TW202226088A - Method and system for anticipating delivery time - Google Patents

Abstract

A method and a system for anticipating a delivery time are provided. The system relies on production history data in an enterprise resource planning system, present data about materials and production equipment, and the data learning from the above data through a machine-learning algorithm to anticipate a delivery time. For example, the system can create a prediction model from the machine-learning algorithm for predicting the delivery time. The prediction model provides a weight-setting function that allows a decision maker to change production combination by modifying weights applied to parameters for material planning and schedule planning. Therefore, the system can be used to simulate a decision-making process so as to obtain an appropriate solution of production such as one or more production combinations achieving the delivery time.

Description

Intelligent delivery forecast method and system

The disclosure document discloses a method for predicting the delivery date, especially a method and system for predicting the delivery date based on historical data and production information through intelligent means.

In the product manufacturing process, enterprises need to prepare production lines for raw materials, production equipment and personnel. On the factory side, the delivery rate and production selection greatly affect the internal operation and financial status of the enterprise. If the above-mentioned key factors can be accurately controlled The subject will be able to effectively control the operation of the factory, improve the operation and financial situation. However, the production process of products in the current factory is often caused by many uncontrollable factors and cannot be delivered as expected, and it is impossible to quickly decide how to respond when the production line is changed.

Furthermore, in response to the trend of just in time production technology (Just In Time, JIT) in a small amount of variety, the delivery time for companies to respond to customers is closely related to customer satisfaction. The current industry norm is a relatively short-term (such as 72 hours to 1 week) delivery time. Replies often cause trouble for front-line businesses.

In order to accurately provide the customer delivery date, the disclosure document proposes an intelligent delivery forecasting method and a system for implementing the method. The intelligent delivery forecasting system includes software using computer technology and functional modules implemented with hardware to execute Intelligent delivery forecasting method, which mainly provides data collection means for extracting an enterprise resource planning system (ERP) data in entities (such as companies, factories), uses machine learning algorithms to learn the data obtained by the data collection means, and learns The correlation of various information in the data to form a model training method for predicting the delivery date. When the data collection means receives a production demand data, it can predict the delivery date through the established forecasting model, and realize one or more production combinations on this delivery date, form a decision, and finally provide the company boss with a decision.

Further, the intelligent delivery forecasting system may also include other functional modules, such as a data cleaning method, which is used to clean the data obtained through the enterprise resource planning system, so as to form data in a data format conforming to the learning required by the machine learning algorithm; and It can include an automatic optimization method. When the model training method uses one or more machine learning algorithms to learn data to obtain multiple prediction models, it can select or form a better performance prediction model through the automatic optimization method. It can also include an automatic learning method. When new data is obtained through the data collection method, the model training method can use the machine learning algorithm to learn the new data, so that the subsequent learning of the new data can be used to obtain various kinds of data. Relevance of information optimizes predictive models.

What's more, a weight setting function can be provided in the forecasting model, so that the decision maker of the entity can modify the weights of parameters in the material planning and/or scheduling planning in the production combination to change the production sequence; and, the system further includes a production combination. Selection means, wherein another machine learning algorithm is used to learn the production combinations selected by the decision maker of the entity in the past and to correct the historical data of the weights of the parameters in each production combination to form a production combination selection model, and provide the entity for production reassignment.

Preferably, the data obtained through the enterprise resource planning system is the historical data of the entity's past production combination, the historical data at least includes at least one customer order and at least one factory shipping order, and the machine learning algorithm is used to learn the entity's past through the historical data. production mix, resulting in a forecasting model for predicting delivery dates. Furthermore, the data obtained through the enterprise resource planning system also includes the production data of the factory and the production time of the machines therein. The parameters of the material planning include the inventory of raw materials, components and/or semi-finished products required to produce a product; the parameters of the schedule planning include the delivery ratio and quantity of the products produced according to the date.

For a further understanding of the features and technical content of the present invention, please refer to the following detailed descriptions and drawings of the present invention. However, the drawings provided are only for reference and description, and are not intended to limit the present invention.

