TW202141369A - Shipping volume prediction method, device, computer device and storage media - Google Patents

Abstract

The invention provides a shipping volume prediction method, a shipping volume prediction device, a computer device and a computer storage medium. The method includes: obtaining a material name and at least one material number code corresponding to the material name; calling a material usage prediction model, and the material usage prediction model is used to predict a quantity of a material corresponding to the at least one material number code needed to produce at least one type of product within a preset time; according to the quantity of the material, querying a corresponding relation table between a material number code and a product information to calculate a shipment quantity of at least one type of product corresponding to the at least one material number code.

Description

Shipment forecast method, device, computer device and storage medium

The invention relates to the technical field of supply chain management, in particular to a method for forecasting shipments, a device for forecasting shipments, a computer device and a computer storage medium.

With the vigorous development of the electronic information industry, people's demand for electronic products is increasing, and electronic products are updated at a fast speed, so the requirements for the production efficiency of electronic products are also getting higher and higher. However, the structure of electronic products is complex, and there are many parts and components required to produce an electronic product, which poses greater challenges to the logistics and warehousing of parts. In actual production, people need to forecast product shipments, so as to reasonably arrange the procurement and logistics of raw materials. Some current shipment forecasting methods mostly use manual statistical analysis to predict the future shipments at a preset time. The existing shipment forecasting methods are inefficient and unwise.

In view of the above, it is necessary to propose a shipment forecasting method, a shipment forecasting device, a computer device and a computer storage medium, so that the shipment forecast can be carried out in a more efficient and intelligent way.

The first aspect of the present application provides a method for forecasting shipments, the method including: Obtain the material name and at least one material number code corresponding to the material name; The material consumption prediction model generated by pre-training is called, and the material consumption prediction model is used to predict the usage quantity of the material corresponding to the at least one material number code required to produce at least one model of the product within the preset time, wherein the material The usage prediction model analyzes the characteristic relationship between at least one item number code and the quantity of materials corresponding to the at least one item number code on different types of products in the historical time period, and predicts the at least The quantity of materials corresponding to a material number code on different models of products within a preset time; According to the usage quantity of the material corresponding to the at least one item number code, query the correspondence table of the item number code and the product information, and calculate the shipment volume of the at least one model of the product corresponding to the at least one item number code, wherein the The item number code and product information correspondence table records the item number codes of all materials required to produce each product and the quantity of each material used.

Preferably, the method further includes: According to the shipment volume of the product, output a list of material numbers required for the production of the product, wherein the list of material numbers includes one or more of the material name, the material number code, and the used quantity of the material.

Preferably, the method further includes: According to the material number list, query whether the quantity of materials already in the warehouse is greater than the required material quantity, where the required material quantity is the used quantity of the materials in the material number list; When the quantity of existing materials is less than the used quantity of materials in the material number list, a first prompt message is generated.

Preferably, the method further includes: When the quantity of existing materials in the warehouse is greater than the required quantity of materials, calculating the difference between the quantity of existing materials and the quantity of required materials, and comparing the difference with a preset threshold; If it is greater than the threshold, a second prompt message indicating that the inventory is surplus is generated.

Preferably, the training of the material consumption prediction model includes: Obtain sample data, and divide the sample data into a training set and a validation set. The sample data includes the shipping time of the shipped product, the item number code of the shipped product, and the corresponding item number code of the shipped product The quantity of materials used, where the shipping time of the shipped product and the item number code corresponding to the shipped product are used as the input data of the material usage prediction model, and the item number code corresponding to the shipped product The used quantity of the corresponding material is used as the output data of the material consumption prediction model; Establishing a deep learning model based on a convolutional neural network, and using the training set to train the deep learning model, and obtaining parameters of the deep learning model; Use the verification set to verify the trained deep learning model, and calculate the accuracy of the deep learning model prediction according to the verification result; Judging whether the prediction accuracy rate of the model is less than a preset threshold; If the model prediction accuracy rate is not less than the preset threshold value, the trained deep learning model is used as the material consumption prediction model.

