A material uniformity early warning method and device, a storage medium and a terminal

Abstract

The application discloses a kind of material set early warning method, device, storage medium and terminal, method includes: determining current early warning level, obtains the product demand information to be produced under this early warning level;Load the material set early warning model pre-trained for this early warning level;The product demand information to be produced is input into the model, and the actual inventory of each material corresponding to the early warning level and the predicted usage of each material are output;According to actual inventory and the predicted usage of each material, judge whether the product to be produced satisfies set, and the product and its corresponding semi-finished product not set are early warned for not satisfying set.Due to the material set early warning model of each early warning level under five early warning levels is trained in the present application, so when obtaining current early warning level and product demand information, it can be automatically judged whether the product to be produced satisfies set, and the product and its corresponding semi-finished product not set are early warned for not satisfying set, so as to improve production efficiency.

Description

Technical Field

[0001] This invention relates to the field of machine learning technology, and in particular to a material availability early warning method, device, storage medium and terminal. Background Technology

[0002] Material availability refers to the completeness and usability of all materials required to complete the product needed by the customer. In industrial manufacturing, due to the numerous material suppliers and the vast quantity and variety of assembly materials, the untimely transmission of material availability information during product assembly often leads to production line stoppages due to material shortages, making the determination of material availability extremely difficult. Inability to obtain timely material availability directly impacts the start-up time of each stage of product assembly and the overall assembly cycle. If material insufficiency is only discovered when an order is about to go live, it directly results in significant production line downtime losses, affects product delivery dates, and ultimately impacts the product's ability to respond to the market.

[0003] In the current technology, the material kitting process, especially for small workpieces, is inefficient due to low manual operation. Once an error occurs, it is difficult to inspect and determine whether the kit is fully prepared and whether the specifications are appropriate. Errors in material kitting are difficult to detect, thus reducing production efficiency. Summary of the Invention

[0004] This application provides a material availability early warning method, apparatus, storage medium, and terminal. To provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not intended as a general commentary, nor is it intended to identify key / important components or describe the scope of protection of these embodiments. Its sole purpose is to present some concepts in a simple form as a prelude to the detailed description that follows.

[0005] In a first aspect, embodiments of this application provide a material availability early warning method, the method comprising:

[0006] Determine the current warning level and obtain the product demand information under the current warning level;

[0007] Load the material completeness early warning model pre-trained for the current warning level;

[0008] Input the product demand information to be produced into the material availability early warning model, and output the forecast information of each material corresponding to the current early warning level; the forecast information includes the actual inventory of each material and the expected usage of each material.

[0009] Based on the actual inventory of each material and the expected usage of each material, determine whether the products to be produced meet the requirements for completeness, and issue early warnings for products that do not meet the requirements and their corresponding incomplete semi-finished products.

[0010] Optionally, determine the current warning level, including:

[0011] Determine the delivery date for the products to be manufactured;

[0012] If the time difference between the current date and the product delivery date is greater than or equal to 12 months, a Level 1 alert is established to generate a product production plan based on customer demand variables, and the alert level of Level 1 is set as the current alert level; or,

[0013] When the time difference between the current date and the delivery date is greater than 6 months but less than 12 months, a secondary warning is established to generate inventory planning variables based on rolling planning variables, and the warning level of the secondary warning is set as the current warning level. Here, the rolling planning variable is the rolling inventory quantity within a continuous preset time period; or...

[0014] When the time difference between the current date and the delivery date is greater than 3 months but less than 6 months, a Level 3 alert is established to generate assembly plan variables based on shipping plan variables, and the alert level of the Level 3 alert is set as the current alert level. Here, the assembly plan variable is the product assembly plan inventory level determined based on historical product assembly data; or...

[0015] When the time difference between the current date and the delivery date is greater than 1 month but less than 3 months, a Level 4 early warning system is established to create production planning variables based on customer secondary expedited delivery requests, and the warning level under Level 4 is determined as the current warning level; or...

[0016] When the time difference between the current date and the delivery date is greater than 1 day but less than 1 month, a Level 5 warning is determined for the expedited production variable, and the warning level under the Level 5 warning is determined as the current warning level.

[0017] Optionally, obtain the target product demand information for the current warning level, including:

[0018] When the current warning level is Level 1, obtain the operating budget parameters as the target product demand information for the current warning level; the operating budget parameters should at least include the product type, the quantity of the first product required, the BOM for each product type, and the real-time inventory of the first product; or...

[0019] When the current alert level is Level 2, obtain the product plan parameters as the target product demand information for the current alert level; the product plan parameters should at least include the product name, the BOM of the first product, the required quantity of the second product, and the real-time inventory of the second product; or...

[0020] When the current warning level is Level 3, the inventory planning parameters are obtained as the target product demand information for the current warning level; the inventory planning parameters include the first material name, material inventory standard, and real-time inventory of the first material; or...

[0021] When the current warning level is Level 4, the assembly plan parameters are obtained as the target product demand information for the current warning level; the assembly plan parameters include the second material name, material requirement quantity, second product BOM, and real-time inventory of the second material; or...

[0022] When the current warning level is Level 5, the secondary commitment production parameters are obtained as the target product demand information for the current warning level. The secondary commitment production parameters include the committed product, the committed quantity, the third product BOM, and the real-time inventory of the third material.