The following are specific embodiments to illustrate the embodiments of the present invention, and those skilled in the art can understand the advantages and effects of the present invention from the content disclosed in this specification. The present invention can be implemented or applied through other different specific embodiments, and various details in this specification can also be modified and changed based on different viewpoints and applications without departing from the concept of the present invention. In addition, the drawings of the present invention are merely schematic illustrations, and are not drawn according to the actual size, and are stated in advance. The following embodiments will further describe the related technical contents of the present invention in detail, but the disclosed contents are not intended to limit the protection scope of the present invention.

It should be understood that although terms such as "first", "second" and "third" may be used herein to describe various elements or signals, these elements or signals should not be limited by these terms. These terms are primarily used to distinguish one element from another element, or a signal from another signal. In addition, the term "or", as used herein, should include any one or a combination of more of the associated listed items, as the case may be.

In order to provide enterprises with accurate delivery dates for customers before products are manufactured, the specification discloses an intelligent delivery forecast method and system, in which the machine learning method (or with the deep learning method) is used to learn the production data provided by the enterprise to generate a forecast delivery date Predictive models that simulate corporate decision-making processes. In particular, in the process of simulating enterprise decision-making, the historical data of the enterprise is used, and boundary conditions such as cost can be introduced without affecting the operation of the real factory. Robotic Process Automation (RPA) method is used for many times Simulation, and then use machine learning to optimize the predictive model. Further, when a suitable solution for the final decision is obtained, a suitable safety stock solution can also be reversed.

According to the embodiment of the intelligent delivery forecast method, the main body is a software solution running on a computer system, which includes a multi-objective optimization core system using artificial intelligence (AI), a parameterized production target decision-making system, and a production line. Customized production lines up the simulation system. When the production parameters are given according to customer requirements, the intelligent delivery forecast system can simulate the relationship between equipment, materials, semi-finished products and personnel in each process in the manufacturing process to calculate the completion time of each batch of products. The intelligent delivery forecasting system can be realized by Advanced Planning and Scheduling (APS). The computer system implementing the method also includes an interface to an enterprise resource planning system (Enterprise Resource Planning, ERP), which can obtain data such as finance, personnel, equipment, materials, etc. ) interface to read historical production data, and the intelligent delivery forecast system can actively initiate the execution of commands.

Please refer to the conceptual schematic diagram of the operation of the intelligent delivery forecasting system proposed in the disclosure book shown in FIG. 1 . This figure shows that the intelligent delivery forecasting system takes intelligent means as the core, and can build a model according to the historical data 101 obtained from the enterprise, wherein the proposed system The model 103 includes the delivery model 131 and the capacity model 132, that is to say, through the intelligent delivery forecast system, the delivery date (ie, the delivery date) can be predicted according to the customer demand and the resources of the enterprise, and the capacity and the capacity can also be estimated. Production related parameters.

Under the concept of the operation of the intelligent delivery forecast system, the delivery model 131 obtains an expected delivery date (ie, the number of days 105 ) according to the information provided by the enterprise, and also includes the delivery probability of the delivery date. The production capacity model 132 selects the production combination according to the past historical data, and allows the machine to learn the production combination selected by the decision maker in the past. The relevant production data such as product classification, including existing commodities, existing quantities, quantity changes, similar new products and other information, propose a set of production standards 107 , then according to the batch time in production 109 and the production rule 111 , the decision maker makes a production selection 113 , and finally generates a production selection suggestion 115 .

It is mentioned here that when the system provides the production selection suggestion 115, it can let enterprise decision makers (such as business, boss, etc.) know that the demand for new orders may affect the production of existing orders, and make them predict and produce according to the delivery time. The combination determines the delivery date of the order to be received and the various possibilities of materials and substitutions, and finally allows the decision maker to choose the final solution.

FIG. 2 shows a schematic diagram of the architecture of the intelligent delivery forecasting system.

The figure shows a schematic diagram of the system architecture for realizing the delivery date forecasting system 20 and its surrounding to provide data, one of which is the enterprise resource planning system 24, which is a traditional resource planning computer system commonly used in the enterprise, and connects the management servers of various departments in the enterprise. , unified management and recording of various resources and information, recording data such as sales, production, purchasing inventory and other data at various levels of the enterprise, forming a huge historical production database, these data can be used as the data learned in the intelligent delivery forecast system 20 to form prediction model.

