Order processing method, apparatus, device, storage medium, and program product

Abstract

The application relates to an order processing method and device, equipment, a storage medium and a program product, which can be used in the technical field of vehicles. The method comprises the following steps: acquiring vehicle order information, determining bill of materials information corresponding to the vehicle order information; performing decomposition processing on the bill of materials information to obtain total demand information of vehicle parts corresponding to the vehicle order information; determining target allocation scheme information corresponding to the total demand information according to the total demand information and multi-dimensional attribute information of suppliers of the vehicle parts; and generating supply order information corresponding to a target supplier according to the target allocation scheme information, and correspondingly issuing the supply order information to a production management system of the target supplier. The method can improve the efficiency of issuing the supply order information.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to an order processing method, apparatus, device, storage medium, and program product. Background Technology

[0002] With the rapid development of the automotive manufacturing industry and the increasing diversification of market demand, automobile manufacturers face the challenge of numerous order types and tight production cycles. In actual production, each vehicle order typically involves thousands of parts, requiring coordination among multiple suppliers for supply.

[0003] In related technologies, the main method for handling supplier supply arrangements is manual allocation; however, this method requires a lot of manual processing time when dealing with complex orders, resulting in low efficiency in issuing supply order information. Summary of the Invention

[0004] Therefore, it is necessary to provide an order processing method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can improve the efficiency of issuing supply order information in response to the above-mentioned technical problems.

[0005] Firstly, this application provides an order processing method. The method includes:

[0006] Obtain vehicle order information and determine the bill of materials information corresponding to the vehicle order information;

[0007] The bill of materials information is decomposed to obtain the total demand information for vehicle parts corresponding to the vehicle order information;

[0008] Based on the total demand information and the multi-dimensional attribute information of the vehicle component suppliers, the target allocation scheme information corresponding to the total demand information is determined;

[0009] Based on the target allocation scheme information, the corresponding supply order information for the target supplier is generated, and the supply order information is sent to the production management system of the target supplier.

[0010] Technical Effects: By acquiring vehicle order information and determining the corresponding bill of materials (BOM) information, precise demand acquisition driven by real-time orders is achieved; by decomposing the BOM information to obtain total demand information, the automatic conversion from vehicle demand to component demand is realized, which is conducive to accurately determining the actual demand of each component; by combining total demand information and multi-dimensional attribute information of suppliers, target allocation scheme information is determined, achieving comprehensive optimal allocation, which is conducive to the rational allocation of supplier resources and shortening allocation decision time; by generating supply order information based on target allocation scheme information and sending it to the production management system of target suppliers, the automated flow from demand analysis to order issuance is realized, thereby improving the efficiency of supply order information issuance.

[0011] In an optional embodiment of the first aspect, after the supply order information is sent to the production management system of the target supplier, the method further includes:

[0012] Obtain production and quality data fed back from the target supplier's production management system;

[0013] The production data is compared with the production node data corresponding to the target supplier to obtain production deviation data, and the quality data is compared with the quality threshold corresponding to the target supplier to obtain quality deviation data.

[0014] The production deviation data and the quality deviation data are input into a pre-trained risk prediction model for risk prediction processing to obtain the risk prediction information corresponding to the supply order information.

[0015] When the risk prediction information reaches a preset risk threshold, risk warning information corresponding to the supply order information is generated.

[0016] Technical benefits: By acquiring production and quality data from the target supplier's production management system and comparing them with preset production node data and quality thresholds, it is beneficial to monitor the supplier's production execution and quality status in real time; by inputting production deviation data and quality deviation data into a pre-trained risk prediction model for risk prediction processing, it is beneficial to quantitatively assess potential supply risks; by generating risk warning information when the risk prediction information reaches a preset risk threshold, it is beneficial to proactively identify and provide early warnings of supply chain anomalies.

[0017] In an optional embodiment of the first aspect, after generating risk warning information corresponding to the supply order information when the risk prediction information reaches a preset risk threshold, the method further includes:

[0018] Obtain the target supplier's production capacity and transportation data;

[0019] Based on the production capacity data, the transportation data, and the risk prediction information, risk response plan information corresponding to the supply order information is generated.

[0020] Technical benefits: By acquiring the target supplier's capacity and transportation data, it is beneficial to have a comprehensive understanding of the supply chain's resource status and logistics progress; by generating risk response plans based on capacity data, transportation data, and risk prediction information, it is beneficial to provide targeted remedial measures for different types of supply risks, thereby improving the speed of risk response and the efficiency of risk handling.

[0021] In an optional embodiment of the first aspect, the step of decomposing the bill of materials information to obtain the total demand information for vehicle parts corresponding to the vehicle order information includes:

[0022] The bill of materials information is decomposed and validated layer by layer to obtain the net required quantity of each vehicle component.

[0023] The net demand quantity is aggregated according to a preset time window to obtain the total demand information.

[0024] Technical benefits: By decomposing and validating the bill of materials information layer by layer, it is beneficial to accurately calculate the net demand quantity of each vehicle component; by aggregating the net demand quantity according to a preset time window, it is beneficial to summarize the scattered component demands into complete total demand information, thereby improving the accuracy and completeness of material demand calculation.

[0025] In an optional embodiment of the first aspect, determining the target allocation scheme information corresponding to the total demand information based on the total demand information and the multi-dimensional attribute information of the vehicle component suppliers includes:

[0026] Based on the total demand information and the multi-dimensional attribute information, a multi-objective optimization model is constructed; the optimization objectives of the multi-objective optimization model include minimizing total cost, minimizing delivery cycle, and maximizing capacity utilization.

[0027] The multi-objective optimization model is solved to obtain the objective allocation scheme information.

[0028] Technical benefits: By constructing a multi-objective optimization model based on total demand information and multi-dimensional attribute information, the component allocation problem can be transformed into a mathematical model that can be quantified and solved. By setting optimization objectives of minimizing total cost, minimizing delivery cycle, and maximizing capacity utilization, comprehensive optimization can be carried out from multiple dimensions such as cost, timeliness, and resource utilization. Solving the multi-objective optimization model can help obtain information on the globally optimal objective allocation scheme, thereby improving the accuracy of production task allocation.

[0029] In an optional embodiment of the first aspect, determining the bill of materials information corresponding to the vehicle order information includes:

[0030] Extract vehicle model identification information, configuration identification information, and order time information from the vehicle order information;

[0031] Based on the vehicle identification information, the configuration identification information, and the order time information, determine the query information corresponding to the preset product data management system;

[0032] Based on the query information, the bill of materials information corresponding to the vehicle order information is determined from the product data management system.

[0033] Technical benefits: By extracting vehicle model identification information, configuration identification information, and order time information from vehicle order information, it is beneficial to obtain key feature parameters for determining bill of materials (BOM) information; by determining query information based on vehicle model identification information, configuration identification information, and order time information and performing accurate matching in the product data management system, it is beneficial to ensure that the obtained BOM information accurately corresponds to the vehicle order information, thereby improving the accuracy of BOM information matching.

[0034] In an optional embodiment of the first aspect, the method further includes:

[0035] Obtain the predicted arrival time of the parts transport vehicle corresponding to the supply order information; the predicted arrival time represents the predicted time when the parts transport vehicle will arrive at the vehicle manufacturer corresponding to the vehicle parts.

[0036] If the predicted arrival time meets the preset time threshold, a delivery warning message is sent to the production management system of the vehicle manufacturer; the delivery warning message is used to trigger the vehicle manufacturer to perform resource preparation operations.