[0023] Optionally, based on the actual inventory and expected usage of each material, determine whether the products to be produced meet the requirements for completeness, and issue early warnings for products that do not meet the requirements and their corresponding incomplete semi-finished products, including:

[0024] Determine whether the actual inventory of each material equals the expected usage of each material;

[0025] If the actual inventory of each material equals the expected usage of each material, then the products to be produced are determined to be complete; or, if the actual inventory of each material does not equal the expected usage of each material, then the products to be produced are determined to be incomplete.

[0026] Calculate the optimal inventory for incomplete products and their corresponding incomplete semi-finished products.

[0027] Warning messages are generated for incomplete products and their corresponding incomplete semi-finished products;

[0028] The optimal inventory and its warning information are packaged into an early warning message, which is then pushed to the early warning client for notification.

[0029] Optionally, before determining the current warning level, the following steps are also included:

[0030] Establish model training samples for each warning level;

[0031] Construct material availability early warning models for each warning level;

[0032] Input the model training samples for each warning level into the corresponding material matching warning model, and output the model loss value.

[0033] When the model loss value reaches its minimum, a pre-trained material availability early warning model for each early warning level is generated; or when the model loss value does not reach its minimum, the model loss value is backpropagated to update the model parameters of the material availability early warning model, and the step of inputting the model training samples for each early warning level into its corresponding material availability early warning model continues until the model loss value reaches its minimum.

[0034] Optionally, model training samples are created for each warning level, including:

[0035] Obtain historical product demand information for each warning level;

[0036] Based on the historical product demand information under each warning level, determine the material parameters required for the products to be produced under each warning level at different times;

[0037] Establish a mapping relationship between historical product demand information under each warning level and the material parameters required by the products to be produced at different times, and obtain the first training sample for each warning level;

[0038] Obtain the inventory variables corresponding to changes in production date for each material under each warning level;

[0039] Establish a mapping relationship between time periods and inventory variables to obtain a second training sample for each warning level;

[0040] The first and second training samples are vectorized to obtain the first vector set and the second vector set.

[0041] The first vector set and the second vector set are combined into a vector matrix to obtain the vector matrix for each warning level;

[0042] The vector matrix of each warning level is used to determine the model training samples for each warning level.

[0043] Optionally, the expression for the loss function of the material availability early warning model is:

[0044]

[0045] Among them, y i Let be the vector matrix representing the i-th warning level, where i represents the i-th warning level among multiple warning levels. λh(i)‖f is the cross-entropy loss function for material matching early warning, where k is the type of material, j is the material number, e is the natural constant, w is the fully connected layer parameter, T is the transpose operation, and λh(i)‖f i || 2 f represents the magnitude constraint loss on the length of the eigenvectors in the feature matrix when there is an error in the material inventory calculation. iThe model extracts features from the input vector matrix, h(i) is the category indicator value, h(i) = 1 when there is an error in the material inventory, and h(i) = 0 otherwise; λ is the weight of the constraint. This is the loss due to the magnitude constraint on the length of the eigenvectors in the feature matrix when the material inventory is correct. γ is the constraint weight, and ε is a number to prevent the denominator from being zero; ε is set to 10. -7 .

[0046] Secondly, embodiments of this application provide a material availability early warning device, the device comprising:

[0047] The information acquisition module is used to determine the current warning level and acquire the product demand information to be produced under the current warning level;

[0048] The model loading module is used to load the material completeness early warning model pre-trained for the current early warning level;

[0049] The forecast information output module is used to input the demand information of the products to be produced into the material kitting early warning model and output the forecast information of each material corresponding to the current early warning level. The forecast information includes the actual inventory of each material and the expected usage of each material.

[0050] The kitting early warning module is used to determine whether the products to be produced meet the kitting requirements based on the actual inventory and expected usage of each material, and to issue early warnings for products that do not meet the kitting requirements and their corresponding incomplete semi-finished products.

[0051] Thirdly, embodiments of this application provide a computer storage medium storing multiple instructions adapted for loading and execution of the above-described method steps by a processor.

[0052] Fourthly, embodiments of this application provide a terminal that may include: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and executed by the above-described method steps.

[0053] The technical solutions provided in this application embodiment may include the following beneficial effects:

[0054] In this embodiment, the material availability early warning device first determines the current early warning level, obtains the product demand information for the products to be produced under that early warning level, then loads a pre-trained material availability early warning model for that early warning level, inputs the product demand information for the products to be produced into the model, and outputs the actual inventory of each material and the expected usage of each material corresponding to that early warning level. Finally, based on the actual inventory and the sum and expected usage of each material, it determines whether the products to be produced meet the availability requirements, and issues early warnings for products that do not meet the availability requirements and their corresponding incomplete semi-finished products. Since this application trains a material availability early warning model for each of the five early warning levels, it can automatically determine whether the products to be produced meet the availability requirements when the current early warning level and product demand information are obtained, and issue early warnings for products that do not meet the availability requirements and their corresponding incomplete semi-finished products, thereby improving production efficiency.