The delivery date prediction system 20 mainly includes an artificial intelligence multi-objective optimization core 21 and a production scheduling simulation system 22 . The artificial intelligence multi-objective optimization core 21 provides a variety of intelligent means, such as one or more intelligent algorithms described by the algorithm module 211, which schematically indicates that there are several modules, such as genetic algorithm A, particle swarm optimization algorithm B and decision tree algorithm C , and the actual operation is not limited by the several algorithms shown in the figure.

The algorithm module 211 represents several intelligent algorithms that can be applied to the system, such as genetic algorithm (GA) A, which is a computer simulation method that can be used in the system to simulate the production schedule and solve the problem. problems in the actual production process.

The algorithm module 211 proposes a particle swarm optimization (Particle Swarm Optimization, PSO) algorithm B, and the particle swarm optimization algorithm B is used in the delivery prediction system 20 to obtain the best solution for decision-making according to historical data, especially for production The optimization problem when purchasing raw materials simulates the best solution.

The algorithm module 211 may include a decision tree algorithm (RF, XGB) C. The decision tree algorithm C is a machine learning algorithm, which uses classification and regression methods to sample and randomly select features in the data, and after the data features are obtained. , which can simulate the results of decision-making, in order to generate a variety of decision-making directions for decision-makers.

After one or more intelligent algorithms in the algorithm module 211 perform machine learning calculations and modeling on the data provided by the enterprise resource planning system 24, scheduling parameters, material and personnel planning parameters, and various delivery schedule combinations can be provided to the intelligent delivery schedule. The production scheduling simulation system 22 in the forecasting system 20 . The production scheduling simulation system 22 is also added from the manufacturing execution system 27 for collecting real-time information on the process and receiving data on the actual production line. The production scheduling simulation system 22 also obtains data such as the production equipment 251 , the materials 252 , and the products 253 in the production system 25 .

In this way, the production scheduling simulation system 22 can calculate the production-related schedule, raw materials, delivery schedule, actual historical production data, and actual data on the production line based on the historical data, and the data generated by the production scheduling simulation system 22 It can feed back to the artificial intelligence multi-objective optimization core 21, provide multi-configuration results to provide the prediction model established in the optimization, and provide the decision-making system through the prediction model 23 Multiple sets of product order delivery, production cost and batch production options and other multiple solutions , the final decision is made by the decision-making system 23 , including the delivery date provided to the business end 29 to the customer, and the resources and production instructions required by the manufacturing execution system 27 for production to carry out production. When the decision-making system 23 makes the final judgment on the delivery date, it can also retrospectively provide the best solution for the inventory that the enterprise should have.

Through the intelligent delivery forecasting system 20, the decision makers of the enterprise can obtain the delivery date and production information obtained by simulation. One of the main purposes is to provide the business end 29 with a fast and relatively accurate response to the expected delivery date of the customer, and according to the established The forecasting model extends to the production mix selection model, which can help factory managers to quickly judge how to plan production and estimate the possibility of cost changes under multiple selections.

FIG. 3 shows various functional means of the intelligent delivery forecasting system 20 implemented by means of a computer system and software in the intelligent delivery forecasting system, and various functional means are described by the functional modules shown in the figure.

The main intelligent means in the intelligent delivery forecasting system 20 include a data collection module 301, and the way of realizing data collection is, for example, a computer system obtains the internal data of an entity (such as a company, a factory) through a network or a specific connection through wired or wireless communication. Data, such as data provided by an enterprise resource planning system (ERP), the data is mainly the historical data of the entity's past production combination, and can also include the production data of the factory and the production time of the machines therein, which can then be established in the intelligent delivery forecast system 20. For the customized database of this enterprise, the model training module 307 uses a machine learning algorithm to learn the collected data, encodes the data, and allows the machine learning algorithm to find association rules according to the provided data, and learn the data in the data. The correlation of various information can finally form a prediction model for predicting the delivery date. Wherein, when the data of production demand is received by the communication means of the above-mentioned data collection module 301, the delivery date can be predicted through the prediction model, and one or more production combinations of the delivery date can be realized, so as to provide enterprise decision makers with decision making.

