Part packaging tool demand prediction method, device, equipment and storage medium

Abstract

The application discloses a kind of part packaging appliance demand prediction method, device, equipment and storage medium, wherein the method includes the following steps: according to the mapping relationship of established vehicle configuration and parts list, determine target parts;Based on part attribute, packaging appliance attribute and pre-set matching rule, construct knowledge graph, and utilize the knowledge graph to determine the packaging appliance matched with the target parts;The preliminary demand of the packaging appliance is calculated, and the preliminary demand is optimized using a pre-set optimization algorithm, to obtain the final demand prediction result of the packaging appliance of the target parts.This application can improve the accuracy of vehicle parts packaging appliance demand prediction, and improve the response speed, reduce operating costs while improving management efficiency.

Description

Technical Field

[0001] This invention relates to the field of vehicle manufacturing technology, and in particular to a method, apparatus, equipment, and storage medium for predicting the demand for parts packaging equipment. Background Technology

[0002] In the automotive manufacturing industry, the transportation of parts from suppliers to vehicle manufacturers relies on specialized packaging equipment (such as racks, turnover boxes, pallets, and collapsible boxes). With the accelerating pace of product updates and iterations in the automotive industry, traditional methods of determining demand, which primarily depend on manual experience, present the following problems: First, relying on manual verification of component packaging requirements based on the vehicle model's Bill of Materials (BOM) is labor-intensive, error-prone, and limited by single considerations, leading to inappropriate equipment selection and configuration. Second, existing requirement calculations are typically theoretical values, lacking subsequent multi-objective constraint optimization. In other words, the calculated requirements are not validated or optimized, resulting in solutions that are often infeasible or suboptimal in practice. Finally, when vehicle configuration data (BOM) changes, the system usually requires a complete recalculation of all parts, resulting in massive data processing and significant time consumption, failing to meet the rapid logistics response requirements of agile manufacturing. Furthermore, it cannot intelligently optimize and dynamically adjust the model based on actual usage data and historical data.

[0003] Therefore, how to accurately predict the demand for packaging equipment for vehicle parts without relying on manual labor is a technical problem that urgently needs to be solved. Summary of the Invention

[0004] The main objective of this invention is to provide a method, apparatus, equipment, and storage medium for predicting the demand for packaging equipment for vehicle parts, which can improve the accuracy of predicting the demand for packaging equipment for vehicle parts, increase response speed, reduce operating costs, and improve management efficiency.

[0005] In a first aspect, this application provides a method for forecasting the demand for parts packaging equipment, wherein the method includes the following steps: Based on the established mapping relationship between vehicle configuration and parts list, the target parts are determined; Based on part attributes, packaging equipment attributes, and preset matching rules, a knowledge graph is constructed, and the knowledge graph is used to determine the packaging equipment that matches the target part. The initial demand for the packaging equipment is calculated, and the initial demand is optimized using a preset optimization algorithm to obtain the final demand prediction result for the packaging equipment of the target part.

[0006] In conjunction with the first aspect mentioned above, as an optional implementation method, Based on the obtained average daily parts demand, the number of parts loaded per packaging container, and the packaging container turnover rate, calculate the basic demand for packaging containers. Based on the obtained packaging equipment turnover rate and transportation cycle, as well as the basic demand, calculate the in-transit demand for packaging equipment. Based on the obtained safety stock factor and the basic demand and in-transit demand, calculate the preliminary demand for packaging equipment.

[0007] In conjunction with the first aspect mentioned above, as an optional implementation method, the part attributes are constructed as a first type of entity node, and the part attributes include: size, weight, fragility and material; The packaging equipment attributes are constructed as a second type of entity node, and the packaging equipment attributes include: packaging equipment type and specifications. The preset matching rule is encapsulated as a rule node, wherein the preset matching rule is to match the corresponding packaging container according to the part attributes; Construct relationship edges connecting the first type of entity node, the second type of entity node, and the rule node. The relationship edges are the matching relationships between entity nodes and rule nodes, and the matching relationships include: applicable, excluded, and priority. A knowledge graph is constructed based on the first type of entity nodes, the second type of entity nodes, rule nodes, and relationship edges.

[0008] In conjunction with the first aspect mentioned above, as an optional implementation, based on the attributes of the current target part, a forward traversal is performed along the relational edges of the knowledge graph, and applicable rule nodes are activated to generate a list of candidate packaging containers. For each packaging device in the candidate packaging device list, a reverse search is performed to determine whether there is an exclusion relationship between it and the current target part; If it exists, the packaging device will be removed from the list of candidate packaging devices. If, after the elimination operation, multiple packaging containers matching the current target part are detected in the candidate packaging container list, the final packaging container matching the current target part is determined according to the priority weight value corresponding to the relation edge of the connection rule node.