[0055] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0056] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0057] Figure 1 This is a flowchart illustrating a material availability early warning method provided in an embodiment of this application;

[0058] Figure 2 This is a schematic diagram illustrating the mapping relationship between early warning levels and product demand information provided in an embodiment of this application;

[0059] Figure 3 This is a schematic diagram illustrating the vectorization process of a training sample provided in an embodiment of this application;

[0060] Figure 4 This is a schematic diagram of the training process of a material completeness early warning model provided in an embodiment of this application;

[0061] Figure 5 This is a schematic diagram of the structure of a material completeness early warning device provided in an embodiment of this application;

[0062] Figure 6 This is a schematic diagram of the structure of a terminal provided in an embodiment of this application. Detailed Implementation

[0063] The following description and accompanying drawings fully illustrate specific embodiments of the invention to enable those skilled in the art to practice them.

[0064] It should be understood that the described embodiments are merely some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0065] In the following description, when referring to the accompanying drawings, the same numbers in different drawings denote the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.

[0066] In the description of this invention, it should be understood that the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Those skilled in the art can understand the specific meaning of these terms in this invention based on the specific circumstances. Furthermore, in the description of this invention, unless otherwise stated, "multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0067] This application provides a material availability early warning method, apparatus, storage medium, and terminal to solve the problems existing in the aforementioned related technologies. In the technical solution provided by this application, since a material availability early warning model has been trained for each of the five early warning levels, it can automatically determine whether the products to be produced meet the availability requirements when the current early warning level and product demand information are obtained, and issue early warnings for products that do not meet the availability requirements and their corresponding incomplete semi-finished products, thereby improving production efficiency. The following is a detailed description using exemplary embodiments.

[0068] The following will be combined with the appendix Figure 1 -Appendix Figure 4 This application provides a detailed description of the material availability early warning method provided in its embodiments. This method can be implemented using a computer program and can run on a material availability early warning device based on the von Neumann architecture. This computer program can be integrated into an application or run as a standalone utility application.

[0069] Please see Figure 1 The diagram below illustrates a method for early warning of material availability, as provided in this application embodiment. Figure 1 As shown, the method in this application embodiment may include the following steps:

[0070] S101, Determine the current warning level and obtain the product demand information under the current warning level;

[0071] The current warning level is determined by the system based on the product delivery date, and can be specifically determined within the five warning levels based on the product delivery date. Product demand information is based on the demand parameters set for different warning levels within the five warning levels.

[0072] In this embodiment of the application, when determining the current warning level, the delivery date of the product to be produced is first determined; then, if the time difference between the current date and the product delivery date is greater than or equal to 12 months, a first-level warning is determined for generating a product production plan based on customer demand variables, and the warning level of the first-level warning is determined as the current warning level.

[0073] Alternatively, if the time difference between the current date and the delivery date is greater than 6 months but less than 12 months, a secondary warning is determined to generate inventory planning variables based on rolling planning variables, and the warning level of the secondary warning is determined as the current warning level. Here, the rolling planning variable is the rolling inventory quantity within a continuous preset time period.

[0074] Alternatively, if the time difference between the current date and the delivery date is greater than 3 months but less than 6 months, a Level 3 warning is determined to generate an assembly plan variable based on the shipping plan variable, and the warning level of the Level 3 warning is determined as the current warning level. Here, the assembly plan variable is the product assembly plan inventory quantity formulated based on historical product assembly data.

[0075] Alternatively, if the time difference between the current date and the delivery date is greater than 1 month but less than 3 months, a Level 4 early warning system is established to create production plan variables based on the customer's secondary expedited delivery demand variable, and the warning level under the Level 4 early warning system is determined as the current warning level.

[0076] Alternatively, if the time difference between the current date and the delivery date is greater than 1 day but less than 1 month, a Level 5 warning is determined for the expedited production variable, and the warning level under the Level 5 warning is determined as the current warning level.

[0077] In this embodiment of the application, when obtaining the product demand information to be produced under the current warning level, when the current warning level is Level 1, the operating budget parameters are obtained as the target product demand information for the current warning level; the operating budget parameters include at least the product type, the quantity of the first product required, the BOM of each type of product, and the real-time inventory of the first product.

[0078] Alternatively, when the current warning level is Level 2, obtain the product plan parameters as the target product demand information for the current warning level; the product plan parameters should include at least the product name, the BOM of the first product, the required quantity of the second product, and the real-time inventory of the second product.

[0079] Alternatively, when the current warning level is Level 3, the inventory planning parameters can be obtained as the target product demand information for the current warning level; the inventory planning parameters include the first material name, the material inventory standard, and the real-time inventory of the first material.

[0080] Alternatively, when the current warning level is Level 4, the assembly plan parameters can be obtained as the target product demand information for the current warning level; the assembly plan parameters include the name of the second material, the quantity of the material required, the BOM of the second product, and the real-time inventory of the second material.

[0081] Alternatively, when the current warning level is Level 5, the secondary commitment production parameters can be obtained as the target product demand information for the current warning level. The secondary commitment production parameters include the committed product, the committed quantity, the third product BOM, and the real-time inventory of the third material.

[0082] It should be noted that under the five-level warning status, product demand information under that warning status can be obtained based on the determined warning status.

[0083] In one possible implementation, the system calculates the current warning level in real time based on the product delivery date, and after determining the warning level, it can obtain product demand information under that warning level.

[0084] Furthermore, when obtaining the target product demand information for the current warning level, a pre-generated relationship mapping table between the warning level and product demand information can be loaded first. The warning level and product demand information are stored in the relationship mapping table in the form of key-value pairs. Then, the product demand information corresponding to the current warning level is determined in the pre-generated relationship mapping table between the warning level and product demand information, and the product demand information is extracted to obtain the target product demand information.

