Smart card order prediction method and device, storage medium and computer equipment

Abstract

The smart card order prediction method and device, the storage medium and the computer device provided by the application, when receiving a smart card order initiated by a customer, the actual card issuing data of the product card amount corresponding to the smart card order in a preset historical time period is called as data support, the card issuing prediction of the current month is calculated to avoid the deviation of subjective judgment of the salesperson, then the grade coefficient of the smart card order is determined according to the card issuing prediction, which is used for the optimization adjustment of the initial card issuing prediction, so that the optimized prediction obtained by the adjustment is more suitable for the production characteristics of different scale orders, finally, the historical production data, the online inventory quantity and the demand quantity of the customer order of the product card amount are obtained, and the card issuing prediction and the optimized prediction are comprehensively calculated, and finally the order prediction meeting the potential demand in the future is obtained, so that the order characteristics of small batch and multiple batches can be fundamentally adapted, and the delivery time limit of the customer order can be ensured while reducing the comprehensive cost of production and operation.

Description

Technical Field

[0001] This application relates to the field of smart card technology, and in particular to a smart card order prediction method, apparatus, storage medium and computer equipment. Background Technology

[0002] With the rapid popularization of financial payments, communication services, and city smart cards, the application scenarios of smart card products are constantly expanding, and the market demand for customized card designs is continuously increasing. The production and operation scale of the entire industry is also steadily growing. The existing smart card production and operation order model directly arranges production and delivery based on the order information provided by the customer. However, as the variety of product cards increases and the market changes faster, customers are increasingly adopting a small-batch, multi-batch order model to meet their own cost reduction needs. Because production and operation adopt a make-to-order production model, it is necessary to frequently start up the machine for production, passively carrying out multiple small-batch productions, which greatly increases production and operation costs.

[0003] Currently, most mainstream production demand forecasting in the industry is done by sales personnel on the business side, combining their subjective judgment of market conditions with their past experience dealing with clients. A standardized and systematic forecasting mechanism has not yet been established. However, forecasting methods relying on manual experience are extremely unstable. If the forecast value is much higher than the actual demand, it results in a large backlog of customized cards, leading to substantial losses from obsolete inventory. Conversely, if the forecast value is lower than the actual order demand, it leads to insufficient raw material inventory, making it impossible to quickly respond to customer delivery requirements and even affecting long-term cooperative relationships. In short, current smart card order forecasting methods have poor accuracy and struggle to simultaneously balance the dual needs of production cost control and delivery efficiency assurance. Summary of the Invention

[0004] The purpose of this application is to address at least one of the aforementioned technical deficiencies, particularly the poor accuracy of existing smart card order prediction methods, which makes it difficult to simultaneously balance the dual requirements of production cost control and delivery efficiency assurance.

[0005] This application provides a smart card order prediction method, the method comprising: Identify the product card type corresponding to the smart card order initiated by the customer, and determine the predicted card issuance volume for the current month based on the actual card issuance data of the product card type within a preset historical time period; The level coefficient of the smart card order is determined based on the card issuance forecast, and the card issuance forecast is optimized using the level coefficient to obtain the optimized forecast. Obtain the historical production data and online inventory quantity of the product card, as well as the order demand quantity of the smart card order. Then, comprehensively calculate the smart card production quantity based on the historical production data, the online inventory quantity, the order demand quantity, the card issuance forecast quantity, and the optimized forecast quantity to obtain the order forecast quantity.

[0006] Optionally, determining the predicted card issuance volume for the current month based on the actual card issuance data of the product card type within a preset historical time period includes: Obtain the actual number of cards issued for the product card type in each month within a preset time period to form actual card issuance data; The actual card issuance volume for each month in the actual card issuance data is iteratively predicted according to the time sequence to obtain the predicted card issuance volume for the current month.

[0007] Optionally, determining the grade coefficient of the smart card order based on the predicted card issuance volume includes: If the preset number of cards issued exceeds the first preset threshold, then the level coefficient of the smart card order is determined to be the first coefficient; If the preset number of cards issued is lower than the first preset threshold but exceeds the preset second threshold, then the level coefficient of the smart card order is determined to be the second coefficient. If the preset number of cards issued is lower than the second preset threshold, then the level coefficient of the smart card order is determined to be the third coefficient; The first coefficient, the second coefficient, and the third coefficient increase sequentially.

[0008] Optionally, the step of optimizing the card issuance prediction quantity using the grade coefficient to obtain an optimized prediction quantity includes: Multiply the grade coefficient by the card issuance prediction amount to obtain the multiplication result; Determine the rounding base corresponding to the grade coefficient, and use the rounding base to round the multiplication result to obtain the optimized prediction amount.

[0009] Optionally, the step of comprehensively calculating the smart card production quantity based on the historical production data, the online inventory quantity, the order demand quantity, and the optimized forecast quantity to obtain the order forecast quantity includes: The defective consumption corresponding to the order demand quantity is calculated based on the product card, and the minimum order quantity of the product card is determined. The defective consumption, minimum order quantity, historical production data, online inventory quantity, order demand quantity, card issuance forecast quantity, and optimized forecast quantity are packaged into basic judgment data; The smart card order prediction model is invoked, and the basic judgment data is evaluated and calculated using the smart card order prediction model to obtain the order prediction quantity.