According to the embodiment of the intelligent delivery forecasting system 20, it may also include other data processing and learning software and functional modules implemented by hardware, such as a data cleaning module 303. The implemented data cleaning means is used to clean the data through the enterprise resource planning system. The obtained data is used to form data in the data format required by the machine learning algorithm, so that subsequent methods can use this format as the data for model training.

The intelligent delivery forecasting system 20 may also include an automatic optimization module 309. When the model training module 307 learns data through one or more machine learning algorithms to obtain multiple prediction models, the automatic optimization module 309 can realize the The software compares various models with each other, and selects or composes a better-performing forecasting model as the forecasting model for predicting the delivery date.

When new data is obtained through the above-mentioned data collection module 301, the system uses the automatic learning module 305 to learn the new data with the machine learning algorithm for the model training module 307, and automatically extracts new production processes and learns new data. , especially based on learning new data, the correlation of various information can be obtained, and fine-tuning can be performed to optimize the prediction model.

The intelligent delivery forecasting system 20 may further be provided with a production combination selection module 311, which is to use another machine learning algorithm to learn the production combination selection software after the intelligent delivery forecasting system 20 obtains the predicted delivery date. Describe the production combinations selected by the entity's decision-makers in the past and correct the historical data of the weights of the parameters in each production combination, and then form a production combination selection model to provide the entity with a production reclassification. According to an embodiment, the formed production combination selection model is used to propose a proposed combination of physical part delivery or diversion of materials to form a new production combination of new material planning and/or new scheduling planning.

According to a situational application that the intelligent delivery prediction system 20 can be applied to. When an enterprise is carrying out production, the business personnel need to reply to the expected delivery date of the customer's batch when the factory places an order. However, it is often the case that the business personnel need to communicate with the production line personnel and material management personnel to confirm the current factory production capacity, and give them according to experience. There is a pre-delivery date, but this pre-delivery date is often much different from the actual delivery date. Therefore, the intelligent delivery forecast system 20 proposed in the disclosure book adopts the intelligent means of the above-mentioned functional modules, obtains historical data from enterprises, such as customer orders, factory shipping orders, etc., and then uses machine learning algorithms to learn the data. A forecasting model is developed to make delivery forecasts for existing products. Since this prediction model refers to the past data, it can handle the situation of new products or a small number of products lacking complete information in the future through intelligent means. Time, machine capacity and parameters, running time between processes, etc., and learn the delivery time and production combination that meet the needs of the enterprise.

Next, FIG. 4 shows a flow chart of an embodiment of the intelligent delivery date prediction method, wherein the action description can refer to FIG. 3 .

The intelligent delivery forecast method is implemented in a computer system, and various learning algorithms are implemented through the processing circuit, memory, and database in the computer system. The process includes, at the beginning, the computer system obtains the enterprise resource planning through internal or external network. The data of the system at least includes at least one customer order and at least one factory shipping order (step S401 ), and the data is cleaned by means of software, mainly cleaning the data obtained through the enterprise resource planning system, so as to form a machine learning algorithm for learning The data in the required data format can also filter unnecessary, invalid or performance-impacting data (step S403 ), and then start to use the machine learning algorithm to learn the information correlation in the data (step S405 ) to form a prediction model ( Step S407). Wherein, if multiple prediction models are obtained by learning data through one or more machine learning algorithms, the computer system can also be used to select or compose a prediction model with better performance as a prediction model for predicting the delivery date. Afterwards, according to an embodiment, if new data is generated, the machine learning algorithm can continue to learn the new data, and the correlation of various information in the new data can be obtained according to the learned new data, and fed back to the system to optimize the prediction model.

After the prediction model is completed, the production data is received (step S409 ). For example, the business end receives data such as customer orders, product items, unit quantity, and expected delivery date of the order, and can accept multiple orders at the same time. The details include the data of the materials, processes, semi-finished products and finished products required for the manufacture of each product item, which can also be derived from the Enterprise Resource Planning System (ERP) and Manufacturing Execution System (MES).

