Artificial intelligence-based cargo transportation path planning method for automatic warehouse logistics

Abstract

The invention relates to an artificial intelligence-based cargo transportation path planning method and system for automatic warehouse logistics. The method comprises the steps of performing weighted scoring calculation based on customer historical transaction data and cargo attributes, and generating service label data for distinguishing a high-value hierarchy and a common hierarchy; a differentiation algorithm strategy is called according to the service label, an exclusive transportation path is distributed to the high-value goods, obstacle avoidance is optimized in real time, and adjacent orders are matched for common goods to be merged and distributed; in combination with real-time road conditions and storage scheduling data, through path weight dynamic calculation and genetic algorithm iterative optimization, generating a global transportation scheme considering both time efficiency and cost; customer preference parameters are updated in a closed loop mode based on execution feedback data, and system self-adaptive learning is achieved. According to the method, the problems that differentiated services, dynamic response to environment changes and low-efficiency resource utilization cannot be achieved in a traditional method are solved, the punctuality rate of high-value orders and common orders can be increased, and meanwhile the transportation cost of the common orders can be reduced.

Description

Technical Field

[0001] The present invention relates to the field of warehouse freight planning, and particularly to a method for planning the transportation path of goods based on artificial intelligence in an automated warehousing and logistics system. Background Art

[0002] With the rapid development of e-commerce and intelligent manufacturing, automated warehousing and logistics systems are faced with the demand for efficient distribution of a large number of orders. In a complex warehousing environment, the planning of the goods transportation path directly affects logistics costs, distribution timeliness, and customer satisfaction. Traditional path planning methods usually rely on fixed rules (such as shortest path first) or static algorithms, and generate a unified transportation plan for all orders through the analysis of historical data. Although such methods can meet the basic distribution requirements, they lack flexibility and intelligent decision-making capabilities when dealing with dynamic environmental changes (such as sudden traffic congestion, order priority differences), and it is particularly difficult to achieve optimized resource allocation for different value customers.

[0003] In the prior art, most warehousing and logistics systems still adopt a "one-size-fits-all" path planning mode, making it difficult to balance the timeliness requirements of high-value orders and the cost control objectives of low-value orders. For example, high-value goods (such as pharmaceutical cold-chain materials) may experience temperature control failure due to path congestion because they cannot obtain priority path resources; while the independent distribution of low-value orders results in a too high vehicle empty load rate and significant energy waste. At the same time, traditional methods rely on offline calculations and manual interventions, making it difficult to respond in a timely manner to real-time road conditions changes, and lacking a closed-loop learning mechanism for historical execution data, resulting in the system being in a static strategy state for a long time and unable to adapt to the dynamic changes in customer needs. Summary of the Invention

[0004] Based on this, the object of the present invention is to provide a method for planning the transportation path of goods based on artificial intelligence in an automated warehousing and logistics system, which can achieve differential service grading, dynamic path optimization, and intelligent resource scheduling.

[0005] The object of the present invention is achieved by the following solutions:

[0006] In the first aspect, the present invention provides a method for planning the transportation path of goods based on artificial intelligence in an automated warehousing and logistics system, including the following steps:

[0007] S1: Perform weighted scoring calculations on the obtained customer historical transaction records and real-time goods data to obtain service level label data corresponding to the goods data, and the service level label data includes a high-value level and a normal level;

[0008] S2: Based on the service level label data, call the priority path algorithm to optimize the path of the high-value level cargo data, generate the initial transportation plan data, and call the shared transportation matching algorithm to match the path of the general-level cargo data to generate the merged order data;

[0009] S3: Based on the real-time traffic condition data and the warehousing scheduling data, perform path weight calculation processing on the initial transportation plan data to obtain the total path weight data; identify whether the total path weight data exceeds the preset dynamic optimization threshold. If it exceeds, based on the dynamic route optimization algorithm, perform optimization processing on the initial transportation plan data to generate the sub-optimal path data;

[0010] S4: Based on the genetic algorithm, perform iterative optimization processing on the sub-optimal path data and the merged order data to generate the final personalized transportation plan data;

[0011] S5: According to the execution status data of the final personalized transportation plan, process the actual delay time and cost data of the transportation path, and update the customer's historical transaction records.

[0012] In one embodiment, S1 of the method for planning the cargo transportation path based on artificial intelligence in an automated warehousing and logistics provided by the present invention specifically includes the following steps:

[0013] S11: Assign preset weight coefficients to the transaction frequency and transaction amount in the customer's historical transaction records respectively, and perform linear weighted summation calculation processing to generate customer value index data;

[0014] S12: Perform user-cargo parameter matching and service level analysis on the customer value index data and the cargo weight, volume, and urgency parameters of the real-time cargo data to generate service level score data for different user cargo data;

[0015] S13: According to the preset score threshold, perform classification and determination processing on each service level score data to obtain the service level label data corresponding to the cargo data.

[0016] In one embodiment, S3 of the method for planning the cargo transportation path based on artificial intelligence in an automated warehousing and logistics provided by the present invention specifically includes the following steps:

[0017] S31: Based on the traffic flow monitoring interface and the weather forecast interface, obtain the real-time traffic condition data including road passage time data and weather disaster warning data; and based on the warehousing management system, obtain the warehousing scheduling data including inventory location coordinate data;

[0018] S32: Combine the real-time traffic condition data and the warehousing scheduling data to generate real-time dynamic environment parameters;

[0019] S33: Quantitatively evaluate the time cost and risk coefficient of each path node in the initial transportation plan data based on real-time dynamic environmental parameters, and generate total path weight data;

[0020] S34: Identify whether the total path weight data exceeds the preset dynamic optimization threshold. If it exceeds, optimize the initial transportation plan data based on the dynamic route optimization algorithm to generate sub-optimal path data.