Preferably, after determining whether the model prediction accuracy rate is less than a preset threshold, the method further includes: If the model prediction accuracy rate is less than the preset threshold, adjust the parameters of the deep learning model, and use the training set to retrain the adjusted deep learning model; Use the verification set to verify the retrained deep learning model, re-statistically obtain the model prediction accuracy rate according to each verification result, and determine whether the re-statistical model prediction accuracy rate is less than the preset threshold; If the prediction accuracy rate of the model obtained by re-statistics is not less than the preset threshold, the deep learning model completed by the re-training is used as the material consumption prediction model; If the model prediction accuracy rate obtained by re-statistics is less than the preset threshold, repeat the adjustment of the parameters of the deep learning model, and use the training set to retrain the adjusted deep learning model until it passes The model prediction accuracy rate verified by the verification set is not less than the preset threshold; Wherein, the parameters of the deep learning model based on the convolutional neural network include at least one of the number of convolution kernels, the number of elements in the pooling layer, the number of elements in the fully connected layer, and the connection relationship between different connected layers. A sort of.

Preferably, the method for establishing the correspondence table between the part number code and the product information includes: Obtain the design drawing of the product, obtain the material name, part number code, and material used quantity of the product from the design drawing, and establish the material number code and the material number code according to the material name, material number code, and material used quantity of the product Product information correspondence table; Obtain the processing parameter information of the product, obtain the consumable information for processing the product, the part number code of the consumable and the used quantity of the consumable from the processing parameter information of the product, according to the consumable information of the product, the part number code of the consumable and The used quantity of consumables establishes the corresponding relationship table between the item number code and the product information.

A second aspect of the present application provides a shipment forecasting device, the device including: The obtaining module is used to obtain the material name and at least one material number code corresponding to the material name; The prediction module is used to call the material consumption prediction model generated by pre-training, and use the material consumption prediction model to predict the usage quantity of the material corresponding to the at least one item number code to produce at least one model of the product within a preset time , Wherein the material consumption prediction model analyzes the characteristic relationship between at least one material number code and the quantity of materials corresponding to the at least one material number code in different models of products in the historical time period, and passes the The characteristic relationship predicts the usage quantity of the material corresponding to the at least one material number code on different models of products within a preset time; The calculation module is used to query the correspondence table of the part number code and product information according to the usage quantity of the material corresponding to the at least one part number code, and calculate the shipment of the at least one model product corresponding to the at least one part number code The item number code and product information correspondence table records the item number codes of all materials required to produce each product and the used quantity of each material.

A third aspect of the present application provides a computer device, the computer device includes a processor and a memory, and the processor is configured to execute the computer program stored in the memory to implement the aforementioned method for forecasting shipments.

The fourth aspect of the present application provides a computer storage medium on which a computer program is stored, and when the computer program is executed by a processor, the method for forecasting shipments as described above is realized.

The shipment volume forecasting method, the shipment volume forecasting device, the computer device and the computer storage medium of the present invention are used to predict the usage volume of the material corresponding to the obtained material number code at a preset time in the future through the material usage prediction model, And according to the usage amount of the material and the corresponding relationship table of the item number code and the product information, the shipment volume of at least one product corresponding to the at least one item number code is calculated. The method can make the forecasting method of product shipments more efficient and intelligent.

In order to be able to understand the above objectives, features and advantages of the present invention more clearly, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other if there is no conflict.

In the following description, many specific details are set forth in order to fully understand the present invention. The described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments, and are not intended to limit the present invention.

Example one

Referring to FIG. 1, it is a schematic diagram of the application environment architecture of the method for forecasting shipment volume provided by Embodiment 1 of the present invention.

The method for forecasting shipment volume in the present invention is applied to a computer device 1, and the computer device 1 and at least one user terminal 2 establish a communication connection via a network. The network may be a wired network or a wireless network, such as radio, wireless fidelity (WIFI), cellular, satellite, broadcasting, etc. The user terminal 2 is used to send the material number code to be queried. The computer device 1 is used for predicting the usage quantity of the material corresponding to the part number code on the product to be produced in a preset time period, and calculates the part number code according to the correspondence table of the part number code and product information The shipment volume of at least one model of the corresponding product.

The computer device 1 may be an electronic device installed with shipment forecast software, such as a personal computer, a server, etc., where the server may be a single server, a server cluster, or a cloud server.

The user terminal 2 is an electronic device with a computing storage function, including but not limited to a smart phone, a tablet computer, a laptop computer, a desktop computer, and production and processing equipment.