Then the weights can be set (step S411 ). The forecast model provides a weight setting function, which is to provide decision makers to adjust production parameters. In this step, the decision makers of the entity can be allowed to revise the material planning and/or scheduling planning in the production combination. The weights of the parameters change the production order. For example, if this customer is more important than other customers, or if this semi-finished product is a critical component of many other products, parameters not yet considered by the system can be weighted to increase their priority.

Finally, the delivery date, production combination, etc. are obtained through the prediction model (step S413), wherein each production combination can record material planning and scheduling planning, and/or machine production time, and the parameters of material planning can include production-a Inventory of raw materials, components, and/or semi-finished products required for a product, and parameters for scheduling can include delivery ratios and quantities to produce the product by date. In one embodiment, another machine learning algorithm can also be used to learn the production combinations selected by the decision maker of the entity in the past, and to correct the historical data of the weights of the parameters in each production combination, so as to form a production combination selection model. , providing the entity to perform a production redistribution.

For example, taking aluminum forging as an example, forging is divided into two or more processes such as rough forging and precision forging. The forging equipment used in rough forging and precision forging is different, and some equipment can also be used in different processes. The raw material for forging is aluminum. There are also molds that can be reused many times. The forged semi-finished products are rough forged blanks, and the finished products are aluminum forgings formed by precision forging. , data such as finished products, scraps, and mass production yields, as well as statistical data on their dependence on different equipment, are imported from the above-mentioned data sources. If the forecast target is the item that has been executed by the system, the same The historical data of the item is directly brought in, and the final complete production model data is confirmed by the engineering and production management personnel.

FIG. 5 shows a flow chart of another embodiment of the intelligent delivery forecast method, which expresses the processing flow of the proposed intelligent delivery forecast system for existing products and new products. The first part is aimed at the existing products of the enterprise. In the method, the existing product information is obtained first (step S501 ), and data processing is performed, including data cleaning and filtering, in order to obtain modelable data (step S503 ), and then the machine The learning algorithm learns the features and correlations of the data (step S505 ), and establishes a prediction model (step S507 ). On the other hand, for new products, new product information is obtained (step S509 ), including the introduction of data such as feeding time, machine parameters and production time, and process steps (step S511 ). Similarly, through data processing, a modelable model is obtained. After the data is collected (step S513 ), a machine learning algorithm is used to learn the features and correlations in the new data (step S515 ) to establish a prediction model (step S517 ).

It is mentioned here that, for new products, this part often lacks the complete content provided by the enterprise resource planning system, so the data of similar raw materials, machine equipment, and similar process engineering methods can be used as the relevant learning target. , After the data is cleaned, a prediction model can be established for each project and unified into a prediction model.

It can be seen that the system has formed prediction models for both existing products and new products, and can obtain multiple prediction models through multiple machine learning algorithms. In step S519, the system can continue to use the model algorithms to obtain their respective results. , and then select one of the prediction models (step S521 ). The prediction model is used to generate the due date (step S525 ). Similarly, the newly generated data will continue to automatically optimize the model (step S523 ).

The system architecture for realizing the above method flow can continue to refer to the schematic diagram of the architecture example of the delivery model and the capacity model for realizing the intelligent delivery forecast method shown in FIG. The department shows a delivery model structure 61, which is concerned with time data 611, and obtains order information 612, sales information 613 and other information 614 such as other related personnel in the enterprise according to the customer demand obtained by the enterprise resource planning system, and performs data cleaning. 615, and subsequent steps of modeling, training 616, etc., resulting in a prediction model 617 that provides delivery time.

On the other hand, the production capacity model architecture 62 described in the next half, the production capacity includes the lead time 621 that is not easy to change and the parameter model 622 required for production. Similarly, data cleaning (623, 624), modeling, and training (625, 626) and other steps to establish a pre-processing model 627 for pre-processing and a parameter model 628 for processing production parameters, thus starting material planning and scheduling 629, and importing the above-mentioned forecast model to generate delivery time 630.

FIG. 7 then schematically shows the details of processing new and old product data in the intelligent delivery forecast method and an embodiment of how to establish data and optimize models through feedback.

According to the figure, for the existing product 71, the enterprise resource planning system (ERP) provides the factory data 711, including the delivery note 712 and the order 713, after data cleaning, the modelable data 714 is obtained, and the learning and Training is used to build a model 715, and the prediction model is used to predict the delivery date 716 until the system obtains the actual delivery date 717. The predicted delivery date and the actual delivery date formed by this part can be fed back to the enterprise resource planning system and become the existing Part of factory data 711 in product 71.

