain demand instruction set, real-time data in the port logistics and urban industry supply chain data lake.

[0093] S3.1 Extract real-time port logistics data and real-time urban industry data from the port logistics and urban industry supply chain data lake. Based on historical operation cycle data, real-time ship AIS forecast data, enterprise production cycle data and road traffic forecast data in the port logistics and urban industry supply chain data lake, obtain the planned timeline in the supply chain demand instruction set through operations research planning.

[0094] Furthermore, the latest real-time port logistics data and urban industrial data are extracted from the real-time data partitions of the port logistics and urban industrial supply chain data lake. At the same time, historical operation cycle data is obtained from historical data partitions, real-time ship AIS forecast data and road traffic prediction data are received from external data interfaces, and production cycle data is collected from enterprise production data streams. Based on these multi-source data, the critical path method in operations research is used to plan the planned start time and planned end time of each operation activity in the supply chain demand instruction set, forming the planned timeline of the supply chain demand instruction set.

[0095] S3.2. Accurately align the planned timeline in the supply chain demand instruction set with the timestamps of real-time port logistics data and real-time urban industry data to form a planned-actual comparison dataset.

[0096] Furthermore, the planned timeline of each operation in the supply chain demand instruction set is aligned and matched with the timestamps of the actual operation start time, actual operation end time recorded in the port logistics real-time data, and the actual material delivery time and actual production start time recorded in the city industry real-time data with millisecond-level precision. A time series alignment algorithm is used to establish a line-by-line correspondence between planned values ​​and actual values, forming a planned-actual comparison dataset.

[0097] S3.3. Based on the planned-actual comparison dataset, time series pattern recognition and association rule mining techniques are used to extract port-side indicators, industry-side indicators, and linkage-side indicators. The port-side indicators, industry-side indicators, and linkage-side indicators are then summarized to form a set of linkage performance indicators.

[0098] Furthermore, based on the planned-actual comparison dataset, the time series decomposition algorithm is used to extract port-side indicators such as the average port vessel time and the average operating efficiency of quay cranes. The association rule mining algorithm is used to extract industry-side indicators such as raw material inventory turnover days and production plan completion rate. The correlation analysis method is used to extract linkage-side indicators such as port-production linkage response degree and transportation capacity resource matching degree. All extracted indicator data are collected, classified and stored to generate a structured linkage performance indicator set.

[0099] S3.4. The entropy weight method is used to assign weights to the indicators in the linkage performance indicator set, and the port-production linkage comprehensive index is calculated.

[0100] The expression for the Hong Kong-industry linkage composite index is:

[0101]

[0102] Wherein, G is the Hong Kong-industrial composite index, and w j Let r be the weight of the j-th indicator. jLet j be the standardized value of the j-th indicator in the current evaluation period, where j is the indicator index and n is the total number of indicators.

[0103] Furthermore, the entropy value of each indicator in the linkage performance index set is calculated using the entropy weight method, and the difference coefficient is calculated based on the entropy value. A weight coefficient is assigned to each indicator according to the magnitude of the difference coefficient. The standardized value of each indicator is linearly weighted and summed with the corresponding weight coefficient to calculate the comprehensive port-industry linkage index that comprehensively reflects the linkage level between the port and the industry.

[0104] S3.5. Set linkage thresholds by analyzing the historical linkage performance index set data in the port logistics and urban industrial supply chain data lake.

[0105] Furthermore, by statistically analyzing the historical linkage performance index data stored in the port logistics and urban industrial supply chain data lake, the historical average and standard deviation of the port-industry linkage comprehensive index are obtained, and the upper and lower limits of the linkage threshold are set by adding or subtracting twice the standard deviation from the historical average.

[0106] S3.6 Monitor the values ​​of the linkage performance index set and the port-production linkage comprehensive index. When the value of the linkage comprehensive index exceeds the linkage threshold, a warning signal is triggered.

[0107] Furthermore, the system continuously monitors the real-time values ​​of various indicators in the linkage performance index and the results of the port-production linkage comprehensive index. Through real-time data stream processing technology, the value of the port-production linkage comprehensive index is dynamically compared with the upper and lower limits of the linkage threshold. When the value of the port-production linkage comprehensive index is continuously higher than the upper limit of the linkage threshold or continuously lower than the lower limit of the linkage threshold, an early warning signal is automatically triggered.

[0108] S4. Based on performance indicators, a causal inference analysis technique is used to diagnose the bottlenecks and root causes of the linkage between port logistics and urban industries.