[0021] In one embodiment, step S33 of the method for planning a goods transportation path based on artificial intelligence in an automated warehousing and logistics provided by the present invention specifically includes the following steps:

[0022] S331: Conduct a risk analysis on each path node of the initial transportation plan based on real-time dynamic environmental parameters, and retrieve detour paths for path nodes with congestion or high weather risks to generate an alternative path set;

[0023] S332: Perform multi-objective cost calculation on the travel time and energy consumption data in the alternative path set to generate path priority ranking data;

[0024] S333: Select the path with the lowest comprehensive cost as the sub-optimal path data according to the path priority ranking data.

[0025] In one embodiment, step S5 of the method for planning a goods transportation path based on artificial intelligence in an automated warehousing and logistics provided by the present invention specifically includes the following steps:

[0026] S51: Perform real-time trajectory tracking on the actual driving path of the final personalized transportation plan, collect transportation delay time and fuel consumption data, and generate execution deviation value data;

[0027] S52: Identify whether the execution deviation value data exceeds the preset safety warning threshold. If it exceeds, dynamically calibrate the execution status data of the final personalized transportation plan based on the root cause analysis model to generate an anomaly detection result;

[0028] S53: Update the transportation preference parameters of the customer's historical transaction records based on the anomaly detection result.

[0029] In a second aspect, the present invention provides an automated warehousing and logistics goods transportation path planning system based on artificial intelligence, including:

[0030] A goods level evaluation module, configured to perform weighted scoring calculation on the obtained customer historical transaction records and real-time goods data to obtain service level label data corresponding to the goods data. The service level label data includes a high-value level and a normal level;

[0031] A hierarchical path generation module, which is used to optimize the path of the cargo data at the high-value level based on the service hierarchical label data by calling the priority path algorithm, generate the initial transportation plan data, and call the shared transportation matching algorithm to match the cargo data at the ordinary level to generate the merged order data;

[0032] A dynamic path optimization module, which is used to calculate the path weight of the initial transportation plan data based on the real-time road condition data and the warehousing scheduling data to obtain the total path weight data; identify whether the total path weight data exceeds the preset dynamic optimization threshold. If it exceeds, optimize the initial transportation plan data based on the dynamic route optimization algorithm to generate the sub-optimal path data;

[0033] A personalized transportation generation module, which is used to iteratively optimize the sub-optimal path data and the merged order data based on the genetic algorithm to generate the final personalized transportation plan data;

[0034] A user transaction update module, which is used to process the actual delay time and cost data of the transportation path according to the execution status data of the final personalized transportation plan and update the customer historical transaction record.

[0035] In a third aspect, the present application provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements any one of the above-mentioned artificial intelligence-based cargo transportation path planning methods for automated warehousing logistics.

[0036] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements any one of the above-mentioned artificial intelligence-based cargo transportation path planning methods for automated warehousing logistics.

[0037] In summary, the artificial intelligence-based cargo transportation path planning method for automated warehousing logistics provided by the present invention can achieve accurate classification of customer goods, efficient transportation path planning, dynamic optimization adjustment, and generation of personalized service plans through scientific and reasonable technical methods and algorithm applications. From the in-depth mining and analysis of customer historical data and real-time cargo data, to the application of various intelligent optimization technologies such as the priority path algorithm, the shared transportation matching algorithm, the dynamic route optimization algorithm, and the genetic algorithm, the entire process can fully consider various factors such as cargo value, transportation cost, time limit, real-time road conditions, etc., and provide differentiated high-quality transportation services for customers at different levels. At the same time, by continuously feedbacking and updating the customer historical transaction record, it can achieve the continuous improvement and optimization of the transportation service, improve customer satisfaction and transportation efficiency, reduce transportation costs, and enhance the competitiveness of the enterprise in the market.

[0038] For better understanding and implementation, the present invention will be described in detail below with reference to the accompanying drawings. Brief Description of the Drawings

[0039] Figure 1 It is a schematic flowchart of a method for planning a cargo transportation path based on artificial intelligence in an automated warehousing and logistics provided by an embodiment of the present application;

[0040] Figure 2 It is a schematic flowchart of generating sub - optimal path data provided by an embodiment of the present application;

[0041] Figure 3 It is a schematic structural diagram of a system for planning a cargo transportation path based on artificial intelligence in an automated warehousing and logistics provided by another embodiment of the present application. Detailed Embodiment

[0042] For ease of understanding of the present invention, the present invention will be described more comprehensively below with reference to the relevant drawings. Preferred embodiments of the present invention are shown in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, these embodiments are provided so that the understanding of the disclosure of the invention is more thorough and comprehensive.

[0043] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs. The terms used in the description of the present invention herein are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0044] In one embodiment, as Figure 1 shown, a method for planning a cargo transportation path based on artificial intelligence in an automated warehousing and logistics is provided. In this embodiment, it is exemplified that the method is applied to a terminal. It can be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is realized through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0045] S1: Perform weighted scoring calculation on the obtained customer historical transaction records and real - time cargo data to obtain service - level label data corresponding to the cargo data. The service - level label data includes a high - value level and a normal level.

[0046] Specifically, the system obtains customer historical transaction records from the warehouse management system and the order management system, including information such as transaction frequency, transaction amount, cargo type, customer credit rating, etc.; at the same time, real - time cargo data is obtained, such as cargo weight, volume, shelf life, transportation priority, etc. Then, these data are cleaned to remove outliers, missing values and normalized.

