Production scheduling plan generation method and device, computer equipment and storage medium

Abstract

The embodiment of the invention belongs to the technical field of artificial intelligence and natural language processing, and relates to a production scheduling plan generation method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining order interaction data; constructing order data according to the order interaction data; obtaining standard man-hour index data and standard algorithm factor data; constructing model parameter data according to the standard man-hour index data and the standard algorithm factor data; calling a production scheduling plan and a control algorithm model, and inputting the model parameter data into the production scheduling plan and the control algorithm model for time sequence prediction operation to obtain target production data; and writing the target production data into a database to form a target production scheduling plan. According to the method, the production scheduling process can be simplified, the self-adaptive capability is enhanced, the system expandability is improved, and the continuous optimization capability is improved.

Description

Technical Field

[0001] The present application relates to the technical field of artificial intelligence and natural language processing, and in particular to a method, apparatus, computer equipment and storage medium for generating a production schedule. Background Art

[0002] With the rapid development of artificial intelligence technology, the production process of the metal processing industry has become more intelligent through the application of artificial intelligence technology. Using machine learning, deep learning and other algorithms, production data can be analyzed in real time, production processes can be optimized, and production efficiency can be improved. However, the existing production order scheduling in the metal processing industry usually has the following problems:

[0003] 1. Changes in standard working hours on production lines lead to lower production line utilization

[0004] 2. Changes in production scheduling lead to reduced production efficiency

[0005] 3. Temporary changes in order duration, especially changes in orders close to the delivery date, lead to unbalanced production line load

[0006] These problems directly lead to low production line utilization and production efficiency in the production scheduling of metal processing industry orders, unbalanced production line load, and the phenomenon of "over-busy" and "over-idle" production lines. Summary of the invention

[0007] The purpose of the embodiments of the present application is to propose a production schedule generation method, device, computer equipment and storage medium, which generates a production schedule by continuously adjusting standard working hours and algorithm factors and provides capacity utilization, production balance rate and punctuality rate, thereby improving continuous optimization capabilities.

[0008] In order to solve the above technical problems, the embodiment of the present application provides a method for generating a production schedule, which adopts the following technical solution:

[0009] Get order interaction data;

[0010] Constructing order data according to the order interaction data;

[0011] Obtain standard working hours index data and standard algorithm factor data;

[0012] Constructing model parameter data according to the standard working time index data and the standard algorithm factor data;

[0013] Calling a production scheduling and control algorithm model, and inputting the model parameter data into the production scheduling and control algorithm model to perform a time series forecasting operation to obtain target production data;

[0014] The target production data is written into a database to form a target production schedule.

[0015] Furthermore, after the step of writing the target production data into the database to form a target production schedule, the following steps are also included:

[0016] Acquire real-time production data obtained from the production process according to the target production schedule;

[0017] Performing a dynamic working time adjustment operation on the standard working time index data according to the real-time production data and the manufacturing capability algorithm model to obtain dynamic working time index data;

[0018] Performing a factor dynamic adjustment operation on the standard algorithm factor data according to the real-time production data and the manufacturing capability algorithm model to obtain dynamic algorithm factor data;

[0019] Constructing dynamic model parameter data according to the dynamic working time index data and the dynamic algorithm factor data;

[0020] Inputting the dynamic model parameter data into the production scheduling and control algorithm model to obtain dynamic production data;

[0021] The dynamic production data is written into the database to update the target production schedule.

[0022] Furthermore, after the step of writing the target production data into the database to form a target production schedule, the following steps are also included:

[0023] extracting actual production data sets from the database;

[0024] Generate a visualization analysis report based on the actual production data set, and output the visualization analysis report;

[0025] Receiving parameter adjustment data sent by a user terminal;

[0026] The standard working time index data and the standard algorithm factor data are adjusted according to the parameter adjustment data.

[0027] Further, the target production data is expressed as:

[0028] y t =T(t)+S(t)+E(t)+F(t)+A(t)+L(t)

[0029] Among them, T(t) represents the trend at time t; S(t) represents the seasonal effect at time t; E(t) represents the event and holiday effect at time t; F(t) represents the regression effect of future known exogenous variables at time t; A(t) represents the autoregressive effect at time t based on past observations; L(t) represents the regression effect of lagged observations of exogenous variables at time t.

