Vehicle production plan change demand optimization method, device, equipment and storage medium

Abstract

The application discloses a vehicle production plan change demand optimization method and device, equipment and a storage medium, and relates to the technical field of intelligent manufacturing. The method comprises the following steps: acquiring initial change demand of a vehicle style production plan, checking parts overage of the initial change demand, sorting vehicle styles based on multi-dimensional sorting factors when there is parts overage, obtaining a style reduction sorting result, adjusting the initial change demand based on the style reduction sorting result, obtaining optimized change demand meeting an optimization target, evaluating the optimized change demand based on multi-dimensional optimization evaluation factors, obtaining a recommended score of the optimized change demand, and determining target change demand of the vehicle style production plan based on the recommended score of the optimized change demand. In the above manner, the most suitable change demand optimization scheme is generated by comprehensively considering demand increment and supply chain influence, and change demand and supply chain response difficulty are effectively balanced.

Description

Technical Field

[0001] This application relates to the field of intelligent manufacturing technology, and in particular to methods, apparatus, equipment and storage media for optimizing vehicle production plan changes. Background Technology

[0002] With intensifying competition in the automotive market and ever-changing customer demands, simply relying on changes in market demand to adjust production patterns (increases and decreases) only considers the single dimension of market order changes, failing to comprehensively consider the pull and adjustment of the entire supply chain and the inventory of finished vehicles. This can easily lead to drastic supply chain fluctuations, as well as high adjustment costs and claims risks.

[0003] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main objective of this application is to provide a method, apparatus, equipment, and storage medium for optimizing vehicle production plan changes, aiming to solve the technical problem in the prior art of balancing the changing demands of vehicle models with the ease of supply chain response.

[0005] To achieve the above objectives, this application provides a method for optimizing vehicle production plan change requirements, the method comprising: Obtain the initial change requirements for the vehicle style production plan, and perform component oversize checks on the initial change requirements; When there are parts exceeding the allowable size, the vehicle styles are sorted based on multi-dimensional sorting factors to obtain the style reduction sorting result; Based on the pattern reduction sorting results, the initial change requirements are adjusted to obtain optimized change requirements that meet the optimization objectives. The optimization change requirements are evaluated based on multi-dimensional evaluation factors to obtain a recommended score for the optimization change requirements; Based on the recommended score of the optimized change requirements, the target change requirements for the vehicle style production plan are determined.

[0006] In one embodiment, the step of sorting the vehicle patterns based on multi-dimensional sorting factors to obtain a pattern reduction sorting result includes: Obtain multi-dimensional ranking factors, which include at least the sales priority factor, the combination sales trend factor, the style sales trend factor, the main model factor, the number of oversized parts factor, the small quantity factor, the small quantity summation factor, the reservation factor, and the oversized parts ratio factor. Calculate the score of the multi-dimensional ranking factor corresponding to the vehicle pattern; Based on the weight value range of the multi-dimensional ranking factors, multiple weight combinations of the multi-dimensional ranking factors are determined. Based on the scores of the multi-dimensional ranking factors corresponding to the vehicle type and the multiple weight combinations of the multi-dimensional ranking factors, the reduction priority of the vehicle type corresponding to different weight combinations is determined. Based on the reduction priority of vehicle styles corresponding to different weight combinations, the reduction ranking result of styles corresponding to different weight combinations is determined.

[0007] In one embodiment, the step of adjusting the initial change requirements based on the pattern reduction sorting results to obtain optimized change requirements that meet the optimization objective includes: When the optimization objective is to ensure that the parts do not exceed the allowable size, the parts reduction ranking result is determined based on the number of vehicle parts exceeding the allowable size and the reduction ranking result of the aforementioned pattern. Based on the order quantity and frozen quantity of the vehicle type, determine the protection increment of the vehicle type; Based on the protection increment of the vehicle type and the changed quantity of the vehicle type, calculate the maximum reducible amount of the vehicle type. Based on the maximum reducible quantity of the vehicle type and the ranking results of the component reduction, the initial change requirements are adjusted to determine the optimized change requirements that meet the optimization objectives.

[0008] In one embodiment, the step of adjusting the initial change requirements based on the maximum reducible quantity of the vehicle type and the component reduction ranking results to determine the optimized change requirements that meet the optimization objective includes: Based on the component reduction ranking results, the current component to be reduced is determined; Based on the excess quantity of the current reduced parts and the production quantity of the parts for the vehicle model, determine the excess quantity that can be reduced for the vehicle model corresponding to the current reduced parts. Based on the excess reduction amount of the vehicle pattern corresponding to the current reduction part and the maximum reduction amount of the vehicle pattern, the reduction amount of the vehicle pattern corresponding to the current reduction part is determined. Based on the reduction in vehicle type corresponding to the current reduced parts, the initial change requirements are adjusted to obtain the first adjustment requirements; When the first adjustment requirement meets the optimization and reduction objectives, calculate the maximum amount that can be added to the vehicle type; Based on the maximum amount that can be added to the vehicle type, the first adjustment requirement is adjusted to obtain the second adjustment requirement; When the second adjustment requirement meets the optimization objective, the second adjustment requirement is taken as the optimization change requirement.

[0009] In one embodiment, the step of adjusting the initial change requirements based on the pattern reduction sorting results to obtain optimized change requirements that meet the optimization objective includes: When the optimization objective is to maximize supply capacity, the protection increment for the vehicle type is determined based on the order quantity and frozen quantity of the vehicle type. Based on the protection increment of the vehicle type and the changed quantity of the vehicle type, calculate the maximum reducible amount of the vehicle type. Based on the maximum reducible quantity of the vehicle type and the sorting result of the type reduction, the initial change requirements are adjusted to obtain optimized change requirements that meet the optimization objectives.

[0010] In one embodiment, the step of adjusting the initial change requirements based on the maximum reducible amount of the vehicle pattern and the pattern reduction ranking result to obtain optimized change requirements that meet the optimization objective includes: Based on the sorting results of the pattern reduction, the current reduction pattern is determined; Based on the excess quantity of the parts in the current reduction pattern and the production quantity of the parts in the current reduction pattern, determine the amount of excess that can be reduced in the current reduction pattern. Based on the over-reduction amount and maximum reduction amount of the current reduction pattern, the reduction amount of the current reduction pattern is determined; Based on the reduction of the current reduction pattern, the initial change requirement is adjusted; When the adjusted initial change requirements meet the optimization and reduction objectives, the adjusted initial change requirements will be used as the optimized change requirements.

[0011] In one embodiment, the step of evaluating the optimization change requirement based on multi-dimensional evaluation factors to obtain a recommended score for the optimization change requirement includes: Obtain multi-dimensional evaluation factors and their weights. The multi-dimensional evaluation factors include at least the average deviation rate factor of the sample, the direction of sample change factor, the average overshoot ratio factor of the bottleneck component, the maximum overshoot ratio factor, the number of overshoot components factor, and the overshoot factor before the change. Calculate the scores of the multi-dimensional evaluation factors corresponding to the optimized change requirements; Based on the scores of the multi-dimensional evaluation factors corresponding to the optimization change requirements and the weights of the multi-dimensional evaluation factors, the recommended score for the optimization change requirements is determined.

[0012] Furthermore, to achieve the above objectives, this application also proposes a vehicle production plan change demand optimization device, which includes: The oversize inspection module is used to obtain the initial change requirements of the vehicle style production plan and to perform component oversize inspection on the initial change requirements. The demand optimization module is used to sort the vehicle patterns based on multi-dimensional sorting factors when there are parts exceeding the allowable size, and obtain the pattern reduction sorting result. The demand optimization module is also used to adjust the initial change demand based on the pattern reduction sorting result to obtain an optimized change demand that meets the optimization objective. An optimization evaluation module is used to evaluate the optimization change requirements based on multi-dimensional evaluation factors and obtain a recommended score for the optimization change requirements. The optimization evaluation module is also used to determine the target change requirements of the vehicle style production plan based on the recommended score of the optimization change requirements.

[0013] In addition, to achieve the above objectives, this application also proposes a vehicle production plan change demand optimization device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. The computer program is configured to implement the steps of the vehicle production plan change demand optimization method described above.

[0014] In addition, to achieve the above objectives, the present invention also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the vehicle production plan change demand optimization method described above.

[0015] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the vehicle production plan change demand optimization method described above.