Example two

Please refer to FIG. 2, which is a flowchart of a method for forecasting shipments according to a second embodiment of the present invention. According to different needs, the order of the steps in the flowchart can be changed, and some steps can be omitted.

Step S1: Obtain a material name and at least one material number code corresponding to the material name.

The part number code can be a combination of letters and numbers. The letters and digits in the part number code are used to describe the material of the part number, the installation location, the applied product model, the product brand, the country and region where it is sold, and so on. For example, material number ABC123, where A is the material code of the material, and the material information of the material can be obtained according to the preset material code and the comparison relationship of the material; B is the installation position code of the material, which can be based on the preset material code The comparison relationship between the installation position and the material obtains the installation position of the material; C is the model of the product corresponding to the material number; 1 is the product brand corresponding to the material number; 2 is the sales corresponding to the material number Country; 3 is the sales area corresponding to the part number.

Step S2: Invoke the material consumption prediction model generated by pre-training, and use the material consumption prediction model to predict the usage quantity of the material corresponding to the at least one material number code required to produce at least one type of product within a preset time.

Wherein, the material consumption prediction model analyzes the characteristic relationship between at least one material number code and the quantity of materials corresponding to the at least one material number code in different models of products in the historical time period, and adopts the characteristic The relationship predicts the amount of use of the material corresponding to the at least one item number code on products of different models within a preset time.

A material number code can be input into the material consumption prediction model to predict the quantity of the material number code required to produce a product of a model within a preset time. It is also possible to input multiple material number codes corresponding to the same material into the material consumption prediction model to predict the quantity of the material number codes required to produce multiple models of products within a preset time. The preset time can be one month, twenty days, etc., and the staff can set it according to the actual situation.

In an embodiment of the present invention, the characteristic relationship between the at least one item number code in the material consumption prediction model and the quantity of materials corresponding to the at least one item number code on different types of products may adopt mathematical statistics. Analyze the method. For example, statistics the usage quantity of any material number code and the material corresponding to the material number code in the historical time period, import the quantity into the prediction model based on statistical algorithm, and the analysis place will preset the material number code in the future The production of at least one type of product within a time requires the use quantity of the material corresponding to the at least one part number code. The statistical algorithm includes any one of a time series model (Time Series Model), a long short-term memory model (LongShort-Term Memory Model), and an implicit Markov model (Hidden Markov Model).

In another embodiment of the present invention, the characteristic relationship between the at least one material number code in the material consumption prediction model and the quantity of materials corresponding to the at least one material number code on different models of products can also be adopted The analysis of the deep learning model of the convolutional neural network shows that the training steps of the material consumption prediction model include: Obtain sample data, and divide the sample data into a training set and a validation set. The sample data includes the shipping time of the shipped product, the item number code of the shipped product, and the corresponding item number code of the shipped product The quantity of materials used, where the shipping time of the shipped product and the item number code corresponding to the shipped product are used as the input data of the material usage prediction model, and the item number code corresponding to the shipped product The used quantity of the corresponding material is used as the output data of the material consumption prediction model; Establishing a deep learning model based on a convolutional neural network, and using the training set to train the deep learning model, and obtaining parameters of the deep learning model; Use the verification set to verify the trained deep learning model, and calculate the accuracy of the deep learning model prediction according to the verification result; Judging whether the prediction accuracy rate of the model is less than a preset threshold; If the model prediction accuracy rate is not less than the preset threshold value, the trained deep learning model is used as the material consumption prediction model.

If the model prediction accuracy rate is less than the preset threshold, adjust the parameters of the deep learning model, and use the training set to retrain the adjusted deep learning model; Use the verification set to verify the retrained deep learning model, re-statistically obtain the model prediction accuracy rate according to each verification result, and determine whether the re-statistical model prediction accuracy rate is less than the preset threshold; If the prediction accuracy rate of the model obtained by re-statistics is not less than the preset threshold, the deep learning model completed by the re-training is used as the material consumption prediction model; If the model prediction accuracy rate obtained by re-statistics is less than the preset threshold, repeat the adjustment of the parameters of the deep learning model, and use the training set to retrain the adjusted deep learning model until it passes The model prediction accuracy rate verified by the verification set is not less than the preset threshold; Wherein, the parameters of the deep learning model based on the convolutional neural network include at least one of the number of convolution kernels, the number of elements in the pooling layer, the number of elements in the fully connected layer, and the connection relationship between different connected layers. A sort of.