For the new product 72, the product data 721 is obtained after the customer has specified specifications, and it also includes various in-plant data 722 required for production, such as the machine 723, the incoming and outgoing materials 724, and the process 725, etc. After data cleaning, it is obtained. Data can be modeled (726, 727, 728), then machine learning algorithms are used to learn the data of each project, and models for each project (729, 730, 731) can be built. Establish an integrated model 732, which can propose a new product delivery forecast 733 for new products. When the real delivery date 734 is obtained, the generated new product delivery forecast 733 and the real delivery date 734 will form the new product data in the system, which is also the future optimization model. in accordance with.

Finally, the delivery date predicted by the system will also be compared with the actual delivery date. For related procedures, please refer to the embodiment diagram of using enterprise data in the intelligent delivery date prediction method shown in FIG. 8 .

The figure shows that the order data that the intelligent delivery date prediction system can obtain from the enterprise resource planning system 80 includes an order with an accurate pre-delivery date 801, a shipper with an accurate pre-delivery date 802, an order with an inaccurate pre-delivery date 803, and the pre-delivery date. For inaccurate shipping orders 804, the accurate and inaccurate data on the pre-delivery date will be evaluated separately, and the modelable data (805, 807) will be obtained respectively, and the prediction model 806 will be established. The delivery date 808 is used as the basis for confirming the model 809 .

According to the above embodiment, the intelligent delivery forecast system adopts the data provided by the artificial intelligence multi-objective optimization core (refer to Fig. 2, 21) to provide the production scheduling simulation system (refer to Fig. 2, 22) to construct a production model , the production model considers the collaborative work of the production line to produce multiple items and batches at the same time, the allocation and use of equipment and raw materials, the priority of each item batch using limited equipment resources, and the split or merge of production orders, Financial planning such as time and cost of raw material acquisition are all adjustable parameters for multi-objective optimization.

For example, in the process of aluminum forging, the preheating and pressure forging time required for different workpieces may be different. At the same time, factors such as the proficiency of the operator and the yield rate of each process equipment need to be considered. Through the above The process parameters and historical data generated by the process can be used to obtain statistical models of process time consumption and materials. According to the embodiment, the Worst Case, Typical Case, Best Case (Worst Case, Typical Case, Best Case) analysis of the statistical model is adopted, or the more complete statistical sampling is adopted, and the Monte Carlo method (MC) can be used for simulation in parallel. .

The model constructed by the multi-objective optimization core can generate multiple sets of adjustable production parameters, which can be brought into the production scheduling simulation system for simulation, and a large number of parameters can be simulated simultaneously by parallel computing methods to obtain optimal solutions for delivery and finance. . Related artificial intelligence machine learning algorithms, such as the genetic algorithm (GA), particle swarm algorithm (PSO) and decision tree algorithm (RF, GB, XGB) mentioned in Figure 2, can be used in high-dimensional wide-area parameter space. It iterates continuously in the middle, and accurately converges to the best parameter combination with extremely high efficiency.

The intelligent delivery date prediction system finally predicts that the delivery date will be closer and closer to the real delivery date after updating the model, so that the delivery date provided by the intelligent delivery date prediction system can become the accurate basis for the business side and the customer to negotiate the order delivery date. , At the same time, the obtained production parameters can be confirmed by engineering and production management personnel. Based on the interface between the intelligent delivery forecast system, the enterprise resource planning system and the manufacturing execution system, it is possible to directly order raw materials and execute production orders. Make sure that the delivery date of the final completed order is in line with the delivery schedule of the forecast plan.

To sum up, the above embodiment describes an intelligent delivery date prediction method and system. The proposed intelligent delivery date prediction system first obtains the data provided by the enterprise, such as the historical data of past production and the related data of current materials and production equipment. It uses intelligent means to learn data to form a forecast model for predicting the delivery date, thereby simulating the decision-making process, and providing suitable solutions for the enterprise, and finally the decision makers make production planning and delivery judgments. In this way, the method can provide decision makers and management strata of the enterprise to answer customer orders when the production capacity is tight, without considering the short-term labor and the increase of machinery and equipment, the decision-making priority, and provide the most suitable for the replacement orders and substitute materials. solution.