[0047] Preferably, the system can use a weighted scoring algorithm to calculate the integrated data. First, determine the weights of each influencing factor. For example, the weight of the transaction amount is 0.4, the weight of the transaction frequency is 0.3, the weight of the goods value is 0.2, the weight of the delivery time requirement is 0.1, etc. The weight distribution can be flexibly adjusted according to business priorities and customer needs. Then, the system standardizes each factor to eliminate the influence of dimension and dimension unit, making different factors comparable. Finally, based on the determined weight parameters, calculate the weighted score of each goods data, and set a threshold according to the comprehensive score result to divide the service levels. Specifically, the system marks the goods with higher scores as the high-value level. These goods usually have higher economic value, urgent transportation needs, or special requirements for storage conditions; while the goods with lower scores are marked as the ordinary level. For example, pharmaceutical cold chain materials may be classified as the high-value level due to their short shelf life and high economic value; while ordinary daily necessities belong to the ordinary level.

[0048] S2: Based on the service level label data, call the priority path algorithm to optimize the path of the high-value level goods data, generate the initial transportation plan data, and call the shared transportation matching algorithm to match the path of the ordinary level goods data to generate the combined order data.

[0049] Specifically, for the high-value level goods data, the system calls the priority path algorithm for path optimization. This algorithm comprehensively considers factors such as the urgency of the goods, the distance to the destination, traffic conditions, and warehouse layout, and gives priority to finding the optimal path for high-value goods. For example, for urgent high-value goods, the algorithm will preferentially select the shortest and traffic-smooth route to ensure that the goods can be quickly and safely delivered to the destination. According to the calculation results of the priority path algorithm, the system generates the initial transportation plan data for high-value goods. Specifically, the initial transportation plan data details information such as the transportation route of the goods, the estimated departure and arrival times, the selection of transportation tools, and the operation instructions for each node, ensuring that high-value goods are given priority and efficiently distributed throughout the transportation process.

[0050] For the ordinary-level cargo data, the system calls the shared transportation matching algorithm for route matching. Based on factors such as the similarity of the cargo destinations, the consistency of the transportation directions, and the volume and weight of the cargo, this algorithm integrates multiple ordinary orders. For example, goods going to the same area can be grouped through clustering analysis, or goods going the same way can be matched according to the transportation direction to achieve the shared utilization of transportation resources. According to the matching results of the shared transportation matching algorithm, the system generates merged order data. The merged order data not only contains the transportation information of multiple ordinary goods but also optimizes the transportation route, thereby reducing the empty mileage during transportation, lowering the transportation cost while improving the transportation efficiency, enabling ordinary goods to be delivered in a more economical and reasonable manner.

[0051] S3: Calculate the path weight for the initial transportation plan data based on the real-time traffic condition data and the warehousing scheduling data to obtain the total path weight data; identify whether the total path weight data exceeds the preset dynamic optimization threshold. If it exceeds, optimize the initial transportation plan data based on the dynamic route optimization algorithm to generate the sub-optimal path data.

[0052] Specifically, the system obtains the real-time traffic condition data from the traffic information platform, including road congestion, traffic accident information, road construction conditions, etc.; at the same time, the system synchronously obtains the warehousing scheduling data from the warehousing management system, such as the inbound and outbound status of warehouse goods, inventory levels, equipment operation conditions, etc. Combining these real-time data with the initial transportation plan data provides comprehensive data support for path weight calculation.

[0053] Specifically, the system assigns a comprehensive weight value to each transportation path through the analysis and processing of these data. This weight value reflects the feasibility and quality of the path. Then, identify whether the total path weight data exceeds the preset dynamic optimization threshold. If it exceeds, optimize the initial transportation plan data based on the dynamic route optimization algorithm to generate the sub-optimal path data. The dynamic route optimization algorithm can analyze the current traffic conditions and warehousing situations in real time, re-plan the transportation path, and find a better route combination. For example, the algorithm may choose to bypass congested sections or adjust the transfer order of goods between different warehouses to reduce the total path weight and improve the transportation efficiency, ultimately generating the sub-optimal path data.

[0054] S4: Perform iterative optimization on the sub-optimal path data and the merged order data based on the genetic algorithm to generate the final personalized transportation plan data.

[0055] Specifically, the system first initializes the parameters of the genetic algorithm, sets the relevant parameters of the genetic algorithm, such as population size, crossover probability, mutation probability, etc. The population size determines the search scope of the algorithm, while the crossover probability and mutation probability affect the exploration ability of the algorithm. According to the scale and complexity of the actual problem, the system selects the genetic-related parameters to ensure that the algorithm can find high-quality solutions within a limited number of iterations. After initialization, the system constructs a fitness function to evaluate the quality of solutions in each generation. The fitness function comprehensively considers multiple factors such as transportation cost, transportation time, timeliness requirements of goods, and vehicle utilization rate. For example, for high-value goods, the weight of transportation time may be higher; while for ordinary goods, the weight of transportation cost may be greater. Through the fitness function, the genetic algorithm can screen out better transportation plans.

[0056] Specifically, the system takes the sub-optimal path data and combined order data as the initial population and substitutes them into the genetic algorithm for iterative optimization. In each generation of iteration, new populations are generated through operations such as selection, crossover, and mutation. The selection operation selects better individuals as parents according to the values of the fitness function; the crossover operation exchanges and combines the genes of parent individuals to generate new offspring individuals; the mutation operation randomly changes individual genes to increase the diversity of the population. After multiple generations of iteration, the algorithm gradually converges to a high-quality solution, that is, the final personalized transportation plan data. The obtained final personalized transportation plan data comprehensively considers various factors and provides the optimal transportation path and distribution arrangement for goods at different levels. This plan can not only meet the timeliness requirements of high-value goods but also reduce the overall transportation cost and improve the operation efficiency of the logistics system while ensuring the transportation quality.