[0009] In conjunction with the first aspect mentioned above, as an optional implementation method, multiple resource consumption indicators are used as the objective function. These multiple resource consumption indicators include: cost indicators, space occupancy indicators, response time indicators, and stockout risk indicators. Set constraints, the preset conditions including: supplier capacity constraints, warehouse capacity constraints, total budget constraints, and equipment lifespan constraints; The optimal value of the objective function is obtained by using a genetic algorithm or particle swarm optimization algorithm under the premise of satisfying the constraints, and the optimal value is used as the final demand prediction result for the packaging equipment of the target part.

[0010] In conjunction with the first aspect mentioned above, as an optional implementation method, the configuration data of the target vehicle model is obtained; The parts list corresponding to the target vehicle model is parsed based on the configuration data to establish a mapping relationship between the vehicle configuration and the parts list of the target vehicle model; Based on the mapping relationship, all the parts required for the target vehicle model are determined and designated as the target parts.

[0011] In conjunction with the first aspect mentioned above, vehicle configuration can be monitored as an optional implementation method. If a change in vehicle configuration is detected, the change type is identified based on the differences before and after the change. The change types include: addition, modification, and deletion. Execute the corresponding processing strategy based on the change type.

[0012] Secondly, this application provides a demand forecasting device for parts packaging equipment, the device comprising: The determination module is used to determine the target parts based on the established mapping relationship between vehicle configuration and parts list; The processing module is used to construct a knowledge graph based on part attributes, packaging equipment attributes and preset matching rules, and use the knowledge graph to determine the packaging equipment that matches the target part. The prediction module is used to calculate the initial demand for the packaging equipment and optimize the initial demand using a preset optimization algorithm to obtain the final demand prediction result for the packaging equipment of the target part.

[0013] Thirdly, this application also provides an electronic device, the electronic device comprising: a processor; and a memory storing computer-readable instructions, which, when executed by the processor, implement the method described in any one of the first aspects.

[0014] Fourthly, this application also provides a computer-readable storage medium storing computer program instructions that, when executed by a computer, cause the computer to perform the method described in any of the first aspects.

[0015] This application provides a method, apparatus, device, and storage medium for predicting the demand for vehicle parts packaging equipment. The method includes the following steps: determining target parts based on an established mapping relationship between vehicle model configurations and parts lists; constructing a knowledge graph based on part attributes, packaging equipment attributes, and preset matching rules, and using the knowledge graph to determine packaging equipment matching the target parts; calculating the preliminary demand for the packaging equipment, and optimizing the preliminary demand using a preset optimization algorithm to obtain the final demand prediction result for the packaging equipment of the target parts. This application can improve the accuracy of demand prediction for vehicle parts packaging equipment, increase response speed, reduce operating costs, and improve management efficiency.

[0016] It should be understood that the above general description and the following detailed description are merely exemplary and do not limit the invention. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0018] Figure 1 This is a flowchart of a demand forecasting method for parts packaging equipment provided in the embodiments of this application; Figure 2 This is a schematic diagram of a demand forecasting device for parts packaging equipment provided in an embodiment of this application; Figure 3 This is a schematic diagram of an electronic device provided in an embodiment of this application; Figure 4 This is a schematic diagram of a computer-readable program medium provided in an embodiment of this application. Detailed Implementation

[0019] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.

[0020] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. Some of the block diagrams shown in the drawings represent functional entities and do not necessarily correspond to physically or logically independent entities.

[0021] The embodiments of this application will be further described in detail below with reference to the accompanying drawings.

[0022] Reference Figure 1 , Figure 1 The diagram shown is a flowchart of a demand forecasting method for parts packaging equipment provided by the present invention. Figure 1 As shown, the method includes the following steps: Step S101: Determine the target parts based on the established mapping relationship between vehicle configuration and parts list.

[0023] Specifically, this involves obtaining the configuration data of the target vehicle model; The parts list corresponding to the target vehicle model is parsed based on the configuration data to establish a mapping relationship between the vehicle configuration and the parts list of the target vehicle model; Based on the mapping relationship, all the parts required for the target vehicle model are determined and designated as the target parts.