[0085] Specifically, a pre-generated mapping table between early warning levels and product demand information, for example... Figure 2 As shown, at Level 1 warning, product demand information is the operating budget parameter; at Level 2 warning, product demand information is the product plan parameter; at Level 3 warning, product demand information is the inventory plan parameter; at Level 4 warning, product demand information is the assembly plan parameter; and at Level 5 warning, product demand information is the secondary commitment production parameter.

[0086] S102, Load the material kitting early warning model pre-trained for the current early warning level;

[0087] Among them, the material availability early warning model is a mathematical model that can output the actual inventory of each material and the expected usage of each material. This model can be constructed based on neural networks.

[0088] In this embodiment of the application, each warning level corresponds to a pre-trained material availability warning model. This model is deployed on the server. After determining the current warning level, the level identifier of the warning level can be obtained. Then, based on the level identifier, the server searches for the corresponding pre-trained material availability warning model. If it exists, the found pre-trained material availability warning model is loaded.

[0089] In this embodiment, when training the material availability early warning model for each early warning level, firstly, model training samples are established for each early warning level; then, a material availability early warning model is constructed for each early warning level; secondly, the model training samples for each early warning level are input into its corresponding material availability early warning model, and the model loss value is output; finally, when the model loss value reaches its minimum, a pre-trained material availability early warning model for each early warning level is generated; or when the model loss value does not reach its minimum, the model loss value is backpropagated to update the model parameters of the material availability early warning model, and the step of inputting the model training samples for each early warning level into its corresponding material availability early warning model continues until the model loss value reaches its minimum.

[0090] Specifically, when establishing model training samples for each warning level, the historical product demand information for each warning level is first obtained. Then, based on the historical product demand information for each warning level, the material parameters required for the products to be produced at different times under each warning level are determined. Next, a mapping relationship is established between the historical product demand information for each warning level and the material parameters required for the products to be produced at different times, resulting in the first training sample for each warning level. Then, the inventory variables corresponding to the changes in production dates for each material under each warning level are obtained. A mapping relationship is then established between the time period and the inventory variables, resulting in the second training sample for each warning level. Finally, the first and second training samples are vectorized to obtain the first and second vector sets. The first and second vector sets are then combined into a vector matrix to obtain the vector matrix for each warning level. The vector matrix for each warning level is then used as the model training sample for each warning level.

[0091] For example Figure 3 As shown, Figure 3 This is a schematic diagram of a vectorization process provided in this application. The first training sample and the second training sample are vector-encoded by a one-hot encoder, and the encoded vectors are further processed to obtain vector value representations.

[0092] Specifically, the expression for the loss function of the material availability early warning model is as follows:

[0093]

[0094] Among them, y i Let be the vector matrix representing the i-th warning level, where i represents the i-th warning level among multiple warning levels. λh(i)‖f is the cross-entropy loss function for material matching early warning, where k is the type of material, j is the material number, e is the natural constant, w is the fully connected layer parameter, T is the transpose operation, and λh(i)‖f i || 2 f represents the magnitude constraint loss on the length of the eigenvectors in the feature matrix when there is an error in the material inventory calculation. i The model extracts features from the input vector matrix, h(i) is the category indicator value, h(i) = 1 when there is an error in the material inventory, and h(i) = 0 otherwise; λ is the weight of the constraint. This is the loss due to the magnitude constraint on the length of the eigenvectors in the feature matrix when the material inventory is correct. γ is the constraint weight, and ε is a number to prevent the denominator from being zero; ε is set to 10. -7 .

[0095] In one possible implementation, after obtaining the product demand information to be produced under the current warning level, a material kitting warning model pre-trained for the current warning level can be loaded on the server.

[0096] S103: Input the product demand information to be produced into the material kitting early warning model and output the prediction information of each material corresponding to the current early warning level.

[0097] The forecast information includes the actual inventory of each material and the expected usage of each material.

[0098] In one possible implementation, when the current warning level is Level 1, the product type, the required quantity of the first product, the BOM of each type of product, and the real-time inventory of the first product are input into the material matching warning model. After the model is processed, the actual inventory of each material corresponding to the Level 1 warning and the expected usage of each material can be obtained.

[0099] In another possible implementation, when the current warning level is Level 2, the product name, the BOM of the first product, the required quantity of the second product, and the real-time inventory of the second product are input into the material kitting warning model. After the model is processed, the actual inventory of each material corresponding to the Level 2 warning and the expected usage of each material can be obtained.

[0100] In another possible implementation, when the current warning level is level three, the name of the first material, the material inventory standard, and the real-time inventory of the first material are input into the material completeness warning model. After the model is processed, the actual inventory of each material corresponding to the level three warning and the expected usage of each material can be obtained.

[0101] In another possible implementation, when the current warning level is level four, the name of the second material, the quantity required for the material, the BOM of the second product, and the real-time inventory of the second material are input into the material completeness warning model. After the model is processed, the actual inventory of each material corresponding to the level four warning and the expected usage of each material can be obtained.

[0102] In another possible implementation, when the current warning level is level 5, the committed product, committed quantity, third product BOM, and real-time inventory of the third material are input into the material completeness warning model. After the model is processed, the actual inventory of each material corresponding to level 4 warning and the expected usage of each material can be obtained.