[0016] This application provides a method for optimizing the changing demand of vehicle production plans. It obtains the initial changing demand of the vehicle model production plan and performs a component overrun check on the initial changing demand. When component overruns exist, the vehicle models are ranked based on multi-dimensional ranking factors to obtain a model reduction ranking result. Based on the model reduction ranking result, the initial changing demand is adjusted to obtain optimized changing demand that meets the optimization objective. The optimized changing demand is evaluated based on multi-dimensional evaluation factors to obtain a recommended score for the optimized changing demand. Based on the recommended score of the optimized changing demand, the target changing demand of the vehicle model production plan is determined. This application determines the reduction priority of different models by quantifying multi-dimensional ranking factors, generating multiple optimization schemes. Based on the balance between sales demand and supply impact, multi-dimensional evaluation factors are set, and the recommended scores of each optimization scheme are quantified using these multi-dimensional evaluation factors. The optimal solution is selected from these, comprehensively considering demand increments and supply chain impacts to generate the most suitable changing demand optimization scheme. This effectively balances demand changes and supply chain response, solving the technical problem of balancing the changing demand of the entire vehicle model with the ease of supply chain response. Attached Figure Description

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

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating an embodiment of the vehicle production plan change demand optimization method of this application; Figure 2 A schematic diagram of the overall architecture of the vehicle production plan change demand optimization method provided in Embodiment 1 of this application; Figure 3 This is a flowchart illustrating Embodiment 2 of the method for optimizing vehicle production plan changes in this application; Figure 4 This is a schematic diagram of the component not exceeding the range in the vehicle production plan change demand optimization method provided in Embodiment 2 of this application; Figure 5 This is a flowchart illustrating Embodiment 3 of the method for optimizing vehicle production plan changes in this application; Figure 6 A schematic diagram illustrating the process of maximizing supply capacity in the vehicle production plan change demand optimization method provided in Embodiment 3 of this application; Figure 7This is a schematic diagram of the module structure of the vehicle production plan change demand optimization device according to an embodiment of this application; Figure 8 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the vehicle production plan change demand optimization method in this application embodiment.

[0020] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0022] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0023] The main solution of this application embodiment is as follows: First, obtain the initial change requirements of the vehicle pattern production plan; second, perform component overrun checks on the initial change requirements; third, when component overruns exist, sort the vehicle patterns based on multi-dimensional ranking factors to obtain a pattern reduction ranking result; fourth, based on the pattern reduction ranking result, adjust the initial change requirements to obtain optimized change requirements that meet the optimization objectives; fifth, evaluate the optimized change requirements based on multi-dimensional evaluation factors to obtain a recommended score for the optimized change requirements; and sixth, based on the recommended score for the optimized change requirements, determine the target change requirements for the vehicle pattern production plan.

[0024] This application provides a solution that determines the reduction priority of different styles by quantifying multi-dimensional ranking factors, generates multiple optimization schemes, sets multi-dimensional evaluation factors based on the balance between sales demand and supply impact, quantifies the recommendation score of each optimization scheme using multi-dimensional evaluation factors, selects the optimal solution, can comprehensively consider demand increment and supply chain impact, generates the most suitable variable demand optimization scheme, and effectively balances demand changes and supply chain response.

[0025] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device capable of performing the above functions, such as a vehicle production plan change demand optimization device. This embodiment does not specifically limit it in this regard. The following uses a vehicle production plan change demand optimization device as an example to describe this embodiment and the following embodiments.

[0026] This application provides a method for optimizing vehicle production plan changes, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the vehicle production plan change demand optimization method of this application.

[0027] In this embodiment, the method for optimizing vehicle production plan change requirements includes steps S10 to S50: Step S10: Obtain the initial change requirements of the vehicle style production plan, and perform a part oversize check on the initial change requirements. It should be noted that the initial change request for the production plan is the change request given by the sales side, which is the production plan that the sales side wants to adjust this time. It usually includes the style / model / configuration that needs to be reduced, the specific reduction amount, the style / model / configuration that needs to be increased, the specific increase amount, the quantity before the reduction / increase (quantity before change), and the quantity after the reduction / increase (quantity after change). The reporting cycle of the initial change request from the sales side can be determined according to the actual situation, for example, 1 week. This embodiment does not make a specific limitation on this.

[0028] Additionally, it should be noted that the BOM (Bill of Materials) table can determine the correspondence between vehicle models and parts (components), thus identifying which parts are required for each model. This allows the quantities related to the model to be converted into the quantities of the parts. For example, the quantities of the model before the change can be converted into the quantities of the parts before the change, and the quantities of the model after the change can be converted into the quantities of the parts after the change.

[0029] It is understandable that by summarizing the quantities of components after the changes, the total demand for each component after the changes can be determined. At this point, checking for component over-limitation for the initial changed demand is equivalent to checking for over-limitation of the total demand for components. Each component has a corresponding allowable variation range (e.g., 20%, which is usually related to the supplier's supply situation; this embodiment does not specify a specific range). If the variation exceeds this allowable variation range, the component is considered to be over-limited and can be considered an over-limit component.

[0030] Step S20: When there are parts exceeding the size limit, sort the vehicle styles based on multi-dimensional sorting factors to obtain the style reduction sorting result; It should be noted that if there are any parts exceeding the allowable size, it indicates that the initial change requirements need to be optimized. In this embodiment, all styles are sorted according to a pre-set multi-dimensional sorting factor to determine the priority order for reducing their size, i.e., the style reduction sorting result.

[0031] In one feasible implementation, step S20 may include steps S201 to S205: Step S201: Obtain multi-dimensional sorting factors; It should be noted that the multi-dimensional ranking factors include at least the sales priority factor, the combined sales trend factor, the style sales trend factor, the main model factor, the number of oversized parts factor, the small quantity factor, the sum of small quantity factors, the reserved factor, and the proportion of oversized parts factor.

[0032] Sales priority is a direct factor that the sales side can influence the style ranking, and it is usually the most weighted factor. The sales side typically assigns a sales priority to each style (related to user preferences, and can be divided into high, medium, and low levels). This priority can be updated and maintained before each optimization. If the sales side does not maintain it, the default sales priority for all styles is medium. Styles with low sales priority are reduced in quantity first.

[0033] The combined sales trend factor is determined by the sales trend based on the combined variable (the change in quantity after the change compared to the quantity before the change). A positive value of the variable indicates an increasing sales trend (increase trend), while a negative value indicates a decreasing sales trend (decrease trend). Combinations with a decreasing trend are typically prioritized for reduction, with a stronger decreasing trend (smaller variable) being given higher priority. Combinations usually include KATA combinations, optional package combinations, and grade combinations, determined by the number of features defined in the vehicle model's sales BOM; different vehicle models have different combinations.

[0034] The style sales trend factor is a supplementary factor to the combination sales trend factor. It's possible that the combination is decreasing, but a particular style might have the largest increase. If only the combination trend is considered, that style should be reduced first. However, if its own trend is considered, it should be reduced last. Therefore, the style's own trend should be considered in its ranking to avoid being dragged down by the combination trend. Typically, styles are ranked according to their own variables, with those showing a stronger decreasing trend being reduced first.

[0035] The "mainstream model factor" is a quantity factor of the combination before the change. The larger the quantity of the combination before the change, the higher the priority for quantity reduction. Whether a model is a mainstream model can be determined based on its quantity before the change. Mainstream models usually have a large quantity before the change, ensuring sufficient stock. If quantity reduction is prioritized for mainstream models, the impact on sales will not be significant. However, smaller models already have limited stock, and the quantity before the change is even smaller. If quantity reduction is prioritized for these models, it can easily lead to supply shortages. The grouping of mainstream models is usually configurable (a Cartesian product combination of trim level and optional packages). For example, if the trim levels are high-end, mid-range, and low-end, and the optional package includes a technology package, then the grouping of mainstream models could be: high-end + with technology package, high-end + without technology package, mid-range + with technology package, mid-range + without technology package, low-end + with technology package, low-end + without technology package.

[0036] The oversized component number factor is a factor related to the number of oversized components used in a design. The more oversized components a design uses, the more it is recommended to reduce the number of components (reducing one design may make multiple components not oversized).

[0037] The "small quantity factor" is related to the small quantity of oversized components used in a design. A small quantity component is the component with the smallest pre-calculation quantity among the oversized components used in the design. If there are multiple components with the smallest pre-calculation quantity, the oversized ratio is further considered, and the component with the highest oversized ratio is designated as the small quantity component. Compared to other oversized components, small quantity components are more prone to oversized risk. The smaller the pre-calculation quantity and the larger the oversized ratio of the small quantity component corresponding to the design, the higher the priority for quantity reduction.