[0010] Optionally, the step of evaluating and calculating the basic judgment data using the smart card order prediction model to obtain the order prediction quantity includes: The smart card order prediction model is used to detect whether the online inventory quantity is greater than the sum of the order demand quantity, the card issuance prediction quantity, and the defective consumption quantity. If so, then the order forecast quantity for the product card is determined to be 0; If not, determine whether the product card was not produced during the historical production cycle; If the product is not in production, the order forecast quantity for the product card is determined to be 0 when the order demand quantity is not lower than the minimum order quantity; and the order forecast quantity for the product card is determined to be the difference between the minimum order quantity and the order demand quantity when the order demand quantity is lower than the minimum order quantity. If it is not unproduced, then when the order demand quantity is not less than three times the card issuance forecast quantity, it is determined whether the order demand quantity is lower than the minimum order quantity; If the order quantity is lower than the minimum order quantity, the order forecast quantity for the product card is determined to be the difference between the minimum order quantity and the order demand quantity. If the order quantity is not lower than the minimum order quantity, the order forecast quantity for the product card is determined to be 0. And, when the order demand quantity is less than three times the card issuance forecast quantity, determine whether the card issuance forecast quantity exceeds a preset minimum baseline; If the preset minimum baseline is exceeded, then when the sum of the order demand data and the optimized forecast quantity exceeds the minimum order quantity, the optimized forecast quantity is used as the order forecast quantity for the product card; and when the sum of the order demand data and the optimized forecast quantity does not exceed the minimum order quantity, the order forecast quantity for the product card is determined as the difference between the minimum order quantity and the order demand quantity. If the order quantity does not exceed the preset minimum baseline, then when the order demand quantity is not lower than the minimum order quantity, the order forecast quantity for the product card is confirmed to be 0; and when the order demand quantity is lower than the minimum order quantity, the order forecast quantity for the product card is confirmed to be the difference between the minimum order quantity and the order demand quantity.

[0011] Optionally, the method further includes: If the predicted order quantity is greater than 0, then a future predicted order corresponding to the predicted order quantity is generated, and the future predicted order is pushed to the approval channel, and the approval result returned by the approval channel is obtained; Based on the approval results and the smart card order, a smart card production order is generated and pushed to the production system so that the production system can produce smart cards.

[0012] This application also provides a smart card order prediction device, comprising: The card issuance volume prediction module is used to identify the product card type corresponding to the smart card order initiated by the customer, and determine the predicted card issuance volume for the current month based on the actual card issuance data of the product card type within a preset historical time period. The prediction quantity optimization module is used to determine the level coefficient of the smart card order based on the card issuance prediction quantity, and to optimize the card issuance prediction quantity using the level coefficient to obtain the optimized prediction quantity. The production volume determination module is used to obtain the historical production data and online inventory quantity of the product card, as well as the order demand quantity of the smart card order, and to comprehensively calculate the smart card production quantity based on the historical production data, the online inventory quantity, the order demand quantity, the card issuance forecast quantity, and the optimized forecast quantity to obtain the order forecast quantity.

[0013] This application also provides a storage medium storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of the smart card order prediction method as described in any of the above embodiments.

[0014] This application also provides a computer device, including: one or more processors, and memory; The memory stores computer-readable instructions, which, when executed by the one or more processors, perform the steps of the smart card order prediction method as described in any of the above embodiments.

[0015] As can be seen from the above technical solutions, the embodiments of this application have the following advantages: The smart card order forecasting method, apparatus, storage medium, and computer equipment provided in this application, upon receiving a smart card order initiated by a customer, can first identify the corresponding product card model for the smart card order. This allows for the retrieval of actual card issuance data for that product card model within a preset historical time period as data support, calculating the forecast issuance volume for the current month and avoiding biases from sales personnel's subjective judgment. Then, based on the forecast issuance volume, a level coefficient for the smart card order can be determined, and this level coefficient can be used to optimize and adjust the initial forecast issuance volume to adapt to the production characteristics of orders of different sizes, resulting in a more accurate optimized forecast volume. Finally, historical production data, current online inventory quantity, and customer order demand quantity for that product card model can be obtained and comprehensively calculated with the forecast issuance volume and optimized forecast volume to ultimately obtain an order forecast volume that conforms to actual production conditions. This fundamentally adapts to the characteristics of small-batch, multi-order transactions, reducing overall production and operating costs while ensuring timely delivery of customer orders. Attached Figure Description

[0016] 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, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 A flowchart illustrating a smart card order prediction method provided in an embodiment of this application; Figure 2 A flowchart illustrating the detection process of a smart card order prediction model provided in this application embodiment; Figure 3 This is a schematic diagram of the structure of a smart card order prediction device provided in an embodiment of this application; Figure 4 This is a schematic diagram of the internal structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0018] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] Currently, most mainstream production demand forecasting in the industry is done by sales personnel on the business side, combining their subjective judgment of market conditions with their past experience dealing with clients. A standardized and systematic forecasting mechanism has not yet been established. However, forecasting methods relying on manual experience are extremely unstable. If the forecast value is much higher than the actual demand, it results in a large backlog of customized cards, leading to substantial losses from obsolete inventory. Conversely, if the forecast value is lower than the actual order demand, it leads to insufficient raw material inventory, making it impossible to quickly respond to customer delivery requirements and even affecting long-term cooperative relationships. In short, current smart card order forecasting methods have poor accuracy and struggle to simultaneously balance the dual needs of production cost control and delivery efficiency assurance.

[0020] Based on this, this application proposes the following technical solution, as detailed below: In one embodiment, such as Figure 1 As shown, Figure 1 This is a flowchart illustrating a smart card order prediction method provided in an embodiment of this application; this application provides a smart card order prediction method, including: S110: Identify the product card type corresponding to the smart card order initiated by the customer, and determine the predicted card issuance volume for the current month based on the actual card issuance data of the product card type within a preset historical time period.

[0021] In this step, when a smart card order is received from a customer, the computer device can first identify the corresponding product card type of the smart card order, and retrieve the actual card issuance data of the product card type within a preset historical time period to determine the card issuance forecast for the current month. This allows the device to break away from the traditional forecasting model that relies on the subjective experience of sales personnel, and instead use real historical card issuance behavior as the data support.

[0022] The term "product card model" refers to smart card products of different specifications customized for different application scenarios. These different models vary significantly in card manufacturing processes, materials, and chip models. It should be noted that the product card models used in this application for card issuance volume prediction do not include new products, special processes, or limited-time promotional cards. They are only regular cards that have already been launched and have a continuous issuance record. These card models ensure the integrity of historical card issuance data, providing a reliable data foundation for predictive volume calculations.