[0024] To illustrate this with an example, suppose the target vehicle is the S-model Sport Premium Sedan. The system obtains configuration data for this model that includes optional features such as a panoramic sunroof, leather seats, and a 360-degree surround-view camera. First, this configuration data is parsed, querying the underlying Bill of Materials (BOM). This reveals that the panoramic sunroof corresponds to part number A01, the leather seats to part number B02, and the 360-degree surround-view camera to part number C03, thus establishing a mapping relationship between vehicle configurations and specific parts. Finally, based on this mapping relationship, it is determined that the S-model Sport Premium Sedan must include all components such as parts A01, B02, and C03 during production. These extracted parts (e.g., A01, B02, C03) are then identified as the target parts for subsequent packaging equipment matching and requirements calculation.

[0025] In one embodiment, after obtaining the configuration data of the target vehicle model, it undergoes cleaning, standardization, and correlation processing. Data cleaning includes missing value imputation, outlier removal, and data format standardization.

[0026] In one embodiment, before determining the target part based on the established mapping relationship between vehicle configuration and parts list, the process includes: monitoring the vehicle configuration; if a change in the vehicle configuration is detected, identifying the change type based on the differences before and after the change, wherein the change type includes: addition, modification, and deletion; and executing a corresponding processing strategy based on the change type.

[0027] To illustrate this more clearly, consider the example of a mass-produced vehicle that has added a smart driving luxury option package, which includes five new components such as a lidar and a domain controller.

[0028] Implementation process: 1. Change detection: The BOM version number change (from V2.3 to V2.4) was monitored, and 5 new parts (all of which are new node types) were identified through Diff comparison.

[0029] 2. Incremental calculation: The prediction process (S102-S103) is triggered only for these 5 newly added parts, reusing existing knowledge graph rules and prediction model parameters to achieve incremental calculation without recalculating the remaining parts.

[0030] 3. Impact Analysis: Calculate the new demand (e.g., 50 units / month for 2 types of specialized racks; 30 units / month for 1 type of specialized turnover box) and assess the impact on existing inventory and storage space.

[0031] 4. Solution Generation: Output a list of new equipment requirements and a procurement budget of approximately 150,000 yuan within 30 minutes.

[0032] Understandably, monitoring BOM version number changes and identifying the changed part set through Diff comparison when the version number changes; identifying three types of changes and adopting differentiated processing strategies: New node: Completely execute the entire S102-S103 calculation process; Delete node: Mark it as pending recycling and release equipment resources; Attribute modification node: Only the affected calculation steps are re-executed; 3. Incremental calculation: The prediction process (S102-S103) is triggered only for changed parts, reusing existing knowledge graph rules and prediction model parameters; 4. Impact Analysis: Assess the impact of the changes on existing inventory and storage space; 5. Parallel computing: Supports parallel computing for batch changes, significantly improving response efficiency in scenarios involving large-scale configuration changes.

[0033] This mechanism transforms the traditional full recalculation mode (which usually takes several days) into a partial incremental calculation mode (minutes), greatly improving the response speed in scenarios of rapid model iteration.

[0034] Step S102: Based on the part attributes, packaging equipment attributes, and preset matching rules, construct a knowledge graph, and use the knowledge graph to determine the packaging equipment that matches the target part.

[0035] Specifically, a knowledge graph is constructed based on part attributes, packaging equipment attributes, and preset matching rules, including: The part attributes are constructed as a first type of entity node, and the part attributes include: size, weight, fragility and material; The packaging equipment attributes are constructed as a second type of entity node, and the packaging equipment attributes include: packaging equipment type and specifications. The preset matching rule is encapsulated as a rule node, wherein the preset matching rule is to match the corresponding packaging container according to the part attributes; Construct relationship edges connecting the first type of entity node, the second type of entity node, and the rule node. The relationship edges are the matching relationships between entity nodes and rule nodes, and the matching relationships include: applicable, excluded, and priority. A knowledge graph is constructed based on the first type of entity nodes, the second type of entity nodes, rule nodes, and relationship edges.