[0030] Furthermore, the trend T(t) at time t is expressed as:

[0031] T(t)=(δ0+Γ(t) T δ)·t+(ρ0+Γ(t) T ρ)

[0032] Where δ0 represents the growth rate of the first segment, δ(t) represents the trend growth rate at time t, ρ0 represents the offset of the first segment, and ρ(t) represents the offset at time t;

[0033] The seasonal effect S(t) at time t is expressed as:

[0034]

[0035] Where k represents the number of Fouriers; p represents periodicity;

[0036] The regression effect F(t) of the future known exogenous variable at time t is expressed as:

[0037]

[0038] Among them, F f (t) = d f f(t);

[0039]

[0040] The autoregressive effect A(t) based on past observations at time t is expressed as:

[0041] A t (t),A t (t+1),...,A t (t+h-1)=AR-Net(y t-1 ,y t-2 ,...,y t-p )

[0042] Among them, y represents the input data, h represents the step size;

[0043] The regression effect L(t) of the lagged observation of the exogenous variable at time t is expressed as:

[0044]

[0045] Here, x represents the historical covariate.

[0046] In order to solve the above technical problems, the embodiment of the present application further provides a production scheduling plan generation device, which adopts the following technical solution:

[0047] An interactive data acquisition module, used to acquire order interaction data;

[0048] An order data construction module, used to construct order data according to the order interaction data;

[0049] Standard data acquisition module, used to obtain standard working time index data and standard algorithm factor data;

[0050] A model parameter construction module, used to construct model parameter data according to the dynamic working hour index data and the dynamic algorithm factor data;

[0051] A target production data acquisition module is used to call the production scheduling and control algorithm model, and input the model parameter data into the production scheduling and control algorithm model to perform time series prediction operations to obtain target production data;

[0052] The target production schedule acquisition module is used to write the target production data into the database to form a target production schedule.

[0053] Furthermore, the device also includes:

[0054] A real-time data acquisition module, used to acquire real-time production data obtained during the production process according to the target production scheduling plan;

[0055] A working time dynamic adjustment module is used to perform a working time dynamic adjustment operation on the standard working time index data according to the real-time production data and the manufacturing capability algorithm model to obtain dynamic working time index data;

[0056] A factor dynamic adjustment module, used for performing a factor dynamic adjustment operation on the standard algorithm factor data according to the real-time production data and the manufacturing capability algorithm model to obtain dynamic algorithm factor data;

[0057] A dynamic model parameter construction module, used to construct dynamic model parameter data according to the dynamic working hour index data and the dynamic algorithm factor data;

[0058] A dynamic production data acquisition module, used to input the dynamic model parameter data into the production scheduling and control algorithm model to obtain dynamic production data;

[0059] The target production schedule updating module is used to write the dynamic production data into the database to update the target production schedule.

[0060] Furthermore, the device also includes:

[0061] An actual production data acquisition module, used to extract an actual production data set from the database;

[0062] An analysis report generation module, used to generate a visual analysis report based on the actual production data set and output the visual analysis report;

[0063] A parameter adjustment data acquisition module, used to receive parameter adjustment data sent by a user terminal;

[0064] The adjustment operation module is used to perform adjustment operations on the standard working time index data and the standard algorithm factor data according to the parameter adjustment data.

[0065] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0066] It includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the production scheduling plan generation method as described above when executing the computer-readable instructions.

[0067] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0068] The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps of the production scheduling plan generation method described above are implemented.

[0069] The present application provides a method for generating a production schedule, including: obtaining order interaction data; constructing order data according to the order interaction data; obtaining standard working time index data and standard algorithm factor data; constructing model parameter data according to the standard working time index data and the standard algorithm factor data; calling the production schedule and control algorithm model, and inputting the model parameter data into the production schedule and control algorithm model for time series prediction operation to obtain target production data; writing the target production data into the database to form a target production schedule. Compared with the prior art, the present application dynamically and quickly generates production schedules and analysis reports based on order data, standard working hours, and algorithm factors using AI algorithm models, provides generation efficiency, and simplifies the production schedule process; can quickly update new AI algorithm tokens according to changes in order data, standard working hours, algorithm factors, etc., and strengthen adaptive capabilities; modular design makes the system easy to expand, supports real-time updates of algorithm factors, standard working hours, and order data, and rapid integration of multiple AI algorithm models, and improves system scalability; generates production schedules by continuously adjusting standard working hours and algorithm factors and provides capacity utilization, production balance rate, and punctuality, thereby improving continuous optimization capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0071] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0072] Figure 2 It is a flowchart of the implementation of the production scheduling plan generation method provided in the embodiment of the present application;

[0073] Figure 3 It is a structural schematic diagram of a production scheduling plan generating device provided in an embodiment of the present application;

[0074] Figure 4 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0075] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0076] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0077] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0078] like Figure 1As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0079] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0080] The terminal device 101 can be any electronic device with a display screen and supporting web browsing. In addition to the laptop computer 1011, tablet computer 1012 or mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer, a desktop computer, etc.