[0103] S104, based on the actual inventory of each material and the expected usage of each material, determines whether the products to be produced meet the requirements for completeness, and issues warnings for products that do not meet the requirements for completeness and their corresponding incomplete semi-finished products.

[0104] In one possible implementation, when determining whether the products to be produced meet the requirements for completeness based on the actual inventory and expected usage of each material, and issuing warnings for products that do not meet the requirements and their corresponding incomplete semi-finished products, the process first determines whether the actual inventory of each material equals the expected usage of each material. If the actual inventory equals the expected usage, the products to be produced are determined to meet the requirements for completeness; otherwise, if the actual inventory does not equal the expected usage, the products to be produced are determined to not meet the requirements for completeness. Then, the optimal inventory is calculated for the incomplete products and their corresponding incomplete semi-finished products. Next, warning information is generated for the incomplete products and their corresponding incomplete semi-finished products. Finally, the optimal inventory and the warning information are encapsulated into a warning message, and the warning message is pushed to the warning client for warning.

[0105] In this embodiment, the material availability early warning device first determines the current early warning level, obtains the product demand information for the products to be produced under that early warning level, then loads a pre-trained material availability early warning model for that early warning level, inputs the product demand information for the products to be produced into the model, and outputs the actual inventory of each material and the expected usage of each material corresponding to that early warning level. Finally, based on the actual inventory and the sum and expected usage of each material, it determines whether the products to be produced meet the availability requirements, and issues early warnings for products that do not meet the availability requirements and their corresponding incomplete semi-finished products. Since this application trains a material availability early warning model for each of the five early warning levels, it can automatically determine whether the products to be produced meet the availability requirements when the current early warning level and product demand information are obtained, and issue early warnings for products that do not meet the availability requirements and their corresponding incomplete semi-finished products, thereby improving production efficiency.

[0106] Please see Figure 4 This is a flowchart illustrating a model training method provided in an embodiment of this application. Figure 4 As shown, the method in this application embodiment may include the following steps:

[0107] S201, Establish model training samples for each warning level;

[0108] S202, Construct a material availability early warning model for each early warning level;

[0109] S203: Input the model training samples for each warning level into the corresponding material matching warning model and output the model loss value.

[0110] S204. When the model loss value reaches the minimum, generate a pre-trained material availability early warning model for each early warning level; or when the model loss value does not reach the minimum, backpropagate the model loss value to update the model parameters of the material availability early warning model, and continue to execute the step of inputting the model training samples for each early warning level into its corresponding material availability early warning model until the model loss value reaches the minimum.

[0111] In this embodiment, the material availability early warning device first determines the current early warning level, obtains the product demand information for the products to be produced under that early warning level, then loads a pre-trained material availability early warning model for that early warning level, inputs the product demand information for the products to be produced into the model, and outputs the actual inventory of each material and the expected usage of each material corresponding to that early warning level. Finally, based on the actual inventory and the sum and expected usage of each material, it determines whether the products to be produced meet the availability requirements, and issues early warnings for products that do not meet the availability requirements and their corresponding incomplete semi-finished products. Since this application trains a material availability early warning model for each of the five early warning levels, it can automatically determine whether the products to be produced meet the availability requirements when the current early warning level and product demand information are obtained, and issue early warnings for products that do not meet the availability requirements and their corresponding incomplete semi-finished products, thereby improving production efficiency.

[0112] The following are embodiments of the apparatus of the present invention, which can be used to execute embodiments of the method of the present invention. For details not disclosed in the embodiments of the apparatus of the present invention, please refer to the embodiments of the method of the present invention.

[0113] Please see Figure 5 This diagram illustrates a structural schematic of a material availability early warning device provided in an exemplary embodiment of the present invention. This material availability early warning device can be implemented as all or part of a terminal through software, hardware, or a combination of both. The device 1 includes an information acquisition module 10, a model loading module 20, a prediction information output module 30, and an availability early warning module 40.

[0114] Information acquisition module 10 is used to determine the current warning level and acquire the product demand information to be produced under the current warning level;

[0115] Model loading module 20 is used to load the material completeness early warning model pre-trained for the current early warning level;

[0116] The forecast information output module 30 is used to input the product demand information to be produced into the material kitting early warning model and output the forecast information of each material corresponding to the current early warning level; wherein, the forecast information includes the actual inventory of each material and the expected usage of each material.

[0117] The kitting warning module 40 is used to determine whether the products to be produced meet the kitting requirements based on the actual inventory of each material and the expected usage of each material, and to issue warnings for products that do not meet the kitting requirements and their corresponding non-kitted semi-finished products.

[0118] It should be noted that the material availability early warning device provided in the above embodiments is only illustrated by the division of the above functional modules when executing the material availability early warning method. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the equipment can be divided into different functional modules to complete all or part of the functions described above. In addition, the material availability early warning device and the material availability early warning method embodiments provided in the above embodiments belong to the same concept, and the implementation process is detailed in the method embodiments, which will not be repeated here.