[0036] To illustrate this, let's assume the target part is a glass rearview mirror. Its first type of entity node attributes include dimensions of 20cm x 15cm, weight of 0.5kg, and material as fragile glass. The packaging is a type A blister pack, and its second type of entity node attributes include type as blister pack and model number A-001. The default matching rule is to select shockproof packaging. When constructing relationship edges, the glass rearview mirror node and the type A blister pack node are connected via rule nodes: if the rule node defines that fragile materials are suitable for blister packaging and that a weight greater than 1kg excludes type A, then based on the part's 0.5kg attribute, the applicability relationship is established. If another general cardboard box node exists, and the rule node defines that fragile materials exclude ordinary cardboard boxes, then an exclusion relationship edge is established; if multiple applicable shockproof boxes exist, a priority relationship edge is defined based on priority. Finally, by integrating these entity nodes, rule nodes, and relationship edges describing part characteristics, packaging characteristics, and their determination logic, a knowledge graph containing part attributes, packaging attributes, and matching logic is constructed.

[0037] Understandably, physical nodes include part attributes (size, weight, fragility level, material, whether it is a dangerous good), packaging type (shelves, turnover boxes, pallets, collapsible boxes, specifications), and mode of transport (land transport, sea transport, air transport and its transport conditions).

[0038] Rule node: Encapsulates specific matching logic, such as "IF part weight > 50kg THEN must use rack".

[0039] Relationship edge: connects entities and rules, representing matching relationships such as "applicable", "excluded", and "priority", and the edge weight represents the priority of the rule.

[0040] Applicability Relationship: Derived from historical successful matching cases, indicating that a certain type of part is suitable for use with a certain type of tool. The weight is determined by the frequency and success rate of the cases.

[0041] Exclusion relationship: Originating from safety or process constraints, it indicates that a certain type of part is prohibited from being used with a certain type of equipment (e.g., dangerous goods are prohibited from being used with ordinary turnover boxes), and has the highest priority.

[0042] Priority relationship: derived from cost or standardization strategies, indicating that a certain type of appliance is recommended for use under certain conditions.

[0043] Graph storage method: Use a graph database (such as Neo4j) for storage, and store nodes and edges in a property graph model to facilitate relation traversal and query and graph algorithm execution.

[0044] When a new part arrives, the engine automatically outputs the matching appliance type and confidence level through graph traversal and rule reasoning.

[0045] The method of using the knowledge graph to determine the packaging container that matches the target part includes: Based on the attributes of the current target part, a forward traversal is performed along the relational edges of the knowledge graph, and applicable rule nodes are activated to generate a list of candidate packaging containers. For each packaging device in the candidate packaging device list, a reverse search is performed to determine whether there is an exclusion relationship between it and the current target part; If it exists, the packaging device will be removed from the list of candidate packaging devices. If, after the elimination operation, multiple packaging containers matching the current target part are detected in the candidate packaging container list, the final packaging container matching the current target part is determined according to the priority weight value corresponding to the relationship edge of the connection rule node.

[0046] To illustrate this, let's take a target part, a heavy-duty engine block, as an example. Based on its metal material and high weight attribute, the system traverses the knowledge graph forward, activating rule nodes and initially filtering out heavy-duty wooden crates, iron racks, and ordinary plastic crates as candidate packaging containers. Subsequently, the system performs a reverse search on each container in the list and finds that the rule node defines an exclusion relationship between ordinary plastic crates and high weight attribute (i.e., insufficient load-bearing capacity). Therefore, ordinary plastic crates are removed from the list. At this point, only two suitable containers remain: heavy-duty wooden crates and iron racks. Further examination of the relationship edges connecting the rule nodes reveals that the priority weight value of the iron rack is higher than that of the heavy-duty wooden crate (e.g., the iron rack is more durable). Finally, based on the weight value, the iron rack is determined to be the final packaging container matching this part.

[0047] Step S103: Calculate the preliminary demand for the packaging equipment, and optimize the preliminary demand using a preset optimization algorithm to obtain the final demand prediction result for the packaging equipment of the target part.

[0048] Specifically, the basic demand for packaging equipment is calculated based on the average daily demand for parts, the number of parts loaded per packaging container, and the turnover rate of packaging equipment. Based on the obtained packaging equipment turnover rate and transportation cycle, as well as the basic demand, calculate the in-transit demand for packaging equipment. Based on the obtained safety stock factor and the basic demand and in-transit demand, calculate the preliminary demand for packaging equipment.

[0049] For ease of understanding and illustration, the total demand for packaging equipment is broken down into three independent dimensions: basic demand, in-transit demand, and buffer demand. The total demand is calculated by summing these three dimensions:

[0050] The precise definitions of each item are as follows: (1) Basic demand :

[0051] Equivalent expression form:

[0052] Equipment turnover rate (unit: times / month) is a key efficiency parameter, which physically means: the number of times a single set of packaging equipment is loaded per unit of time. A higher turnover rate means that the service capacity of each set of equipment is stronger, and the required amount of basic equipment is less.