[0057] S5: Process the actual delay time and cost data of the transportation path according to the execution status data of the final personalized transportation plan, and update the customer historical transaction records.

[0058] Specifically, the system obtains the execution status data of the final personalized transportation plan from the logistics execution system, including the actual departure time, arrival time of the goods, whether there are delays during transportation, cost information such as vehicle fuel consumption and tolls, and further refines the actual delay time and cost data of the transportation path. Analyze the reasons for delays, such as traffic congestion, bad weather, loading and unloading delays, etc., and classify and count the time of different types of delays; at the same time, decompose the cost data to clarify the components of transportation costs, such as fuel costs, tolls, labor costs, etc., and the changes in each part of the cost.

[0059] The system will then feed back the actual delay time and cost data to the customer's historical transaction records and update the customer's information. For example, if a customer frequently experiences transportation delays, their service priority weight may be reduced in the historical transaction records; on the contrary, for customers with good transportation records, their weight may be increased, thereby reflecting differentiated service strategies in subsequent service level division and route planning, and achieving dynamic response to customer needs and precise service.

[0060] In summary, the automated warehousing logistics and artificial intelligence-based cargo transportation path planning method provided by the present invention can achieve accurate classification of customer goods, efficient transportation path planning, dynamic optimization adjustment, and generation of personalized service solutions through the application of scientific and reasonable technical methods and algorithms. From the in-depth mining and analysis of customer historical data and real-time cargo data to the use of various intelligent optimization technologies such as priority path algorithms, shared transportation matching algorithms, dynamic route optimization algorithms, and genetic algorithms, the entire process can fully consider various factors, such as cargo value, transportation costs, time limits, real-time road conditions, etc., to provide differentiated high-quality transportation services for customers at different levels. At the same time, by continuously feeding back and updating customer historical transaction records, continuous improvement and optimization of transportation services can be achieved, which improves customer satisfaction and transportation efficiency, reduces transportation costs, and enhances the competitiveness of enterprises in the market.

[0061] In one embodiment, the method S1 of an automated warehousing logistics based on artificial intelligence cargo transportation path planning method provided by the present invention specifically includes the following steps:

[0062] S11: Assign preset weight coefficients to the transaction frequency and transaction amount in the customer's historical transaction records, perform linear weighted summation calculation processing, and generate customer value index data.

[0063] Specifically, customers’ historical transaction records can be obtained from the company’s customer relationship management system (CRM) and order management system, including transaction date, transaction amount, transaction frequency, etc. These data are cleaned and sorted to remove outliers and duplicate records to ensure data accuracy and completeness.

[0064] Specifically, the system determines the weight coefficients of the transaction frequency and transaction amount according to the characteristics of the logistics business and customer requirements. For example, for some customers with high requirements for timeliness, the weight of the transaction frequency may be relatively high; while for some large customers with a large single transaction amount, the weight of the transaction amount may be relatively high. The setting of the weight coefficients can be based on historical data analysis and industry experience, or can be optimized through methods such as machine learning. Subsequently, the system multiplies the preprocessed transaction frequency and transaction amount data by the corresponding weight coefficients respectively, and then performs a summation calculation to generate customer value index data. The customer value index can comprehensively reflect the contribution degree and importance of customers to the enterprise, providing a basis for subsequent service level division.

[0065] S12: Perform user-cargo parameter matching and service level analysis on the cargo weight, volume, and urgency parameters of the customer value index data and real-time cargo data to generate service level score data for different user-cargo data.

[0066] Specifically, the system performs an associated match between the customer value index data and the real-time cargo data, that is, binds the cargo information of the same customer to the value index of this customer. At the same time, key parameters such as the weight, volume, and urgency of the cargo are extracted, and these parameters will serve as important bases for calculating the service level score. For example, a batch of urgent, light, and small cargo of a high-value customer may obtain a relatively high service level score.

[0067] Based on the above parameters, the system constructs a service level analysis model, which comprehensively considers the impacts of multiple factors such as the customer value index, cargo weight, volume, and urgency on the service level. The relative importance of each factor is determined through the analytic hierarchy process, and corresponding evaluation criteria and index systems are established. For example, the urgency may account for a relatively large weight in the service level score because urgent cargo usually needs to be processed preferentially and transported quickly. The system performs a comprehensive calculation on the matched user-cargo parameters according to the service level analysis model to generate service level score data. This score data can reflect the priority and resource allocation requirements of the cargo in the transportation service, providing a quantitative basis for subsequent service level division. For example, cargo with a higher score may need to enjoy a higher service level, such as priority distribution, exclusive transportation channels, etc.

[0068] S13: Perform a classification determination process on each service level score data according to a preset score threshold to obtain service level label data corresponding to the cargo data.

[0069] Specifically, the system sets the threshold of the service level score according to the service strategy and resource allocation of the enterprise. For example, goods with a score higher than 80 points can be classified into the high-value level, and goods with a score lower than 80 points can be classified into the ordinary level. The setting of the threshold should be combined with historical data and business requirements to ensure that goods at different service levels can be reasonably distinguished. Compare the service level score data with the preset score threshold to classify and determine the goods. Goods with a score higher than the threshold are marked as the high-value level. These goods usually have high customer value, urgent transportation needs, or special goods characteristics and require better-quality services and priority resource allocation; goods with a score lower than or equal to the threshold are marked as the ordinary level and are processed according to the regular transportation service process.

[0070] After completing the goods classification, the system generates service level label data corresponding to the goods data according to the classification and determination results. This label data will be an important basis for subsequent path planning and transportation plan formulation, ensuring that goods at different service levels can receive corresponding transportation service arrangements, meeting the diverse needs of customers, and improving customer satisfaction and enterprise competitiveness.