[0038] The small quantity summation factor is also related to the small quantity of oversized parts used in the design. The small quantity factor focuses on the small quantity of parts corresponding to the design, while the small quantity summation factor considers all oversized parts corresponding to the design. The smaller the quantity and the larger the oversized ratio of the oversized parts corresponding to the design before the change, the higher the priority for reduction. Ultimately, one of the small quantity factor and the small quantity summation factor will be selected (the selected one will have a normal weight, and the unselected one will have a weight of 0).

[0039] The reserved factor is a factor reserved for the sales side. The sales side can directly assign the corresponding score, and the lower the score, the higher the priority for reduction.

[0040] The oversized component ratio factor is the oversized component ratio factor corresponding to the pattern. The larger the oversized ratio, the higher the corresponding oversized risk. Patterns with oversized components with the largest oversized ratio are given priority for reduction.

[0041] Step S202: Calculate the score of the multi-dimensional ranking factor corresponding to the vehicle pattern; For the sales priority factor score, different scores are assigned according to the sales priority of the pattern. For example, a high sales priority corresponds to a score of 3 points, a medium sales priority corresponds to a score of 2 points, and a low sales priority corresponds to a score of 1 point. This gives the initial score of each pattern under the sales priority factor. After normalization (0~1 points), the final score of each pattern under the sales priority factor is obtained.

[0042] For the score of the bundled sales trend factor, the bundle to which the style belongs is found according to the sales BOM (e.g., KATA, grade, optional package, etc.). Each bundle is categorized and summarized to obtain the change. The change of each bundle is the score of each bundle. The scores of all bundles are then normalized. Since a style may belong to multiple bundles, the average score of multiple bundles is the score of that style under the bundled sales trend factor.

[0043] For the score of the style sales trend factor, the change in the style itself is the initial score of the style under the style sales trend factor. After normalization, the final score of each style under the style sales trend factor is obtained.

[0044] For the scoring of the main model factor, the main models are first grouped according to the configuration table. If no configuration is available, each style forms its own group. The pre-change quantity of each style is summarized according to the main model category, and this is used as the score for that main model. The score of the main model factor of a style mainly inherits the score of its main model. To differentiate the scores of styles under the same main model, the proportion of each style's pre-change quantity to the total pre-change quantity of the main model is calculated. The initial score of the main model factor of a style = the score of its main model + the pre-change quantity of the style / the pre-change quantity of its main model. The initial score needs to be negative to ensure that: the more mainstream the model, the lower the score, the higher the ranking, and the higher the priority for reduction. After normalization, the final score is obtained. The style with the largest proportion among the main models has the lowest score for the main model factor. For example, assuming the main vehicle models are grouped into Technology Package, Safety Package, and Seat Package, with Model 1 having 10 Technology Packages, Model 2 having 20, Model 3 having 30 Safety Packages, Model 4 having 40 Safety Packages, Model 5 having 50 Seat Packages, and Model 6 having 60 Seat Packages, then the scores for each main vehicle model would be: Technology Package 30 points, Safety Package 70 points, and Seat Package 110 points. The initial scores of the main vehicle model factors for each pattern are as follows: Pattern 1: -(30+10 / 30), Pattern 2: -(30+20 / 30), Pattern 3: -(70+30 / 70), Pattern 4: -(70+40 / 70), Pattern 5: -(110+50 / 110), Pattern 6: -(110+60 / 110). The scores of the main vehicle model factors for each pattern are obtained after normalization of the initial scores of the main vehicle model factors for each pattern.

[0045] For the scoring of the oversized component number factor, firstly, the oversized components are determined based on the oversized inspection results. Then, considering the assembly relationship between the design and the components, the oversized components corresponding to each design are determined, resulting in the number of oversized components corresponding to that design. The negative value of this number is used as the initial score for the oversized component number factor of that design. After normalization, the final score for the oversized component number factor is obtained. The design with the most oversized components has the lowest score for the oversized component number factor. The lower the score of the oversized component number factor, the more preferentially it is recommended to reduce the number of components. For example, assuming the oversized parts are parts A, B, and C, and pattern 1 is associated with parts A and B, and pattern 2 is associated with part C, then the number of oversized parts in pattern 1 is 2, the number of oversized parts in pattern 2 is 1, the initial score of the oversized part number factor in pattern 1 is -2, the initial score of the oversized part number factor in pattern 2 is -1, and after normalization, the score of the oversized part number factor in pattern 1 is 0, and the score of the oversized part number factor in pattern 2 is 1.

[0046] For the score of a small number of parts, the score of the oversized parts of the design is first calculated. The score of the oversized parts is mainly determined by their quantity before the change (the main factor), and secondly by their oversized ratio (a secondary factor, oversized ratio = oversized quantity / quantity before the change). The oversized ratio is normalized to ensure that its value is between 0 and 1, so as to weaken its effect. Except for the case where the quantity before the change is 0, the quantity before the change is usually greater than or equal to the normalized value of the oversized ratio. In this case, the score of the oversized parts = quantity before the change - normalized oversized ratio. The score of the oversized parts is then normalized. It should be noted that parts that do not exceed the oversized ratio are not assigned a score, and normalization is only performed on oversized parts. Next, based on the assembly relationship between the design and the parts, the score of the small quantity factor of the design inherits the minimum score of its corresponding oversized parts. That is, the minimum score of the oversized parts corresponding to the design is used as the initial score of the small quantity factor for that design. If the design does not have a corresponding oversized part, the maximum value of the already calculated initial score + 1 is used as the initial score of the small quantity factor for that design. The initial score is normalized to obtain the final score. Alternatively, the secondary factor can be replaced with the variation range (the proportion of the variable to the quantity before the variation), but this embodiment does not specifically limit this. For example, assuming that the quantity of oversized component A before the change is 2 and the oversized ratio is 20%, the quantity of oversized component B before the change is 2 and the oversized ratio is 10%, and the quantity of oversized component C before the change is 4 and the oversized ratio is 300%, then the normalized oversized ratio of oversized component A is 0.03, the normalized oversized ratio of oversized component B is 0, and the normalized oversized ratio of oversized component C is 1. The score of oversized component A is 2 - 0.03 = 1.97. The score for oversized component B is 2-0=2, and the score for oversized component C is 4-1=3. After normalization, the score for oversized component A is 0, the score for oversized component B is 0.03, and the score for oversized component C is 1. If pattern 1 is associated with oversized components A and B, the minimum value of 0 is selected as the initial score of pattern 1. If pattern 2 is associated with oversized components B and C, the minimum value of 0.03 is selected as the initial score of pattern 2.

[0047] For the score of the summation factor for minor items, the score of the oversized parts of the design is first calculated (refer to the calculation process of the score for the minor item factor). The score of the summation factor for minor items of a design inherits the sum of the scores of all its corresponding oversized parts. That is, the scores of the oversized parts corresponding to the design are added together, and the sum is used as the initial score of the summation factor for minor items of that design. If the design has no corresponding oversized parts, the maximum value of the already calculated initial score is increased by 1, and this is used as the initial score of the summation factor for minor items of that design. The initial score is normalized to obtain the final score. In addition, the minor factor can also be replaced by the variation range, which is not specifically limited in this embodiment.

[0048] For the score of the reserved factor, first obtain the score configured on the sales side. If the sales side has not configured it, the score of the reserved factor for all styles is 0. Normalize it according to the score configured on the sales side to obtain the score of the reserved factor for each style.

[0049] For the score of the oversized component ratio factor, first calculate the oversized ratio of all oversized components corresponding to the pattern. If the pattern corresponds to multiple oversized components, take the negative value of the maximum oversized ratio as the initial score of the oversized component ratio factor of the pattern. After normalization, the score of each pattern under the oversized component ratio factor is obtained.

[0050] Step S203: Based on the weight value range of the multi-dimensional ranking factors, determine multiple weight combinations of the multi-dimensional ranking factors; It should be noted that the multi-dimensional ranking factors are set with corresponding weight ranges. For example, the weight range of the sales priority factor is 20%-30%, the weight range of the combined sales trend factor is 10%-25%, and the weight range of the pattern sales trend factor is 10%-15%. These can be flexibly adjusted according to the actual situation, and this embodiment does not impose specific limitations on them.

[0051] Understandably, by considering the weight range of the multi-dimensional ranking factors, multiple weight combinations can be determined, with the sum of the weights of each combination being 100%. For example, the weights of the sales priority factor, combined sales trend factor, style sales trend factor, main model factor, number of oversized parts factor, small quantity factor, summation factor for small quantity factors, reserved factor, and proportion of oversized parts factor are set to 28%, 15%, 14%, 7%, 22%, 5%, 0%, 4%, and 5%, respectively.