The contents disclosed above are only preferred feasible embodiments of the present invention, and are not intended to limit the scope of the present invention. Therefore, any equivalent technical changes made by using the contents of the description and drawings of the present invention are included in the application of the present invention. within the scope of the patent.

101: Historical data 103: System Models 131: Delivery Model 132: Capacity Model 105: days 107: Standard 109: Batch time 111: Production Rules 113: Production Options 115: Production Selection Recommendations 24: Enterprise Resource Planning Systems 20: Delivery Prediction System 21: AI multi-objective optimization core 211: Algorithm Module A: Genetic algorithm B: Particle Swarm Optimization Algorithm C: decision tree algorithm 22: Production scheduling simulation system 23: Decision System 25: Production System 251: Production Equipment 252:Material 253: Products 27: Manufacturing Execution Systems 29: Business side 301: Data Collection Module 303: Data cleaning module 305: Automatic Learning Module 307: Model training module 309: Automatic optimization module 311: Production combination selection module 61: Delivery Model Architecture 611: Time data 612: Order Information 613: Sales information 614: Other information 615: Data Cleaning 616: Modeling, training 617: Delivery Time Prediction Model 62: Capacity Model Architecture 621: lead time 622: Parametric Model 623,624: Data Cleaning 625, 626: Modeling, Training 627: Front Model 628: Parametric Model 629: Planning Materials and Scheduling 630: Delivery time 71: Existing Products 711: Factory Data 712: Shipper 713: Order 714: Modelable data 715: Modeling 716: Delivery Forecast 717: Real delivery date 72: New Products 721: Product Data 722: In-plant data 723: Machine 724: Loading and unloading 725: Process 726, 727, 728: Modelable data 729, 730, 731: Modeling 732: Build an integrated model 733: New Product Delivery Forecast 734: Real Delivery Date 80: Enterprise Resource Planning System 801: Order with accurate pre-delivery date 802: Shipper with accurate pre-delivery date 803: Order with inaccurate pre-delivery date 804: Shipper with inaccurate pre-delivery date 805, 807: Modelable data 806: Build predictive models 808: Real Delivery Date 809: Confirm model Steps S401-S413: One of the embodiments of intelligent delivery forecasting process Steps S501-S525: the second embodiment of the intelligent delivery forecasting process

Figure 1 shows a conceptual schematic diagram of the operation of the intelligent delivery forecasting system;

Fig. 2 shows the structure embodiment diagram of the intelligent delivery forecast system;

Fig. 3 shows the functional module embodiment diagram of the intelligent delivery forecast system;

FIG. 4 shows a flow chart of one embodiment of the intelligent delivery forecast method;

Fig. 5 shows the flow chart of the second embodiment of the intelligent delivery forecast method;

FIG. 6 shows a schematic diagram of an embodiment of the architecture of the delivery model and the capacity model for realizing the intelligent delivery forecast method;

FIG. 7 shows a schematic diagram of an embodiment of processing product data in an intelligent delivery forecast method; and

FIG. 8 shows an embodiment diagram of using enterprise data in the intelligent delivery forecast method.

101: Historical data

103: System Models

131: Delivery Model

132: Capacity Model

105: days

107: Standard

109: Batch time

111: Production Rules

113: Production Options

115: Production Selection Recommendations

Claims (20)