In other embodiments of the present invention, the material consumption prediction model may also be a deep learning model based on the naive Bayes algorithm, a deep learning model based on a multi-class support vector machine algorithm, and a deep learning model based on a logistic regression classification algorithm. Any one of learning model and deep learning model based on decision tree classification algorithm.

Step S3: Query the correspondence table of the part number code and product information according to the used quantity of the material corresponding to the at least one part number code, and calculate the shipment volume of the at least one model product corresponding to the at least one part number code.

Wherein, the item number code and product information correspondence table records the item number codes of all materials required to produce each product and the quantity of each material used.

The method of obtaining the corresponding relationship table between the part number code and the product information may include:

Obtain the design drawing of the product, obtain the material name, part number code, and material used quantity of the product from the design drawing, and establish the material number code and the material number code according to the material name, material number code, and material used quantity of the product Correspondence table of product information. The item number code of each part of the product and the quantity of the item number code required are recorded in the design drawing of the product.

Obtain the processing parameter information of the product, obtain the consumable information for processing the product, the part number code of the consumable and the used quantity of the consumable from the processing parameter information of the product, according to the consumable information of the product, the part number code of the consumable and The used quantity of consumables establishes the corresponding relationship table between the item number code and the product information. The consumable information may be materials lost during processing, such as grinding wheels, developer solutions, and the like.

In another embodiment of the present invention, the steps of the method for forecasting shipments further include: outputting a list of material numbers required to produce the product according to the shipment volume of the product, wherein the list of material numbers includes materials One or more of the name, item number code, and quantity of materials used. There is a corresponding relationship between the different part number codes of products of the same model. Knowing the shipment volume of the product and the used quantity of the material corresponding to a kind of part number code for the production of the product, according to the corresponding relationship, the production can be calculated The used quantity of materials corresponding to the other part number codes required by the product, and all the material number codes required to produce the product, the material name corresponding to the part number code, and the used quantity corresponding to the material name Output in the form of a data sheet.

In another embodiment of the present invention, the steps of the method for forecasting shipments further include: querying whether the quantity of materials already in the warehouse is greater than the quantity of materials required according to the list of material numbers, wherein the quantity of materials required is the quantity of materials required. The used quantity of the material in the material number list; when the existing material quantity is less than the used quantity of the material in the material number list, a first prompt message is generated. The first prompt message is used to send a first prompt message when the quantity of materials in the current warehouse is insufficient to meet the quantity of materials required to produce the product within a preset time in the future, and the first prompt message is used to remind staff to purchase in time Material. The first prompt message may be output in the form of text, or output in the form of voice.

In yet another embodiment of the present invention, the steps of the method for forecasting shipment volume further include: when the quantity of existing materials in the warehouse is greater than the quantity of required materials, calculating the difference between the quantity of existing materials and the quantity of required materials , And compare the difference with a preset threshold; if it is greater than the threshold, generate a second prompt message of excess inventory. The second prompt message is used to remind the staff that the current inventory of materials is excessive and the purchase plan needs to be rescheduled. The second prompt message may be output in the form of text, or output in the form of voice.

Figure 2 above describes the shipment forecasting method of the present invention in detail. In conjunction with Figures 3-4, the functional modules of the software device that implements the shipment forecasting method and the hardware that implements the shipment forecasting method are described in detail below. Introduction to the body device architecture.

It should be understood that the embodiments are only for illustrative purposes, and are not limited by this structure in the scope of the patent application.

Example three

Fig. 3 is a structural diagram of a preferred embodiment of the device for forecasting shipments of the present invention.

In some embodiments, the shipment forecasting device 10 runs in a computer device. The computer device is connected to multiple user terminals via the network. The shipment forecasting device 10 may include a plurality of functional modules composed of code segments. The code of each program segment in the shipment forecasting device 10 can be stored in the memory of the computer device and executed by the at least one processor to realize the shipment forecasting function.

In this embodiment, the shipment forecasting device 10 can be divided into multiple functional modules according to the functions it performs. Referring to FIG. 3, the functional modules may include: an acquisition module 101, a prediction module 102, and a calculation module 103. The module referred to in the present invention refers to a series of computer program segments that can be executed by at least one processor and can complete fixed functions, which are stored in the memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.

The obtaining module 101 is used to obtain a material name and at least one material number code corresponding to the material name.