[0052] Step S204: Based on the scores of the multi-dimensional ranking factors corresponding to the vehicle type and the multiple weight combinations of the multi-dimensional ranking factors, determine the reduction priority of the vehicle type corresponding to different weight combinations. Understandably, by weighting the scores of multi-dimensional ranking factors using weight combinations, the reduction score of vehicle models under different weight combinations can be obtained. The lower the reduction score, the higher the reduction priority, thus determining the reduction priority of vehicle models under different weight combinations. For example, assuming that the reduction score of model 1 is 0.16, the reduction score of model 2 is 0.7825, and the reduction score of model 3 is 0.8345, then the reduction priority of model 1 > the reduction priority of model 2 > the reduction priority of model 3.

[0053] Step S205: Based on the reduction priority of vehicle styles corresponding to different weight combinations, determine the style reduction ranking result corresponding to different weight combinations.

[0054] It is understandable that the vehicle styles are sorted according to their reduction priority (higher priority means higher ranking), and the resulting sort is the style reduction ranking. Each weight combination needs to have its corresponding style reduction ranking determined separately.

[0055] Step S30: Based on the pattern reduction sorting results, adjust the initial change requirements to obtain optimized change requirements that meet the optimization objectives; It should be noted that since step S20 generates pattern reduction ranking results corresponding to different weight combinations, it is necessary to determine whether different weight combinations meet the optimization objective. In this embodiment, the optimization objective includes two cases: ensuring parts do not exceed the allowable size and maximizing supply capacity. Different optimization objectives are adopted in different scenarios. Ensuring parts do not exceed the allowable size usually means ensuring the increase in demand as much as possible and absolutely ensuring that parts do not exceed the allowable size. Maximizing supply capacity usually means absolutely ensuring the increase in demand and trying to ensure that parts do not exceed the allowable size.

[0056] Understandably, reference Figure 2 Maximizing supply capacity is applicable to demand optimization before the over-survey. That is, after the sales side puts forward the initial change demand and before submitting the over-survey, the initial change demand is optimized with maximizing supply capacity as the optimization goal. Not exceeding the part limit is applicable to demand optimization after the over-survey. That is, after the sales side updates the demand based on the supplier survey results obtained from the over-survey, before formally submitting the demand email, the updated initial change demand is optimized with not exceeding the part limit as the optimization goal.

[0057] It should be understood that optimized change requirements are the improved change requirements. Based on the current optimization goals, the initial change requirements proposed by the sales side are adjusted to obtain optimized change requirements that meet the optimization goals.

[0058] Step S40: Evaluate the optimization change requirements based on multi-dimensional evaluation factors to obtain a recommended score for the optimization change requirements; In one feasible implementation, step S40 may include steps S401 to S403: Step S401: Obtain the multi-dimensional evaluation factors and the weights of the multi-dimensional evaluation factors; It should be noted that the multi-dimensional evaluation factors include at least the average deviation rate factor of the pattern, the direction of pattern change factor, the average overshoot ratio factor of the bottleneck component, the highest overshoot ratio factor, the number of overshoot components factor, and the overshoot factor before the change.

[0059] Additionally, it should be noted that the sample average deviation rate factor is used to describe the deviation between the optimized variable demand and the initial variable demand on the sales side. The smaller the deviation, the better the optimized variable demand.

[0060] It is understandable that if the deviation of the two optimization changes in demand is the same, the direction of all increases / decreases in the first option is the same as the direction of the sales trend, which is more in line with the sales change trend, while the direction of all increases / decreases in the second option is opposite to the direction of the sales trend. Therefore, the first option is considered to be better, and thus the pattern change direction factor is further introduced. Specifically, if the initial variable demand is positive, the corresponding optimized variable demand is also positive; if the initial variable demand is negative, the corresponding optimized variable demand is also negative. In this case, the signs are considered to be consistent. Further evaluation is then conducted to determine if the initial variable demand is met. If the absolute value of the initial variable demand is less than or equal to the absolute value of the corresponding optimized variable demand (e.g., the initial variable demand is +10, and the corresponding optimized variable demand is +12), then the initial variable demand is considered met. In this case, all increases / decreases in the optimized variable demand are in the same direction as the sales trend. Conversely, if the absolute value of the initial variable demand is greater than the absolute value of the corresponding optimized variable demand (e.g., the initial variable demand is -10, and the corresponding optimized variable demand is -8), then the initial variable demand is not met. In this case, all increases / decreases in the optimized variable demand are in the opposite direction to the sales trend. The better the optimized variable demand, the more favorable its direction.

[0061] It should be understood that the bottleneck component average overshoot ratio factor is used to compare which bottleneck component has a lower average overshoot ratio for optimization change requirements. Here, the bottleneck component is pre-configured; it is a component with a corresponding bottleneck from a supplier. The highest overshoot ratio factor is related to the component with the highest overshoot ratio. The component with the highest overshoot ratio has the greatest overshoot risk, so the lower the highest overshoot ratio, the better the corresponding optimization change requirement. The overshoot component number factor is related to the number of overshoot components; the fewer the number of overshoot components, the better the corresponding optimization change requirement.

[0062] Understandably, if there are more small-quantity parts among the excess parts, the optimization of the change requirement is less optimal, because small-quantity parts are more likely to have corresponding non-compliance (NG) situations. Therefore, an excess factor before the change is introduced to measure the excess of small-quantity parts in the optimization of the change requirement. Small-quantity parts are judged based on the quantity of parts before the change. If the optimization of the change requirement involves multiple excess parts, the smaller the average value of all excess parts before the change, the lower the risk of the corresponding small-quantity parts, and the better the optimization of the change requirement. If the average values ​​before the change are the same, the average excess ratio is also considered; the lower the average excess ratio, the better the optimization of the change requirement.

[0063] Step S402: Calculate the scores of the multi-dimensional evaluation factors corresponding to the optimization change requirements; The score for the sample average deviation rate factor consists of two parts: the deviation rate calculation result (average deviation rate score) and the variance calculation result (deviation rate variance). First, the deviation rate for each sample is calculated as: Deviation rate = (Quantity after optimization change requirement calculation - Quantity after initial change requirement calculation) / (Quantity after initial change requirement calculation + 1). The "+1" ensures the divisor is not zero. Then, the average deviation rate of all samples is calculated to obtain the average deviation rate score for the optimization change requirement. Next, based on the deviation rate of each sample, the variance of the optimization change requirement is calculated. This measures the dispersion of the deviation rate; the smaller the variance, the better the optimization change requirement. The score for the sample average deviation rate factor (before normalization) = average deviation rate score + deviation rate variance. The scores for different optimization change requirements need to be normalized to obtain the final score. The smaller the score for the sample average deviation rate factor, the better the optimization change requirement.

[0064] To score the pattern change direction factor, first determine which patterns in the optimized change requirements are in the same direction and which are in the opposite direction. Count the number of patterns with opposite directions and calculate the total deviation value of these patterns (the sum of the absolute values ​​of the differences between the absolute values ​​of the variables in the optimized change requirements and the absolute values ​​of the variables in the initial change requirements). Normalize this total deviation value to weaken this factor, allowing the number of patterns with opposite directions to play a decisive role in this factor. The score of the pattern change direction factor = the number of patterns with opposite directions + the normalized total deviation value. Scores for different optimized change requirements need to be normalized to obtain the final score. The lower the score of the pattern change direction factor, the better the optimized change requirement.

[0065] To score the average overshoot ratio factor for bottleneck components, first, calculate the overshoot ratio of all bottleneck components in the optimized variable requirement, then calculate the average overshoot ratio of all bottleneck components. This average overshoot ratio is used as the score for the average overshoot ratio factor of bottleneck components for that optimized variable requirement. The scores for different optimized variable requirements need to be normalized to obtain the final score. The lower the score of the average overshoot ratio factor for bottleneck components, the better the optimized variable requirement.

[0066] For the score of the highest overshoot ratio factor, first calculate the overshoot ratio of each component in the optimized variable requirement, find the largest overshoot ratio, and use it as the score of the highest overshoot ratio factor of the optimized variable requirement. The scores of different optimized variable requirements need to be normalized to obtain the final score.

[0067] For the score of the number of oversized parts factor, first calculate the oversized ratio of the parts, count the number of oversized parts for the optimization change requirements (the number of parts with an oversized ratio greater than 0), and use this as the score of the number of oversized parts factor for the optimization change requirements. The scores of different optimization change requirements need to be normalized to obtain the final score.