[0081] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0082] It should be noted that the production schedule generation method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the production schedule generation device is generally arranged in the server / terminal device.

[0083] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0084] Continue to refer Figure 2 , shows a flow chart of an embodiment of a method for generating a production schedule according to the present application. The method for generating a production schedule includes: step S201, step S202, step S203, step S204, step S205 and step S206.

[0085] In step S201, order interaction data is obtained.

[0086] In an embodiment of the present application, the present application includes an order maintenance module, wherein the order maintenance module maintains order information through operations such as adding, importing, editing, and deleting. The present application captures interactive data such as product model, quantity, delivery date, and customer in the order in the system in real time from the order information.

[0087] In step S202, order data is constructed according to the order interaction data.

[0088] In an embodiment of the present application, an order-based calculation data set is constructed from the captured data, mainly including order number, overseas order number, download date, download date after one lock, production company, product name, customer code, order quantity, salesperson, product model, one lock date, main planning period, order type, order status, and production workshop to form a calculation data set.

[0089] In step S203, standard man-hour index data and standard algorithm factor data are obtained.

[0090] In the embodiment of the present application, standard working time management mainly maintains the standard working time indicator data set (the indicator data mainly includes company name, product model, product name, production line number, production line name, number of people, standard working hours, and production capacity) through operations such as adding, importing, editing, and deleting.

[0091] In the embodiment of the present application, algorithm factor management is mainly carried out to maintain algorithm factors through operations such as adding, importing, and editing (algorithm factors mainly include one lock day (one lock day refers to the number of days that the order will be locked and cannot be changed after scheduling, and the order information can only be changed after unlocking or reaching the first lock day), two lock days (two lock days refer to the number of days that the order will be automatically locked for the second time after the order is scheduled and has exceeded the first lock day. After locking, the order cannot be changed. It also needs to be unlocked or reached The second lock day can change the order information), customers who may not comply with the two lock regulations, orders that may not comply with the two lock regulations, key customers and corresponding production lines, production can be scheduled according to the floating quantity of the standard production line, days for early delivery, daily plan lock days, and factory calendar).

[0092] In step S204, model parameter data is constructed according to the standard man-hour index data and the standard algorithm factor data.

[0093] In step S205, the production scheduling and control algorithm model is called, and the model parameter data is input into the production scheduling and control algorithm model to perform time series prediction operations to obtain target production data.

[0094] In the embodiment of the present application, the AI ​​algorithm model execution engine: integrates multiple AI algorithm models to improve the recognition accuracy and calculation speed of the algorithm, reduce the consumption of computing resources, and expand the application scenarios. This invention has trained and integrated three algorithm models, namely, the AI ​​manufacturing capability algorithm model (the model adopts the K-means clustering [K-MeansClustering] in the clustering model: divides the data points into K categories and hierarchical clustering: based on the tree structure, gradually merges or divides the data set; the model is mainly obtained by training based on historical production result data), the AI ​​material supply algorithm model (the model adopts the hierarchical clustering in the clustering model: based on the tree structure, gradually merges or divides the data set; at the same time, a multi-objective genetic algorithm (MOGA) and a genetic algorithm (GA) are used: to solve the optimization problem with multiple objective functions, and find a balance between multiple orders, materials and other targets, that is, to find a set of solutions; the model is mainly obtained by training based on historical materials, orders and other data) and the AI ​​production scheduling and control algorithm model (the model is based on the user-friendly time series prediction NeuralProphet implemented in PyTorch), specifically:

[0095] The target production data is expressed as:

[0096] y t =T(t)+S(t)+E(t)+F(t)+A(t)+L(t)

[0097] Among them, T(t) represents the trend at time t; S(t) represents the seasonal effect at time t; E(t) represents the event and holiday effect at time t; F(t) represents the regression effect of future known exogenous variables at time t; A(t) represents the autoregressive effect at time t based on past observations; L(t) represents the regression effect of lagged observations of exogenous variables at time t.