[0119] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0120] In this embodiment, the material availability early warning device first determines the current early warning level, obtains the product demand information for the products to be produced under that early warning level, then loads a pre-trained material availability early warning model for that early warning level, inputs the product demand information for the products to be produced into the model, and outputs the actual inventory of each material and the expected usage of each material corresponding to that early warning level. Finally, based on the actual inventory and the sum and expected usage of each material, it determines whether the products to be produced meet the availability requirements, and issues early warnings for products that do not meet the availability requirements and their corresponding incomplete semi-finished products. Since this application trains a material availability early warning model for each of the five early warning levels, it can automatically determine whether the products to be produced meet the availability requirements when the current early warning level and product demand information are obtained, and issue early warnings for products that do not meet the availability requirements and their corresponding incomplete semi-finished products, thereby improving production efficiency.

[0121] The present invention also provides a computer-readable medium having program instructions stored thereon, which, when executed by a processor, implement the material kitting early warning method provided in the above-described method embodiments.

[0122] The present invention also provides a computer program product containing instructions that, when run on a computer, causes the computer to execute the material kitting early warning method of the above-described method embodiments.

[0123] Please see Figure 6 This is a schematic diagram of the structure of a terminal provided in an embodiment of this application. Figure 6 As shown, terminal 1000 may include: at least one processor 1001, at least one network interface 1004, user interface 1003, memory 1005, and at least one communication bus 1002.

[0124] The communication bus 1002 is used to realize the connection and communication between these components.

[0125] The user interface 1003 may include a display screen and a camera. Optionally, the user interface 1003 may also include a standard wired interface and a wireless interface.

[0126] The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0127] The processor 1001 may include one or more processing cores. The processor 1001 connects to various parts within the electronic device 1000 using various interfaces and lines. It executes various functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 1005, and by calling data stored in the memory 1005. Optionally, the processor 1001 may be implemented using at least one hardware form selected from Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA). The processor 1001 may integrate one or more of the following: a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), and a modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content to be displayed on the screen; and the modem handles wireless communication. It is understood that the modem may also be implemented as a separate chip, without being integrated into the processor 1001.

[0128] The memory 1005 may include random access memory (RAM) or read-only memory. Optionally, the memory 1005 may include a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 1005 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 1005 may also be at least one storage device located remotely from the aforementioned processor 1001. Figure 6 As shown, the memory 1005, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a material availability early warning application.

[0129] exist Figure 6 In the terminal 1000 shown, the user interface 1003 is mainly used to provide an input interface for the user and to obtain the user's input data; while the processor 1001 can be used to call the material kitting early warning application stored in the memory 1005 and specifically perform the following operations:

[0130] Determine the current warning level and obtain the product demand information under the current warning level;

[0131] Load the material completeness early warning model pre-trained for the current warning level;

[0132] Input the product demand information to be produced into the material availability early warning model, and output the forecast information of each material corresponding to the current early warning level; the forecast information includes the actual inventory of each material and the expected usage of each material.

[0133] Based on the actual inventory of each material and the expected usage of each material, determine whether the products to be produced meet the requirements for completeness, and issue early warnings for products that do not meet the requirements and their corresponding incomplete semi-finished products.

[0134] In one embodiment, when determining the current warning level, the processor 1001 performs the following operations:

[0135] Determine the delivery date for the products to be manufactured;

[0136] If the time difference between the current date and the product delivery date is greater than or equal to 12 months, a Level 1 alert is established to generate a product production plan based on customer demand variables, and the alert level of Level 1 is set as the current alert level; or,

[0137] When the time difference between the current date and the delivery date is greater than 6 months but less than 12 months, a secondary warning is established to generate inventory planning variables based on rolling planning variables, and the warning level of the secondary warning is set as the current warning level. Here, the rolling planning variable is the rolling inventory quantity within a continuous preset time period; or...

[0138] When the time difference between the current date and the delivery date is greater than 3 months but less than 6 months, a Level 3 alert is established to generate assembly plan variables based on shipping plan variables, and the alert level of the Level 3 alert is set as the current alert level. Here, the assembly plan variable is the product assembly plan inventory level determined based on historical product assembly data; or...

[0139] When the time difference between the current date and the delivery date is greater than 1 month but less than 3 months, a Level 4 early warning system is established to create production planning variables based on customer secondary expedited delivery requests, and the warning level under Level 4 is determined as the current warning level; or...

[0140] When the time difference between the current date and the delivery date is greater than 1 day but less than 1 month, a Level 5 warning is determined for the expedited production variable, and the warning level under the Level 5 warning is determined as the current warning level.

[0141] In one embodiment, when the processor 1001 executes the process of obtaining target product demand information for the current warning level, it specifically performs the following operations:

[0142] When the current warning level is Level 1, obtain the operating budget parameters as the target product demand information for the current warning level; the operating budget parameters should at least include the product type, the quantity of the first product required, the BOM for each product type, and the real-time inventory of the first product; or...

[0143] When the current alert level is Level 2, obtain the product plan parameters as the target product demand information for the current alert level; the product plan parameters should at least include the product name, the BOM of the first product, the required quantity of the second product, and the real-time inventory of the second product; or...

[0144] When the current warning level is Level 3, the inventory planning parameters are obtained as the target product demand information for the current warning level; the inventory planning parameters include the first material name, material inventory standard, and real-time inventory of the first material; or...

[0145] When the current warning level is Level 4, the assembly plan parameters are obtained as the target product demand information for the current warning level; the assembly plan parameters include the second material name, material requirement quantity, second product BOM, and real-time inventory of the second material; or...