[0037] Technical effect: By sending a delivery warning to the vehicle manufacturer's production management system when the predicted arrival time meets the preset time threshold, it is beneficial to trigger the vehicle manufacturer to carry out resource preparation operations in advance, thereby improving the efficiency of vehicle operation.

[0038] Secondly, this application also provides an order processing apparatus. The apparatus includes:

[0039] The information acquisition module is used to acquire vehicle order information and determine the bill of materials information corresponding to the vehicle order information;

[0040] The information decomposition module is used to decompose the bill of materials information to obtain the total demand information for vehicle parts corresponding to the vehicle order information.

[0041] The information determination module is used to determine the target allocation scheme information corresponding to the total demand information based on the total demand information and the multi-dimensional attribute information of the suppliers of the vehicle parts;

[0042] The information generation module is used to generate supply order information corresponding to the target supplier based on the target allocation scheme information, and to send the supply order information to the production management system of the target supplier.

[0043] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described above.

[0044] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described above.

[0045] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method described in any of the above aspects.

[0046] Regarding the beneficial effects of any of the technical solutions in the second to fifth aspects mentioned above, refer to the beneficial effects of the corresponding technical solutions in the first aspect; repeated examples will not be listed here. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 This is a schematic diagram of an optional flow of an order processing method in one embodiment;

[0049] Figure 2This is a schematic diagram of an optional flow of the order processing method in another embodiment;

[0050] Figure 3 This is an optional flowchart illustrating the steps of bill of materials decomposition in one embodiment;

[0051] Figure 4 This is a schematic diagram of an optional process for warning and decision-making in one embodiment;

[0052] Figure 5 This is a schematic diagram of an optional system architecture for an order processing method in one embodiment;

[0053] Figure 6 This is a schematic diagram of an optional structure of the order processing device in one embodiment;

[0054] Figure 7 This is a schematic diagram of an optional internal structure of a computer device in one embodiment. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0056] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0057] In one exemplary embodiment, such as Figure 1 As shown, an order processing method is provided. This embodiment illustrates the method applied to a terminal. It is understood that this method can also be applied to a server, or to a system including both a terminal and a server, and is implemented through interaction between the terminal and the server. The terminal can be, but is not limited to, various personal computers, laptops, smartphones, tablets, etc.; the server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. In this embodiment, the method includes the following steps:

[0058] Step S101: Obtain vehicle order information and determine the bill of materials information corresponding to the vehicle order information;

[0059] Step S102: Decompose the bill of materials information to obtain the total demand information for vehicle parts corresponding to the vehicle order information;

[0060] Step S103: Based on the total demand information and the multi-dimensional attribute information of the vehicle parts suppliers, determine the target allocation scheme information corresponding to the total demand information;

[0061] Step S104: Based on the target allocation scheme information, generate the corresponding supply order information for the target supplier, and send the supply order information to the target supplier's production management system.

[0062] Among them, vehicle order information can be real-time data of car orders placed by customers obtained by the sales terminal. Vehicle order information includes vehicle configuration, color, optional packages, and delivery time.

[0063] The bill of materials information can be product structure data retrieved from the product data management system. The bill of materials information is used to describe all the parts required for the vehicle and their hierarchical relationships.

[0064] The decomposition process can be achieved by using a recursive descent tree traversal algorithm to decompose the bill of materials information layer by layer and calculate the net requirement quantity of each component.

[0065] The total demand information can be obtained by decomposing the bill of materials information and then using a time-window-based streaming processing mechanism to accumulate the demand quantities of all components generated within a preset time window.

[0066] The supplier's multi-dimensional attribute information can be pre-maintained supplier-related data, including capacity levels, geographical distribution, historical performance indicators, and contract prices. Historical performance indicators can be quantitative data used to evaluate the supplier's past performance, including historical on-time delivery rate and historical defect rate per million units.

[0067] The target allocation scheme information can be the optimal allocation scheme obtained by solving a multi-objective optimization algorithm based on total demand information and multi-dimensional attribute information of suppliers. This information indicates the quantity of each material allocated to each supplier. The multi-objective optimization algorithm can be an optimization algorithm with the objectives of minimizing total cost, minimizing delivery cycle, and maximizing capacity utilization, while satisfying demand fulfillment constraints, supplier capacity constraints, quality access constraints, and logistics time constraints. Total cost can be the sum of costs including procurement expenses, transportation costs, and inventory management-related expenses. Delivery cycle can be the total time required from the issuance of the supply order information to the arrival of materials. Capacity utilization can be a utilization rate indicator achieved by evenly allocating supplier resources to avoid idleness or overload. Demand fulfillment constraints can be constraints that ensure the total demand for all components is fully covered. Supplier capacity constraints can be constraints that prevent the allocation quantity from exceeding the supplier's maximum production capacity. Quality access constraints can be constraints that only allow the selection of suppliers that meet preset historical performance thresholds and standard certifications. Logistics time constraints can be constraints that consider the impact of geographical location on transportation timeliness to minimize potential delay risks.

[0068] Among them, the target supplier can be the supplier that undertakes the production task, as determined based on the target allocation scheme information.

[0069] Among them, the supply order information can be order data automatically generated by converting the decomposed production tasks based on the target allocation plan information.

[0070] The production management system can be a system used by the target supplier to execute production tasks and collect process data. The production management system includes manufacturing execution systems and quality management systems, etc.

[0071] Optionally, the terminal obtains vehicle order information, extracts the vehicle model code, configuration code, and order timestamp from the vehicle order information as a composite query key, and performs a precise matching query of the multi-key-value index within the product data management system to determine the uniquely valid master bill of materials version at the order timestamp, which serves as the bill of materials information corresponding to the vehicle order information. A recursive descent tree traversal algorithm is used to decompose the bill of materials information layer by layer. During the decomposition process, the material master data table is queried in real time to obtain the current status field of each component. When the status field indicates discontinued production, the preset alternative parts relationship table is automatically queried and replaced with a valid alternative part code. When the status field indicates frozen production, a warning signal is generated and... The calculation of demand for the material is stopped; a time-window-based streaming processing mechanism is adopted to accumulate the demand quantities of the components generated within the preset time window, thereby obtaining the total demand information of vehicle components corresponding to the vehicle order information; based on the total demand information and the multi-dimensional attribute information of the vehicle component suppliers, a rule-based fast allocation strategy is adopted for general or standard parts, and a multi-objective optimization algorithm is used to solve for key or customized parts, thereby determining the target allocation scheme information corresponding to the total demand information; the target allocation scheme information is automatically converted into the supply order information corresponding to the target supplier, and the supply order information is sent to the production management system of the target supplier through a standardized interface.

[0072] In the above order processing method, by acquiring vehicle order information and determining the corresponding bill of materials information, precise demand acquisition driven by real-time orders is achieved; by decomposing the bill of materials information to obtain total demand information, the automatic conversion from vehicle demand to component demand is realized, which is conducive to accurately determining the actual demand of each component; by combining total demand information and multi-dimensional attribute information of suppliers, target allocation scheme information is determined, achieving comprehensive optimal allocation, which is conducive to rationally allocating supplier resources and shortening allocation decision time; by generating supply order information based on target allocation scheme information and sending it to the production management system of the target supplier, the automated flow from demand analysis to order issuance is realized, thereby improving the efficiency of supply order information issuance.