[0098] Furthermore, the trend T(t) at time t is expressed as:

[0099] T(t)=(δ0+Γ(t) T δ)·t+(ρ0+Γ(t) T ρ)

[0100] Among them, the trend T(t) of t is pushed down to get a vectorized equation: The trend part of T(t) is the classic way to model the trend as an offset m and a growth rate k. The trend effect at time t1 is the growth rate multiplied by the time difference from the starting point t0 at the top of the offset m:

[0101] T(t1)=T(t0)+k·□t=m+k·(t1-t0)

[0102] NeuralProphet uses this classical approach to model the trend component, but allows the growth rate to vary at multiple locations. Thus, the trend is modeled as a continuous piecewise linear series. This leads to an interpretable but nonlinear form of trend modeling. It is simple to interpret, as in a segment between two points, the trend effect is given by a steady growth rate multiplied by the time difference. We can generalize the trend growth rate δ(t) and the time-dependent offset ρ(t) by defining the time-dependent trend growth rate δ(t) and the time-dependent offset ρ(t).

[0103] T(t)=δ(t)·t+ρ(t)

[0104] A piecewise linear trend changes the growth rate only at a finite number of change points. The set of change points is written as C = (c1, c2, ..., cn) between which the trend growth rate remains constant. The growth rate and offset of the first segment are given as δ0 and ρ0. The rate adjustment for each change point can be defined as a vector δ∈R, where δj is the rate change change point at j. The growth rate at time t is determined by adding the initial growth rate δ0 to the sum of the rate adjustments for all change points up to time step t. Each growth rate change δj is a parameter to be fit on the data. A corresponding offset adjustment vector can be defined as ρ∈R. Similarly, the offset at time t is given by the initial offset ρ0 and the sum of the offset adjustments at each change point.

[0105] However, the offset of the change point cj is not an independent parameter, but is defined as ρj = -cjδj. This special offset definition makes the piecewise linear sequence continuous. Further, we introduce a binary vector Γ(t)∈R that indicates whether time t is in the past for each change point. Therefore, we can define the vectorized equation above for the trend T(t) at time t.

[0106] The seasonal effect S(t) at time t is expressed as:

[0107]

[0108] Among them, seasonality in NeuralProphet is handled by using Fourier terms (Harvey & Shephard, 1993) which was originally done in Prophet (Taylor & Letham, 2017). In this technique, a number of Fourier terms are defined for each seasonality in Equation 4, where k refers to the number of Fourier terms defined for seasonality with periodicity p. Fourier terms are defined as sine, cosine pairs and allow modeling of multiple seasonalities as well as seasonality with non-integer periods, such as annual seasonality for daily data (p = 365.25) or weekly data (p = 52.18). In a multiple seasonality scenario, different values ​​of n can be defined for each periodicity. Fourier terms are a good tool for modeling seasonality because they produce smooth functions that are easy to interpret and stable to fit the data. However, Fourier terms only model deterministically assuming a fixed seasonal shape over time. More Fourier terms allow the model to fit more complex seasonal patterns. Too much flexibility can lead to overfitting or random patterns between observations. Thus, each Fourier term corresponds to a frequency p proportional to j, modeled by a weighted combination of sine and cosine transforms. Each Fourier term corresponds to a frequency p proportional to j, modeled by a weighted combination of sine and cosine transforms. Each seasonality is associated with 2k coefficients. For time step t, all seasonalities considered in the model can be represented by S(t) in the following equation, where P refers to the set of all periods.

[0109] The regression effect F(t) of future known exogenous variables at time t is expressed as:

[0110]

[0111] Among them, it is required that the history and future of the exogenous data are known. Given a regression number, you can choose the addition or multiplication mode. The addition mode is used by default:

[0112] F f (t) = d f f(t)

[0113]

[0114] The autoregressive effect A(t) based on past observations at time t is expressed as:

[0115] A t (t),A t (t+1),...,A t (t+h-1)=AR-Net(y t-1 ,y t-2 ,...,y t-p )

[0116] Among them, y historical covariates are input, and h-step outputs are obtained through the AR network. The aspects that need to be paid attention to are similar to the autoregressive part. The default regression module is the simplest linear regression network with no hidden layer. It is a neural network with only one layer without activation function, y inputs, and h outputs. In this way, the weight coefficient of each output corresponds to the input one by one, and the contribution of each input to the output can be seen intuitively.