[0053] (2) Demand in transit : = *Packaging equipment turnover rate*Transportation cycle. Among them, The physical meaning is: the number of packaging containers currently in transit and not yet delivered to the vehicle assembly plant for use. It is a real, independent part of the supply chain, and the transportation cycle is measured in days.

[0054] (3) Buffer requirements :

[0055] Where K is the safety stock coefficient, where , The quantiles of the normal distribution corresponding to the service level are 95% and 95% of the service level. =1.65, 99% service level corresponds =2.33, where service level can be understood as the ability to continuously meet the needs of the production line. The historical daily demand standard deviation is calculated based on actual daily demand data from the past 6-12 months. The transportation cycle is in days.

[0056] The turnover rate is explained as follows: Packaging equipment turnover rate is an efficiency parameter that reflects the efficiency of the recycling of packaging equipment. A higher turnover rate means less material is needed to complete the same production task. The smaller the value, the better. Iterative optimization using gradient descent is employed. value.

[0057] Using a preset optimization algorithm, the initial demand is optimized to obtain the final demand forecast result for the packaging equipment of the target part, including: The objective function is to use multiple resource consumption indicators, including: cost indicators, space occupancy indicators, response time indicators, and stockout risk indicators. Set constraints, the preset conditions including: supplier capacity constraints, warehouse capacity constraints, total budget constraints, and equipment lifespan constraints; The optimal value of the objective function is obtained by using a genetic algorithm or particle swarm optimization algorithm under the premise of satisfying the constraints, and the optimal value is used as the final demand prediction result for the packaging equipment of the target part.

[0058] To illustrate this with an example, the initial demand for Type A shelving is 146 units. First, an objective function is constructed that considers multiple dimensions, including cost, space, response time, and stockout risk. Constraints are set, such as a maximum warehouse capacity (e.g., only 140 large shelving units) and a total budget limit. Then, a genetic algorithm is used to iteratively optimize the resource consumption of the 146 shelving units while satisfying these constraints. The algorithm finds that maintaining 146 shelving units would exceed warehouse capacity and lead to a surge in inventory costs. Adjusting the quantity to 138 units (and compensating for the shortfall by shortening the turnover frequency) satisfies both the warehouse capacity constraint and the total budget requirement, while also minimizing overall cost. Finally, the calculated quantity of 138 units is used as the final demand forecast for Type A shelving units.

[0059] Understandably, a multi-objective optimization model is established with the goals of minimizing total investment cost, warehouse space occupancy, stockout risk, and maximizing response speed. Before inputting the data into the optimization algorithm, the four components—Cost, Space, Risk, and Speed—are normalized using Min-Max or Z-score to map them to the same numerical range and eliminate dimensional conflicts. Constraints such as supplier capacity, warehouse capacity, budget, and equipment lifespan are set, and a genetic algorithm (GA) or particle swarm optimization (PSO) is used to solve the problem. When the initial optimization results do not meet the constraints, the system automatically adjusts the parameters and re-solves until all constraints are met or the maximum number of iterations is reached.

[0060] Among them, Min-Max normalization: ,in and These are the minimum and maximum values ​​in the historical data, respectively.

[0061] Z-score standardization:

[0062] in, This is the average of historical data. The standard deviation is denoted as .

[0063] Objective function (revised)

[0064] in, To normalize the total investment cost, To standardize the space occupied by warehouses, To normalize the stockout risk (calculated based on a combination of historical stockout rates and safety stock coverage). This refers to the normalized response speed (the speed at which the system responds to configuration changes and generates new prediction schemes). , , and These are the corresponding weighting coefficients.

[0065] It should also be noted that a feedback mechanism between the forecast results and actual usage data is established: the root mean square error (RMSE) between the forecasted demand and the actual usage is calculated, and model parameter recalibration is triggered when the RMSE exceeds a preset threshold. The preset threshold is determined based on the forecast error distribution over the past three months, with a trigger threshold of 1.2 to 2.0 times the historical average RMSE, or it can be set by business personnel based on an acceptable forecast deviation rate. Model parameters are corrected based on the actual deviation, supporting rapid recalculation when vehicle configuration changes. In one embodiment, the final demand forecast result for packaging equipment of the target part is obtained, generating a packaging equipment demand list, multi-dimensional analysis reports, setting inventory warning thresholds, and supporting simulation analysis of demand changes.