[0023] Specifically, when a computer device receives a smart card order from a customer, it can first parse the product identifier in the smart card order, such as the product model and customization number, and use this to identify the product card type corresponding to the order. Subsequently, the computer device can use this product card type as the query object to retrieve the actual card issuance data corresponding to this product card type within a preset historical time period from the historical business database. Since this actual card issuance data can reflect the real product delivery situation in the market, the computer can use the current month as the target month and the actual card issuance data within the preset historical event period as the basic data to predict the card issuance volume corresponding to the current month, providing accurate and objective forecast data for subsequent production needs.

[0024] S120: Determine the level coefficient of smart card orders based on the card issuance forecast, and use the level coefficient to optimize the card issuance forecast to obtain the optimized forecast.

[0025] In this step, after the card issuance forecast is obtained through step S110, the computer equipment can determine the level coefficient of the smart card order based on the card issuance forecast, and use the level coefficient to optimize and adjust the card issuance forecast to adapt to the production characteristics of orders of different sizes, so as to obtain a more accurate optimized forecast.

[0026] Among them, the grade coefficient can characterize the different requirements of different order sizes for forecast accuracy and production scheduling. For example, for larger orders, the corresponding quantity fluctuations have a greater impact on the overall production plan. Therefore, a smaller grade coefficient is needed to appropriately compress the forecast size to reduce inventory backlog. On the other hand, for smaller batch orders, the tolerance for production quantity is lower. Once there is insufficient forecasting, it will directly affect the delivery time. Therefore, a larger grade coefficient is needed to appropriately increase the forecast size to reserve buffer space, while reducing the number of production times for such small batch orders.

[0027] Specifically, when optimizing the card issuance forecast, the computer equipment can first obtain the order level configuration information from the configuration management platform. This order level configuration information pre-establishes the correspondence between order levels and level coefficients. Therefore, through this order level configuration information, the computer equipment can determine the corresponding level coefficient based on the order level where the card issuance forecast belongs. This level coefficient can then be used to correct and calculate the card issuance forecast, resulting in an optimized forecast that better matches the production demand characteristics of smart card orders of different sizes, effectively reducing inventory backlog or product shortages.

[0028] S130: Obtain historical production data and online inventory quantity of product card models, as well as the order demand quantity of smart card orders, and comprehensively calculate the smart card production quantity based on historical production data, online inventory quantity, order demand quantity, card issuance forecast quantity, and optimized forecast quantity to obtain the order forecast quantity.

[0029] In this step, after obtaining the optimized forecast quantity through step S120, the computer equipment can also obtain the historical production data and current online inventory quantity of the product card model, and determine the demand quantity of smart card orders. These parameters are then combined with the card issuance forecast quantity and the optimized forecast quantity to calculate the order forecast quantity that meets the potential demand in the current cycle. This can fundamentally adapt to the characteristics of small-batch, multi-order orders, reduce the overall production and operation costs, and ensure the delivery time of customer orders.

[0030] Historical production data refers to real data generated during the production process of a product card model, including the actual total production volume, production yield, and average defect consumption rate within the most recent production period. This data reflects the material consumption characteristics of the product card model during actual processing. Online inventory refers to the quantity of finished products that can be directly used for order fulfillment; this includes existing inventory and production in transit. Furthermore, order forecast refers to the number of smart cards that need to be produced in the current production cycle to meet potential future order demand.

[0031] Specifically, the computer equipment can comprehensively calculate all production-related parameters, including historical production data, online inventory levels, order demand, card issuance forecasts, and optimized forecasts, making the final order forecasts more closely reflect the company's actual production conditions. Through comprehensive calculation of multi-dimensional production influencing factors, this application can effectively balance the contradiction between production start-up frequency and inventory holding costs. It avoids both excessive forecasting leading to a large backlog of customized cards and insufficient raw material reserves resulting in frequent production starts, thus achieving a two-way balance between production cost control and online inventory.

[0032] For example, when the online inventory can directly meet the demand for smart card orders, there is no need to arrange additional production, thus avoiding unnecessary start-up costs and raw material losses. When the online inventory is low, the amount of production that needs to be supplemented can be calculated by combining historical production data, order demand, and forecast data, so as to reserve a reasonable buffer space while avoiding overproduction that occupies inventory.

[0033] In the above embodiments, upon receiving a smart card order initiated by a customer, the corresponding product card model can be identified first. This allows for the retrieval of actual card issuance data for that product card model within a preset historical time period as data support, enabling the calculation of the current month's issuance forecast and avoiding biases from sales personnel's subjective judgment. Then, the order's grade coefficient can be determined based on this issuance forecast, and the initial issuance forecast can be optimized using this coefficient to adapt to the production characteristics of orders of different sizes, resulting in a more accurate optimized forecast. Finally, historical production data, current online inventory, and customer order demand for that product card model can be obtained and comprehensively calculated with the issuance forecast and optimized forecast to ultimately obtain an order forecast that meets future potential demand. This fundamentally adapts to the characteristics of small-batch, multi-order transactions, reducing overall production and operating costs while ensuring timely delivery of customer orders.

[0034] In one embodiment, the process of determining the predicted card issuance volume for the current month based on the actual card issuance data of the product card type within a preset historical time period in step S110 may include: S111: Obtain the actual number of product cards issued each month within a preset time period to generate actual card issuance data.

[0035] S112: Iteratively predict the actual card issuance volume for each month in the actual card issuance data according to the time sequence to obtain the predicted card issuance volume for the current month.

[0036] In this embodiment, when predicting the number of cards issued, the computer device can first obtain the actual number of cards issued for each month within a preset time period to form actual card issuance data. Then, iteratively predict the actual number of cards issued for each month in the actual card issuance data according to the time sequence to obtain the predicted number of cards issued for the current month.