An intelligent delivery forecast system, comprising: a data collection means to extract data from an enterprise resource planning system within an entity; and a model training method, using a machine learning algorithm to learn the data obtained by the data collection method, and to learn the correlation of various information in the data, so as to form a prediction model for predicting a delivery date; Wherein, when the data collection means receives data of a production demand, the delivery date is predicted by the prediction model, and one or more production combinations of the delivery date are realized. The intelligent delivery forecasting system according to claim 1, further comprising a data cleaning means for cleaning the data obtained through the enterprise resource planning system to form data in a data format required by the machine learning algorithm for learning . The intelligent delivery forecasting system according to claim 1, further comprising an automatic optimization means, when the model training means learns data through one or more machine learning algorithms to obtain multiple prediction models, the automatic optimization means Select or compose a forecasting model with better performance as the forecasting model for predicting the delivery date. The intelligent delivery date prediction system according to claim 1, further comprising an automatic learning means, when new data is obtained through the data collection means, the model training means is made to learn the new data with the machine learning algorithm, The predictive model is optimized based on learning the new data to derive correlations of various information therein. The intelligent delivery forecasting system according to claim 1, wherein the data obtained through the enterprise resource planning system is the historical data of the entity's past production combinations, and the historical data at least includes at least one customer order and at least one factory shipping order, The machine learning algorithm learns the past production mix of the entity through the historical data, and derives the predictive model that predicts the delivery date. The intelligent delivery forecast system according to claim 5, wherein the data obtained through the enterprise resource planning system further includes the production data of the factory and the production time of the machines therein. The intelligent delivery forecasting system according to any one of claims 1 to 6, wherein each production combination records material planning, scheduling planning, and/or machine production time. The intelligent delivery forecasting system according to claim 7, wherein the parameters of the material planning include the inventory of raw materials, components and/or semi-finished products required to produce a product; the parameters of the schedule planning include the production of the product according to the date. Delivery ratio and quantity. The intelligent delivery forecasting system as claimed in claim 8, wherein a weight setting function is provided in the forecasting model, allowing the decision maker of the entity to modify the weights of the parameters in the material planning and/or the scheduling planning in the production combination Change the production order. The intelligent delivery forecasting system as claimed in claim 9, further comprising a production combination selection means, wherein another machine learning algorithm is used to learn the production combinations selected by the decision maker of the entity in the past and to modify the parameters in each production combination. The historical data of the weights form a production mix selection model that provides the entity for a production reclassification. The intelligent delivery forecasting system as claimed in claim 10, wherein the production combination selection model is used to propose the proposed combination of the physical partial delivery or the diversion of materials to form a new material plan and/or a new schedule Planning a new production mix. An intelligent delivery date prediction method, executed in a computer system, includes: Connect an enterprise resource planning system in an entity through the computer system, and extract the data of the enterprise resource planning system; executing a machine learning algorithm to learn the correlation of various information in the data to form a predictive model for predicting a delivery date; and A production demand data is received, the delivery date is predicted by the forecasting model, and one or more production combinations that achieve the delivery date. The intelligent delivery date forecasting method according to claim 12, wherein the data obtained through the enterprise resource planning system is further cleaned to form data in a data format required by the machine learning algorithm for learning. The intelligent delivery forecasting method as claimed in claim 12, wherein when a plurality of forecasting models are obtained by learning data through one or more machine learning algorithms, the computer system is used to select or compose a forecast with better performance by itself model, as the forecast model for predicting the delivery date. The intelligent delivery date prediction method according to claim 12, wherein when new data is obtained, the machine learning algorithm is used to learn the new data, and the relevance of various information therein is obtained according to the learning of the new data to optimize the prediction model. The intelligent delivery forecast method according to claim 12, wherein the data obtained through the enterprise resource planning system is historical data of past production combinations of the entity, and the historical data at least includes at least one customer order and at least one factory shipping order, The machine learning algorithm learns the past production mix of the entity through the historical data, and derives the predictive model that predicts the delivery date. The intelligent delivery forecast method according to any one of claims 12 to 16, wherein each production combination records material planning and scheduling planning, and/or machine production time. The intelligent delivery forecast method according to claim 17, wherein the parameters of the material planning include the inventory of raw materials, components and/or semi-finished products required to produce a product; the parameters of the schedule planning include the production of the product according to the date. Delivery ratio and quantity. The intelligent delivery forecast method as claimed in claim 18, wherein a weight setting function is provided in the forecast model to allow the decision maker of the entity to modify the weights of the parameters in the material planning and/or the scheduling planning in the production combination Change the production order. The intelligent delivery forecasting method as claimed in claim 19, wherein another machine learning algorithm is used to learn the production combinations selected by the decision maker of the entity in the past and to correct the historical data of the weights of parameters in each production combination to form a production combination Select the model to provide this entity for a production redraw.

Images