[0073] In an exemplary embodiment, after the supply order information is sent to the target supplier's production management system, the following steps are also included: obtaining production data and quality data fed back by the target supplier's production management system; comparing the production data with the production node data corresponding to the target supplier to obtain production deviation data, and comparing the quality data with the quality threshold corresponding to the target supplier to obtain quality deviation data; inputting the production deviation data and quality deviation data into a pre-trained risk prediction model for risk prediction processing to obtain risk prediction information corresponding to the supply order information; and generating risk warning information corresponding to the supply order information when the risk prediction information reaches a preset risk threshold.

[0074] The production data can be real-time production process data collected from the target supplier's manufacturing execution system, including the output quantity at each workstation and the status of the equipment.

[0075] The quality data can be quality inspection data collected in real time from the target supplier's quality management system, including measurements of key dimensions and acceptance criteria.

[0076] Among them, production node data can be the pre-set output target data that the target supplier should complete at each production stage, which is used to compare with the actual production data.

[0077] Among them, the quality threshold can be a pre-set quality acceptance standard, used to determine whether the quality data meets the requirements.

[0078] Among them, production deviation data can be the deviation value obtained by comparing production data with the production node data corresponding to the target supplier, which is used to reflect the difference between the actual production progress and the planned progress.

[0079] Among them, the quality deviation data can be the deviation value obtained by comparing the quality data with the quality threshold corresponding to the target supplier, which is used to reflect the difference between the actual quality level and the preset standard.

[0080] The risk prediction model can be a pre-trained machine learning model based on logistic regression and random forest. The input feature vector of the risk prediction model can include the percentage deviation of production deviation data, the remaining time until the planned delivery node, the criticality level of components, the historical on-time delivery rate of the target supplier, and the historical defect rate per million units, etc.

[0081] Among them, risk prediction information can be the multi-level risk rating results output by the risk prediction model, and risk prediction information is used to characterize the supply risk level corresponding to the supply order information.

[0082] Among them, the preset risk threshold can be a pre-set risk level judgment standard. When the risk level indicated by the risk prediction information is medium risk or high risk, the risk prediction information is judged to have reached the preset risk threshold.

[0083] Among them, risk warning information can be a warning notification generated when the risk prediction information reaches a preset risk threshold, which is used to alert managers to potential supply risks.

[0084] Optionally, after the terminal sends the supply order information to the target supplier's production management system, it retrieves production and quality data from the target supplier's manufacturing execution system and quality management system via a real-time push mechanism. The production data is compared with the target supplier's corresponding production node data to calculate the deviation between actual and planned output, yielding production deviation data. Similarly, the quality data is compared with the target supplier's corresponding quality thresholds to calculate the deviation between actual quality indicators and preset standards, yielding quality deviation data. The production and quality deviation data undergo preprocessing and feature extraction. The processed data is then input into a pre-trained risk prediction model for risk prediction, resulting in risk prediction information corresponding to the supply order information. If the risk prediction information reaches a preset risk threshold, an early warning mechanism is automatically triggered, generating risk warning information corresponding to the supply order information and pushing this warning information to the management terminal of the administrator.

[0085] For example, the terminal receives production data in real time from the target supplier's manufacturing execution system via a distributed message queue real-time push mechanism. This production data includes information such as the output quantity at each workstation and equipment status. Simultaneously, it receives quality data in real time from the target supplier's quality management system, including measurements of critical dimensions and pass / fail criteria. The production data is compared with the target supplier's corresponding production node data to calculate the production deviation percentage, yielding production deviation data. The quality data is then compared with the target supplier's corresponding quality thresholds to determine if the quality indicators exceed preset ranges, yielding quality deviation data. Data preprocessing and feature extraction are performed on the production and quality deviation data to construct an input feature vector. This input feature vector includes the deviation percentage of the production deviation data, the remaining time until the planned delivery node, the criticality level of the component, the target supplier's historical on-time delivery rate, and historical defect rate per million units. This input feature vector is then fed into a pre-trained risk prediction model based on logistic regression and random forest for risk prediction processing, resulting in risk prediction information corresponding to the supply order information. This risk prediction information is a multi-level risk rating, including high, medium, and low risk levels. When the risk prediction information indicates high or medium risk, the risk prediction information is determined to have reached the preset risk threshold, and the early warning mechanism is automatically triggered. The risk warning information corresponding to the supply order information is generated and pushed to the management terminal of the management personnel for confirmation or revision.

[0086] The technical solution provided in this embodiment obtains production and quality data fed back from the target supplier's production management system, and compares the production and quality data with preset production node data and quality thresholds, which is beneficial for real-time monitoring of the supplier's production execution and quality status. By inputting production deviation data and quality deviation data into a pre-trained risk prediction model for risk prediction processing, it is beneficial for quantitatively assessing potential supply risks. By generating risk warning information when the risk prediction information reaches a preset risk threshold, it is beneficial for proactively identifying and providing early warnings of supply chain anomalies.

[0087] In an exemplary embodiment, after generating risk warning information corresponding to the supply order information when the risk prediction information reaches a preset risk threshold, the method further includes: obtaining the target supplier's capacity data and transportation data; and generating risk response plan information corresponding to the supply order information based on the capacity data, transportation data, and risk prediction information.

[0088] Among them, the capacity data can be the current capacity status data of the target supplier and other available suppliers obtained from the global supplier capacity pool. The capacity data is used to evaluate the supplier's production capacity and resource availability.

[0089] The transportation data can be in-transit transportation status data and transportation cycle data related to supply order information. The transportation data is used to assess the transportation progress and estimated arrival time of materials.

[0090] Among them, the risk response plan information can be remedial measures for supply risks that are automatically generated based on capacity data, transportation data and risk forecast information. The risk response plan information includes measures such as sending production reminders to suppliers, activating backup suppliers and automatically generating new purchase orders, and dynamically adjusting the production schedule of the vehicle manufacturer according to the material delay arrival situation.

[0091] Optionally, after generating risk warning information corresponding to the supply order information, the terminal obtains the current capacity status of the target supplier and the available capacity status of other backup suppliers from the global supplier capacity pool to obtain capacity data; simultaneously, it obtains the in-transit transportation status and transportation cycle related to the supply order information to obtain transportation data. Based on the capacity data, the terminal assesses the production capacity information of the target supplier and backup suppliers, and based on the transportation data, it assesses the transportation progress of the materials. Combining the production capacity information of the target supplier and backup suppliers, the transportation progress of the materials, and the risk prediction information, the terminal determines the risk response strategy, thereby generating risk response plan information corresponding to the supply order information.

[0092] The technical solution provided in this embodiment, by acquiring the target supplier's capacity and transportation data, is conducive to a comprehensive understanding of the supply chain's resource status and logistics progress; by generating risk response plan information based on capacity data, transportation data, and risk prediction information, it is conducive to providing targeted remedial measures for different types of supply risks, thereby improving the speed of risk response and the efficiency of risk handling.

[0093] In an exemplary embodiment, the bill of materials information is decomposed to obtain the total demand information for vehicle parts corresponding to the vehicle order information. Specifically, this includes: performing layer-by-layer decomposition and validity verification on the bill of materials information to obtain the net demand quantity for each vehicle part; and aggregating the net demand quantities according to a preset time window to obtain the total demand information.

[0094] The layer-by-layer decomposition process can be a recursive descent tree traversal algorithm that decomposes the bill of materials information into multiple levels from the complete vehicle to the parts, in order to calculate the required quantity of each part.