[0071] In one embodiment, as Figure 2 shown, step S3 of the goods transportation path planning method based on artificial intelligence for an automated warehousing and logistics provided by the present invention specifically includes the following steps:

[0072] S31: Based on the traffic flow monitoring interface and the weather forecast interface, obtain real-time road condition data including road travel time data and weather disaster warning data; and based on the warehouse management system, obtain warehouse scheduling data including inventory location coordinate data.

[0073] Specifically, through the traffic flow monitoring interface and the weather forecast interface, real-time road condition data including road travel time data and weather disaster warning data can be obtained. The traffic flow monitoring interface can provide real-time information such as the traffic flow, average vehicle speed, and congestion degree of each road section, while the weather forecast interface provides the weather conditions for a period of time in the future, including meteorological information such as rainfall, snowfall, and strong winds that may affect road traffic. At the same time, based on the warehouse management system, warehouse scheduling data including inventory location coordinate data is obtained. These data cover key information such as the specific storage location of goods in the warehouse, inbound and outbound plans, and the loading and unloading capacity of the warehouse, which helps to understand the warehouse storage status and scheduling possibilities of the goods.

[0074] S32: Combine the real-time road condition data and the warehouse scheduling data to generate real-time dynamic environment parameters.

[0075] Specifically, the system deeply combines real-time traffic data and warehousing scheduling data, and unifies and correlates data from different sources through a data fusion algorithm. For example, it combines road travel time data with the location information of the warehouse to determine the optimal route from the warehouse to each transportation node; it correlates weather disaster warning data with the storage location and transportation priority of goods to evaluate the impact of bad weather on the transportation of different goods. Subsequently, the system extracts key parameters from the fused data, such as road congestion degree, weather impact factor, warehouse goods distribution density, etc., and performs corresponding calculations and processing. For example, it calculates the congestion index of each road section based on traffic flow data to measure the smoothness of the road; it calculates the weather risk coefficient based on weather data to reflect the impact of weather on transportation safety and timeliness; it calculates the available time of goods based on warehousing scheduling data, and combines the transportation distance and road travel time to estimate the earliest available shipping time of the goods, etc.

[0076] Based on the above-extracted and calculated parameters, the system constructs real-time dynamic environmental parameters. The real-time dynamic environmental parameters can comprehensively reflect various influencing factors in the current transportation environment, providing basic data support for subsequent route planning and optimization, and ensuring that the route planning can adapt to the real-time changing external conditions and internal warehousing status.

[0077] S33: Quantitatively evaluate and process the time cost and risk coefficient of each path node in the initial transportation plan data based on the real-time dynamic environmental parameters to generate total path weight data.

[0078] Preferably, the total path weight data is generated through the following steps:

[0079] S331: Conduct a risk analysis on each path node of the initial transportation plan based on the real-time dynamic environmental parameters, and perform a detour path retrieval process on the path nodes with congestion or high weather risk to generate an alternative path set.

[0080] Specifically, the system analyzes real-time dynamic environmental parameters such as traffic flow and weather conditions of each path node to determine whether there is a congestion risk or a weather disaster risk. For example, if the current traffic flow of a certain road section is too large, resulting in a significant increase in travel time, or there is a weather disaster warning for this road section, such as heavy rain, heavy snow, etc., which may affect transportation safety and efficiency, it will be identified as a high-risk node. For these high-risk nodes, the system uses a path search algorithm to find alternative detour paths in the map data and collects these detour paths to form an alternative path set.

[0081] S332: Perform a multi-objective cost calculation process on the travel time and energy consumption data in the alternative path set to generate path priority ranking data.

[0082] Specifically, the system performs multi-objective cost calculation processing on each path in the set of alternative paths. Two key objectives, namely travel time and energy consumption data, are mainly considered. The calculation of travel time combines factors such as real-time traffic conditions data and road length to accurately estimate the actual travel time of each path; the calculation of energy consumption data estimates the energy consumption cost of each path based on information such as the driving conditions of the vehicle, road gradient, and cargo weight. For example, for a path with more congested sections, the travel time cost will be higher; for a path with better road conditions but a longer distance, the energy consumption cost may be relatively large.

[0083] According to the calculation results of the multi-objective costs of travel time and energy consumption data, the system performs priority ranking on the paths in the set of alternative paths. Preferably, the weighted comprehensive evaluation method can be adopted to assign corresponding weights to travel time and energy consumption data respectively, calculate the comprehensive cost of each path, and then sort them in ascending order of the comprehensive cost to generate path priority ranking data. Based on this method, the paths with higher priorities can consider both time efficiency and energy consumption economy, providing a scientific basis for selecting the optimal path.

[0084] S333: According to the path priority ranking data, select the path with the lowest comprehensive cost as the sub-optimal path data.

[0085] Specifically, the system selects the path with the lowest comprehensive cost as the sub-optimal path data according to the path priority ranking data. That is, on the premise of meeting the requirements of the transportation task, the path with the best comprehensive performance in terms of travel time and energy consumption cost is selected from the set of alternative paths as the best transportation path selection under the current conditions.

[0086] S34: Identify whether the total path weight data exceeds the preset dynamic optimization threshold. If it exceeds, optimize the initial transportation plan data based on the dynamic route optimization algorithm to generate sub-optimal path data.

[0087] Specifically, the dynamic optimization threshold is a benchmark value determined according to historical data, transportation experience, and business requirements, and is used to judge whether the total path weight exceeds the acceptable range. Compare the calculated total path weight data with the preset dynamic optimization threshold. If the total path weight exceeds the threshold, it indicates that the transportation conditions of the current path are poor and need to be optimized and adjusted.