[0109] S4.1. Convergence cross-mapping analysis is performed on the average port time of port vessels and the number of days of raw material inventory of enterprises in the port-production linkage comprehensive index and the linkage performance index set. The causal strength and direction between the average port time of port vessels and the number of days of raw material inventory of enterprises are quantified. The convergence cross-mapping algorithm is used to calculate the causal contribution between the average port time of port vessels and the number of days of raw material inventory of enterprises.

[0110] The expression for causal contribution is:

[0111] TE X→Y =H(Y) future |Y past )-H(Y future |Y past ,X past );

[0112] Among them, TE X→Y To represent the causal contribution, X is the average time ships spend in port, and Y is the number of days the company has raw material inventory. future Y is the predicted number of days of raw material inventory for the enterprise at the next point in time. past To predict the future based on a set of historical data on raw material inventory days for a company, X past This refers to historical data on the average time vessels spend in port.

[0113] Furthermore, a convergent cross-mapping analysis is conducted on the average port vessel time series and the enterprise raw material inventory days time series in the linkage performance index set and the port-production linkage comprehensive index. By reconstructing the shadow manifolds of the average port vessel time and the enterprise raw material inventory days and calculating the prediction accuracy based on the manifold, the strength and direction of the causal influence of the average port vessel time on the enterprise raw material inventory days are quantified. The causal contribution between the average port vessel time and the enterprise raw material inventory days is calculated using the convergent cross-mapping algorithm.

[0114] S4.2 Based on causal contribution, identify the port vessel average time in port, port access road average speed and industrial raw material inventory turnover days as the indicators that have a concentrated impact on the port-industry linkage comprehensive index, thus forming bottleneck links.

[0115] Furthermore, based on causal contribution, the causal contribution of all indicators in the linkage performance index set is sorted and filtered to identify the indicators with the highest causal contribution: average port vessel dwell time, average port access road speed, and industrial raw material inventory turnover days. These indicators are then formally identified as the bottlenecks affecting the port-industry linkage comprehensive index.

[0116] S4.3. Perform correlation analysis between the bottleneck process and the planned-actual comparison dataset to locate the specific operational events of the bottleneck process and obtain the root cause analysis results.

[0117] Furthermore, the identified bottlenecks are correlated with the planned-actual comparison dataset for analysis. By using timestamp matching and event tracing methods, the specific operational events causing abnormal fluctuations in the bottlenecks are located. The decrease in the average traffic speed on the port access roads is correlated with traffic accident records or road maintenance operation records within a specific time period to obtain detailed root cause analysis results.

[0118] S4.4 Integrate the bottleneck links, causal strength, and root cause analysis results to form a bottleneck link and root cause diagnosis report for the linkage between port logistics and urban industries.

[0119] Furthermore, the identified bottleneck list, causal strength values, and root cause analysis results of specific operational events are integrated and compiled to generate a structured report on the bottlenecks and root causes of port logistics and urban industrial linkages.

[0120] S5. Taking the supply chain demand instruction set as the optimization objective, the resource data in the port logistics and urban industrial supply chain data lake as constraints, and the bottleneck links and root causes as the optimization focus, a multi-objective optimization model is constructed.

[0121] S5.1 Based on the supply chain demand instruction set and the bottleneck and root cause diagnosis report of port logistics and urban industry linkage, extract resource data from the port logistics and urban industry supply chain data lake.

[0122] Furthermore, based on the product categories, demand quantities, and delivery time requirements clearly defined in the supply chain demand instruction set, and combined with the bottleneck links and key bottleneck indicators identified in the root cause diagnosis report of port logistics and urban industry linkage, corresponding resource data such as the number of port berths, quay crane working efficiency, yard capacity, transport fleet size, road traffic capacity, production line capacity, and warehouse capacity are extracted from the resource data partitions of the port logistics and urban industry supply chain data lake, providing complete input parameters for the construction of the optimization model.

[0123] S5.2 By taking the supply chain demand instruction set as the target and resource data as the constraint, the bottleneck links in the port logistics and urban industry linkage and the bottlenecks in the root cause diagnosis report are mathematically compressed into enhanced constraints, and a multi-objective optimization model is constructed.

[0124] Furthermore, by setting the minimization of the total demand satisfaction and total cost of the supply chain demand instruction set as the main optimization objective, and using the extracted resource data as the capability constraints of the mathematical programming model, the bottlenecks in the linkage between port logistics and urban industries, as well as the quantitative characteristics of the bottlenecks in the root cause diagnosis report, are transformed into reinforcement constraints through a mathematical contraction mechanism. For example, the bottleneck of insufficient port access road capacity in the diagnosis report is transformed into an artificial contraction constraint on the upper limit of the road section's capacity. Thus, a mixed integer programming model containing multiple objective functions, resource capability constraints, and bottleneck reinforcement constraints is constructed.