[0095] Among them, the validity verification process can be a process in which the material master data table is queried in real time during the layer-by-layer decomposition process to obtain the current status field of each component, and the validity of the material is judged based on the status field. For example, when the status field indicates that production is stopped, the preset alternative part relationship table is automatically queried and the valid alternative part code is used for replacement. When the status field indicates that it is frozen, an early warning signal is generated and the demand calculation for the material is stopped.

[0096] The net demand quantity can be the actual demand quantity of each vehicle component calculated after layer-by-layer decomposition and validity verification.

[0097] The preset time window can be a pre-defined time range for aggregating net demand quantities, used to accumulate the component demand quantities within the preset time window.

[0098] Among them, aggregation processing can be a process that uses a time window-based streaming processing mechanism to accumulate and summarize the net demand quantities of each vehicle component within a preset time window.

[0099] Optionally, the terminal employs a recursive descent tree traversal algorithm to decompose the bill of materials (BOM) information layer by layer. During this process, the terminal queries the material master data table in real time to obtain the current status field of each vehicle component, performs validity checks on the BOM information, and automatically queries the preset alternative parts relationship table and replaces the component with a valid alternative part code when the status field indicates "production halted." When the status field indicates "frozen," a warning signal is generated and the demand calculation for that material is stopped. Through layer-by-layer decomposition and validity checks, the net demand quantity for each vehicle component is obtained. Based on a preset time window, a time-window-based streaming processing mechanism is used to aggregate the net demand quantities, summing up the net demand quantities of each vehicle component within the preset time window to obtain the total demand information.

[0100] The technical solution provided in this embodiment, by performing layer-by-layer decomposition and validity verification of the bill of materials information, facilitates the accurate calculation of the net demand quantity of each vehicle component; by aggregating the net demand quantity according to a preset time window, it helps to summarize the scattered component demands into complete total demand information, thereby improving the accuracy and completeness of material demand calculation.

[0101] In an exemplary embodiment, the target allocation scheme information corresponding to the total demand information is determined based on the total demand information and the multi-dimensional attribute information of the vehicle parts suppliers. Specifically, this includes: constructing a multi-objective optimization model based on the total demand information and the multi-dimensional attribute information; the optimization objectives of the multi-objective optimization model include minimizing the total cost, minimizing the delivery cycle, and maximizing the capacity utilization rate; and solving the multi-objective optimization model to obtain the target allocation scheme information.

[0102] The multi-objective optimization model can be a mathematical model that models the component allocation problem as having multiple optimization objectives. The decision variables in the multi-objective optimization model represent the quantity of materials allocated to suppliers. Minimizing total cost can be the first optimization objective of the multi-objective optimization model, encompassing procurement costs, transportation costs, and inventory management-related costs. Minimizing delivery cycle time can be the second optimization objective, defined as the total time required from the issuance of the supply order information to the arrival of the materials. Maximizing capacity utilization can be the third optimization objective, achieved by balancing the allocation of supplier resources to avoid idleness or overload.

[0103] The solution process can employ a non-dominated sorting genetic algorithm, using a non-dominated sorting mechanism and a crowding comparison operator to solve a multi-objective optimization model and obtain the optimal allocation scheme. The crowding comparison operator is a selection mechanism used in multi-objective optimization algorithms to maintain population diversity. It measures the density of solutions around an individual by calculating the crowding distance between each individual and its neighbors in the target space within the same non-dominated level. A larger crowding distance indicates a sparser region of solutions, and the individual is more likely to be preferentially retained in the selection operation. This avoids excessive concentration of solutions in a local area of ​​the target space, ensuring that the final Pareto optimal solution set is evenly distributed throughout the entire target space.

[0104] Optionally, the terminal constructs a multi-objective optimization model based on total demand information and multi-dimensional attribute information. The decision variables of the multi-objective optimization model represent the quantity of materials allocated to suppliers. The optimization objectives of the multi-objective optimization model include minimizing total cost, minimizing delivery cycle, and maximizing capacity utilization. The multi-objective optimization model also satisfies demand fulfillment constraints, supplier capacity constraints, quality access constraints, and logistics time constraints. A non-dominated sorting genetic algorithm is used to solve the multi-objective optimization model. Iterative optimization is performed through a non-dominated sorting mechanism and a crowding comparison operator to obtain the target allocation scheme information.

[0105] For example, the terminal obtains the required quantity of each vehicle component based on total demand information, and obtains information such as the capacity level, geographical distribution, historical performance indicators, and contract prices of each supplier based on multi-dimensional attribute information. A multi-objective optimization model is then constructed based on the total demand information and multi-dimensional attribute information. The decision variable of the multi-objective optimization model represents the quantity of materials allocated to suppliers. The optimization objectives of the multi-objective optimization model include minimizing total cost, minimizing delivery cycle, and maximizing capacity utilization. Minimizing total cost means minimizing the sum of procurement costs, transportation costs, and inventory management-related costs. Minimizing delivery cycle means minimizing the overall time required from the issuance of the supply order information to the arrival of materials. Maximizing capacity utilization means avoiding idle or overloaded resources by evenly allocating supplier resources. The multi-objective optimization model also satisfies the following constraints: demand satisfaction constraint ensures that the total demand for all components is fully covered; supplier capacity constraint prevents the allocation quantity from exceeding the supplier's maximum production capacity; quality access constraint only allows the selection of suppliers that meet preset historical performance thresholds and standard certifications; and logistics time constraint considers the impact of geographical location on transportation timeliness to minimize potential delay risks. A non-dominated sorting genetic algorithm is used to solve the multi-objective optimization model. The individuals in the population are sorted hierarchically through the non-dominated sorting mechanism, and the population diversity is maintained by the crowding comparison operator. After multiple generations of iterative optimization, the target allocation scheme information is obtained, which indicates the optimal quantity of each material to be allocated to each supplier.

[0106] The technical solution provided in this embodiment, by constructing a multi-objective optimization model based on total demand information and multi-dimensional attribute information, helps to transform the component allocation problem into a mathematical model that can be quantified and solved; by setting optimization objectives of minimizing total cost, minimizing delivery cycle, and maximizing capacity utilization, it is beneficial to carry out comprehensive optimization from multiple dimensions such as cost, timeliness, and resource utilization; by solving the multi-objective optimization model, it is beneficial to obtain information on the globally optimal objective allocation scheme, thereby improving the accuracy of production task allocation.

[0107] In an exemplary embodiment, determining the bill of materials information corresponding to the vehicle order information specifically includes the following: extracting vehicle model identification information, configuration identification information, and order time information from the vehicle order information; determining query information corresponding to a preset product data management system based on the vehicle model identification information, configuration identification information, and order time information; and determining the bill of materials information corresponding to the vehicle order information from the product data management system based on the query information.

[0108] Among them, the vehicle model identification information can be code information extracted from vehicle order information to identify the vehicle model.

[0109] The configuration identification information can be code information extracted from vehicle order information to identify vehicle configuration, and the configuration identification information corresponds to the vehicle's optional packages, colors, and other configuration options.

[0110] The order time information can be the order generation timestamp information extracted from the vehicle order information, which is used to determine the valid bill of materials version at that point in time.

[0111] The product data management system can be a system used to store and manage product structure data. The product data management system stores bill of materials information for different models, configurations, and time versions.

[0112] The query information can be a composite query key consisting of vehicle model identification information, configuration identification information, and order time information, which is used for precise matching queries in the product data management system.