[0088] When it is determined that optimization is needed, the system optimizes the initial transportation plan data based on the dynamic route optimization algorithm. The dynamic route optimization algorithm comprehensively considers the changes in real-time dynamic environment parameters, such as the real-time update of traffic flow, the dynamic changes in weather conditions, and the adjustment of warehousing scheduling data, etc., and re-plans and optimizes the routes in the initial transportation plan. Through intelligent search and optimization techniques, the algorithm finds a better transportation route among numerous possible routes to adapt to the current dynamic transportation environment and improve transportation efficiency and reliability. After being processed by the dynamic route optimization algorithm, new sub-optimal path data is generated. This sub-optimal path data fully considers the impact of the real-time dynamic environment, can minimize transportation costs, improve transportation timeliness, and ensure the safety and stability of the transportation process while meeting transportation requirements. The generated sub-optimal path data is fed back into the transportation scheduling system to replace the original initial transportation plan data and guide the actual cargo transportation operation.

[0089] The above-mentioned artificial intelligence-based cargo transportation route planning method for automated warehousing and logistics fully utilizes technical methods such as real-time data processing, risk analysis, multi-objective optimization, and dynamic adjustment. It can scientifically and reasonably evaluate and optimize the initial transportation plan according to real-time traffic, weather, and warehousing conditions, improve the flexibility, reliability, and economy of transportation services, and provide customers with a more high-quality and efficient transportation solution.

[0090] In one embodiment, step S5 of the artificial intelligence-based cargo transportation route planning method for automated warehousing and logistics provided by the present invention specifically includes the following steps:

[0091] S51: Perform real-time trajectory tracking on the actual driving route of the final personalized transportation plan, collect transportation delay time and fuel consumption data, and generate execution deviation value data.

[0092] Specifically, the system can use technologies such as GPS (Global Positioning System) and GIS (Geographic Information System) to perform real-time tracking on the actual driving route of the final personalized transportation plan. Install a GPS device on the transportation vehicle, collect the vehicle's position information at preset time intervals (such as every minute) or preset distance intervals (such as every kilometer), and combine with electronic map data to generate detailed driving trajectory data. At the same time, collect the vehicle's operating status information, such as vehicle speed and engine speed, through on-vehicle sensors to provide a basis for subsequent data analysis.

[0093] Calculate the transportation delay time based on the actual driving route and the estimated arrival time in the initial transportation plan. Obtain the transportation delay time data by comparing the difference between the actual arrival time of the vehicle and the estimated arrival time. At the same time, monitor the fuel consumption in real time through the on-vehicle fuel sensor, and calculate the fuel consumption data in combination with the vehicle's fuel consumption model and driving mileage. Integrate the transportation delay time and the fuel consumption data to generate the execution deviation value data.

[0094] S52: Identify whether the execution deviation value data exceeds the preset safety warning threshold. If it exceeds, perform dynamic calibration processing on the execution status data of the final personalized transportation plan based on the root cause analysis model to generate an anomaly detection result.

[0095] Specifically, the system sets the safety warning thresholds for the transportation delay time and the fuel consumption data according to historical data and business experience. For example, the transportation delay time threshold is set to 30 minutes, and the fuel consumption deviation threshold is set to 10%. When the execution deviation value data exceeds these thresholds, it is considered that the execution status of the transportation plan is abnormal. When it is identified that the execution deviation value data exceeds the preset safety warning threshold, the root cause analysis model is started. This model comprehensively considers various factors such as real-time road conditions, vehicle status, and driver behavior, and deeply analyzes the execution status data of the final personalized transportation plan. For example, by analyzing the real-time road condition data, it can be judged whether the delay is caused by a sudden traffic event, by monitoring the vehicle fault alarm information, the impact of vehicle faults on transportation can be determined, and by analyzing the driver's driving habits and operation behaviors, the deviation caused by human factors can be evaluated.

[0096] According to the results of the root cause analysis, the system performs dynamic calibration processing on the final personalized transportation plan. If the delay is caused by a change in road conditions, re-plan the route to avoid congested sections; if it is a vehicle fault, arrange maintenance in time and adjust the transportation plan; if it is a driver problem, conduct corresponding training or replace the driver. After dynamic calibration, an anomaly detection result is generated, including information such as the anomaly type, cause analysis, and handling measures.

[0097] S53: Update the transportation preference parameters in the customer's historical transaction records based on the anomaly detection result.

[0098] Specifically, the system conducts a detailed analysis of the generated anomaly detection result and extracts the transportation preference information related to the customer's historical transaction records. For example, if a customer's goods are often delayed due to congestion on a specific section of the road, it may be necessary to adjust the transportation route preference of this customer; if a customer's goods have a high fuel consumption under specific weather conditions, it may be necessary to optimize the transportation time or vehicle configuration preference.

[0099] Based on the extracted customer preference information, the system formulates corresponding update strategies for transportation preference parameters according to the analysis of the anomaly detection results. For customers with frequent delays, the preference weight for transportation methods with high timeliness requirements is reduced, and the preference for alternative routes or more reliable transportation methods is increased; for customers with excessive fuel consumption, their vehicle selection preferences are adjusted, and more energy-efficient vehicles are preferred or the transportation route is optimized to reduce energy consumption; and the formulated update strategies for transportation preference parameters are applied to the customer's historical transaction records to update the customer's transportation preference parameters. In subsequent transportation route planning and service level division, these updated preference parameters are fully considered to provide personalized services that better meet the actual needs and transportation habits of customers, improving customer satisfaction and the quality of logistics services.