[0066] For ease of understanding, a complete implementation example is provided: Step S1: Data Acquisition and Preprocessing Acquire vehicle configuration data, parts master data, and historical usage data, and perform cleaning, standardization, and correlation processing. Data cleaning includes missing value imputation, outlier removal, and data format standardization; feature extraction includes key attributes such as part dimensions (length, width, height), weight, fragility level, and whether it is a hazardous material.

[0067] Step S2: Establish vehicle configuration-part mapping relationship Based on vehicle BOM data, a mapping relationship between vehicle configuration (such as long-range version) and parts list is established, and a configuration rule engine and assembly relationship graph are constructed.

[0068] Step S2.1: Configuration Change Detection and Incremental Calculation Monitor BOM version number changes. When a version number changes, use BOM version difference comparison (Diff comparison) to identify the set of changed parts, identifying three types of changes: Add a new node: Perform the full S3-S5 process calculation; Delete node: Mark it as pending recycling and release equipment resources; Attribute modification node: Only re-executes the affected calculation steps.

[0069] For non-modified parts, existing calculation results can be directly reused, while local recalculation is triggered only for modified parts. Existing knowledge graph rules and prediction model parameters can be reused to achieve a rapid response within minutes.

[0070] Step S3: Intelligent matching of packaging container types Based on part attributes (size, weight, fragility, transportation conditions, etc.), the optimal packaging container type and specifications are intelligently matched using a knowledge graph rule engine based on graph database storage and forward chain reasoning.

[0071] Step S4: Multi-dimensional demand forecasting calculation Calculate the demand for packaging equipment in three independent dimensions: Basic demand Based on production planning and daily parts demand calculations, the equipment turnover rate is incorporated as an efficiency parameter. Demand in transit The number of appliances currently circulating in the supply chain, calculated based on the transportation cycle; Buffer demand : The number of buffer devices used to cope with demand fluctuations, calculated based on the safety stock factor.

[0072] Step S5: Constraint Optimization A multi-objective optimization model is established to minimize total investment cost, warehouse space usage, stockout risk, and maximize response speed. Before inputting the data into the optimization algorithm, the four components—Cost, Space, Risk, and Speed—are normalized using Min-Max or Z-score normalization to map them to the same numerical range and eliminate dimensional conflicts. Constraints such as supplier capacity, warehouse capacity, budget, and equipment lifespan are set, and a genetic algorithm (GA) or particle swarm optimization (PSO) is used to solve the problem. When the initial optimization results do not meet the constraints, the system automatically adjusts the parameters and re-solves until all constraints are met or the maximum number of iterations is reached.

[0073] Step S6: Dynamic Adjustment and Update Establish a feedback mechanism between forecast results and actual usage data. Calculate the root mean square error (RMSE) between forecasted demand and actual usage. When the RMSE exceeds a preset threshold, trigger model parameter recalibration. The preset threshold is determined based on the forecast error distribution over the past three months, using 1.2 to 2.0 times the historical average RMSE as the trigger threshold, or it can be set by business personnel based on an acceptable forecast deviation rate. Adjust model parameters based on actual deviations, supporting rapid recalculation when vehicle configuration changes.

[0074] Step S7: Result Output and Visualization Generate a list of packaging equipment requirements, multi-dimensional analysis reports, set inventory warning thresholds, and support simulation analysis of demand changes.

[0075] In summary, the beneficial effects of this application include: reduced equipment investment, lower warehousing costs, improved forecasting accuracy, faster response times, reduced operating costs, and improved management efficiency.

[0076] Reference Figure 2 , Figure 2 The diagram shown is a schematic of a demand forecasting device for parts packaging equipment provided by the present invention. Figure 2 As shown, the device includes: The determination module 201 is used to determine the target part based on the established mapping relationship between vehicle configuration and parts list; The processing module 202 is used to construct a knowledge graph based on part attributes, packaging equipment attributes and preset matching rules, and use the knowledge graph to determine the packaging equipment that matches the target part; The prediction module 203 is used to calculate the initial demand for the packaging equipment and optimize the initial demand using a preset optimization algorithm to obtain the final demand prediction result for the packaging equipment of the target part.

[0077] Furthermore, in one possible implementation, the prediction module is also used for Based on the obtained average daily demand for parts, the number of parts loaded per packaging container, and the turnover rate of packaging containers, calculate the basic demand for packaging containers. Based on the obtained packaging equipment turnover rate and transportation cycle, as well as the basic demand, calculate the in-transit demand for packaging equipment. Based on the obtained safety stock factor and the basic demand and in-transit demand, calculate the preliminary demand for packaging equipment.