[0117] The regression effect L(t) of the lagged observation of the exogenous variable at time t is expressed as:

[0118]

[0119] Among them, the lagged regression reflects the correlation between the past observations of the exogenous data and the target data:

[0120]

[0121] A t (t),A t (t+1),...,A t (t+h-1)=AR-Net(y t-1 ,y t-2 ,...,y t-p )

[0122] Input x historical covariates and obtain h-step outputs through the AR network. The aspects that need to be paid attention to are similar to those in the autoregressive part, so I will not go into details here.

[0123] In an embodiment of the present application, the steps of using the AI ​​algorithm model execution engine mainly include preparing data, training models, creating visualization jobs (optional), importing models, deploying online, testing services, and clearing corresponding resources. Here, the AI ​​algorithm model execution engine and the three integrated AI algorithm models have been trained and deployed, and can be directly called and used.

[0124] In an embodiment of the present application, the previously generated order data set and the generated AI algorithm token are used as parameters to call the AI ​​algorithm model execution engine in the fourth step, and the AI ​​algorithm model execution engine executes the "AI production scheduling and control model" and "AI material supply algorithm model" according to the trained algorithm model. The two algorithm models calculate the actual production data set (the data set includes production line number, production line name, order number, product model, product name, standard working hours (pieces / hour), delivery period, delivery volume, number of people, reporting date, etc.).

[0125] In step S206, the target production data is written into the database to form a target production schedule.

[0126] In an embodiment of the present application, the actual production data set is written into the database to form a production schedule, which provides data support for the subsequent display of the production schedule.

[0127] In some optional implementation methods of the embodiments of the present application, the actual production data set can be used as the calculation data set of the "AI manufacturing capability algorithm model" for self-learning, and the algorithm factors and standard working hours can be dynamically adjusted according to whether the capacity utilization rate, production balance rate and punctuality rate in the result data are normal, so as to continuously optimize the AI ​​algorithm model and form the self-learning and adaptability of the AI ​​algorithm model.

[0128] In an embodiment of the present application, a method for generating a production schedule is provided, including: obtaining order interaction data; constructing order data according to the order interaction data; obtaining standard working time index data and standard algorithm factor data; constructing model parameter data according to the standard working time index data and standard algorithm factor data; calling the production schedule and control algorithm model, and inputting the model parameter data into the production schedule and control algorithm model for time series prediction operation to obtain target production data; writing the target production data into the database to form a target production schedule. Compared with the prior art, the present application dynamically and quickly generates production schedules and analysis reports based on order data, standard working hours, and algorithm factors using AI algorithm models, provides generation efficiency, and simplifies the production schedule process; can quickly update new AI algorithm tokens according to changes in order data, standard working hours, algorithm factors, etc., and strengthen adaptive capabilities; modular design makes the system easy to expand, supports real-time updates of algorithm factors, standard working hours, and order data, and rapid integration of multiple AI algorithm models, and improves system scalability; generates production schedules by continuously adjusting standard working hours and algorithm factors and provides capacity utilization, production balance rate, and punctuality, thereby improving continuous optimization capabilities.

[0129] In some optional implementations of the embodiments of the present application, after the above step of writing the target production data into the database to form a target production schedule, the following steps are also included:

[0130] Obtain real-time production data from the production process according to the target production schedule;

[0131] According to the real-time production data and the manufacturing capacity algorithm model, the standard working time index data is dynamically adjusted to obtain dynamic working time index data;

[0132] Perform dynamic adjustment operations on standard algorithm factor data based on real-time production data and manufacturing capability algorithm model to obtain dynamic algorithm factor data;

[0133] Construct dynamic model parameter data based on dynamic working hour index data and dynamic algorithm factor data;

[0134] Input the dynamic model parameter data into the production scheduling and control algorithm model to obtain dynamic production data;

[0135] Write dynamic production data to the database to update the target production schedule.

[0136] In an embodiment of the present application, the dynamic standard working time adjuster is based on the actual data of the production process (production line number, production line name, order number, product model, product name, standard working time (pieces / hour), delivery period, delivery volume, number of people, reporting date, etc.), extracts relevant standard working time data in multiple dimensions, and uses the "AI manufacturing capability algorithm model" to dynamically generate a new standard working time indicator data set (the indicator data mainly includes company name, product model, product name, production line number, production line name, number of people, standard working hours, and production capacity).

[0137] In an embodiment of the present application, a token of the AI ​​algorithm model of the "AI production scheduling and control algorithm model" is formed through standard working hours and a standard working hour indicator data set dynamically generated by using the "AI manufacturing capability algorithm model" (the token includes: company name, product model, product name, production line number, production line name, number of people, standard working hours, and production capacity).