[0037] Specifically, the computer equipment can retrieve the actual card issuance volume for each month within a preset time period from the historical business database. The actual card issuance volumes for each month can be arranged chronologically to form actual card issuance data, reflecting changes in market demand for the target product card over a historical period. Subsequently, the computer equipment can sort the actual card issuance data by time and perform iterative predictions month by month. That is, the actual card issuance volume of the previous month and the already predicted volume are used as the data basis for the prediction of the next month, gradually updating the prediction status to obtain the prediction results for each month. When the iterative prediction reaches the current month, the predicted card issuance volume for the current month can be determined. Therefore, the card issuance volume prediction process of this application can continuously inherit historical trends and gradually reflect the dynamic pattern of card issuance demand evolving over time, thereby improving the accuracy of the predicted card issuance volume for the current month.

[0038] For example, the preset time period used in this application can be the most recent 6 months. If the continuous card issuance record for the product card exceeds 6 months, the actual card issuance data within the most recent 6 months will be used; if it does not exceed 6 months, the actual card issuance data for all card issuance months will be used. In addition, the predicted volume for each month is 90% of the actual card issuance volume of the previous month and 10% of the predicted volume of the previous month. The predicted volume for the first month can be set as the actual card issuance volume of the first month.

[0039] In one embodiment, the process of determining the grade coefficient of a smart card order based on the predicted card issuance volume in step S120 may include: S121: If the number of cards issued exceeds the first preset threshold, then the level coefficient of the smart card order is determined to be the first coefficient.

[0040] S122: If the preset card issuance quantity is lower than the first preset threshold but exceeds the preset second threshold, then the level coefficient of the smart card order is determined to be the second coefficient; S123: If the preset number of cards issued is lower than the second preset threshold, then the level coefficient of the smart card order is determined to be the third coefficient.

[0041] In this embodiment, smart card orders can be divided into three level coefficients. When the preset card issuance quantity exceeds a first preset threshold, the computer device can determine the smart card order's level coefficient as the first coefficient; when the preset card issuance quantity is lower than the first preset threshold but exceeds a preset second threshold, the computer device can determine the smart card order's level coefficient as the second coefficient; when the preset card issuance quantity is lower than the second preset threshold, the computer device can determine the smart card order's level coefficient as the third coefficient. It should be noted that the first coefficient, second coefficient, and third coefficient increase sequentially.

[0042] Understandably, in order to employ different forecasting and adjustment strategies for smart card orders of different sizes, computer equipment can pre-establish a correspondence between order levels and level coefficients, with each order level corresponding to a forecast range. For example, this application can divide the card issuance forecast into three level ranges using a first preset threshold and a second preset threshold, corresponding to the first coefficient, the second coefficient, and the third coefficient, respectively.

[0043] Specifically, for large orders exceeding the first preset threshold, such as orders with a forecast of more than 5,000 cards, the sheer size and high demand base mean that even a small forecast deviation can lead to a large backlog of inventory. Therefore, a smaller first coefficient is used to appropriately compress the forecast size and control the risk of obsolete inventory for large-scale orders. For medium-sized orders with a forecast size between the first and second preset thresholds, such as orders with a forecast size of more than 500 cards but less than 5,000 cards, the risk level caused by demand fluctuations is also at a moderate level. Therefore, a moderate second coefficient is used to match the production needs of these orders. For small-batch orders below the second preset threshold, such as orders with a forecast size of less than 500 cards, since the demand for these orders is small, the inventory cost caused by forecast deviations is far lower than the loss from delivery delays. Therefore, a larger third coefficient is used to appropriately increase the forecast size, reserving buffer space to avoid affecting order delivery due to insufficient forecasting. At the same time, it can also enable the centralized production of similar small-batch orders, reduce unnecessary production starts, and balance production and inventory costs.

[0044] In one embodiment, the process of optimizing the card issuance prediction quantity using a grade coefficient in step S120 to obtain the optimized prediction quantity may include: S124: Multiply the grade coefficient by the card issuance prediction amount to obtain the multiplication result.

[0045] S125: Determine the rounding base corresponding to the grade coefficient, and use the rounding base to round the multiplication result to obtain the optimized prediction.

[0046] In this embodiment, when optimizing the prediction amount, the computer device can first multiply the grade coefficient with the card issuance prediction amount to obtain the multiplication result, then determine the rounding base corresponding to the grade coefficient, and use the rounding base to round the multiplication result to obtain the optimized prediction amount.

[0047] Specifically, different order sizes correspond to different grade coefficients, and the appropriate rounding bases also differ. Generally, the smaller the order size, the smaller the corresponding rounding base value. After calculating the product of the grade coefficient and the card issuance forecast, the computer equipment can round the result up according to the corresponding grade's rounding base to obtain the final optimized forecast. This allows the optimized forecast to be adapted to the production scheduling requirements of different order grades, avoiding material waste caused by non-full batch production.

[0048] For example, for small-batch orders corresponding to the third coefficient, the grade coefficient can be 3, and the rounding base can be set to the fiftieth place; for medium-sized orders corresponding to the second coefficient, the grade coefficient can be 2, and the rounding base can be set to the hundreds place; for large-scale orders corresponding to the first coefficient, the grade coefficient can be 1, and the rounding base can be set to the thousands place.

[0049] In one embodiment, the process of comprehensively calculating the smart card production quantity based on historical production data, online inventory quantity, order demand quantity, and optimized forecast quantity in step S130 to obtain the order forecast quantity may include: S131: Calculate the defective consumption corresponding to the order demand quantity based on the product card, and determine the minimum order quantity for the product card.

[0050] S132: Package defective consumption, minimum order quantity, historical production data, online inventory quantity, order demand quantity, card issuance forecast quantity, and optimized forecast quantity into basic judgment data; S133: Call the smart card order prediction model and use the smart card order prediction model to evaluate and calculate the basic judgment data to obtain the order prediction quantity.

[0051] In this embodiment, before generating the forecast quantity assessment, the computer device can first calculate the defective consumption corresponding to the order demand quantity based on the product card type, and determine the minimum order quantity for the product card type. Then, the defective consumption, minimum order quantity, historical production data, online inventory quantity, order demand quantity, card issuance forecast quantity, and optimized forecast quantity are packaged into basic judgment data. Next, the computer device can call the smart card order forecast model and use the smart card order forecast model to evaluate and calculate the basic judgment data to obtain the order forecast quantity that can meet future potential demand.