[0113] Optionally, the terminal extracts vehicle model identification information, configuration identification information, and order time information from the vehicle order information. The vehicle model identification information identifies the vehicle model, the configuration identification information identifies the vehicle configuration, and the order time information determines the valid bill of materials (BOM) version. Based on the vehicle model identification information, configuration identification information, and order time information, a composite query key is constructed to obtain the query information corresponding to the preset product data management system. Based on the query information, a precise matching query using a multi-key-value index is performed in the product data management system to determine the uniquely valid master BOM version at the time indicated by the order time information, thereby obtaining the BOM information corresponding to the vehicle order information.

[0114] The technical solution provided in this embodiment extracts vehicle model identification information, configuration identification information, and order time information from vehicle order information, which helps to obtain key feature parameters for determining bill of materials information. By determining query information based on vehicle model identification information, configuration identification information, and order time information and performing accurate matching in the product data management system, it helps to ensure that the obtained bill of materials information accurately corresponds to the vehicle order information, thereby improving the accuracy of bill of materials information matching.

[0115] In an exemplary embodiment, the method further includes: obtaining the predicted arrival time of the parts transport vehicle corresponding to the supply order information; the predicted arrival time represents the predicted time when the parts transport vehicle arrives at the vehicle manufacturer corresponding to the parts; if the predicted arrival time meets a preset time threshold condition, sending a delivery warning information to the production management system of the vehicle manufacturer; the delivery warning information is used to trigger the vehicle manufacturer to perform resource preparation operations.

[0116] Among them, the parts transport vehicle can be a transport vehicle used to transport the vehicle parts corresponding to the supply order information.

[0117] The predicted arrival time can be calculated by integrating information such as the location and speed of the transport vehicle through an IoT gateway, indicating the predicted time when the transport vehicle will arrive at the vehicle manufacturing plant.

[0118] The preset time threshold condition can be a pre-set time judgment condition used to determine whether to send a delivery warning information. When the predicted arrival time falls within the preset time threshold range, it is determined that the predicted arrival time meets the preset time threshold condition. For example, the preset time threshold range can be 60 minutes or other preset time ranges.

[0119] Among them, the delivery warning information can be a warning notification sent to the production management system of the vehicle manufacturer when the predicted arrival time meets the preset time threshold condition. The delivery warning information is used to trigger the vehicle manufacturer to carry out resource preparation operations.

[0120] Resource preparation work can be the unloading preparation work carried out by the vehicle manufacturer after receiving the arrival warning information. Resource preparation work includes pre-allocating unloading platforms, dispatching forklifts, and notifying quality inspection personnel.

[0121] Optionally, the terminal obtains the predicted arrival time of the parts transport vehicle corresponding to the supply order information. The predicted arrival time represents the predicted time when the parts transport vehicle will arrive at the vehicle manufacturer corresponding to the parts. The predicted arrival time is compared with a preset time threshold. For example, if the predicted arrival time is within 60 minutes, it is determined that the predicted arrival time meets the preset time threshold condition. If the predicted arrival time meets the preset time threshold condition, a delivery warning information is sent to the production management system of the vehicle manufacturer. The delivery warning information is used to trigger the vehicle manufacturer to carry out resource preparation operations, including pre-allocating unloading platforms, dispatching forklifts, and notifying quality inspection personnel.

[0122] The technical solution provided in this embodiment sends a delivery warning to the production management system of the vehicle manufacturer when the predicted arrival time meets the preset time threshold condition. This helps to trigger the vehicle manufacturer to carry out resource preparation operations in advance, thereby improving the efficiency of vehicle operation.

[0123] The following example illustrates the order processing method provided in this application. This example demonstrates the application of this method to a terminal.

[0124] With the rapid development of the new energy vehicle industry, its supply chain management faces increasingly complex challenges. Compared with traditional automobiles, new energy vehicles have a wide variety of parts, significantly different production cycles, and highly dynamic market demand fluctuations. These factors pose a severe test to traditional automotive supply chain management models. Currently, the traditional supply chain management model adopted by the new energy vehicle manufacturing industry is mainly a push model of forecasting-stocking-production. Vehicle manufacturers formulate production plans based on medium- and long-term market forecasts and linearly decompose and issue production and procurement instructions to suppliers at all levels upstream of the supply chain through systems such as Enterprise Resource Planning (ERP) and Material Requirements Planning (MRP).

[0125] However, these technologies still have many shortcomings. First, traditional supply chain models rely heavily on macro-level market demand forecasts, making them ill-suited to the dynamic demands of the diversified and personalized new energy vehicle market. Especially when facing technological iterations and shifts in consumer preferences, their forecast accuracy is low, leading to high risks of inventory buildup and material shortages. Second, the manufacturing and management systems of vehicle manufacturers and suppliers at all levels are independent, lacking a real-time data integration and collaboration mechanism across the entire supply chain, resulting in significant delays and distortions in information flow. Furthermore, while related technologies aim to build information-sharing platforms to address information silos, most remain at the level of information interconnection, lacking intelligent closed-loop control capabilities from risk identification to autonomous solution generation. Third, related MRP / ERP systems lack real-time optimization and dynamic scheduling capabilities for multiple variables and objectives. When faced with order changes, manual intervention is often required, resulting in insufficient real-time response, low efficiency, and difficulty in achieving an effective balance between multiple objectives such as ensuring delivery cycles, controlling costs, and maximizing capacity utilization. Fourth, the relevant material transportation and distribution information is independent of the production execution system. Vehicle manufacturers cannot accurately track and manage the location, status, and estimated arrival time of materials in transit in real time, hindering precise coordination between material arrival and production line operation. This results in unnecessary delays and resource waste during production. Therefore, improving supply chain efficiency, reducing reliance on forecasting, and enhancing the supply chain's ability to anticipate and respond to risks are urgent issues for the new energy vehicle industry in the face of highly dynamic market demands and complex supply chain environments.

[0126] This embodiment provides a method and system for collaborative production and distribution of new energy vehicle components based on real-time order-driven models, which can solve the problems of material shortages, inventory backlogs, and supply chain risks in traditional push-based supply chain models. This embodiment constructs a full-chain collaborative intelligent control platform, driven by real-time orders, connecting a dynamic collaborative network across the entire supply chain of "sales-planning-production-quality inspection-logistics," ensuring efficient operation and precise coordination of each link in the supply chain.

[0127] (I) Overview of the Holistic Approach:

[0128] refer to Figure 2 The method in this embodiment includes the following steps:

[0129] S1: Dynamic Order Detection and Upload:

[0130] The sales terminal obtains new energy vehicle orders placed by customers in real time. The orders include requirements such as vehicle configuration, color, optional packages, and delivery time. The order data is uploaded to the full-chain collaborative intelligent control platform in real time through an encrypted application programming interface (API). This data serves as the initial data stream for subsequent steps.

[0131] S2: Intelligent BOM (Bill of Materials) Decomposition and Requirements Generation:

[0132] The end-to-end collaborative intelligent control platform receives order data, calls upon the latest product structure data from the Product Data Management (PDM) system, and intelligently decomposes the vehicle requirements in the order into a Bill of Materials (BOM). The process is as follows: Figure 3 (Including: receiving real-time order data; parsing order characteristics; querying the PDM system to obtain the BOM list; decomposing and verifying the BOM list layer by layer; reading the next line of materials; verifying the material status to see if production is stopped / frozen; if production is stopped, querying alternative materials and replacing them; if frozen, triggering a BOM matching anomaly warning; checking if it is the last line; if so, generating the initial material requirement order for this order; demand stream aggregation; generating the total component demand plan; outputting the demand plan to the plan decomposition module), specifically including:

[0133] S2.1: Precise BOM Version Matching: Extract vehicle model code, configuration code, and order timestamp from customer order data as composite query keys. Within the Product Data Management (PDM) system connected to the full-chain collaborative intelligent control platform, perform a precise matching query using multi-key-value indexes to determine a unique and valid Master Bill of Materials (BOM) version at that timestamp.