[0100] In summary, through the implementation of the above methods, the artificial intelligence-based goods transportation route planning method for automated warehousing logistics provided by the present invention forms a transportation service process with a closed-loop monitoring and feedback mechanism; through real-time trajectory tracking, the actual situation during transportation can be timely grasped, the calculation of deviation values and the identification of safety warning thresholds can quickly discover potential problems, the application of the root cause analysis model can achieve accurate positioning and effective solution of problems, and the update of transportation preference parameters further optimizes the customer profile and future transportation service plans. The execution of this series of steps not only improves the reliability and stability of transportation services, but also enhances the customer experience, reduces transportation risks and costs, and enhances the competitiveness of enterprises in the transportation market, enabling continuous improvement and optimization of transportation services and providing customers with more high-quality and efficient logistics solutions.

[0101] In the second aspect, as Figure 3 shown, the present invention provides an artificial intelligence-based goods transportation route planning system 600 for automated warehousing logistics, which is configured with the following modules:

[0102] A goods level evaluation module 610, which is used to perform weighted scoring calculations on the obtained customer historical transaction records and real-time goods data to obtain service level label data corresponding to the goods data. The service level label data includes a high-value level and an ordinary level;

[0103] A level path generation module 620, which is used to optimize the path of the goods data at the high-value level by calling the priority path algorithm based on the service level label data to generate initial transportation plan data, and call the shared transportation matching algorithm to match the path of the goods data at the ordinary level to generate merged order data;

[0104] The dynamic path optimization module 630 is used to calculate the path weight of the initial transportation plan data based on real-time road condition data and warehousing scheduling data to obtain the total path weight data; identify whether the total path weight data exceeds a preset dynamic optimization threshold, and if it exceeds, optimize the initial transportation plan data based on the dynamic route optimization algorithm to generate sub-optimal path data;

[0105] The personalized transportation generation module 640 is used to iteratively optimize the sub-optimal path data and combined order data based on the genetic algorithm to generate the final personalized transportation plan data;

[0106] The user transaction update module 650 is used to process the actual delay time and cost data of the transportation path according to the execution status data of the final personalized transportation plan and update the customer historical transaction record.

[0107] In summary, the automated warehousing and logistics artificial intelligence-based cargo transportation path planning system provided by the present invention can achieve accurate classification of customer goods, efficient transportation path planning, dynamic optimization and adjustment, and generation of personalized service plans through scientific and reasonable technical methods and algorithm applications. From the in-depth mining and analysis of customer historical data and real-time cargo data to the application of various intelligent optimization technologies such as the priority path algorithm, shared transportation matching algorithm, dynamic route optimization algorithm, and genetic algorithm, the entire process can fully consider various factors such as cargo value, transportation cost, time limit, real-time road conditions, etc., and provide differentiated high-quality transportation services for customers at different levels. At the same time, by continuously feedbacking and updating the customer historical transaction record, it can achieve continuous improvement and optimization of transportation services, improve customer satisfaction and transportation efficiency, reduce transportation costs, and enhance the competitiveness of enterprises in the market.

[0108] Preferably, the cargo level evaluation module 610 provided by the present invention is configured with the following units:

[0109] The customer value index generation unit 611 is used to assign preset weight coefficients to the transaction frequency and transaction amount in the customer historical transaction record respectively, perform linear weighted summation calculation to generate customer value index data;

[0110] The service level score generation unit 612 is used to perform user-cargo parameter matching and service level analysis on the customer value index data and the cargo weight, volume, and urgency parameters of the real-time cargo data to generate service level score data for different user cargo data;

[0111] The service level label generation unit 613 is used to classify and determine each service level score data according to a preset score threshold to obtain service level label data corresponding to the cargo data.

[0112] Preferably, the dynamic path optimization module 630 provided by the present invention is configured with the following units:

[0113] A transportation data acquisition unit 631, configured to obtain real-time road condition data including road passage time data and weather disaster warning data based on a traffic flow monitoring interface and a weather forecast interface, and obtain warehousing scheduling data including inventory location coordinate data based on a warehousing management system;

[0114] An environmental parameter generation unit 632, configured to combine the real-time road condition data and the warehousing scheduling data to generate real-time dynamic environmental parameters;

[0115] A path quantification and evaluation unit 633, configured to perform a quantification and evaluation process of time cost and risk coefficient on each path node in the initial transportation plan data based on the real-time dynamic environmental parameters, and generate path total weight data;

[0116] Preferably, the path quantification and evaluation unit 633 is configured with the following sub-units:

[0117] An alternative path generation sub-unit 6331, configured to perform a risk analysis on each path node of the initial transportation plan based on the real-time dynamic environmental parameters, perform a bypass path retrieval process on path nodes with congestion or high weather risk, and generate an alternative path set;

[0118] A path priority calculation sub-unit 6332, configured to perform a multi-objective cost calculation process on the passage time and energy consumption data in the alternative path set, and generate path priority ranking data;

[0119] A sub-optimal path selection sub-unit 6333, configured to select the path with the lowest comprehensive cost as the sub-optimal path data according to the path priority ranking data.

[0120] A transportation plan optimization unit 634, configured to identify whether the path total weight data exceeds a preset dynamic optimization threshold, and if it exceeds, perform an optimization process on the initial transportation plan data based on a dynamic route optimization algorithm to generate sub-optimal path data.

[0121] Preferably, the user transaction update module 650 provided by the present invention is configured with the following units:

[0122] A deviation data collection unit 651, configured to perform real-time trajectory tracking on the actual driving path of the final personalized transportation plan, collect transportation delay time and fuel consumption data, and generate execution deviation value data;

[0123] An anomaly detection and calibration unit 652, configured to identify whether the execution deviation value data exceeds a preset safety warning threshold, and if it exceeds, perform a dynamic calibration process on the execution status data of the final personalized transportation plan based on a root cause analysis model to generate an anomaly detection result;

[0124] A preference parameter update unit 653 is configured to update the transportation preference parameters of the customer's historical transaction records based on the anomaly detection results.