[0138] In an embodiment of the present application, the dynamic algorithm factor adjuster uses a reinforcement learning algorithm to optimize the standard generation process based on the actual data of the production process (production line number, production line name, order number, product model, product name, standard working hours (pieces / hour), delivery period, delivery volume, number of people, reporting date, etc.), adapts to changes in the actual data of the production process, and dynamically generates new algorithm factors through the "AI manufacturing capability algorithm model" (the algorithm factors mainly include one lock days, two lock days, customers who may not comply with the two lock regulations, orders that may not comply with the two lock regulations, key customers and corresponding production lines, production scheduling according to the floating quantity of the standard production line, days for early delivery, daily plan lock days, factory calendar) and updates them.

[0139] In an embodiment of the present application, a token of the AI ​​algorithm model of the "AI production scheduling and control algorithm model" is formed by dynamically generating new algorithm factors through standard algorithm factors and utilizing the "AI manufacturing capability algorithm model" (the token includes: one lock days, two lock days, customers who may not comply with the two lock regulations, orders that may not comply with the two lock regulations, key customers and corresponding production lines, production that can be scheduled according to the floating quantity of the standard production line, days for early delivery, daily plan lock days, and factory calendar).

[0140] In some optional implementations of the embodiments of the present application, after the step of writing the target production data into the database to form a target production schedule, the following steps are also included:

[0141] Extract the actual production data set from the database;

[0142] Generate visual analysis reports based on actual production data sets and output visual analysis reports;

[0143] Receiving parameter adjustment data sent by a user terminal;

[0144] Adjust the standard working time index data and standard algorithm factor data according to the parameter adjustment data.

[0145] In an embodiment of the present application, the actual production data set is read from the database, and a visualized capacity utilization, production balance rate and punctuality analysis report is provided. The user adjusts the unreasonable production schedule according to the visualized report, and dynamically updates the token of the AI ​​algorithm model of the "AI production scheduling and control algorithm model" by adjusting the standard working hours and algorithm factors, continuously optimizing the AI ​​algorithm model, and forming the self-learning and adaptability of the AI ​​algorithm model.

[0146] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0147] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0148] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0149] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0150] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of a production scheduling plan generation device, and the device embodiment is similar to Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0151] like Figure 3 As shown, the production scheduling plan generating device 200 of the embodiment of the present application includes:

[0152] An interaction data acquisition module 210 is used to acquire order interaction data;

[0153] An order data construction module 220, used to construct order data according to order interaction data;

[0154] The standard data acquisition module 230 is used to acquire standard working time index data and standard algorithm factor data;

[0155] A model parameter building module 240 is used to build model parameter data according to dynamic working hour index data and dynamic algorithm factor data;

[0156] The target production data acquisition module 250 is used to call the production scheduling and control algorithm model, and input the model parameter data into the production scheduling and control algorithm model to perform time series prediction operations to obtain the target production data;

[0157] The target production schedule acquisition module 260 is used to write the target production data into the database to form a target production schedule.

[0158] In an embodiment of the present application, a production schedule generation device 200 is provided, including: an interactive data acquisition module 210, used to acquire order interaction data; an order data construction module 220, used to construct order data based on the order interaction data; a standard data acquisition module 230, used to acquire standard working hour index data and standard algorithm factor data; a model parameter construction module 240, used to construct model parameter data based on dynamic working hour index data and dynamic algorithm factor data; a target production data acquisition module 250, used to call the production schedule and control algorithm model, and input the model parameter data into the production schedule and control algorithm model for time series prediction operations to obtain target production data; a target production schedule acquisition module 260, used to write the target production data into the database to form a target production schedule. Compared with the existing technology, the present application uses AI algorithm models to dynamically and quickly generate production schedules and analysis reports based on order data, standard working hours, and algorithm factors, thereby improving generation efficiency and simplifying the production scheduling process; it can quickly update new AI algorithm tokens based on changes in order data, standard working hours, algorithm factors, etc., and enhance adaptive capabilities; the modular design makes the system easy to expand, supports real-time updates of algorithm factors, standard working hours, and order data, and rapid integration of multiple AI algorithm models, thereby improving system scalability; by continuously adjusting standard working hours and algorithm factors to generate production schedules and provide capacity utilization, production balance rate, and punctuality rate, it improves continuous optimization capabilities.