[0052] It is understandable that during the smart card production process, due to factors such as card customization technology and processing precision, a certain percentage of defective products will inevitably be generated in the actual production process. Therefore, this application needs to pre-calculate the amount of defective products required to meet order demands and include this amount in the production assessment scope to avoid insufficient final qualified product quantity due to defective products occupying quotas. At the same time, due to limitations in production start-up costs and material cutting specifications, each product card model has its own minimum order quantity, which also needs to be included as a basic constraint in the assessment data.

[0053] Specifically, after obtaining the defective consumption and minimum order quantity (MOQ), the computer equipment can uniformly encapsulate the defective consumption, MOQ, historical production data, online inventory, order demand, card issuance forecast, and optimized forecast to form basic judgment data. Simultaneously, it calls a pre-trained smart card order prediction model and inputs the basic judgment data into the model for comprehensive calculation. This smart card order prediction model can comprehensively analyze the correlation between multiple factors such as market demand forecasts, inventory resources, and production capacity constraints, fuse and calculate various input parameters, and output an order forecast that conforms to the current production and operation conditions.

[0054] In one embodiment, such as Figure 2 As shown, Figure 2 A flowchart illustrating the detection process of a smart card order prediction model provided in this application embodiment; Figure 2 In step S133, the process of evaluating and calculating the basic judgment data using the smart card order prediction model to obtain the order prediction quantity may include: S1331: Detect whether the online inventory quantity is greater than the sum of the order demand quantity, the card issuance forecast quantity, and the defective consumption quantity through the smart card order prediction model.

[0055] S1332: If so, then determine that the order forecast quantity for the product card is 0.

[0056] S1333: If not, determine whether the product card was not produced within the historical production cycle.

[0057] S1334: If the product is not in production, the order forecast quantity for the product card is set to 0 when the order demand quantity is not less than the minimum order quantity; and the order forecast quantity for the product card is set to the difference between the minimum order quantity and the order demand quantity when the order demand quantity is less than the minimum order quantity.

[0058] S1335: If not in production, determine whether the order demand quantity is lower than the minimum order quantity if the order demand quantity is not less than three times the card issuance forecast quantity.

[0059] S1336: If the quantity is lower than the minimum order quantity, the order forecast quantity for the product card is determined as the difference between the minimum order quantity and the order demand quantity.

[0060] S1337: If the minimum order quantity is not lower than the minimum order quantity, then the order forecast quantity for the product card is set to 0.

[0061] S1338: When the order demand quantity is less than three times the card issuance forecast quantity, determine whether the card issuance forecast quantity exceeds the preset minimum baseline; S1339: If the preset minimum baseline is exceeded, the optimized forecast quantity will be used as the order forecast quantity for the product card when the sum of the order demand data and the optimized forecast quantity exceeds the minimum order quantity; and when the sum of the order demand data and the optimized forecast quantity does not exceed the minimum order quantity, the order forecast quantity for the product card will be determined as the difference between the minimum order quantity and the order demand quantity.

[0062] S1340: If the minimum baseline is not exceeded, the order forecast quantity for the product card is confirmed to be 0 when the order demand quantity is not lower than the minimum order quantity; and the order forecast quantity for the product card is confirmed to be the difference between the minimum order quantity and the order demand quantity when the order demand quantity is lower than the minimum order quantity.

[0063] In this embodiment, the smart card order prediction model can match various production constraints, demand characteristics and inventory resources layer by layer through hierarchical condition judgment, and gradually derive the order prediction quantity that meets the potential future demand. Therefore, it can avoid frequent production starts, reduce unnecessary production costs and material losses, and ensure that there is a sufficient supply of finished products for order demand, avoiding delays in delivery due to insufficient capacity reservation.

[0064] Specifically, the smart card order forecasting model can first detect whether the current online inventory quantity is greater than the sum of the order demand, card issuance forecast, and defective consumption. When the online inventory quantity is greater than the sum of the order demand, card issuance forecast, and defective consumption, it means that the existing inventory can not only meet current customer orders but also cover future potential demand and production losses. Therefore, there is no need to arrange production again, and the computer equipment can determine that the order forecast quantity for the product card is 0, so as to prioritize the consumption of inventory resources and avoid duplicate production that would cause inventory backlog.

[0065] If the online inventory is insufficient to cover the sum of order demand, card issuance forecast, and defective consumption, the smart card order forecasting model can further determine whether the target product card has been in a non-production state during the historical production cycle; the historical production cycle in this application can be the statistical period of the most recent 30 days. When the target product card has not been produced during the historical production cycle, it indicates that the product card is a low-frequency production product or a product that has not been put into production for a long time. At this time, the computer equipment can further determine whether the order demand has reached the minimum order quantity. When the order demand is not lower than the minimum order quantity, it indicates that the smart card orders can meet the production batch requirements, so there is no need to arrange additional production for forecast demand, and the computer equipment can determine that the order forecast quantity of the product card is 0; when the order demand is lower than the minimum order quantity, in order to avoid excessively high unit manufacturing costs due to insufficient production quantity, the computer equipment can determine that the order forecast quantity of the product card is the difference between the minimum order quantity and the order demand quantity, so that the final production quantity reaches the minimum economic production batch.

[0066] When the target product card has a production record in the historical production cycle, the smart card production forecasting model can further determine whether the order demand quantity reaches three times the card issuance forecast. If the order demand quantity is not less than three times the card issuance forecast, it indicates that current customer orders can basically cover the customer's future needs, such as usage within the next three months. To reduce the risk of obsolete inventory, this production demand mainly comes from current orders, rather than future market forecast demand. Therefore, the computer equipment can continue to determine whether the order demand quantity is lower than the minimum order quantity. If the order demand quantity is lower than the minimum order quantity, the computer equipment can determine that the order forecast quantity for the product card is the difference between the minimum order quantity and the order demand quantity, ensuring that the production quantity meets the minimum production batch requirement. If the order demand quantity is not lower than the minimum order quantity, it indicates that the current order itself has reached the economic production scale, therefore no additional forecast production quantity is needed, and the computer equipment can determine that the order forecast quantity for the product card is 0.