The part number code can be a combination of letters and numbers. The letters and digits in the part number code are used to describe the material of the part number, the installation location, the applied product model, the product brand, the country and region where it is sold, and so on. For example, material number ABC123, where A is the material code of the material, and the material information of the material can be obtained according to the preset material code and the comparison relationship of the material; B is the installation position code of the material, which can be based on the preset material code The comparison relationship between the installation position and the material obtains the installation position of the material; C is the model of the product corresponding to the material number; 1 is the product brand corresponding to the material number; 2 is the sales corresponding to the material number Country; 3 is the sales area corresponding to the part number.

The prediction module 102 is configured to call a material consumption prediction model generated by pre-training, and use the material consumption prediction model to predict that the material corresponding to the at least one item number code is required to produce at least one model of product within a preset time The number of uses.

Wherein, the material consumption prediction model analyzes the characteristic relationship between at least one material number code and the quantity of materials corresponding to the at least one material number code in different models of products in the historical time period, and adopts the characteristic The relationship predicts the amount of use of the material corresponding to the at least one item number code on products of different models within a preset time.

A material number code can be input into the material consumption prediction model to predict the quantity of the material number code required to produce a product of a model within a preset time. It is also possible to input multiple material number codes corresponding to the same material into the material consumption prediction model to predict the quantity of the material number codes required to produce multiple models of products within a preset time. The preset time can be one month, twenty days, etc., and the staff can set it according to the actual situation.

In an embodiment of the present invention, the characteristic relationship between the at least one item number code in the material consumption prediction model and the quantity of materials corresponding to the at least one item number code on different types of products may adopt mathematical statistics. Analyze the method. For example, statistics the usage quantity of any material number code and the material corresponding to the material number code in the historical time period, import the quantity into the prediction model based on statistical algorithm, and the analysis place will preset the material number code in the future The production of at least one type of product within a time requires the use quantity of the material corresponding to the at least one part number code. The statistical algorithm includes any one of a time series model (Time Series Model), a long short-term memory model (LongShort-Term Memory Model), and an implicit Markov model (Hidden Markov Model).

In another embodiment of the present invention, the characteristic relationship between the at least one material number code in the material consumption prediction model and the quantity of materials corresponding to the at least one material number code on different models of products can also be adopted The analysis of the deep learning model of the convolutional neural network shows that the training steps of the material consumption prediction model include: Obtain sample data, and divide the sample data into a training set and a validation set. The sample data includes the shipping time of the shipped product, the item number code of the shipped product, and the corresponding item number code of the shipped product The quantity of materials used, where the shipping time of the shipped product and the item number code corresponding to the shipped product are used as the input data of the material usage prediction model, and the item number code corresponding to the shipped product The used quantity of the corresponding material is used as the output data of the material consumption prediction model; Establishing a deep learning model based on a convolutional neural network, and using the training set to train the deep learning model, and obtaining parameters of the deep learning model; Use the verification set to verify the trained deep learning model, and calculate the accuracy of the deep learning model prediction according to the verification result; Judging whether the prediction accuracy rate of the model is less than a preset threshold; If the model prediction accuracy rate is not less than the preset threshold value, the trained deep learning model is used as the material consumption prediction model.

If the model prediction accuracy rate is less than the preset threshold, adjust the parameters of the deep learning model, and use the training set to retrain the adjusted deep learning model; Use the verification set to verify the retrained deep learning model, re-statistically obtain the model prediction accuracy rate according to each verification result, and determine whether the re-statistical model prediction accuracy rate is less than the preset threshold; If the prediction accuracy rate of the model obtained by re-statistics is not less than the preset threshold, the deep learning model completed by the re-training is used as the material consumption prediction model; If the model prediction accuracy rate obtained by re-statistics is less than the preset threshold, repeat the adjustment of the parameters of the deep learning model, and use the training set to retrain the adjusted deep learning model until it passes The model prediction accuracy rate verified by the verification set is not less than the preset threshold; Wherein, the parameters of the deep learning model based on the convolutional neural network include at least one of the number of convolution kernels, the number of elements in the pooling layer, the number of elements in the fully connected layer, and the connection relationship between different connected layers. A sort of.