[0125] In one embodiment, the present application further provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the above-mentioned method for planning the cargo transportation path of an automated warehousing and logistics system based on artificial intelligence.

[0126] In one embodiment, the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the above-mentioned method for planning the cargo transportation path of an automated warehousing and logistics system based on artificial intelligence.

[0127] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0128] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can refer to the partial descriptions of the method embodiments. The device embodiments described above are merely illustrative. The components described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the present disclosure solution. Those of ordinary skill in the art can understand and implement it without creative effort.

[0129] As described above, the above are only the specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of various changes or substitutions within the technical scope disclosed by the present application, and these should all be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An artificial intelligence-based method for planning the cargo transportation route in an automated warehousing and logistics system, characterized in that, It includes the following steps: S1: Perform weighted scoring calculations on the obtained customer historical transaction records and real-time cargo data to obtain service level label data corresponding to the cargo data. The service level label data includes a high-value level and an ordinary level; S2: Based on the service level label data, call the priority path algorithm to perform path optimization processing on the cargo data at the high-value level to generate initial transportation plan data, and call the shared transportation matching algorithm to perform path matching on the cargo data at the ordinary level to generate merged order data; S3: Perform path weight calculation processing on the initial transportation plan data based on real-time traffic conditions data and warehouse scheduling data to obtain total path weight data; Identify whether the total path weight data exceeds a preset dynamic optimization threshold. If it exceeds, perform optimization processing on the initial transportation plan data based on the dynamic route optimization algorithm to generate sub-optimal path data; S4: Perform iterative optimization processing on the sub-optimal path data and the merged order data based on the genetic algorithm to generate final personalized transportation plan data; S5: Process the actual delay time and cost data of the transportation path according to the execution status data of the final personalized transportation plan, and update the customer historical transaction records.

2. The method according to claim 1, wherein The S1 includes: S11: Assign preset weight coefficients to the transaction frequency and transaction amount in the customer historical transaction records respectively, and perform linear weighted summation calculation processing to generate customer value index data; S12: Perform user-cargo parameter matching and service level analysis on the customer value index data and the cargo weight, volume, and urgency parameters of the real-time cargo data to generate service level score data for different user cargo data; S13: Perform classification and determination processing on each service level score data according to a preset score threshold to obtain service level label data corresponding to the cargo data.

3. The method according to claim 1, wherein The S3 includes: S31: Based on the traffic flow monitoring interface, weather forecast interface, obtain real-time traffic conditions data including road passage time data and weather disaster warning data; and obtain warehouse scheduling data including inventory location coordinate data based on the warehouse management system; S32: Combine the real-time traffic conditions data and the warehouse scheduling data to generate real-time dynamic environment parameters; S33: Perform quantitative evaluation processing on the time cost and risk coefficient of each path node in the initial transportation plan data based on the real-time dynamic environment parameters to generate total path weight data; S34: Identify whether the total path weight data exceeds a preset dynamic optimization threshold. If it exceeds, perform optimization processing on the initial transportation plan data based on the dynamic route optimization algorithm to generate sub-optimal path data.

4. The method according to claim 3, wherein The S33 includes: S331: Perform risk analysis on each path node of the initial transportation plan based on the real-time dynamic environment parameters, and perform detour path retrieval processing on path nodes with congestion or high weather risk to generate an alternative path set; S332: Perform multi-objective cost calculation processing on the passage time and energy consumption data in the alternative path set to generate path priority ranking data; S333: Sort the data according to the path priority, and select the path with the lowest comprehensive cost as the sub-optimal path data.

5. The method according to any one of claims 1-4, characterized in that The S5 includes: S51: Perform real-time trajectory tracking on the actual driving path of the final personalized transportation plan, collect transportation delay time and fuel consumption data, and generate execution deviation value data; S52: Identify whether the execution deviation value data exceeds a preset safety warning threshold. If it exceeds, perform dynamic calibration processing on the execution status data of the final personalized transportation plan based on the root cause analysis model to generate an anomaly detection result; S53: Update the transportation preference parameters of the customer historical transaction record based on the anomaly detection result.

6. An automated warehousing and logistics artificial intelligence-based cargo transportation route planning system, characterized in that, The system includes: A goods level evaluation module, configured to perform weighted scoring calculation on the customer historical transaction record and real-time goods data obtained, to obtain service level label data corresponding to the goods data, where the service level label data includes a high-value level and a normal level; A level path generation module, configured to, based on the service level label data, call a priority path algorithm to perform path optimization processing on the goods data of the high-value level, generate initial transportation plan data, and call a shared transportation matching algorithm to perform path matching on the goods data of the normal level to generate combined order data; A dynamic path optimization module, configured to perform path weight calculation processing on the initial transportation plan data based on real-time road condition data and warehouse scheduling data to obtain path total weight data; identify whether the path total weight data exceeds a preset dynamic optimization threshold. If it exceeds, perform optimization processing on the initial transportation plan data based on a dynamic route optimization algorithm to generate sub-optimal path data; A personalized transportation generation module, configured to perform iterative optimization processing on the sub-optimal path data and the combined order data based on a genetic algorithm to generate final personalized transportation plan data; A user transaction update module, configured to process the actual delay time and cost data of the transportation path according to the execution status data of the final personalized transportation plan, and update the customer historical transaction record.

7. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the method according to any one of claims 1 to 5.

8. 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 method according to any one of claims 1 to 5.

Images