[0146] When the current warning level is Level 5, the secondary commitment production parameters are obtained as the target product demand information for the current warning level. The secondary commitment production parameters include the committed product, the committed quantity, the third product BOM, and the real-time inventory of the third material.

[0147] In one embodiment, when the processor 1001 determines whether the products to be produced meet the requirements for completeness based on the actual inventory and expected usage of each material, and issues warnings for products that do not meet the requirements and their corresponding incomplete semi-finished products, the processor 1001 specifically performs the following operations:

[0148] Determine whether the actual inventory of each material equals the expected usage of each material;

[0149] If the actual inventory of each material equals the expected usage of each material, then the products to be produced are determined to be complete; or, if the actual inventory of each material does not equal the expected usage of each material, then the products to be produced are determined to be incomplete.

[0150] Calculate the optimal inventory for incomplete products and their corresponding incomplete semi-finished products.

[0151] Warning messages are generated for incomplete products and their corresponding incomplete semi-finished products;

[0152] The optimal inventory and its warning information are packaged into an early warning message, which is then pushed to the early warning client for notification.

[0153] In one embodiment, before determining the current warning level, the processor 1001 also performs the following operations:

[0154] Establish model training samples for each warning level;

[0155] Construct material availability early warning models for each warning level;

[0156] Input the model training samples for each warning level into the corresponding material matching warning model, and output the model loss value.

[0157] When the model loss value reaches its minimum, a pre-trained material availability early warning model for each early warning level is generated; or when the model loss value does not reach its minimum, the model loss value is backpropagated to update the model parameters of the material availability early warning model, and the step of inputting the model training samples for each early warning level into its corresponding material availability early warning model continues until the model loss value reaches its minimum.

[0158] In one embodiment, when the processor 1001 executes the model training samples for each warning level, it specifically performs the following operations:

[0159] Obtain historical product demand information for each warning level;

[0160] Based on the historical product demand information under each warning level, determine the material parameters required for the products to be produced under each warning level at different times;

[0161] Establish a mapping relationship between historical product demand information under each warning level and the material parameters required by the products to be produced at different times, and obtain the first training sample for each warning level;

[0162] Obtain the inventory variables corresponding to changes in production date for each material under each warning level;

[0163] Establish a mapping relationship between time periods and inventory variables to obtain a second training sample for each warning level;

[0164] The first and second training samples are vectorized to obtain the first vector set and the second vector set.

[0165] The first vector set and the second vector set are combined into a vector matrix to obtain the vector matrix for each warning level;

[0166] The vector matrix of each warning level is used to determine the model training samples for each warning level.

[0167] In this embodiment, the material availability early warning device first determines the current early warning level, obtains the product demand information for the products to be produced under that early warning level, then loads a pre-trained material availability early warning model for that early warning level, inputs the product demand information for the products to be produced into the model, and outputs the actual inventory of each material and the expected usage of each material corresponding to that early warning level. Finally, based on the actual inventory and the sum and expected usage of each material, it determines whether the products to be produced meet the availability requirements, and issues early warnings for products that do not meet the availability requirements and their corresponding incomplete semi-finished products. Since this application trains a material availability early warning model for each of the five early warning levels, it can automatically determine whether the products to be produced meet the availability requirements when the current early warning level and product demand information are obtained, and issue early warnings for products that do not meet the availability requirements and their corresponding incomplete semi-finished products, thereby improving production efficiency.

[0168] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The material availability warning program can be stored in a computer-readable storage medium. When executed, the program can include the processes of the embodiments of the above methods. The storage medium for the material availability warning program can be a magnetic disk, optical disk, read-only memory, or random access memory, etc.

[0169] The above-disclosed embodiments are merely preferred embodiments of this application and should not be construed as limiting the scope of this application. Therefore, any equivalent variations made in accordance with the claims of this application shall still fall within the scope of this application.

Claims

1. A method for early warning of material availability, characterized in that, The method includes: Determine the current warning level and obtain the product demand information under the current warning level; Obtain the product demand information to be produced under the current warning level, including: When the current warning level is Level 1, operating budget parameters are obtained as the product demand information to be produced for that current warning level; the operating budget parameters include at least the product type, the quantity of the first product required, the BOM for each type of product, and the real-time inventory of the first product; or, when the current warning level is Level 2, product plan parameters are obtained as the product demand information to be produced for that current warning level; the product plan parameters include at least the product name, the BOM of the first product, the quantity of the second product required, and the real-time inventory of the second product; or, when the current warning level is Level 3, inventory plan parameters are obtained as the product demand information to be produced for that current warning level. The production demand information; the inventory planning parameters include the first material name, material inventory standard, and real-time inventory of the first material; or, when the current warning level is level four, the assembly planning parameters are obtained as the production demand information for the current warning level; the assembly planning parameters include the second material name, material demand quantity, second product BOM, and real-time inventory of the second material; or, when the current warning level is level five, the secondary commitment production parameters are obtained as the production demand information for the current warning level, the secondary commitment production parameters include the committed product, committed quantity, third product BOM, and real-time inventory of the third material; Load the material kitting early warning model pre-trained for the current early warning level; The product demand information to be produced is input into the material availability early warning model, and the predicted information of each material corresponding to the current early warning level is output; wherein, the predicted information includes the actual inventory of each material and the expected usage of each material; Based on the actual inventory of each material and the expected usage of each material, determine whether the products to be produced meet the requirements for completeness, and issue warnings for products that do not meet the requirements for completeness and their corresponding incomplete semi-finished products. The process of determining whether the products to be produced meet the requirements for completeness based on the actual inventory and expected usage of each material, and issuing early warnings for products that do not meet the requirements and their corresponding incomplete semi-finished products, includes: Determine whether the actual inventory of each material equals the expected usage of each material; if the actual inventory of each material equals the expected usage of each material, then determine that the products to be produced meet the requirement of completeness; or, if the actual inventory of each material does not equal the expected usage of each material, then determine that the products to be produced do not meet the requirement of completeness; calculate the optimal inventory for the incomplete products and their corresponding incomplete semi-finished products; generate warning information for the incomplete products and their corresponding incomplete semi-finished products; encapsulate the optimal inventory and the warning information into a warning message, and push the warning message to the warning client for warning; Before determining the current warning level, the process also includes: Establish model training samples for each warning level; construct a material availability warning model for each warning level; input the model training samples for each warning level into its corresponding material availability warning model and output the model loss value; when the model loss value reaches the minimum, generate a pre-trained material availability warning model for each warning level.