In other embodiments of the present invention, the material consumption prediction model may also be a deep learning model based on the naive Bayes algorithm, a deep learning model based on a multi-class support vector machine algorithm, and a deep learning model based on a logistic regression classification algorithm. Any one of learning model and deep learning model based on decision tree classification algorithm.

The calculation module 103 is configured to query the correspondence table of the part number code and the product information according to the usage quantity of the material corresponding to the at least one part number code, and calculate the at least one type of product corresponding to the at least one part number code Shipments.

Wherein, the item number code and product information correspondence table records the item number codes of all materials required to produce each product and the quantity of each material used.

The method of obtaining the corresponding relationship table between the part number code and the product information may include: Obtain the design drawing of the product, obtain the material name, part number code, and material used quantity of the product from the design drawing, and establish the material number code and the material number code according to the material name, material number code, and material used quantity of the product Correspondence table of product information. The item number code of each part of the product and the quantity of the item number code required are recorded in the design drawing of the product.

Obtain the processing parameter information of the product, obtain the consumable information for processing the product, the part number code of the consumable and the used quantity of the consumable from the processing parameter information of the product, according to the consumable information of the product, the part number code of the consumable and The used quantity of consumables establishes the corresponding relationship table between the item number code and the product information. The consumable information may be materials lost during processing, such as grinding wheels, developer solutions, and the like.

In another embodiment of the present invention, the steps of the method for forecasting shipments further include: outputting a list of material numbers required to produce the product according to the shipment volume of the product, wherein the list of material numbers includes materials One or more of the name, item number code, and quantity of materials used. There is a corresponding relationship between the different part number codes of products of the same model. Knowing the shipment volume of the product and the used quantity of the material corresponding to a kind of part number code for the production of the product, according to the corresponding relationship, the production can be calculated The used quantity of materials corresponding to the other part number codes required by the product, and all the material number codes required to produce the product, the material name corresponding to the part number code, and the used quantity corresponding to the material name Output in the form of a data sheet.

In another embodiment of the present invention, the steps of the method for forecasting shipments further include: querying whether the quantity of materials already in the warehouse is greater than the quantity of materials required according to the list of material numbers, wherein the quantity of materials required is the quantity of materials required. The used quantity of the material in the material number list; when the existing material quantity is less than the used quantity of the material in the material number list, a first prompt message is generated. The first prompt message is used to send a first prompt message when the quantity of materials in the current warehouse is insufficient to meet the quantity of materials required to produce the product within a preset time in the future, and the first prompt message is used to remind staff to purchase in time Material. The first prompt message may be output in the form of text, or output in the form of voice.

In yet another embodiment of the present invention, the steps of the method for forecasting shipment volume further include: when the quantity of existing materials in the warehouse is greater than the quantity of required materials, calculating the difference between the quantity of existing materials and the quantity of required materials , And compare the difference with a preset threshold; if it is greater than the threshold, generate a second prompt message of excess inventory. The second prompt message is used to remind the staff that the current inventory of materials is excessive and the purchase plan needs to be rescheduled. The second prompt message may be output in the form of text, or output in the form of voice.

Embodiment four

Fig. 4 is a schematic diagram of a preferred embodiment of the computer device of the present invention.

The computer device 1 includes a memory 20, a processor 30, and a computer program 40 stored in the memory 20 and running on the processor 30, such as a shipment forecast program. When the processor 30 executes the computer program 40, the steps in the embodiment of the method for forecasting shipment volume are implemented, such as steps S1 to S3 shown in FIG. 2. Alternatively, when the processor 30 executes the computer program 40, the functions of the modules/units in the above-mentioned embodiment of the shipment forecasting device are realized, for example, the units 101-103 in FIG. 3.

Exemplarily, the computer program 40 may be divided into one or more modules/units, and the one or more modules/units are stored in the memory 20 and executed by the processor 30 , To complete the present invention. The one or more modules/units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program 40 in the computer device 1. For example, the computer program 40 can be divided into the acquisition module 101, the prediction module 102, and the calculation module 103 in FIG. 3.

The computer device 1 may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a cloud server. Those skilled in the art can understand that the schematic diagram is only an example of the computer device 1 and does not constitute a limitation on the computer device 1. Components, for example, the computer device 1 may also include input and output equipment, network access equipment, busbars, and the like.