[0067] When the order demand is less than three times the card issuance forecast, it indicates that the current order size is relatively normal, and future market demand still has high reference value. Therefore, the smart card production forecast model can further determine whether the card issuance forecast exceeds the preset minimum baseline. This preset minimum baseline represents the minimum forecast standard that the company believes has sustainable market demand. When the card issuance forecast exceeds the preset minimum baseline, it indicates that the product card model still has sustainable demand in the future. Therefore, the computer equipment can further determine whether the sum of the order demand and the optimized forecast exceeds the minimum order quantity. When the sum of the order demand and the optimized forecast exceeds the minimum order quantity, it indicates that the current order and forecast demand combined have reached the economic production scale. Therefore, the computer equipment can directly determine the optimized forecast as the order forecast quantity for the product card model, enabling current production to cover future market demand in advance. When the sum of the order demand and the optimized forecast does not exceed the minimum order quantity, to ensure production economy, the computer equipment can determine the order forecast quantity for the product card model as the difference between the minimum order quantity and the order demand, so that the final production quantity meets the minimum order quantity requirement.

[0068] When the predicted card issuance quantity does not exceed the preset minimum baseline, it indicates that future market demand is low, and it is not suitable to produce in advance based on the forecast results. Therefore, the computer equipment can re-evaluate whether the order demand quantity has reached the minimum order quantity. When the order demand quantity is not lower than the minimum order quantity, it indicates that the current order has met the conditions for independent production, and there is no need to increase the predicted production quantity. Therefore, the computer equipment can determine that the order forecast quantity for the product card is 0. When the order demand quantity is lower than the minimum order quantity, the computer equipment can determine that the order forecast quantity for the product card is the difference between the minimum order quantity and the order demand quantity to ensure that the production batch meets the minimum production requirements.

[0069] Understandably, by using the hierarchical condition determination of the smart card order prediction model, this application can make the order prediction results more in line with the production characteristics of the smart card industry, which are characterized by small batches, multiple batches, and rapid changes in demand. This can ensure timely delivery of customer orders, reduce inventory backlog, reduce the cost of frequent equipment startup and production switching, and improve the overall production and operation efficiency of enterprises.

[0070] In one embodiment, the method may further include: S140: If the order forecast quantity is greater than 0, generate a future forecast order corresponding to the order forecast quantity, push the future forecast order to the approval channel, and obtain the approval result returned by the approval channel.

[0071] S150: Generate a smart card production order based on the approval results and smart card orders, and push the smart card production order to the production system so that the production system can produce smart cards.

[0072] In this embodiment, when the order forecast quantity is greater than 0, the computer device can generate a future forecast order corresponding to the order forecast quantity, push the future forecast order to the approval channel, and obtain the approval result returned by the approval channel. Thus, a smart card production order can be generated based on the approval result and the smart card order, and the smart card production order can be pushed to the production system so that the production system can carry out smart card production.

[0073] Specifically, future forecast orders are additional production plans generated based on projected future market demand, rather than fixed orders directly initiated by customers. Therefore, they require manual approval from relevant departments such as production and planning to avoid conflicts between projected and actual production plans. Once approved, the computer system merges the customer-initiated smart card order with the approved future forecast order to generate the final smart card production order. This order is then pushed to the enterprise's production system, which coordinates the entire process of production scheduling, processing, testing, and delivery. If the approval is rejected, the smart card production order can be cancelled or modified based on the approval result, and the approval process can be re-initiated.

[0074] Furthermore, when the order forecast quantity is 0, if the online inventory quantity is greater than the sum of the order demand quantity, the card issuance forecast quantity, and the defective consumption quantity, the computer equipment can directly obtain the corresponding product quantity from the inventory and deliver it to the customer; otherwise, the smart card order initiated by the customer will be pushed to the production system for production arrangement, without the need to increase the forecast production quantity.

[0075] The smart card order prediction device provided in the embodiments of this application is described below. The smart card order prediction device described below can be referred to in correspondence with the smart card order prediction method described above.

[0076] In one embodiment, such as Figure 3 As shown, Figure 3 This application provides a schematic diagram of a smart card order prediction device according to an embodiment of the present application. The present application also provides a smart card order prediction device, including a card issuance volume prediction module 210, a prediction volume optimization module 220, and a production volume determination module 230, specifically comprising the following: The card issuance prediction module 210 is used to identify the product card type corresponding to the smart card order initiated by the customer, and to determine the predicted card issuance volume for the current month based on the actual card issuance data of the product card type within a preset historical time period.

[0077] The prediction quantity optimization module 220 is used to determine the level coefficient of smart card orders based on the card issuance prediction quantity, and to optimize the card issuance prediction quantity using the level coefficient to obtain the optimized prediction quantity.

[0078] The production volume determination module 230 is used to obtain historical production data and online inventory of product card models, as well as the order demand quantity of smart card orders. It also performs a comprehensive calculation on the smart card production quantity based on historical production data, online inventory, order demand quantity, card issuance forecast quantity, and optimized forecast quantity to obtain the order forecast quantity.

[0079] In the above embodiments, upon receiving a smart card order initiated by a customer, the corresponding product card model can be identified first. This allows for the retrieval of actual card issuance data for that product card model within a preset historical time period as data support, enabling the calculation of the current month's issuance forecast and avoiding biases from sales personnel's subjective judgment. Then, the order's grade coefficient can be determined based on this issuance forecast, and the initial issuance forecast can be optimized using this coefficient to adapt to the production characteristics of orders of different sizes, resulting in a more accurate optimized forecast. Finally, historical production data, current online inventory, and customer order demand for that product card model can be obtained and comprehensively calculated with the issuance forecast and optimized forecast to ultimately obtain an order forecast that meets future potential demand. This fundamentally adapts to the characteristics of small-batch, multi-order transactions, reducing overall production and operating costs while ensuring timely delivery of customer orders.