[0068] To score the pre-change excess factor, first, the excess ratio and pre-change quantity of components in the optimized change requirement are statistically analyzed. The excess ratio of components is normalized to weaken its effect and highlight the dominant role of the pre-change quantity (the main factor measuring the excess risk of a small number of components). Then, the score for each component is calculated: Component score = Normalized excess ratio - Pre-change quantity. Here, the pre-change quantity is the dominant factor in the score, and the excess ratio (after normalization) is a secondary factor. The average score of all excess components is taken as the pre-change excess factor score for that optimized change requirement. The scores of different optimized change requirements need to be normalized to obtain the final score. For example, assuming that the quantity of component A before the change is 2 and the overshoot ratio is 20%, the quantity of component B before the change is 3 and the overshoot ratio is 10%, and the quantity of component C before the change is 4 and the overshoot ratio is 300%, then the normalized overshoot ratio of component A is 0.03, the normalized overshoot ratio of component B is 0, and the normalized overshoot ratio of component C is 1. The score of component A is -2 + 0.03 = -1.97, the score of component B is -3 + 0 = -3, and the score of component C is -4 + 1 = -3. The average score of the component scores is taken as the score of the overshoot factor before the change, that is, (-1.97 - 3 - 3) / 3 = -2.66. Subsequently, normalization is performed based on the scores of all optimization change requirements.

[0069] Step S403: Based on the scores of the multi-dimensional evaluation factors corresponding to the optimization change requirements and the weights of the multi-dimensional evaluation factors, determine the recommended score for the optimization change requirements.

[0070] It should be noted that the weights of the multi-dimensional evaluation factors can be set according to the actual situation / needs. For example, the weights of the average deviation rate factor, the direction of change factor, the average overshoot ratio factor of bottleneck parts, the highest overshoot ratio factor, the number of overshoot parts factor, and the overshoot factor before the change can be set to 30%, 20%, 10%, 12%, 15%, and 13%, respectively, without any specific limitation.

[0071] Understandably, the scores of the multi-dimensional evaluation factors are weighted using the weights of the multi-dimensional evaluation factors, and the resulting calculation is the recommendation score, thereby calculating the recommendation score corresponding to each optimization change requirement.

[0072] Step S50: Based on the recommended score of the optimized change requirements, determine the target change requirements of the vehicle style production plan.

[0073] It should be noted that the lower the recommendation score, the better the corresponding optimization change requirement. In other words, we need to find the one with the lowest recommendation score among all optimization change requirements and use it as the final change requirement, i.e., the target change requirement.

[0074] For example, suppose the recommended score for optimization change requirement A is 0.7315, the recommended score for optimization change requirement B is 0.527, and the recommended score for optimization change requirement C is 0.49. In this case, optimization change requirement C has the lowest recommended score, so optimization change requirement C is selected as the target change requirement.

[0075] This embodiment provides a method for optimizing vehicle production plan change requirements. It obtains the initial change requirements of the vehicle model production plan and performs a component overrun check on these requirements. When component overruns exist, the vehicle models are ranked based on multi-dimensional ranking factors to obtain a model reduction ranking result. Based on the model reduction ranking result, the initial change requirements are adjusted to obtain optimized change requirements that meet the optimization objectives. The optimized change requirements are evaluated based on multi-dimensional evaluation factors to obtain a recommended score for the optimized change requirements. Based on the recommended score of the optimized change requirements, the target change requirements for the vehicle model production plan are determined. This embodiment determines the reduction priority of different models by quantifying multi-dimensional ranking factors, generating multiple optimization schemes. Based on the balance between sales demand and supply impact, multi-dimensional evaluation factors are set, and the recommended scores of each optimization scheme are quantified using these factors. The optimal solution is selected from these, comprehensively considering demand increments and supply chain impacts to generate the most suitable change requirement optimization scheme, effectively balancing demand changes and supply chain response.

[0076] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in Embodiment 1 above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 3 Step S30 may include steps S301 to S304: Step S301: When the optimization objective is that the parts do not exceed the allowable size, the parts reduction ranking result is determined based on the number of vehicle parts exceeding the allowable size and the pattern reduction ranking result. It should be noted that the excess quantity of vehicle parts refers to the specific quantity corresponding to the allowable fluctuation range of the parts. The quantity exceeding the allowable fluctuation range is the excess quantity. For example, assuming the normal supply of vehicle parts is 100 and the allowable fluctuation range is 20%, the maximum supply of vehicle parts is 120. If the demand given by the sales side is 130, then there is an excess, and the excess quantity is 10.

[0077] Understandably, the parts are first sorted in descending order of their excess length (the more excess length a part has, the higher it ranks). Then, the corresponding styles for each part are sorted according to the style reduction ranking, resulting in the final part reduction ranking. For example, part 1 has an excess length of 20, and its styles are Style 1 and Style 2; part 2 has an excess length of 10, and its styles are Style 1 and Style 3; part 3 has an excess length of 15, and its styles are Style 2 and Style 3. The style reduction ranking is: Style 1, Style 3, Style 2. Therefore, the parts are ranked as: Part 1, Part 3, Part 2. For part 1, the further style ranking is: Style 1, Style 2; for part 2, the further style ranking is: Style 1, Style 3; and for part 3, the further style ranking is: Style 3, Style 2.

[0078] Step S302: Based on the order quantity and frozen quantity of the vehicle type, determine the protection increment of the vehicle type; It should be noted that the order quantity for vehicle styles refers to the number of different styles ordered by customers, and this order quantity cannot be reduced. The frozen quantity is the quantity that cannot be reduced during the optimization process, and the protected increment is the increment that needs to be protected during the optimization process and cannot be changed in the current calculation round. Generally speaking, the protected increment is the maximum value between the order quantity and the frozen quantity.

[0079] Understandably, for optimization goals that ensure parts do not exceed acceptable limits, two rounds of calculations are typically used. In the first round, the frozen quantity for each style is determined based on sales priority. If sales priorities differ, styles with high or medium sales priority are protected, while styles with low sales priority are not protected. In other words, the changed quantity of styles with high or medium sales priority is used as the frozen quantity. If sales priorities are the same, all styles are protected, meaning the changed quantity of each style is used as the frozen quantity. In the second round, the frozen quantity is set to 0, and the protection increment equals the order quantity.

[0080] Step S303: Based on the protection increment of the vehicle pattern and the changed quantity of the vehicle pattern, calculate the maximum reducible amount of the vehicle pattern. It should be noted that the changed quantities of each style can be determined based on the initial change requirements. The maximum reducible quantity is the maximum quantity that can be reduced, and the maximum reducible quantity = changed quantity - protection increment.

[0081] Understandably, reference Figure 4If, in the first round of calculation, the maximum reduction amount for all patterns corresponding to the oversized parts is 0, or if there are still oversized parts after all patterns are reduced according to the maximum reduction amount, then it is considered that the current round cannot obtain the optimization change requirements that meet the optimization objectives, and the second round of calculation will begin, without protecting the original increment.

[0082] Step S304: Based on the maximum reducible quantity of the vehicle type and the sorting results of the component reduction, adjust the initial change requirements to determine the optimized change requirements that meet the optimization objectives.

[0083] In one feasible implementation, step S304 may include steps A11 to A17: Step A11: Based on the component reduction sorting results, determine the current component to be reduced; It should be noted that the component ranked first in the component reduction ranking results is selected as the current component to be reduced.

[0084] Step A12: Based on the excess quantity of the current reduced part and the part production quantity of the vehicle pattern, determine the excess quantity that can be reduced for the vehicle pattern corresponding to the current reduced part. It should be noted that when calculating the allowable reduction for oversize, if the oversize quantity is negative, it should be represented by 0. The component production quantity refers to the number of components required to produce the vehicle model.

[0085] Understandably, by dividing the current excess quantity of the reduced parts by the production quantity of the parts for the vehicle model, we can calculate the excess reduction amount for each model corresponding to the current reduced parts (rounding the final result up to the integer). That is, for the excess quantity of the parts that can be reduced, after reducing the excess quantity according to the excess reduction amount of the vehicle model, the parts corresponding to that model will not exceed the excess quantity.

[0086] Step A13: Based on the excess reduction amount of the vehicle pattern corresponding to the current reduction part and the maximum reduction amount of the vehicle pattern, determine the reduction amount of the vehicle pattern corresponding to the current reduction part. It should be noted that the smaller value between the over-limit reduction and the maximum reduction of the vehicle type shall be selected as the reduction of the vehicle type.