The so-called processor 30 may be a central processing unit (Central Processing Unit, CPU), or other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), and dedicated integrated circuits (Application Specific Integrated Circuit, ASIC). , Ready-made programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor 30 can also be any conventional processor, etc. The processor 30 is the control center of the computer device 1 and connects the entire computer device 1 with various interfaces and lines. Various parts.

The memory 20 can be used to store the computer programs 40 and/or modules/units, and the processor 30 can run or execute the computer programs and/or modules/units stored in the memory 20, and The data stored in the memory 20 is called to realize various functions of the computer device 1. The memory 20 may mainly include a storage program area and a storage data area. The storage program area may store an operating system, an application program required by at least one function (such as a sound playback function, an image playback function, etc.), etc.; The area can store data (such as audio data, phone book, etc.) created based on the use of the computer device 1. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), and a secure digital (Secure Digital, SD) card, flash memory card (Flash Card), at least one magnetic disk memory device, flash memory device, or other volatile solid-state memory device.

If the integrated module/unit of the computer device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiments and methods, and can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the foregoing method embodiments can be realized. Wherein, the computer program includes computer program code, and the computer program code may be in the form of original program code, object code, executable file, or some intermediate forms. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, removable hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read- Only Memory), Random Access Memory (RAM, Random Access Memory), electric carrier signal, telecommunications signal, software distribution medium, etc. It should be noted that the content contained in the computer-readable medium can be appropriately added or deleted according to the requirements of the legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to the legislation and patent practice, the computer-readable medium Does not include electrical carrier signals and telecommunication signals.

In the several embodiments provided by the present invention, it should be understood that the disclosed computer device and method can be implemented in other ways. For example, the computer device embodiments described above are only illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation.

In addition, the functional units in the various embodiments of the present invention may be integrated in the same processing unit, or each unit may exist alone physically, or two or more units may be integrated in the same unit. The above-mentioned integrated unit can be realized either in the form of hardware, or in the form of hardware plus software functional modules.

For those skilled in the art, it is obvious that the present invention is not limited to the details of the foregoing exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the scope of the appended invention patent application rather than the above description, so it is intended to fall within The meaning of equivalent elements and all changes within the scope of the patent application for invention are included in the present invention. Any reference signs in the scope of the patent application for invention shall not be regarded as limiting the scope of the patent application for the invention involved. In addition, it is obvious that the word "including" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units or computer devices stated in the scope of the computer device invention patent application can also be implemented by the same unit or computer device through software or hardware. Words such as first and second are used to denote names, but do not denote any specific order.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be Modifications or equivalent replacements are made without departing from the spirit and scope of the technical solution of the present invention.

1: Computer device 2: User terminal 10: Shipment forecasting device 20: memory 30: processor 40: computer program 101: Obtain modules 102: Prediction Module 103: Calculation Module

FIG. 1 is a schematic diagram of an application environment architecture of a method for forecasting shipments provided by Embodiment 1 of the present invention.

Fig. 2 is a flowchart of a method for forecasting shipment volume provided by the second embodiment of the present invention.

FIG. 3 is a schematic diagram of the structure of a shipment forecasting device provided in the third embodiment of the present invention.

Fig. 4 is a schematic diagram of a computer device according to the fourth embodiment of the present invention.

Claims (10)