[0134] S2.2: Recursive Decomposition and Validity Verification: A recursive descent tree traversal algorithm is used to decompose the unique valid BOM version layer by layer to calculate the net requirement quantity of each component. During this decomposition process, the material master data table is queried in real time to obtain the current status field of each component. When the status field indicates "discontinued," the preset alternative part relationship table is automatically queried and the valid alternative part code is used for replacement; when the status field indicates "frozen," an early warning signal is generated and the requirement calculation for that material is stopped.

[0135] S2.3: Demand Stream Aggregation: Using a time window-based streaming processing mechanism, the demand quantities of the components generated within a preset time window are accumulated to generate a total demand list for all components.

[0136] S3: Collaborative Plan Breakdown and Order Issuance:

[0137] The end-to-end collaborative intelligent control platform, based on the total component demand list generated by S2, integrates pre-maintained multi-dimensional supplier data, including but not limited to capacity levels, geographical distribution, historical performance indicators, and contract prices, to decompose planned tasks and issue orders. In the plan decomposition stage, for general or standard parts, the platform employs a rule-based rapid allocation strategy. For critical or customized parts, a Non-Dominated Sorting Genetic Algorithm II (NSGA-II) is used for plan decomposition. Specifically, this optimization model defines the decision variable as X. ij , where X ij This indicates the quantity of material i allocated to supplier j. The multi-objective function of the model includes: (1) minimizing the total cost, which covers procurement costs, transportation costs, and inventory management-related costs; (2) minimizing the delivery cycle, which is defined as the total time required from the issuance of the supply order to the arrival of the material; and (3) maximizing the capacity utilization rate, which is achieved by balancing the allocation of supplier resources to avoid idleness or overload. To ensure the rationality of the plan decomposition and order issuance, the objective function should also meet the following constraints: demand satisfaction constraint, ensuring that the total demand of all parts is fully covered; supplier capacity constraint, preventing the allocation from exceeding the supplier's maximum production capacity; quality access constraint, only allowing the selection of suppliers that meet the preset historical performance threshold and standard certification; and logistics time constraint, considering the impact of geographical location on transportation timeliness to minimize potential delay risks. Subsequently, the full-chain collaborative intelligent control platform uses the NSGA-II algorithm (Nondominated Sorting Genetic Algorithm II) to solve the multi-objective optimization problem through the nondominated sorting mechanism and the crowding comparison operator to obtain the optimal allocation scheme. Based on the generated optimal allocation scheme, the platform automatically converts the decomposed production tasks into supply orders and seamlessly transmits them to the supplier's production management system through a standardized API interface, ensuring the transparency and traceability of task allocation and supporting dynamic adjustments to adapt to supply chain fluctuations.

[0138] S4: Real-time transmission and monitoring of production and quality data:

[0139] After receiving the supply order from S3, the supplier organizes production. The end-to-end collaborative intelligent control platform, based on the real-time push mechanism of the distributed message queue of a distributed messaging system, receives production and quality data in real time from the supplier's Manufacturing Execution System (MES) and Quality Management System (QMS). Production data includes at least the output quantity at each workstation and equipment status; quality data includes at least the measurement values ​​of critical dimensions and acceptance criteria. This step aims to build a high-throughput, low-latency data feedback loop to achieve transparent and synchronized monitoring of the supplier's planned execution process.

[0140] S5: Intelligent Risk Warning and Decision Support

[0141] This step involves analyzing the production and quality data received in real time by S4 to identify potential supply risks and automatically generate remedial measures. (Process Reference) Figure 4 (Including: initiating control and management, real-time monitoring of production and quality data; data preprocessing and feature extraction; deviation calculation; inputting feature vectors; outputting risk levels based on logistic regression and random forest risk rating models; determining whether it is medium or high risk; if so, generating intelligent solutions, including querying global real-time data and generating solutions; determining whether to execute automatically; pushing solutions to management personnel; management personnel confirming or modifying solutions; the system automatically executing solutions; and feedback of execution results), specifically including:

[0142] S5.1: Data monitoring and comparison: The real-time received production and quality data are preprocessed and feature extracted. The processed data is compared with the planned node data and the preset quality threshold to calculate the deviation.

[0143] S5.2: Machine Learning Risk Rating: A pre-trained risk rating model based on logistic regression and random forest is used to rate deviations. The input feature vector of this model includes at least: deviation percentage, remaining time until the planned delivery node, criticality level of the component, and the supplier's historical on-time delivery rate (ODR) and historical defect rate per million units (PPM). The model outputs a multi-level risk rating (high, medium, low).

[0144] S5.3: Intelligent Solution Generation: When the risk rating is determined to be "Medium" or "High," the system will automatically trigger an early warning and activate the intelligent decision-making module. This module generates solutions based on real-time data such as the global supplier capacity pool, in-transit transportation, and transportation cycles. Specifically, the system automatically assesses the current situation and proposes optimization solutions by monitoring key data such as the global supplier capacity pool, in-transit transportation, and transportation cycles. Solutions include, but are not limited to: sending production expediting reminders to suppliers to promptly increase their production priority; activating backup or alternative suppliers and automatically generating new purchase orders to ensure production is not affected by material shortages; and dynamically adjusting the vehicle manufacturer's production schedule based on material delays to prevent production line shutdowns due to material shortages.

[0145] S5.4: Solution Push and Confirmation: The generated solution will be pushed to management personnel for confirmation or revision. In specific risk scenarios, the system can be set to execute automatically to improve response speed and efficiency. After the solution is confirmed or revised, the system will automatically execute the solution, provide feedback on the execution, and continuously monitor production and quality data in real time.

[0146] S6: Visualized Delivery and In-Transit Management

[0147] After component production is completed, the supplier processes the goods shipment and uploads the vehicle information for transporting the components. Through an Internet of Things (IoT) gateway, information such as the location, speed, and estimated arrival time of the transport vehicles is integrated and displayed in real-time on a visual map interface. This embodiment also applies an event-driven architecture. When the estimated arrival time of a vehicle falls within a preset time threshold (e.g., 60 minutes), the end-to-end collaborative intelligent control platform automatically publishes an "approaching arrival" event to the internal message bus. The vehicle manufacturer, as a subscriber to this event, automatically triggers a series of resource preparation tasks upon receiving the signal, such as pre-allocating unloading platforms, dispatching forklifts, and notifying quality control personnel, achieving precise coordination between receiving goods and line-side production.

[0148] (II) System Architecture:

[0149] See Figure 5 This embodiment presents a method and system for dynamic collaborative production and distribution of new energy vehicle components based on real-time order-driven processes. The system architecture comprises a sales terminal, a full-chain collaborative intelligent control platform, a supplier production management system, a logistics tracking system, and a vehicle manufacturer's production management system. These systems are interconnected through secure communication protocols and standardized interfaces, forming an integrated collaborative system among multi-source heterogeneous systems.

[0150] 1. Full-chain collaborative intelligent control platform:

[0151] As the decision-making core and data control center of the entire system, it integrates the following key modules:

[0152] Order receiving module: Receives and verifies real-time order data from the sales terminal to ensure the authenticity and integrity of the orders.