[0078] Furthermore, in one possible implementation, the processing module is also configured to construct the part attributes into a first type of entity node, the part attributes including: size, weight, fragility and material; The packaging equipment attributes are constructed as a second type of entity node, and the packaging equipment attributes include: packaging equipment type and specifications. The preset matching rule is encapsulated as a rule node, wherein the preset matching rule is to match the corresponding packaging container according to the part attributes; Construct relationship edges connecting the first type of entity node, the second type of entity node, and the rule node. The relationship edges are the matching relationships between entity nodes and rule nodes, and the matching relationships include: applicable, excluded, and priority. A knowledge graph is constructed based on the first type of entity nodes, the second type of entity nodes, rule nodes, and relationship edges.

[0079] Furthermore, in one possible implementation, the processing module is also configured to perform a forward traversal along the relational edges of the knowledge graph based on the attributes of the current target part, and activate applicable rule nodes to generate a list of candidate packaging containers. For each packaging device in the candidate packaging device list, a reverse search is performed to determine whether there is an exclusion relationship between it and the current target part; If it exists, the packaging device will be removed from the list of candidate packaging devices. If, after the elimination operation, multiple packaging containers matching the current target part are detected in the candidate packaging container list, the final packaging container matching the current target part is determined according to the priority weight value corresponding to the relationship edge of the connection rule node.

[0080] Furthermore, in one possible implementation, the prediction module is also used to use multiple resource consumption indicators as objective functions, including: cost indicators, space occupancy indicators, response time indicators, and stockout risk indicators. Set constraints, the preset conditions including: supplier capacity constraints, warehouse capacity constraints, total budget constraints, and equipment lifespan constraints; The optimal value of the objective function is obtained by using a genetic algorithm or particle swarm optimization algorithm under the premise of satisfying the constraints, and the optimal value is used as the final demand prediction result for the packaging equipment of the target part.

[0081] Furthermore, in one possible implementation, the determining module is also used to obtain configuration data of the target vehicle model; The parts list corresponding to the target vehicle model is parsed based on the configuration data to establish a mapping relationship between the vehicle configuration and the parts list of the target vehicle model; Based on the mapping relationship, all the parts required for the target vehicle model are determined and designated as the target parts.

[0082] Furthermore, in one possible implementation, the processing module is also used to monitor the vehicle configuration; If a change in vehicle configuration is detected, the change type is identified based on the differences before and after the change. The change types include: addition, modification, and deletion. The appropriate processing strategy is executed based on the type of change.

[0083] The following reference Figure 3 To describe an electronic device 300 according to this embodiment of the present invention. Figure 3 The electronic device 300 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0084] like Figure 3 As shown, the electronic device 300 is presented in the form of a general-purpose computing device. The components of the electronic device 300 may include, but are not limited to: at least one processing unit 310, at least one storage unit 320, and a bus 330 connecting different system components (including storage unit 320 and processing unit 310).

[0085] The storage unit stores program code that can be executed by the processing unit 310, causing the processing unit 310 to perform the steps described in the "Embodiment Methods" section of this specification according to various exemplary embodiments of the present invention.

[0086] Storage unit 320 may include readable media in the form of volatile storage units, such as random access memory (RAM) 321 and / or cache memory 322, and may further include read-only memory (ROM) 323.

[0087] Storage unit 320 may also include a program / utility 324 having a set (at least one) of program modules 325, including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0088] Bus 330 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0089] Electronic device 300 can also communicate with one or more external devices (e.g., keyboard, pointing device, Bluetooth device, etc.), one or more devices that enable a user to interact with electronic device 300, and / or any device that enables electronic device 300 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 350. Furthermore, electronic device 300 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 360. As shown, network adapter 360 communicates with other modules of electronic device 300 via bus 330. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 300, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0090] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0091] According to the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the methods described above is stored. In some possible embodiments, various aspects of the present invention can also be implemented as a program product comprising program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps of the various exemplary embodiments of the present invention described in the "Exemplary Methods" section above.

[0092] refer to Figure 4 As shown, a program product 400 for implementing the above-described method according to an embodiment of the present invention is described. This product may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, the readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0093] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0094] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0095] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0096] Program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0097] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of the present invention, and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0098] The above description is merely a specific embodiment of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

[0099] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

Claims

1. A method for forecasting the demand for parts packaging equipment, characterized in that, include: Based on the established mapping relationship between vehicle configuration and parts list, the target parts are determined; Based on part attributes, packaging equipment attributes, and preset matching rules, a knowledge graph is constructed, and the knowledge graph is used to determine the packaging equipment that matches the target part. The initial demand for the packaging equipment is calculated, and the initial demand is optimized using a preset optimization algorithm to obtain the final demand prediction result for the packaging equipment of the target part.