[0087] Step A14: Based on the reduction of the vehicle style corresponding to the current reduced parts, adjust the initial change requirements to obtain the first adjustment requirements; Understandably, the quantity of the top-ranked design of the currently reduced-quantity parts is adjusted according to the calculated reduction, resulting in the reduced quantity of that design (if the reduction is 0, it is carried over to the next ranked design), thus generating the first adjustment requirement. After adjusting the top-ranked design of the currently reduced-quantity parts, the excess quantity of each part is updated based on the adjustment, and the parts are re-ranked to redetermine the ranking result of the reduced-quantity parts.

[0088] Step A15: When the first adjustment requirement meets the optimization target and the reduction target, calculate the maximum amount that can be added to the vehicle type; It should be noted that when the optimization objective is to ensure that the parts do not exceed the allowable limits, the reduction target can be that the total reduction is less than or equal to the quantity that needs to be reduced, that is, the total production quantity of the first adjustment demand is less than or equal to the total production quantity of the initial variable demand. Generally speaking, the quantity that needs to be reduced is equal to the quantity that has already been increased (which can be determined based on the difference between the quantity of each style after adjustment and the production plan).

[0089] Understandably, reference Figure 4 If the first adjustment demand meets both the optimization and reduction objectives, then it is determined whether the total production quantity of the first adjustment demand is less than the total production quantity of the initial change demand. If the total production quantity of the first adjustment demand is less than the total production quantity of the initial change demand, it means that the reduction has been too large and the total quantity cannot be guaranteed to remain unchanged, so an increase is needed. If the first adjustment demand does not meet either the optimization or reduction objective, then the excess quantity of each component is updated according to the first adjustment demand, the components are re-sorted, and the component reduction sorting result is re-determined. The reduction continues according to the updated component reduction sorting result until a first adjustment demand that meets both the optimization and reduction objectives is found. If a first adjustment demand that meets both the optimization and reduction objectives cannot be found, then it is considered that the current weight combination cannot obtain the target change demand, and the next weight combination is selected.

[0090] It should be understood that the allowable quantity for oversized parts is 0, and the allowable quantity for non-oversized parts is determined based on the oversized quantity (negative value). The absolute value of the oversized quantity is divided by the production quantity of the corresponding part to find the allowable quantity for each non-oversized part corresponding to the specified part. The maximum allowable quantity for each specified part is the minimum allowable quantity for that specified part among all parts.

[0091] Step A16: Based on the maximum amount that can be added to the vehicle model, adjust the first adjustment requirement to obtain the second adjustment requirement; It should be noted that the parts are first sorted in ascending order according to the amount of excess (negative values ​​are retained) (the smaller the amount of excess, the higher the ranking). Then, the patterns corresponding to each part are sorted in descending order according to the pattern reduction ranking result, thus obtaining the part addition ranking result.

[0092] Understandably, the quantity to be increased is determined based on the quantity to be reduced. The top-ranked style from the component quantity increase ranking is selected for quantity increase, and this increase must be less than or equal to the maximum increase quantity of that style (if the maximum increase quantity is 0, it proceeds to the next ranked style). If the increase quantity reaches the required quantity, a second adjustment requirement is generated based on this increase quantity. If the increase quantity does not reach the required quantity, the components are re-ranked based on this increase quantity, the component quantity increase ranking is re-determined, and the top-ranked style is selected again for quantity increase, until the corresponding second adjustment requirement is obtained.

[0093] Step A17: When the second adjustment requirement meets the optimization objective, the second adjustment requirement is taken as the optimization change requirement.

[0094] Understandably, if the second adjustment requirement aligns with the optimization objective of not exceeding the allowable margin of change for the component, then this second adjustment requirement is considered an optimization change requirement. If a second adjustment requirement that satisfies the optimization objective cannot be obtained, then the current weight combination is considered unable to meet the target change requirement, and the next weight combination is selected.

[0095] This embodiment provides a method for optimizing vehicle production plan change requirements. When the optimization objective is to ensure that parts do not exceed limits, the method determines the parts reduction ranking based on the excess quantity of vehicle parts and the style reduction ranking results. Based on the order quantity and frozen quantity of vehicle styles, the method determines the protection increment of vehicle styles. Based on the protection increment of vehicle styles and the changed quantity of vehicle styles, the method calculates the maximum reduction of vehicle styles. Based on the maximum reduction of vehicle styles and the parts reduction ranking results, the initial change requirements are adjusted to determine the optimized change requirements that meet the optimization objective. This embodiment determines the reduction priority of different styles by quantifying multi-dimensional ranking factors. Based on this, with the optimization objective of ensuring that parts do not exceed limits, it strives to guarantee the increase in demand and absolutely guarantees that parts do not exceed limits, generating multiple optimization schemes. Subsequently, based on the balance between sales demand and supply impact, the method recommends and scores each optimization scheme, selecting the optimal solution. This method comprehensively considers the increase in demand and the impact of the supply chain, generating the most suitable change requirement optimization scheme, effectively balancing demand changes and supply chain response.

[0096] Based on the above embodiments of this application, in the third embodiment of this application, the same or similar content as the above embodiments can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 5 Step S30 may include steps S301' to S303': Step S301': When the optimization objective is to maximize supply capacity, determine the protection increment of the vehicle type based on the order quantity and frozen quantity of the vehicle type. It should be noted that the order quantity for vehicle styles refers to the number of different styles ordered by customers, and this order quantity cannot be reduced. The frozen quantity is the quantity that cannot be reduced during the optimization process, and the protected increment is the increment that needs to be protected during the optimization process and cannot be changed in the current calculation round. Generally speaking, the protected increment is the maximum value between the order quantity and the frozen quantity.

[0097] Understandably, for the optimization goal of maximizing supply capacity, the frozen quantity of each style can be determined based on sales priority. If the sales priorities are different, styles with high or medium sales priority are protected, while styles with low sales priority are not protected. In other words, the changed quantity of styles with high or medium sales priority is used as the frozen quantity. If the sales priorities are the same, all styles are protected, which means the changed quantity of the styles is used as the frozen quantity.

[0098] Step S302': Based on the protection increment of the vehicle pattern and the changed quantity of the vehicle pattern, calculate the maximum reducible amount of the vehicle pattern. It should be noted that the changed quantities of each style can be determined based on the initial change requirements. The maximum reducible quantity is the maximum quantity that can be reduced, and the maximum reducible quantity = changed quantity - protection increment.

[0099] Understandably, reference Figure 6 Before officially reducing the quantity, first determine whether there are cases where the maximum reduction quantity of the corresponding style of the oversized parts is 0. If so, it is considered that the current optimization change requirements that meet the optimization goal cannot be obtained, and the next weight combination can be selected to re-optimize the initial change requirements.

[0100] Step S303': Based on the maximum reducible quantity of the vehicle pattern and the pattern reduction ranking result, the initial change requirements are adjusted to obtain optimized change requirements that meet the optimization objective.

[0101] In one feasible implementation, step S303' may include steps B11 to B15: Step B11: Based on the pattern reduction sorting results, determine the current reduction pattern; It should be noted that, based on the sample reduction sorting results, the samples are sorted in descending order according to the oversize quantity of the parts (negative values ​​are retained) (the larger the oversize quantity of the parts, the higher the sorting), and the sample ranked first is selected as the current reduction sample.

[0102] Step B12: Based on the excess quantity of the parts in the current reduction pattern and the production quantity of the parts in the current reduction pattern, determine the excess quantity that can be reduced in the current reduction pattern. It should be noted that the component oversize quantity of the current reduction sample is the same as the component oversize quantity corresponding to the current reduction sample. When calculating the reducible oversize, if the component oversize quantity is negative, it is represented by 0. The component production quantity of the current reduction sample is the quantity of components required to produce the current reduction sample.

[0103] Understandably, by dividing the excess quantity of the parts in the current reduction pattern by the production quantity of the parts in the current reduction pattern, the excess quantity that can be reduced in the current reduction pattern can be calculated (rounding the final result up to the integer). That is, for the excess quantity that can be reduced, after reducing the excess quantity according to the excess quantity that can be reduced in the current reduction pattern, the parts corresponding to this pattern will not exceed the limit.

[0104] Step B13: Based on the over-reduction amount and the maximum reduction amount of the current reduction pattern, determine the reduction amount of the current reduction pattern; It should be noted that the smaller value between the over-reduction amount and the maximum reduction amount of the current reduction pattern is selected as the reduction amount of the current reduction pattern.