[0159] In some optional implementations of the embodiments of the present application, the production scheduling plan generating device 200 includes:

[0160] A real-time data acquisition module is used to obtain real-time production data obtained during the production process according to the target production scheduling plan;

[0161] The working time dynamic adjustment module is used to dynamically adjust the working time index data of the standard working time index data according to the real-time production data and the manufacturing capacity algorithm model to obtain the dynamic working time index data;

[0162] The factor dynamic adjustment module is used to dynamically adjust the standard algorithm factor data according to the real-time production data and the manufacturing capability algorithm model to obtain the dynamic algorithm factor data;

[0163] A dynamic model parameter building module is used to build dynamic model parameter data according to dynamic working hour index data and dynamic algorithm factor data;

[0164] Dynamic production data acquisition module, used to input dynamic model parameter data into production scheduling and control algorithm model to obtain dynamic production data;

[0165] The target production schedule update module is used to write dynamic production data into the database to update the target production schedule.

[0166] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of a computer device according to an embodiment of the present application.

[0167] The computer device 300 includes a memory 310, a processor 320, and a network interface 330 that are interconnected and communicated through a system bus. It should be noted that the figure only shows a computer device 300 having components 310-330, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0168] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0169] The memory 310 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 310 can be an internal storage unit of the computer device 300, such as a hard disk or memory of the computer device 300. In other embodiments, the memory 310 can also be an external storage device of the computer device 300, such as a plug-in hard disk equipped on the computer device 300, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card, etc. Of course, the memory 310 can also include both the internal storage unit of the computer device 300 and its external storage device. In the embodiment of the present application, the memory 310 is generally used to store the operating system and various application software installed on the computer device 300, such as computer-readable instructions of the production scheduling plan generation method. In addition, the memory 310 can also be used to temporarily store various data that have been output or are to be output.

[0170] The processor 320 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 320 is generally used to control the overall operation of the computer device 300. In the embodiment of the present application, the processor 320 is used to run the computer-readable instructions or process data stored in the memory 310, such as computer-readable instructions for running the production scheduling plan generation method.

[0171] The network interface 330 may include a wireless network interface or a wired network interface. The network interface 330 is generally used to establish a communication connection between the computer device 300 and other electronic devices.

[0172] The computer equipment provided in this application uses AI algorithm models to dynamically and quickly generate production scheduling plans and analysis reports based on order data, standard working hours, and algorithm factors, thereby improving generation efficiency and simplifying the production scheduling process; it can quickly update new AI algorithm tokens based on changes in order data, standard working hours, algorithm factors, etc., and enhance adaptive capabilities; the modular design makes the system easy to expand, supports real-time updates of algorithm factors, standard working hours, and order data, and rapid integration of multiple AI algorithm models, thereby improving system scalability; and generates production scheduling plans by continuously adjusting standard working hours and algorithm factors, and provides capacity utilization, production balance rate, and punctuality rate, thereby improving continuous optimization capabilities.

[0173] The present application also provides another embodiment, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the production scheduling plan generation method as described above.

[0174] The computer-readable storage medium provided in the present application uses an AI algorithm model to dynamically and quickly generate production scheduling plans and analysis reports based on order data, standard working hours, and algorithm factors, thereby improving generation efficiency and simplifying the production scheduling process; it can quickly update new AI algorithm tokens based on changes in order data, standard working hours, algorithm factors, etc., and enhance adaptive capabilities; the modular design makes the system easy to expand, supports real-time updates of algorithm factors, standard working hours, and order data, and rapid integration of multiple AI algorithm models, thereby improving system scalability; and it generates production scheduling plans and provides capacity utilization, production balance rate, and punctuality rate by continuously adjusting standard working hours and algorithm factors, thereby improving continuous optimization capabilities.

[0175] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0176] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A method for generating a production schedule, characterized in that: The steps include: Get order interaction data; Constructing order data according to the order interaction data; Obtain standard working hours index data and standard algorithm factor data; Constructing model parameter data according to the standard working time index data and the standard algorithm factor data; Calling a production scheduling and control algorithm model, and inputting the model parameter data into the production scheduling and control algorithm model to perform a time series forecasting operation to obtain target production data; The target production data is written into a database to form a target production schedule.