[0153] Intelligent BOM decomposition module: Built-in intelligent algorithm to decompose and validate the BOM of the whole vehicle order to ensure accurate material requirements.

[0154] The planning decomposition and optimization module combines multi-dimensional supplier data to perform plan decomposition based on rules and multi-objective optimization algorithms, and automatically generates supply orders.

[0155] Data monitoring and risk warning engine: Collects supplier production and quality data in real time, conducts risk assessment through machine learning models, and generates solutions.

[0156] Visualized delivery monitoring module: Connects to the logistics tracking system to display the real-time status of transport vehicles and trigger in-plant receiving preparations.

[0157] Central database: Used to store and manage order data, BOM data, supplier data, production and quality data, logistics data, etc.

[0158] Interface and secure communication module: Enables standardized data interaction with external systems (ERP, MES, QMS, etc.) and ensures the security of data transmission.

[0159] 2. Sales terminals: including 4S store management system, official website or mobile APP (application) backend, used to capture customer order demand in real time and transmit it to the whole chain collaborative intelligent control platform through encrypted channel.

[0160] 3. Supplier Production Management System: including MES, QMS, etc., used to execute production tasks, collect process data and transmit it back in real time.

[0161] 4. Logistics Tracking System: Collects information such as GPS (Global Positioning System) location, speed, and estimated arrival time of transport vehicles, and uploads it to the full-chain collaborative intelligent control platform.

[0162] 5. Vehicle manufacturing plant production management system: It is connected to the internal interface of the full-chain collaborative intelligent control platform to receive accurate arrival information and material demand plans, so as to realize the dynamic matching of production cycle and material supply.

[0163] This embodiment breaks through the limitations of the traditional "forecast-stocking-production" model, realizing end-to-end dynamic optimization and closed-loop control driven by real-time market demand. Compared with related technologies, this embodiment has the following beneficial technical effects:

[0164] 1. Achieving Precise Matching and Efficiency Improvement in the Supply Chain: The technical solution in this embodiment uses real-time orders from end customers (S1) as the data-driven source, replacing the push-based model based on macro market forecasts in related technologies, thus avoiding the inherent risk of forecast bias. Orders are analyzed using an intelligent BOM decomposition method (S2), and validity verification logic is incorporated during the decomposition process to ensure the accuracy of net material requirements calculation. Combined with collaborative planning decomposition using a multi-objective optimization algorithm (S3), production task allocation is based on a comprehensive optimal solution considering cost, cycle time, and capacity utilization. By directly aligning the material flow and information flow of the entire supply chain with real market demand, inventory backlogs or material shortages caused by forecast inaccuracies are effectively suppressed, reducing the total cost of the supply chain.

[0165] 2. Establish a proactive supply chain risk identification and closed-loop control mechanism to enhance supply chain stability: This embodiment introduces a data monitoring and risk early warning engine. By collecting suppliers' production and quality data in real time (S4), a pre-built machine learning model is used to quantify the risk rating of deviations between real-time data and planned data (S5), enabling the pre-identification of potential supply disruptions or quality defects. When the rating result triggers a preset threshold, the system can automatically generate remedial strategies based on the global supplier resource pool. A closed-loop control path of "real-time monitoring - intelligent assessment - automatic decision-making" is constructed, changing the passive and delayed response mode to supply chain anomalies in related technologies, thereby improving the robustness of the supply chain in dealing with emergencies.

[0166] 3. A complete data connectivity and status visualization system was constructed, achieving transparent management of the production and logistics process: This embodiment breaks down data barriers between vehicle manufacturers, suppliers at all levels, and logistics service providers through standardized data interfaces and real-time push mechanisms (S4), integrating isolated production, quality, and logistics information into a full-chain collaborative intelligent control platform. Combined with a visualized delivery and in-transit management module (S6), end-to-end logistics tracking is achieved from parts production line completion to entry into the vehicle assembly plant. This full-chain digital twin capability enables managers to make decisions based on accurate, real-time, and global data, providing a solid data foundation for just-in-time supply and automated, intelligent scheduling of in-plant logistics in lean manufacturing. The full-chain collaborative intelligent control platform in this embodiment acts as a central data hub, integrating heterogeneous data from order receipt (S1), plan generation (S3), production execution monitoring (S4) to in-transit transportation management (S6). Through a real-time data feedback mechanism (S4) and IoT-integrated logistics tracking technology (S6), end-to-end logistics tracking is achieved from parts production line completion to entry into the vehicle assembly plant. This end-to-end digital twin capability enables managers to make decisions based on accurate, real-time, and global data, providing a solid data foundation for achieving just-in-time supply and automated, intelligent scheduling of in-plant logistics in lean manufacturing.

[0167] 4. Dynamic collaboration and optimized allocation of supply chain network resources have been achieved, improving overall operational efficiency and flexibility: In this embodiment, the full-chain collaborative intelligent control platform acts as the central hub, treating all suppliers as a unified, dynamically schedulable global capacity pool. During collaborative plan decomposition (S3) and risk response (S5), the platform, based on a multi-objective optimization algorithm, considers multiple factors such as cost, cycle time, and capacity load from a global perspective to optimize resource allocation. Through a networked collaborative model, dynamic resource allocation is achieved from a globally optimal perspective, overcoming the limitations of isolated supplier capacity and opaque information in traditional models, and significantly improving the flexibility and robustness of the supply chain.

[0168] This embodiment transforms the supply chain management model from "prediction-based push" to "real-time order-driven pull," and achieves real-time perception, intelligent decision-making, and closed-loop control across the entire chain through an integrated "full-chain collaborative intelligent control" platform. Specifically: 1. Closed-loop collaborative control mechanism based on the full-chain collaborative intelligent control platform: This mechanism refers to the connection and integration of six steps—real-time order perception (S1), intelligent BOM decomposition based on validity verification (S2), collaborative plan decomposition based on multi-objective optimization (S3), real-time feedback monitoring of production and quality data (S4), risk warning and decision support based on machine learning (S5), and visualized delivery and internal logistics linkage (S6)—through the full-chain collaborative intelligent control platform. This forms a closed-loop control system with real-time data flow, bidirectional status feedback, and dynamic decision adjustment, solving the technical problems of information fragmentation and response lag in related technologies. 2. Intelligent Early Warning and Autonomous Decision-Making Method for Supply Chain Risks: By comparing production / quality data with planned requirements in real time, and utilizing multi-factor fusion risk rating based on logistic regression and random forest models, this method automatically generates executable decision-making solutions based on global resource pool data (such as the automatic creation of backup supplier orders). This method represents a fundamental shift from manual problem discovery to the system's autonomous identification and handling of problems. 3. Intelligent BOM Decomposition Algorithm for Real-Time Orders: Driven by order characteristics and timestamps, this algorithm achieves unique and valid BOM version matching. The decomposition process incorporates material status validity verification and substitution logic to ensure the accuracy and completeness of demand generation. 4. Collaborative Planning Decomposition Method Considering Multi-Objective Optimization: This method models the component allocation problem as a multi-objective optimization problem, comprehensively considering cost, delivery cycle, and capacity utilization. The NSGA-II algorithm is used for solving this problem, achieving globally optimal production task decomposition and supplier order issuance. 5. Real-time Feedback Interface Mechanism for Production and Quality Data: This mechanism enables real-time push of supplier MES / QMS data through standardized APIs or message queues, replacing traditional timed batch methods and providing a technical foundation for closed-loop feedback in the supply chain. 6. Linkage between logistics information and in-plant systems: By linking the estimated arrival time of transport vehicles with the vehicle manufacturer's warehouse management system in real time, unloading, quality inspection and other preparations are automatically triggered when the vehicle enters the preset time threshold. This overcomes the response delay and reliance on human intervention caused by passive manual notification after the arrival of goods in the traditional supply chain, and achieves lean collaboration of unloading and use as soon as goods arrive.