[0105] Step B14: Adjust the initial change requirement based on the reduction of the current reduction pattern; Understandably, the quantity of the first part in the current reduced pattern is adjusted according to the calculated reduction to obtain the quantity of the pattern after reduction (if the reduction is 0, it will be carried over to the next pattern in the order). After adjusting the first part in the current reduced pattern, the excess quantity of each part is updated according to the adjustment, and the pattern is reordered.

[0106] Step B15: When the adjusted initial change requirements meet the optimization and reduction objectives, the adjusted initial change requirements shall be used as the optimized change requirements.

[0107] It should be noted that when the optimization objective is to maximize supply capacity, the reduction target can be that the total reduction equals the quantity that needs to be reduced, that is, the adjusted total production quantity of the initial variable demand equals the initial variable demand of the total production quantity. Generally speaking, the quantity that needs to be reduced is equal to the quantity that has already been increased (which can be determined based on the difference between the adjusted quantity of each style and the production plan).

[0108] Understandably, reference Figure 6 If the adjusted initial change requirement meets both the optimization and reduction objectives, then the adjusted initial change requirement is the optimized change requirement. If it fails to meet the optimization and reduction objectives, then the current weight combination is considered insufficient to meet the target change requirement, and the next weight combination is selected.

[0109] This embodiment provides a method for optimizing vehicle production plan change requirements. When the optimization objective is to maximize supply capacity, the method determines the protection increment of vehicle styles based on the order quantity and frozen quantity of vehicle styles. Based on the protection increment of vehicle styles and the changed quantity of vehicle styles, the maximum reducible quantity of vehicle styles is calculated. Based on the maximum reducible quantity of vehicle styles and the style reduction ranking results, the initial change requirements are adjusted to obtain optimized change requirements that meet the optimization objective. This embodiment determines the reduction priority of different styles by quantifying multi-dimensional ranking factors. On this basis, with maximizing supply capacity as the optimization objective, it absolutely guarantees the increase in demand and tries to ensure that parts do not exceed the limit. Multiple optimization schemes are generated so that each optimization scheme can be recommended and scored based on the balance between sales demand and supply impact. The optimal solution is selected from these recommendations. This method can comprehensively consider the increase in demand and the impact of the supply chain to generate the most suitable change requirement optimization scheme, effectively balancing demand changes and supply chain response.

[0110] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the vehicle production plan change demand optimization method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0111] This application also provides a vehicle production plan change demand optimization device, please refer to... Figure 7 The vehicle production plan change demand optimization device includes: The oversize inspection module 10 is used to obtain the initial change requirements of the vehicle pattern production plan and perform component oversize inspection on the initial change requirements. The demand optimization module 20 is used to sort the vehicle styles based on multi-dimensional sorting factors when there are parts exceeding the size limit, and obtain the style reduction sorting result. The demand optimization module 20 is also used to adjust the initial change demand based on the pattern reduction sorting result to obtain an optimized change demand that meets the optimization objective. The optimization evaluation module 30 is used to evaluate the optimization change requirements based on multi-dimensional evaluation factors and obtain a recommended score for the optimization change requirements. The optimization evaluation module 30 is also used to determine the target change requirements of the vehicle style production plan based on the recommended score of the optimization change requirements.

[0112] In one feasible implementation, the demand optimization module 20 is further used to obtain multi-dimensional ranking factors, which include at least sales priority factors, combined sales trend factors, style sales trend factors, main model factors, number of oversized parts factors, small quantity factors, summation of small quantity factors, reservation factors, and proportion of oversized parts factors. Calculate the score of the multi-dimensional ranking factor corresponding to the vehicle pattern; Based on the weight value range of the multi-dimensional ranking factors, multiple weight combinations of the multi-dimensional ranking factors are determined. Based on the scores of the multi-dimensional ranking factors corresponding to the vehicle type and the multiple weight combinations of the multi-dimensional ranking factors, the reduction priority of the vehicle type corresponding to different weight combinations is determined. Based on the reduction priority of vehicle styles corresponding to different weight combinations, the reduction ranking result of styles corresponding to different weight combinations is determined.

[0113] In one feasible implementation, the demand optimization module 20 is further configured to determine the component reduction ranking result based on the number of vehicle components exceeding the limit and the pattern reduction ranking result when the optimization objective is that the components do not exceed the limit. Based on the order quantity and frozen quantity of the vehicle type, determine the protection increment of the vehicle type; Based on the protection increment of the vehicle type and the changed quantity of the vehicle type, calculate the maximum reducible amount of the vehicle type. Based on the maximum reducible quantity of the vehicle type and the ranking results of the component reduction, the initial change requirements are adjusted to determine the optimized change requirements that meet the optimization objectives.

[0114] In one feasible implementation, the demand optimization module 20 is further configured to determine the current component to be reduced based on the component reduction sorting results; Based on the excess quantity of the current reduced parts and the production quantity of the parts for the vehicle model, determine the excess quantity that can be reduced for the vehicle model corresponding to the current reduced parts. Based on the excess reduction amount of the vehicle pattern corresponding to the current reduction part and the maximum reduction amount of the vehicle pattern, the reduction amount of the vehicle pattern corresponding to the current reduction part is determined. Based on the reduction in vehicle type corresponding to the current reduced parts, the initial change requirements are adjusted to obtain the first adjustment requirements; When the first adjustment requirement meets the optimization and reduction objectives, calculate the maximum amount that can be added to the vehicle type; Based on the maximum amount that can be added to the vehicle type, the first adjustment requirement is adjusted to obtain the second adjustment requirement; When the second adjustment requirement meets the optimization objective, the second adjustment requirement is taken as the optimization change requirement.

[0115] In one feasible implementation, the demand optimization module 20 is further configured to determine the protection increment of the vehicle type based on the order quantity and frozen quantity of the vehicle type when the optimization objective is to maximize supply capacity. Based on the protection increment of the vehicle type and the changed quantity of the vehicle type, calculate the maximum reducible amount of the vehicle type. Based on the maximum reducible quantity of the vehicle type and the sorting result of the type reduction, the initial change requirements are adjusted to obtain optimized change requirements that meet the optimization objectives.

[0116] In one feasible implementation, the demand optimization module 20 is further configured to determine the current reduction pattern based on the pattern reduction sorting result; Based on the excess quantity of the parts in the current reduction pattern and the production quantity of the parts in the current reduction pattern, determine the amount of excess that can be reduced in the current reduction pattern. Based on the over-reduction amount and maximum reduction amount of the current reduction pattern, the reduction amount of the current reduction pattern is determined; Based on the reduction of the current reduction pattern, the initial change requirement is adjusted; When the adjusted initial change requirements meet the optimization and reduction objectives, the adjusted initial change requirements will be used as the optimized change requirements.

[0117] In one feasible implementation, the optimization evaluation module 30 is further used to obtain multi-dimensional evaluation factors and the weights of the multi-dimensional evaluation factors. The multi-dimensional evaluation factors include at least the average deviation rate factor of the pattern, the direction of pattern change factor, the average overshoot ratio factor of the bottleneck component, the maximum overshoot ratio factor, the number of overshoot components factor, and the overshoot factor before the change. Calculate the scores of the multi-dimensional evaluation factors corresponding to the optimized change requirements; Based on the scores of the multi-dimensional evaluation factors corresponding to the optimization change requirements and the weights of the multi-dimensional evaluation factors, the recommended score for the optimization change requirements is determined.

[0118] The vehicle production plan change demand optimization device provided in this application, employing the vehicle production plan change demand optimization method in the above embodiments, can solve the technical problem of balancing the changing demand of vehicle models with the ease of supply chain response. Compared with the prior art, the beneficial effects of the vehicle production plan change demand optimization device provided in this application are the same as those of the vehicle production plan change demand optimization method provided in the above embodiments, and other technical features in the vehicle production plan change demand optimization device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0119] This application provides a vehicle production plan change demand optimization device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the vehicle production plan change demand optimization method in the above embodiment 1.

[0120] The following is for reference. Figure 8 The diagram illustrates a structural schematic suitable for implementing a vehicle production plan change demand optimization device according to embodiments of this application. The vehicle production plan change demand optimization device in embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 8 The vehicle production plan change demand optimization device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0121] like Figure 8As shown, the vehicle production plan change demand optimization device may include a processing unit 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in ROM (Read Only Memory) 1002 or a program loaded from storage device 1003 into RAM (Random Access Memory) 1004. RAM 1004 also stores various programs and data required for the operation of the vehicle production plan change demand optimization device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via bus 1005. Input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the vehicle production plan change demand optimization equipment to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows a vehicle production plan change demand optimization equipment with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented alternatively.