2. The method according to claim 1, characterized in that, The calculation of the preliminary demand for the packaging equipment includes: Based on the obtained average daily parts demand, the number of parts loaded per packaging container, and the packaging container turnover rate, calculate the basic demand for packaging containers. Based on the obtained packaging equipment turnover rate and transportation cycle, as well as the basic demand, calculate the in-transit demand for packaging equipment. Based on the obtained safety stock factor and the basic demand and in-transit demand, calculate the preliminary demand for packaging equipment.

3. The method according to claim 1, characterized in that, The knowledge graph is constructed based on part attributes, packaging equipment attributes, and preset matching rules, including: The part attributes are constructed as a first type of entity node, and the part attributes include: size, weight, fragility and material; The packaging equipment attributes are constructed as a second type of entity node, and the packaging equipment attributes include: packaging equipment type and specifications. The preset matching rule is encapsulated as a rule node, wherein the preset matching rule is to match the corresponding packaging container according to the part attributes; Construct relationship edges connecting the first type of entity node, the second type of entity node, and the rule node. The relationship edges are the matching relationships between entity nodes and rule nodes, and the matching relationships include: applicable, excluded, and priority. A knowledge graph is constructed based on the first type of entity nodes, the second type of entity nodes, rule nodes, and relationship edges.

4. The method according to claim 1, characterized in that, The step of using the knowledge graph to determine the packaging device that matches the target part includes: Based on the attributes of the current target part, a forward traversal is performed along the relational edges of the knowledge graph, and applicable rule nodes are activated to generate a list of candidate packaging containers. For each packaging device in the candidate packaging device list, a reverse search is performed to determine whether there is an exclusion relationship between it and the current target part; If it exists, the packaging device will be removed from the list of candidate packaging devices. If, after the elimination operation, multiple packaging containers matching the current target part are detected in the candidate packaging container list, the final packaging container matching the current target part is determined according to the priority weight value corresponding to the relationship edge of the connection rule node.

5. The method according to claim 1, characterized in that, The step of optimizing the initial demand using a preset optimization algorithm to obtain the final demand forecast result for the packaging equipment of the target part includes: Multiple resource consumption indicators are used as objective functions, including: cost indicators, space occupancy indicators, response time indicators, and stockout risk indicators. Set constraints, the preset conditions including: supplier capacity constraints, warehouse capacity constraints, total budget constraints, and equipment lifespan constraints; The optimal value of the objective function is obtained by using a genetic algorithm or particle swarm optimization algorithm under the premise of satisfying the constraints, and the optimal value is used as the final demand prediction result for the packaging equipment of the target part.

6. The method according to claim 1, characterized in that, The step of determining the target parts based on the established mapping relationship between vehicle configuration and parts list includes: Obtain the configuration data of the target vehicle model; The parts list corresponding to the target vehicle model is parsed based on the configuration data to establish a mapping relationship between the vehicle configuration and the parts list of the target vehicle model; Based on the mapping relationship, all the parts required for the target vehicle model are determined and designated as the target parts.

7. The method according to claim 1, characterized in that, Before determining the target part based on the established mapping relationship between vehicle configuration and parts list, the process includes: Monitor vehicle configuration; If a change in vehicle configuration is detected, the change type is identified based on the differences before and after the change. The change types include: addition, modification, and deletion. Execute the corresponding processing strategy based on the change type.

8. A demand forecasting device for parts packaging equipment, characterized in that, include: The determination module is used to determine the target parts based on the established mapping relationship between vehicle configuration and parts list; The processing module is used to construct a knowledge graph based on part attributes, packaging equipment attributes and preset matching rules, and use the knowledge graph to determine the packaging equipment that matches the target part. The prediction module is used to calculate the initial demand for the packaging equipment and optimize the initial demand using a preset optimization algorithm to obtain the final demand prediction result for the packaging equipment of the target part.

9. An electronic device, characterized in that, The electronic device includes: processor; A memory storing computer-readable instructions that, when executed by the processor, implement the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It stores computer program instructions that, when executed by a computer, cause the computer to perform the method according to any one of claims 1 to 7.

Images