2. The method for generating a production schedule according to claim 1, characterized in that: After the step of writing the target production data into the database to form a target production schedule, the following steps are also included: Acquire real-time production data obtained from the production process according to the target production schedule; Performing a dynamic working time adjustment operation on the standard working time index data according to the real-time production data and the manufacturing capability algorithm model to obtain dynamic working time index data; Performing a factor dynamic adjustment operation on the standard algorithm factor data according to the real-time production data and the manufacturing capability algorithm model to obtain dynamic algorithm factor data; Constructing dynamic model parameter data according to the dynamic working time index data and the dynamic algorithm factor data; Inputting the dynamic model parameter data into the production scheduling and control algorithm model to obtain dynamic production data; The dynamic production data is written into the database to update the target production schedule.

3. The method for generating a production schedule according to claim 1, characterized in that: After the step of writing the target production data into the database to form a target production schedule, the following steps are also included: extracting actual production data sets from the database; Generate a visualization analysis report based on the actual production data set, and output the visualization analysis report; Receiving parameter adjustment data sent by a user terminal; The standard working time index data and the standard algorithm factor data are adjusted according to the parameter adjustment data.

4. The method for generating a production schedule according to claim 1, characterized in that: The target production data is expressed as: y t =T(t)+S(t)+E(t)+F(t)+A(t)+L(t) Among them, T(t) represents the trend at time t; S(t) represents the seasonal effect at time t; E(t) represents the event and holiday effect at time t; F(t) represents the regression effect of future known exogenous variables at time t; A(t) represents the autoregressive effect at time t based on past observations; L(t) represents the regression effect of lagged observations of exogenous variables at time t.

5. The method for generating a production schedule according to claim 4, characterized in that: The trend T(t) at time t is expressed as: T(t)=(δ0+Γ(t) T δ)·t+(ρ0+Γ(t) T p) Where δ0 represents the growth rate of the first segment, δ(t) represents the trend growth rate at time t, ρ0 represents the offset of the first segment, and ρ(t) represents the offset at time t; The seasonal effect S(t) at time t is expressed as: Where k represents the number of Fouriers; p represents periodicity; The regression effect F(t) of the future known exogenous variable at time t is expressed as: Among them, F f (t) = d f f(t); The autoregressive effect A(t) based on past observations at time t is expressed as: A t (t),A t (t+1),...,A t (t+h-1)=AR-Net(y t-1 ,y t-2 ,...,y t-p ) Among them, y represents the input data, h represents the step size; The regression effect L(t) of the lagged observation of the exogenous variable at time t is expressed as: Here, x represents the historical covariate.

6. A production scheduling plan generating device, characterized in that: include: An interactive data acquisition module, used to acquire order interaction data; An order data construction module, used to construct order data according to the order interaction data; Standard data acquisition module, used to obtain standard working time index data and standard algorithm factor data; A model parameter construction module, used to construct model parameter data according to the dynamic working hour index data and the dynamic algorithm factor data; A target production data acquisition module is used to call the production scheduling and control algorithm model, and input the model parameter data into the production scheduling and control algorithm model to perform time series prediction operations to obtain target production data; The target production schedule acquisition module is used to write the target production data into the database to form a target production schedule.

7. The production schedule generating device according to claim 6, characterized in that: The device also includes: A real-time data acquisition module, used to acquire real-time production data obtained during the production process according to the target production scheduling plan; A working time dynamic adjustment module is used to perform a working time dynamic adjustment operation on the standard working time index data according to the real-time production data and the manufacturing capability algorithm model to obtain dynamic working time index data; A factor dynamic adjustment module, used to perform a factor dynamic adjustment operation on the standard algorithm factor data according to the real-time production data and the manufacturing capability algorithm model to obtain dynamic algorithm factor data; A dynamic model parameter construction module, used to construct dynamic model parameter data according to the dynamic working hour index data and the dynamic algorithm factor data; A dynamic production data acquisition module, used to input the dynamic model parameter data into the production scheduling and control algorithm model to obtain dynamic production data; The target production schedule updating module is used to write the dynamic production data into the database to update the target production schedule.

8. The production schedule generating device according to claim 6, characterized in that: The device also includes: An actual production data acquisition module, used to extract an actual production data set from the database; An analysis report generation module, used to generate a visual analysis report based on the actual production data set and output the visual analysis report; A parameter adjustment data acquisition module, used to receive parameter adjustment data sent by a user terminal; The adjustment operation module is used to perform adjustment operations on the standard working time index data and the standard algorithm factor data according to the parameter adjustment data.

9. A computer device comprising a memory and a processor, characterized in that: The memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the production scheduling plan generation method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the production scheduling plan generation method according to any one of claims 1 to 6 are implemented.

Images