[0122] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0123] The vehicle production plan change demand optimization device provided in this application, employing the vehicle production plan change demand optimization method in the above embodiments, can solve the technical problem of balancing the changing demand of vehicle models with the ease of supply chain response. Compared with the prior art, the beneficial effects of the vehicle production plan change demand optimization device provided in this application are the same as those of the vehicle production plan change demand optimization method provided in the above embodiments, and other technical features of this vehicle production plan change demand optimization device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0124] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0125] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0126] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the vehicle production plan change demand optimization method in the above embodiments.

[0127] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, 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. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0128] The aforementioned computer-readable storage medium may be included in the vehicle production plan change demand optimization device; or it may exist independently and not be installed in the vehicle production plan change demand optimization device.

[0129] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by the vehicle production plan change requirement optimization equipment, the vehicle production plan change requirement optimization equipment: acquires the initial change requirements of the vehicle pattern production plan; performs a part overrun check on the initial change requirements; when part overruns exist, sorts the vehicle patterns based on multi-dimensional sorting factors to obtain a pattern reduction sorting result; adjusts the initial change requirements based on the pattern reduction sorting result to obtain optimized change requirements that meet the optimization objective; evaluates the optimized change requirements based on multi-dimensional evaluation factors to obtain a recommended score for the optimized change requirements; and determines the target change requirements of the vehicle pattern production plan based on the recommended score for the optimized change requirements.

[0130] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0131] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0132] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0133] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described vehicle production plan change demand optimization method. This solves the technical problem of balancing the changing demand of vehicle models with the ease of supply chain response. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the vehicle production plan change demand optimization method provided in the above embodiments, and will not be repeated here.

[0134] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the vehicle production plan change demand optimization method described above.

[0135] The computer program product provided in this application can solve the technical problem of balancing the changing demands of vehicle models with the ease of supply chain response. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the vehicle production plan change demand optimization method provided in the above embodiments, and will not be repeated here.

[0136] The above are only some embodiments of this application and do not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the content of this application specification and drawings, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for optimizing demand due to changes in vehicle production plans, characterized in that, The method includes: Obtain the initial change requirements for the vehicle style production plan, and perform component oversize checks on the initial change requirements; When there are parts exceeding the allowable size, the vehicle styles are sorted based on multi-dimensional sorting factors to obtain the style reduction sorting result; Based on the pattern reduction sorting results, the initial change requirements are adjusted to obtain optimized change requirements that meet the optimization objectives. The optimization change requirements are evaluated based on multi-dimensional evaluation factors to obtain a recommended score for the optimization change requirements; Based on the recommended score of the optimized change requirements, the target change requirements for the vehicle style production plan are determined.

2. The method as described in claim 1, characterized in that, The steps for sorting the vehicle patterns based on multi-dimensional sorting factors to obtain the pattern reduction sorting results include: Obtain multi-dimensional ranking factors, which include at least the sales priority factor, the combination sales trend factor, the style sales trend factor, the main model factor, the number of oversized parts factor, the small quantity factor, the small quantity summation factor, the reservation factor, and the oversized parts ratio factor. Calculate the score of the multi-dimensional ranking factor corresponding to the vehicle pattern; Based on the weight value range of the multi-dimensional ranking factors, multiple weight combinations of the multi-dimensional ranking factors are determined. Based on the scores of the multi-dimensional ranking factors corresponding to the vehicle type and the multiple weight combinations of the multi-dimensional ranking factors, the reduction priority of the vehicle type corresponding to different weight combinations is determined. Based on the reduction priority of vehicle styles corresponding to different weight combinations, the reduction ranking result of styles corresponding to different weight combinations is determined.

3. The method as described in claim 1, characterized in that, The step of adjusting the initial change requirements based on the pattern reduction sorting results to obtain optimized change requirements that meet the optimization objective includes: When the optimization objective is to ensure that the parts do not exceed the allowable size, the parts reduction ranking result is determined based on the number of vehicle parts exceeding the allowable size and the reduction ranking result of the aforementioned pattern. Based on the order quantity and frozen quantity of the vehicle type, determine the protection increment of the vehicle type; Based on the protection increment of the vehicle type and the changed quantity of the vehicle type, calculate the maximum reducible amount of the vehicle type. Based on the maximum reducible quantity of the vehicle type and the ranking results of the component reduction, the initial change requirements are adjusted to determine the optimized change requirements that meet the optimization objectives.

4. The method as described in claim 3, characterized in that, The step of adjusting the initial change requirements based on the maximum reducible quantity of the vehicle type and the ranking results of the component reduction, and determining the optimized change requirements that meet the optimization objectives, includes: Based on the component reduction ranking results, the current component to be reduced is determined; Based on the excess quantity of the current reduced parts and the production quantity of the parts for the vehicle model, determine the excess quantity that can be reduced for the vehicle model corresponding to the current reduced parts. Based on the excess reduction amount of the vehicle pattern corresponding to the current reduction part and the maximum reduction amount of the vehicle pattern, the reduction amount of the vehicle pattern corresponding to the current reduction part is determined. Based on the reduction in vehicle type corresponding to the current reduced parts, the initial change requirements are adjusted to obtain the first adjustment requirements; When the first adjustment requirement meets the optimization and reduction objectives, calculate the maximum amount that can be added to the vehicle type; Based on the maximum amount that can be added to the vehicle type, the first adjustment requirement is adjusted to obtain the second adjustment requirement; When the second adjustment requirement meets the optimization objective, the second adjustment requirement is taken as the optimization change requirement.

5. The method as described in claim 1, characterized in that, The step of adjusting the initial change requirements based on the pattern reduction sorting results to obtain optimized change requirements that meet the optimization objective includes: When the optimization objective is to maximize supply capacity, the protection increment for the vehicle type is determined based on the order quantity and frozen quantity of the vehicle type. Based on the protection increment of the vehicle type and the changed quantity of the vehicle type, calculate the maximum reducible amount of the vehicle type. Based on the maximum reducible quantity of the vehicle type and the sorting result of the type reduction, the initial change requirements are adjusted to obtain optimized change requirements that meet the optimization objectives.

6. The method as described in claim 5, characterized in that, The step of adjusting the initial change requirements based on the maximum reducible quantity of the vehicle style and the style reduction ranking results to obtain optimized change requirements that meet the optimization objective includes: Based on the sorting results of the pattern reduction, the current reduction pattern is determined; Based on the excess quantity of the parts in the current reduction pattern and the production quantity of the parts in the current reduction pattern, determine the amount of excess that can be reduced in the current reduction pattern. Based on the over-reduction amount and maximum reduction amount of the current reduction pattern, the reduction amount of the current reduction pattern is determined; Based on the reduction of the current reduction pattern, the initial change requirement is adjusted; When the adjusted initial change requirements meet the optimization and reduction objectives, the adjusted initial change requirements will be used as the optimized change requirements.

7. The method as described in claim 1, characterized in that, The step of evaluating the optimization change requirements based on multi-dimensional evaluation factors to obtain a recommended score for the optimization change requirements includes: Obtain multi-dimensional evaluation factors and their weights. The multi-dimensional evaluation factors include at least the average deviation rate factor of the sample, the direction of sample change factor, the average overshoot ratio factor of the bottleneck component, the maximum overshoot ratio factor, the number of overshoot components factor, and the overshoot factor before the change. Calculate the scores of the multi-dimensional evaluation factors corresponding to the optimized change requirements; Based on the scores of the multi-dimensional evaluation factors corresponding to the optimization change requirements and the weights of the multi-dimensional evaluation factors, the recommended score for the optimization change requirements is determined.

8. A vehicle production plan change demand optimization device, characterized in that, The device includes: The oversize inspection module is used to obtain the initial change requirements of the vehicle style production plan and to perform component oversize inspection on the initial change requirements. The demand optimization module is used to sort the vehicle patterns based on multi-dimensional sorting factors when there are parts exceeding the allowable size, and obtain the pattern reduction sorting result. The demand optimization module is also used to adjust the initial change demand based on the pattern reduction sorting result to obtain an optimized change demand that meets the optimization objective. An optimization evaluation module is used to evaluate the optimization change requirements based on multi-dimensional evaluation factors and obtain a recommended score for the optimization change requirements. The optimization evaluation module is also used to determine the target change requirements of the vehicle style production plan based on the recommended score of the optimization change requirements.

9. A vehicle production plan change demand optimization device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the vehicle production plan change demand optimization method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the vehicle production plan change demand optimization method as described in any one of claims 1 to 7.

Images