A method for forecasting shipments, the method for forecasting shipments includes: Obtain the material name and at least one material number code corresponding to the material name; The material consumption prediction model generated by pre-training is called, and the material consumption prediction model is used to predict the usage quantity of the material corresponding to the at least one material number code required to produce at least one model of the product within the preset time, wherein the material The usage prediction model analyzes the characteristic relationship between at least one item number code and the quantity of materials corresponding to the at least one item number code on different types of products in the historical time period, and predicts the at least The quantity of materials corresponding to a material number code on different models of products within a preset time; According to the usage quantity of the material corresponding to the at least one item number code, query the correspondence table of the item number code and the product information, and calculate the shipment volume of the at least one model of the product corresponding to the at least one item number code, wherein the The item number code and product information correspondence table records the item number codes of all materials required to produce each product and the quantity of each material used. The method for forecasting shipment volume according to claim 1, wherein the method further includes: According to the shipment volume of the product, output a list of material numbers required for the production of the product, wherein the list of material numbers includes one or more of the material name, the material number code, and the used quantity of the material. The method for forecasting shipment volume according to claim 2, wherein the method further includes: According to the material number list, query whether the quantity of materials already in the warehouse is greater than the required material quantity, where the required material quantity is the used quantity of the materials in the material number list; When the quantity of existing materials is less than the used quantity of materials in the material number list, a first prompt message is generated. The method for forecasting shipment volume according to claim 3, wherein the method further includes: When the quantity of existing materials in the warehouse is greater than the required quantity of materials, calculating the difference between the quantity of existing materials and the quantity of required materials, and comparing the difference with a preset threshold; If it is greater than the threshold, a second prompt message indicating that the inventory is surplus is generated. The shipment volume forecasting method according to claim 1, wherein the training of the material consumption forecasting model includes: Obtain sample data, and divide the sample data into a training set and a validation set. The sample data includes the shipping time of the shipped product, the item number code of the shipped product, and the corresponding item number code of the shipped product The quantity of materials used, where the shipping time of the shipped product and the item number code corresponding to the shipped product are used as the input data of the material usage prediction model, and the item number code corresponding to the shipped product The used quantity of the corresponding material is used as the output data of the material consumption prediction model; Establishing a deep learning model based on a convolutional neural network, and using the training set to train the deep learning model, and obtaining parameters of the deep learning model; Use the verification set to verify the trained deep learning model, and calculate the accuracy of the deep learning model prediction according to the verification result; Judging whether the prediction accuracy rate of the model is less than a preset threshold; If the model prediction accuracy rate is not less than the preset threshold value, the trained deep learning model is used as the material consumption prediction model. The method for forecasting shipment volume according to claim 5, wherein, after determining whether the prediction accuracy of the model is less than a preset threshold, the method further includes: If the model prediction accuracy rate is less than the preset threshold, adjust the parameters of the deep learning model, and use the training set to retrain the adjusted deep learning model; Use the verification set to verify the retrained deep learning model, re-statistically obtain the model prediction accuracy rate according to each verification result, and determine whether the re-statistical model prediction accuracy rate is less than the preset threshold; If the prediction accuracy rate of the model obtained by re-statistics is not less than the preset threshold, the deep learning model completed by the re-training is used as the material consumption prediction model; If the model prediction accuracy rate obtained by re-statistics is less than the preset threshold, repeat the adjustment of the parameters of the deep learning model, and use the training set to retrain the adjusted deep learning model until it passes The model prediction accuracy rate verified by the verification set is not less than the preset threshold; Wherein, the parameters of the deep learning model based on the convolutional neural network include at least one of the number of convolution kernels, the number of elements in the pooling layer, the number of elements in the fully connected layer, and the connection relationship between different connected layers. A sort of. The method for forecasting shipment volume according to claim 1, wherein the method for establishing the correspondence table of item number codes and product information includes: Obtain the design drawing of the product, obtain the material name, part number code, and material used quantity of the product from the design drawing, and establish the material number code and the material number code according to the material name, material number code, and material used quantity of the product Product information correspondence table; Obtain the processing parameter information of the product, obtain the consumable information for processing the product, the part number code of the consumable and the used quantity of the consumable from the processing parameter information of the product, according to the consumable information of the product, the part number code of the consumable and The used quantity of consumables establishes the corresponding relationship table between the item number code and the product information. A device for forecasting shipments, the device comprising: The obtaining module is used to obtain the material name and at least one material number code corresponding to the material name; The prediction module is used to call the material consumption prediction model generated by pre-training, and use the material consumption prediction model to predict the usage quantity of the material corresponding to the at least one item number code to produce at least one model of the product within a preset time , Wherein the material consumption prediction model analyzes the characteristic relationship between at least one material number code and the quantity of materials corresponding to the at least one material number code in different models of products in the historical time period, and passes the The characteristic relationship predicts the usage quantity of the material corresponding to the at least one material number code on different models of products within a preset time; The calculation module is used to query the correspondence table of the part number code and product information according to the usage quantity of the material corresponding to the at least one part number code, and calculate the shipment of the at least one model product corresponding to the at least one part number code The item number code and product information correspondence table records the item number codes of all materials required to produce each product and the used quantity of each material. A computer device, wherein the computer device includes a processor and a memory, and the processor is used to execute the computer program stored in the memory to realize the shipment volume forecast as described in any one of claims 1 to 7 method. A computer-readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to realize the shipment volume forecasting method as described in any one of claim items 1 to 7.

Images