[0125] S6. Solve the multi-objective optimization model to generate a supply chain optimization execution plan.

[0126] S6.1 Obtain the elite strategy by performing a non-dominated sort between the population in the current generation and the set of elite individuals produced in the previous generation.

[0127] Furthermore, by merging the population individuals in the current generation with the set of elite individuals generated during the previous generation's evolution, the merged population is sorted hierarchically according to the objective function value using a fast non-dominated sorting algorithm. The top-ranked non-dominated solutions are then selected based on crowding levels to form a new generation of elite strategy populations.

[0128] S6.2. The fast non-dominated sorting genetic algorithm with an elite strategy is used to solve the multi-objective optimization model and obtain the Pareto optimal solution set.

[0129] The Pareto optimal solution set is expressed as follows:

[0130]

[0131] in, Let x be the Pareto optimal solution set, and x be the decision variable vector. Let x be the set of feasible solutions. * This is the Pareto optimal solution.

[0132] Furthermore, a fast non-dominated sorting genetic algorithm with an elite strategy is used to iteratively solve the multi-objective optimization model. The population is continuously updated through selection, crossover, and mutation operations. Non-dominated sorting and crowding comparison are used to maintain the diversity and convergence of the solution set, and output a Pareto optimal solution set that approximates the Pareto front. Each solution represents an optimization scheme that achieves the best trade-off between total cost, total time, and bottleneck relief objectives.

[0133] S6.3 Using the criterion-based decision analysis method, the final solution is selected from the Pareto optimal solution set based on the preference weights of cost, timeliness, and bottleneck relief, thus forming a supply chain optimization execution plan.

[0134] Furthermore, using a multi-criteria decision analysis method, based on preference weights such as cost, timeliness, and bottleneck relief, the objective function values ​​of all solutions in the Pareto optimal solution set are weighted, standardized, and comprehensively scored. The solution with the highest comprehensive score is selected as the final solution, forming a supply chain optimization execution plan.

[0135] S7. Implement the supply chain optimization plan and feed the implementation effect data back to the port logistics and urban industrial supply chain data lake for iterative updates of the multi-objective optimization model.

[0136] S7.1. Distribute the supply chain optimization implementation plan to port operation terminals, transportation scheduling terminals and enterprise production terminals to drive actual operation, and collect new port logistics data and new urban industry data generated by the actual operation of the supply chain optimization implementation plan.

[0137] Furthermore, the industrial production instruction set and port operation instruction set included in the supply chain optimization execution plan are distributed to the enterprise production execution terminal, port operation terminal and transportation management terminal respectively through standard data interfaces to drive actual production, loading and unloading and transportation operations. Through IoT sensing devices and business database interfaces, new port logistics data and new urban industrial data generated after the execution of the plan are collected, such as the actual operation time of port vessels, real-time inventory in the yard, truck transportation trajectory, actual output of production line and warehouse entry and exit records.

[0138] S7.2. Transfer new port logistics data and new urban industry data back to the port logistics and urban industry supply chain data lake for storage.

[0139] Furthermore, the collected new port logistics data and new urban industry data are transmitted through data pipelines to the real-time data partitions of the port logistics and urban industry supply chain data lake, and the data is converted and partitioned according to the original schema specifications of the data lake to achieve persistent feedback of execution effect data.

[0140] S7.3. Based on historical and new data in the port logistics and urban industrial supply chain data lake, the parameters and weights of the multi-objective optimization model are recalibrated.

[0141] Furthermore, based on historical data accumulated in the port logistics and urban industrial supply chain data lake, as well as new feedback data on port logistics and urban industries, the Bayesian optimization method is used to recalibrate the objective function weight coefficients and constraint compression parameters in the multi-objective optimization model, so that the parameters of the multi-objective optimization model are more in line with the changes in the actual operating environment.

[0142] S7.4 Utilize the updated multi-objective optimization model to generate a new generation of supply chain optimization execution plans, initiating a new round of optimization cycle.

[0143] Furthermore, the multi-objective optimization model with recalibrated parameters is used to solve the problem again, generating a new generation of supply chain optimization execution plan. This plan is then put into practical application, thereby initiating a new closed-loop cycle of data collection, feedback, parameter updates, and plan optimization.

[0144] This embodiment also provides a computer device applicable to a method for constructing a supply chain optimization model linking port logistics and urban industries, comprising: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize the method for constructing a supply chain optimization model linking port logistics and urban industries as proposed in the above embodiment.