[0169] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0170] Based on the same inventive concept, this application also provides an order processing apparatus for implementing the order processing method described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in one or more order processing apparatus embodiments provided below can be found in the limitations of the order processing method described above, and will not be repeated here.

[0171] In one exemplary embodiment, such as Figure 6 As shown, an order processing apparatus 600 is provided, which may include:

[0172] The information acquisition module 601 is used to acquire vehicle order information and determine the bill of materials information corresponding to the vehicle order information.

[0173] The information decomposition module 602 is used to decompose the bill of materials information to obtain the total demand information of vehicle parts corresponding to the vehicle order information.

[0174] The information determination module 603 is used to determine the target allocation scheme information corresponding to the total demand information based on the total demand information and the multi-dimensional attribute information of the suppliers of vehicle parts;

[0175] The information generation module 604 is used to generate supply order information corresponding to the target supplier based on the target allocation scheme information, and to send the supply order information to the target supplier's production management system.

[0176] In an exemplary embodiment, the device 600 further includes: an early warning generation module, configured to acquire production data and quality data fed back by the production management system of the target supplier; compare the production data with the production node data corresponding to the target supplier to obtain production deviation data, and compare the quality data with the quality threshold corresponding to the target supplier to obtain quality deviation data; input the production deviation data and quality deviation data into a pre-trained risk prediction model for risk prediction processing to obtain risk prediction information corresponding to the supply order information; and generate risk early warning information corresponding to the supply order information when the risk prediction information reaches a preset risk threshold.

[0177] In an exemplary embodiment, the device 600 further includes: a solution generation module, used to acquire the target supplier's capacity data and transportation data; and to generate risk response solution information corresponding to the supply order information based on the capacity data, transportation data, and risk prediction information.

[0178] In an exemplary embodiment, the information decomposition module 602 is further configured to perform layer-by-layer decomposition and validity verification on the bill of materials information to obtain the net demand quantity of each vehicle component; and to aggregate the net demand quantity according to a preset time window to obtain the total demand information.

[0179] In an exemplary embodiment, the information determination module 603 is further configured to construct a multi-objective optimization model based on total demand information and multi-dimensional attribute information; the optimization objectives of the multi-objective optimization model include minimizing total cost, minimizing delivery cycle and maximizing capacity utilization; and to solve the multi-objective optimization model to obtain target allocation scheme information.

[0180] In an exemplary embodiment, the information acquisition module 601 is further configured to extract vehicle model identification information, configuration identification information, and order time information from the vehicle order information; determine the query information corresponding to the preset product data management system based on the vehicle model identification information, configuration identification information, and order time information; and determine the bill of materials information corresponding to the vehicle order information from the product data management system based on the query information.

[0181] In an exemplary embodiment, the device 600 further includes: an information sending module, configured to obtain the predicted arrival time of the parts transport vehicle corresponding to the supply order information; the predicted arrival time represents the predicted time when the parts transport vehicle arrives at the vehicle manufacturer corresponding to the parts; if the predicted arrival time meets a preset time threshold condition, the module sends a delivery warning information to the production management system of the vehicle manufacturer; the delivery warning information is used to trigger the vehicle manufacturer to perform resource preparation operations.

[0182] Each module in the aforementioned order processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0183] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 7 As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. 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 input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements an order processing method. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0184] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0185] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0186] In one exemplary embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above-described method embodiments.

[0187] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0188] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0189] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0190] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. An order processing method, characterized in that, The method includes: Obtain vehicle order information and determine the bill of materials information corresponding to the vehicle order information; The bill of materials information is decomposed to obtain the total demand information for vehicle parts corresponding to the vehicle order information; Based on the total demand information and the multi-dimensional attribute information of the vehicle component suppliers, the target allocation scheme information corresponding to the total demand information is determined; Based on the target allocation scheme information, the corresponding supply order information for the target supplier is generated, and the supply order information is sent to the production management system of the target supplier.

2. The method according to claim 1, characterized in that, After the supply order information is sent to the target supplier's production management system, the process also includes: Obtain production and quality data fed back from the target supplier's production management system; The production data is compared with the production node data corresponding to the target supplier to obtain production deviation data, and the quality data is compared with the quality threshold corresponding to the target supplier to obtain quality deviation data. The production deviation data and the quality deviation data are input into a pre-trained risk prediction model for risk prediction processing to obtain the risk prediction information corresponding to the supply order information. When the risk prediction information reaches a preset risk threshold, risk warning information corresponding to the supply order information is generated.

3. The method according to claim 2, characterized in that, After generating risk warning information corresponding to the supply order information when the risk prediction information reaches a preset risk threshold, the process further includes: Obtain the target supplier's production capacity and transportation data; Based on the production capacity data, the transportation data, and the risk prediction information, risk response plan information corresponding to the supply order information is generated.

4. The method according to claim 1, characterized in that, The process of decomposing the bill of materials information to obtain the total demand information for vehicle parts corresponding to the vehicle order information includes: The bill of materials information is decomposed and validated layer by layer to obtain the net required quantity of each vehicle component. The net demand quantity is aggregated according to a preset time window to obtain the total demand information.

5. The method according to claim 1, characterized in that, The step of determining the target allocation scheme information corresponding to the total demand information based on the total demand information and the multi-dimensional attribute information of the vehicle component suppliers includes: Based on the total demand information and the multi-dimensional attribute information, a multi-objective optimization model is constructed; the optimization objectives of the multi-objective optimization model include minimizing total cost, minimizing delivery cycle, and maximizing capacity utilization. The multi-objective optimization model is solved to obtain the objective allocation scheme information.

6. The method according to claim 1, characterized in that, The determination of the bill of materials information corresponding to the vehicle order information includes: Extract vehicle model identification information, configuration identification information, and order time information from the vehicle order information; Based on the vehicle identification information, the configuration identification information, and the order time information, determine the query information corresponding to the preset product data management system; Based on the query information, the bill of materials information corresponding to the vehicle order information is determined from the product data management system.

7. The method according to any one of claims 1 to 6, characterized in that, The method further includes: Obtain the predicted arrival time of the parts transport vehicle corresponding to the supply order information; the predicted arrival time represents the predicted time when the parts transport vehicle will arrive at the vehicle manufacturer corresponding to the vehicle parts. If the predicted arrival time meets the preset time threshold, a delivery warning message is sent to the production management system of the vehicle manufacturer; the delivery warning message is used to trigger the vehicle manufacturer to perform resource preparation operations.

8. An order processing device, characterized in that, The device includes: The information acquisition module is used to acquire vehicle order information and determine the bill of materials information corresponding to the vehicle order information; The information decomposition module is used to decompose the bill of materials information to obtain the total demand information for vehicle parts corresponding to the vehicle order information. The information determination module is used to determine the target allocation scheme information corresponding to the total demand information based on the total demand information and the multi-dimensional attribute information of the suppliers of the vehicle parts; The information generation module is used to generate supply order information corresponding to the target supplier based on the target allocation scheme information, and to send the supply order information to the production management system of the target supplier.

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 according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images