2. The method according to claim 1, characterized in that, Determining the current warning level includes: Determine the delivery date for the products to be manufactured; If the time difference between the current date and the product delivery date is greater than or equal to 12 months, a Level 1 warning is determined for generating a product production plan based on customer demand variables, and the warning level of the Level 1 warning is set as the current warning level; or, When the time difference between the current date and the delivery date is greater than 6 months and less than 12 months, a secondary early warning is determined for generating inventory planning variables based on rolling planning variables, and the warning level of the secondary early warning is set as the current early warning level. The rolling planning variable is the rolling inventory quantity within a continuous preset time period; or... When the time difference between the current date and the delivery date is greater than 3 months but less than 6 months, a Level 3 warning is determined for generating assembly plan variables based on shipping plan variables, and the warning level of the Level 3 warning is set as the current warning level. The assembly plan variable is the product assembly plan inventory quantity determined based on historical product assembly data; or... When the time difference between the current date and the delivery date is greater than 1 month but less than 3 months, a Level 4 early warning system is established to create production plan variables based on the customer's secondary expedited delivery demand variable, and the warning level under the Level 4 early warning system is determined as the current warning level; or... When the time difference between the current date and the delivery date is greater than 1 day and less than 1 month, a Level 5 warning is determined for the expedited production variable, and the warning level under the Level 5 warning is determined as the current warning level.

3. The method according to claim 1, characterized in that, The method further includes: When the model loss value has not reached the minimum, the model loss value is backpropagated to update the model parameters of the material availability early warning model, and the step of inputting the model training samples of each early warning level into the corresponding material availability early warning model continues until the model loss value reaches the minimum.

4. The method according to claim 1, characterized in that, The process of establishing model training samples for each warning level includes: Obtain historical product demand information for each warning level; Based on the historical product demand information under each warning level, determine the material parameters required for the products to be produced under each warning level at different times. Establish a mapping relationship between historical product demand information under each warning level and the material parameters required by the products to be produced at different times, and obtain the first training sample for each warning level; Obtain the inventory variables corresponding to changes in production date for each material under each warning level; Establish a mapping relationship between time periods and inventory variables to obtain a second training sample for each warning level; The first and second training samples are vectorized to obtain a first vector set and a second vector set. The first vector set and the second vector set are combined into a vector matrix to obtain the vector matrix for each warning level; The vector matrix of each warning level is used to determine the model training samples for each warning level.

5. The method according to claim 1, characterized in that, The expression for the loss function of the material completeness early warning model is as follows: in, Let be the vector matrix representing the i-th warning level, where i represents the i-th warning level among multiple warning levels. This is the cross-entropy loss function for material completeness early warning, where k is the type of material and j is the material number. It is a natural constant. These are parameters of the fully connected layer. It is a transpose operation. This represents the magnitude constraint loss on the length of the eigenvectors in the feature matrix when there is an error in the material inventory calculation. h represents the features extracted by the model from the input vector matrix. This is a category indicator value; it is used when there is an error in the material inventory. =1, otherwise h =0; These are the weights of the constraints; It is the loss due to the magnitude constraint on the length of the eigenvectors in the feature matrix when the material inventory is correct. It is the weight of the constraint. To prevent numbers with a denominator of 0, set =10 -7 .

6. A material kitting early warning device implemented using the method described in any one of claims 1-5, characterized in that, The device includes: The information acquisition module is used to determine the current warning level and acquire the product demand information to be produced under the current warning level; The model loading module is used to load the material completeness early warning model pre-trained for the current early warning level; The forecast information output module is used to input the product demand information to be produced into the material availability early warning model and output the forecast information of each material corresponding to the current early warning level; wherein, the forecast information includes the actual inventory of each material and the expected usage of each material. The kitting warning module is used to determine whether the products to be produced meet the kitting requirements based on the actual inventory of each material and the expected usage of each material, and to issue warnings for products that do not meet the kitting requirements and their corresponding incomplete semi-finished products.

7. A computer storage medium, characterized in that, The computer storage medium stores a plurality of instructions adapted for loading by a processor and executing the method as described in any one of claims 1-5.

8. A terminal, characterized in that, include: A processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and executed as described in any one of claims 1-5.

Images