[0080] In one embodiment, the card issuance volume prediction module 210 may include: The data acquisition submodule is used to obtain the actual number of product cards issued each month within a preset time period, forming actual card issuance data.

[0081] The iterative prediction submodule is used to iteratively predict the actual card issuance volume for each month in the actual card issuance data according to the time sequence, so as to obtain the predicted card issuance volume for the current month.

[0082] In one embodiment, the prediction optimization module 220 may include: The first threshold judgment submodule is used to determine the level coefficient of the smart card order as the first coefficient if the preset number of cards issued exceeds the first preset threshold.

[0083] The second threshold judgment submodule is used to determine the level coefficient of the smart card order as the second coefficient if the preset number of cards issued is lower than the first preset threshold but exceeds the preset second threshold. The third threshold judgment submodule is used to determine the level coefficient of the smart card order as the third coefficient if the preset number of cards issued is lower than the second preset threshold.

[0084] The first, second, and third coefficients increase sequentially.

[0085] In one embodiment, the prediction optimization module 220 may further include: The coefficient multiplication submodule is used to multiply the grade coefficient by the card issuance prediction amount to obtain the multiplication result.

[0086] The result rounding submodule is used to determine the rounding base corresponding to the grade coefficient, and to round the multiplication result using the rounding base to obtain the optimized prediction.

[0087] In one embodiment, the production quantity determination module 230 may include: The parameter calculation submodule is used to calculate the defective consumption corresponding to the order demand quantity based on the product card type, and to determine the minimum order quantity for the product card type.

[0088] The parameter packaging submodule is used to package defective consumption, minimum order quantity, historical production data, online inventory quantity, order demand quantity, card issuance forecast quantity, and optimized forecast quantity into basic judgment data; The model prediction submodule is used to call the smart card order prediction model and use the smart card order prediction model to evaluate and calculate the basic judgment data to obtain the order prediction volume.

[0089] In one embodiment, the model prediction submodule may include: The first parameter evaluation unit is used to detect whether the online inventory quantity is greater than the sum of the order demand quantity, the card issuance forecast quantity, and the bad consumption quantity through the smart card order prediction model.

[0090] The first result determination unit is used to determine the order forecast quantity of the product card as 0 if the result is true.

[0091] The second parameter evaluation unit is used to determine whether the product card was not produced during the historical production cycle if no.

[0092] The second result determination unit is used to determine the order forecast quantity of the product card as 0 when the order demand quantity is not lower than the minimum order quantity if the product card is not produced; and to determine the order forecast quantity of the product card as the difference between the minimum order quantity and the order demand quantity when the order demand quantity is lower than the minimum order quantity.

[0093] The third parameter evaluation unit is used to determine whether the order demand quantity is lower than the minimum order quantity if the order demand quantity is not less than three times the card issuance forecast quantity, provided that the order demand quantity is not less than three times the card issuance forecast quantity.

[0094] The third result determination unit is used to determine the order forecast quantity for the product card as the difference between the minimum order quantity and the order demand quantity if it is lower than the minimum order quantity.

[0095] The fourth result determination unit is used to determine the order forecast quantity of the product card as 0 if it is not lower than the minimum order quantity.

[0096] The fourth parameter evaluation unit is used to determine whether the card issuance forecast exceeds the preset minimum baseline when the order demand quantity is less than three times the card issuance forecast quantity. The fifth result determination unit is used to determine the order forecast quantity of the product card as the order forecast quantity when the sum of the order demand data and the optimized forecast quantity exceeds the minimum order quantity if the preset minimum baseline is exceeded; and to determine the order forecast quantity of the product card as the difference between the minimum order quantity and the order demand quantity when the sum of the order demand data and the optimized forecast quantity does not exceed the minimum order quantity.

[0097] The sixth result determination unit is used to confirm that the order forecast quantity for the product card is 0 if the order demand quantity is not lower than the minimum order quantity when the preset minimum baseline is not exceeded; and to confirm that the order forecast quantity for the product card is the difference between the minimum order quantity and the order demand quantity when the order demand quantity is lower than the minimum order quantity.

[0098] In one embodiment, the apparatus may further include: The order approval module is used to generate future predicted orders corresponding to the order predicted quantity if the order predicted quantity is greater than 0, push the future predicted orders to the approval channel, and obtain the approval results returned by the approval channel.

[0099] The order production module is used to generate smart card production orders based on the approval results and the smart card orders, and push the smart card production orders to the production system so that the production system can produce smart cards.

[0100] In one embodiment, this application also provides a storage medium storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of the smart card order prediction method as described in any of the above embodiments.

[0101] In one embodiment, this application also provides a computer device storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of the smart card order prediction method as described in any of the above embodiments.

[0102] Indicatively, such as Figure 4 As shown, Figure 4 This is a schematic diagram of the internal structure of a computer device 300 provided in an embodiment of this application. The computer device 300 can be provided as a server. (Refer to...) Figure 4 The computer device 300 includes a processing component 302, which further includes one or more processors, and memory resources represented by memory 301 for storing instructions, such as application programs, that can be executed by the processing component 302. The application programs stored in memory 301 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processing component 302 is configured to execute instructions to perform the smart card order prediction method of any of the above embodiments.

[0103] The computer device 300 may also include a power supply component 303 configured to perform power management of the computer device 300, a wired or wireless network interface 304 configured to connect the computer device 300 to a network, and an input / output (I / O) interface 305. The computer device 300 may operate on an operating system stored in memory 301, such as Windows Server™, Mac OS X™, Unix™, Linux™, Free BSD™, or similar.

[0104] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0105] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0106] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can be referred to each other.