[0145] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0146] This embodiment also provides a storage medium storing a computer program. When executed by a processor, the program implements a supply chain optimization model construction method for linking port logistics and urban industries, as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0147] In summary, this invention constructs a supply chain data lake by collecting and integrating multi-source data, predicts and generates demand instruction sets based on consumption data, calculates and monitors linkage performance indicators in real time, and uses causal inference technology to accurately diagnose bottlenecks and their root causes. It constructs a multi-objective optimization model with instruction sets as the target, resource data as the constraint, and bottlenecks as the focus, and solves the model to generate execution solutions. Through execution feedback, it achieves iterative optimization of the model, forming a data-driven, causally-aware, and continuously evolving closed-loop collaborative decision-making system, which effectively improves the accuracy, dynamism, and overall efficiency of port-industry linkage.

[0148] 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, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for constructing a supply chain optimization model that links port logistics with urban industries, characterized in that: This includes collecting port logistics data, urban industry data, and urban consumption data, cleaning and integrating them to form a data lake for port logistics and urban industrial supply chains; Based on urban consumption data in the port logistics and urban industrial supply chain data lake, we forecast consumption demand and inversely transform it into a set of supply chain demand instructions for industrial production and port operations. Based on the supply chain demand instruction set and real-time data from the port logistics and urban industrial supply chain data lake, calculate and monitor the performance indicators of the linkage between port logistics and urban industries. Based on performance indicators, a causal inference analysis technique is used to diagnose the bottlenecks and root causes of the linkage between port logistics and urban industries. By taking the supply chain demand instruction set as the optimization objective, the resource data in the port logistics and urban industrial supply chain data lake as the constraints, and the bottleneck links and root causes as the optimization focus, a multi-objective optimization model is constructed, the multi-objective optimization model is solved, and a supply chain optimization execution plan is generated. Implement supply chain optimization plans and feed the implementation results data back to the port logistics and urban industrial supply chain data lake for iterative updates to the multi-objective optimization model.

2. The method for constructing a supply chain optimization model linking port logistics and urban industries as described in claim 1, characterized in that: The process involves collecting port logistics data, urban industry data, and urban consumption data, cleaning and integrating them to form a port logistics and urban industrial supply chain data lake. This includes the following steps: Port logistics data, urban industry data, and urban consumption data are acquired through sensing devices and data interfaces. The data is then deduplicated, corrected for errors, and processed for outliers to obtain cleaned port logistics data, urban industry data, and urban consumption data. The cleaned port logistics data, urban industry data, and urban consumption data are converted into a unified spatiotemporal format and unit of measurement to obtain standardized port logistics data, urban industry data, and urban consumption data. The standardized port logistics data, urban industry data, and urban consumption data are aligned and correlated according to entities and time to obtain integrated port logistics data, urban industry data, and urban consumption data. The integrated port logistics data, urban industry data, and urban consumption data will be persistently stored to form a data lake for port logistics and urban industry supply chains.

3. The method for constructing a supply chain optimization model linking port logistics and urban industries as described in claim 2, characterized in that: Based on urban consumption data from port logistics and urban industrial supply chain data lakes, consumer demand is predicted and then reverse-engineered into a set of supply chain demand instructions for industrial production and port operations. This includes the following steps: Extract urban consumption data over a one-year timeframe from the port logistics and urban industrial supply chain data lake; Based on urban consumption data, association rule mining methods are used to construct derived features, and a long short-term memory network model is used to train the derived features to generate an urban consumption demand forecast report. By collecting data on the maximum operating rate of port equipment, saturated capacity of storage yards, upper limit of road traffic capacity, maximum load of enterprise production lines, and size of transport fleets, and after cleaning and standardization, capacity and transport constraints are formed in the port logistics and urban industrial supply chain data lake. Using the city's consumer demand forecast report as the optimization target, and combining the capacity and transportation constraints in the port logistics and city industrial supply chain data lake, the industrial production instruction set and port operation instruction set are obtained through mathematical programming. The industrial production instruction set and the port operation instruction set are merged to form the supply chain demand instruction set.

4. The method for constructing a supply chain optimization model linking port logistics and urban industries as described in claim 3, characterized in that: Based on the supply chain demand instruction set and real-time data from the port logistics and urban industrial supply chain data lake, performance indicators for the linkage between port logistics and urban industries are calculated and monitored, including the following steps. Real-time port logistics data and real-time urban industry data are extracted from the port logistics and urban industry supply chain data lake. Based on historical operation cycle data, real-time ship AIS forecast data, enterprise production cycle data and road traffic forecast data in the port logistics and urban industry supply chain data lake, the planned timeline of the supply chain demand instruction set is obtained through operations research planning. The planned timeline in the supply chain demand instruction set is precisely aligned with the timestamps of real-time port logistics data and real-time urban industry data to form a planned-actual comparison dataset. Based on the planned-actual comparison dataset, time series pattern recognition and association rule mining techniques are used to extract port-side indicators, industry-side indicators, and linkage-side indicators. The port-side indicators, industry-side indicators, and linkage-side indicators are then summarized to form a linkage performance indicator set. The entropy weight method is used to assign weights to the indicators in the linkage performance index set, and the port-production linkage comprehensive index is calculated. A linkage threshold was set by analyzing historical linkage performance index data in the port logistics and urban industrial supply chain data lake. Monitor the values ​​of the linkage performance indicator set and the port-production linkage comprehensive index. When the value of the linkage comprehensive index exceeds the linkage threshold, an early warning signal is triggered.

5. The method for constructing a supply chain optimization model linking port logistics and urban industries as described in claim 4, characterized in that: Based on performance indicators, a causal inference analysis technique is used to diagnose the bottlenecks and root causes in the linkage between port logistics and urban industries. The diagnostic report includes the following steps: A convergent cross-mapping analysis was conducted on the average port time of port vessels and the number of days of raw material inventory of enterprises in the port-production linkage comprehensive index and the linkage performance index set. The causal strength and direction between the average port time of port vessels and the number of days of raw material inventory of enterprises were quantified. The convergent cross-mapping algorithm was used to calculate the causal contribution between the average port time of port vessels and the number of days of raw material inventory of enterprises. Based on the causal contribution, the indicators that have a concentrated impact on the port-industry linkage performance index, namely the average port vessel time in port, the average speed of port access roads, and the inventory turnover days of industrial raw materials, are identified as bottleneck links. By performing correlation analysis between the bottleneck process and the planned-actual comparison dataset, the specific operational events of the bottleneck process can be located, and the root cause analysis results can be obtained. The bottleneck links, causal strength, and root cause analysis results are integrated to form a bottleneck link and root cause diagnosis report for the linkage between port logistics and urban industries.

6. The method for constructing a supply chain optimization model linking port logistics and urban industries as described in claim 5, characterized in that: Using the supply chain demand instruction set as the optimization objective, resource data from the port logistics and urban industrial supply chain data lake as constraints, and bottlenecks and root causes as the optimization focus, a multi-objective optimization model is constructed, including the following steps. Based on the supply chain demand instruction set and the bottleneck and root cause diagnosis report of the linkage between port logistics and urban industries, resource data is extracted from the port logistics and urban industrial supply chain data lake. By taking the supply chain demand instruction set as the target and resource data as the constraint, the bottleneck links in the linkage between port logistics and urban industries and the bottlenecks in the root cause diagnosis report are mathematically compressed into enhanced constraints, and a multi-objective optimization model is constructed.

7. The method for constructing a supply chain optimization model linking port logistics and urban industries as described in claim 6, characterized in that: Solving the multi-objective optimization model to generate a supply chain optimization execution plan includes the following steps: Elite strategies are obtained by performing a non-dominated ranking between the population in the current generation and the set of elite individuals produced in the previous generation. A fast non-dominated sorting genetic algorithm using an elite strategy is used to solve a multi-objective optimization model, yielding a Pareto optimal solution set. The criterion-based decision analysis method selects the final solution from the Pareto optimal solution set based on the preference weights of cost, timeliness, and bottleneck relief, thus forming a supply chain optimization execution plan.

8. The method for constructing a supply chain optimization model linking port logistics and urban industries as described in claim 6, characterized in that, Implement the supply chain optimization plan and feed the implementation results data back to the port logistics and urban industrial supply chain data lake. Iterate and update the multi-objective optimization model, including the following steps: The supply chain optimization implementation plan is distributed to port operation terminals, transportation scheduling terminals and enterprise production terminals to drive actual operation, and new port logistics data and new urban industrial data generated by the actual operation of the supply chain optimization implementation plan are collected. New port logistics data and new urban industry data are transmitted back to the port logistics and urban industry supply chain data lake for storage. Based on historical and new data from the port logistics and urban industrial supply chain data lake, the parameters and weights of the multi-objective optimization model are recalibrated. By utilizing the updated multi-objective optimization model, a new generation of supply chain optimization execution solutions is generated, initiating a new round of optimization cycles.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the method for constructing a supply chain optimization model that links port logistics and urban industries as described in any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the method for constructing a supply chain optimization model that links port logistics and urban industries as described in any one of claims 1 to 8.

Images