[0107] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A smart card order prediction method, characterized in that, The method includes: Identify the product card type corresponding to the smart card order initiated by the customer, and determine the predicted card issuance volume for the current month based on the actual card issuance data of the product card type within a preset historical time period; The level coefficient of the smart card order is determined based on the card issuance forecast, and the card issuance forecast is optimized using the level coefficient to obtain the optimized forecast. Obtain the historical production data and online inventory quantity of the product card, as well as the order demand quantity of the smart card order. Then, comprehensively calculate the smart card production quantity based on the historical production data, the online inventory quantity, the order demand quantity, the card issuance forecast quantity, and the optimized forecast quantity to obtain the order forecast quantity.

2. The smart card order prediction method according to claim 1, characterized in that, The step of determining the predicted card issuance volume for the current month based on the actual card issuance data of the product card type within a preset historical time period includes: Obtain the actual number of cards issued for the product card type in each month within a preset time period to form actual card issuance data; The actual card issuance volume for each month in the actual card issuance data is iteratively predicted according to the time sequence to obtain the predicted card issuance volume for the current month.

3. The smart card order prediction method according to claim 1, characterized in that, The step of determining the grade coefficient of the smart card order based on the predicted card issuance volume includes: If the preset number of cards issued exceeds the first preset threshold, then the level coefficient of the smart card order is determined to be the first coefficient; If the preset number of cards issued is lower than the first preset threshold but exceeds the preset second threshold, then the level coefficient of the smart card order is determined to be the second coefficient. If the preset number of cards issued is lower than the second preset threshold, then the level coefficient of the smart card order is determined to be the third coefficient; The first coefficient, the second coefficient, and the third coefficient increase sequentially.

4. The smart card order prediction method according to claim 1, characterized in that, The step of optimizing the card issuance prediction quantity using the grade coefficient to obtain the optimized prediction quantity includes: Multiply the grade coefficient by the card issuance prediction amount to obtain the multiplication result; Determine the rounding base corresponding to the grade coefficient, and use the rounding base to round the multiplication result to obtain the optimized prediction amount.

5. The smart card order prediction method according to claim 1, characterized in that, The step of comprehensively calculating the smart card production quantity based on the historical production data, the online inventory quantity, the order demand quantity, and the optimized forecast quantity to obtain the order forecast quantity includes: The defective consumption corresponding to the order demand quantity is calculated based on the product card, and the minimum order quantity of the product card is determined. The defective consumption, minimum order quantity, historical production data, online inventory quantity, order demand quantity, card issuance forecast quantity, and optimized forecast quantity are packaged into basic judgment data; The smart card order prediction model is invoked, and the basic judgment data is evaluated and calculated using the smart card order prediction model to obtain the order prediction quantity.

6. The smart card order prediction method according to claim 5, characterized in that, The step of evaluating and calculating the basic judgment data using the smart card order prediction model to obtain the order prediction quantity includes: The smart card order prediction model is used to detect whether the online inventory quantity is greater than the sum of the order demand quantity, the card issuance prediction quantity, and the defective consumption quantity. If so, then the order forecast quantity for the product card is determined to be 0; If not, determine whether the product card was not produced during the historical production cycle; If the product is not in production, the order forecast quantity for the product card is determined to be 0 when the order demand quantity is not lower than the minimum order quantity; and the order forecast quantity for the product card is determined to be the difference between the minimum order quantity and the order demand quantity when the order demand quantity is lower than the minimum order quantity. If it is not unproduced, then when the order demand quantity is not less than three times the card issuance forecast quantity, it is determined whether the order demand quantity is lower than the minimum order quantity; If the order quantity is lower than the minimum order quantity, the order forecast quantity for the product card is determined to be the difference between the minimum order quantity and the order demand quantity. If the order quantity is not lower than the minimum order quantity, the order forecast quantity for the product card is determined to be 0. And, when the order demand quantity is less than three times the card issuance forecast quantity, determine whether the card issuance forecast quantity exceeds a preset minimum baseline; If the preset minimum baseline is exceeded, then when the sum of the order demand data and the optimized forecast quantity exceeds the minimum order quantity, the optimized forecast quantity will be used as the order forecast quantity for the product card. And, when the sum of the order demand data and the optimized forecast quantity does not exceed the minimum order quantity, the order forecast quantity for the product card is determined to be the difference between the minimum order quantity and the order demand quantity; If the order quantity does not exceed the preset minimum baseline, then when the order demand quantity is not lower than the minimum order quantity, the order forecast quantity for the product card is confirmed to be 0; and when the order demand quantity is lower than the minimum order quantity, the order forecast quantity for the product card is confirmed to be the difference between the minimum order quantity and the order demand quantity.

7. The smart card order prediction method according to claim 1, characterized in that, The method further includes: If the predicted order quantity is greater than 0, then a future predicted order corresponding to the predicted order quantity is generated, and the future predicted order is pushed to the approval channel, and the approval result returned by the approval channel is obtained; Based on the approval results and the smart card order, a smart card production order is generated and pushed to the production system so that the production system can produce smart cards.

8. A smart card order prediction device, characterized in that, include: The card issuance volume prediction module is used to identify the product card type corresponding to the smart card order initiated by the customer, and determine the predicted card issuance volume for the current month based on the actual card issuance data of the product card type within a preset historical time period. The prediction quantity optimization module is used to determine the level coefficient of the smart card order based on the card issuance prediction quantity, and to optimize the card issuance prediction quantity using the level coefficient to obtain the optimized prediction quantity. The production volume determination module is used to obtain the historical production data and online inventory quantity of the product card, as well as the order demand quantity of the smart card order, and to comprehensively calculate the smart card production quantity based on the historical production data, the online inventory quantity, the order demand quantity, the card issuance forecast quantity, and the optimized forecast quantity to obtain the order forecast quantity.

9. A storage medium, characterized in that: The storage medium stores computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of the smart card order prediction method as described in any one of claims 1 to 7.

10. A computer device, characterized in that, include: One or more processors, and memory; The memory stores computer-readable instructions that, when executed by the one or more processors, perform the steps of the smart card order prediction method as described in any one of claims 1 to 7.

Images