CN117592905A - Data generation method, device, equipment and storage medium - Google Patents

Data generation method, device, equipment and storage medium Download PDF

Info

Publication number
CN117592905A
CN117592905A CN202311632279.0A CN202311632279A CN117592905A CN 117592905 A CN117592905 A CN 117592905A CN 202311632279 A CN202311632279 A CN 202311632279A CN 117592905 A CN117592905 A CN 117592905A
Authority
CN
China
Prior art keywords
data
scene
materials
order
characteristic information
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202311632279.0A
Other languages
Chinese (zh)
Inventor
欧阳文理
董智辰
严骏驰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Jiaotong University
Lenovo Beijing Ltd
Original Assignee
Shanghai Jiaotong University
Lenovo Beijing Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shanghai Jiaotong University, Lenovo Beijing Ltd filed Critical Shanghai Jiaotong University
Priority to CN202311632279.0A priority Critical patent/CN117592905A/en
Publication of CN117592905A publication Critical patent/CN117592905A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/04—Manufacturing
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Primary Health Care (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • General Health & Medical Sciences (AREA)
  • Operations Research (AREA)
  • Health & Medical Sciences (AREA)
  • Manufacturing & Machinery (AREA)
  • Development Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Quality & Reliability (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application discloses a data generation method, a device, equipment and a storage medium, wherein the method comprises the following steps: determining at least one product corresponding to the target material alignment scene by utilizing a data generation rule, and expanding production materials step by step aiming at each product in the at least one product until the expansion is carried out to a target level, so as to obtain corresponding materials at all levels; the data generation rule is generated based on real material matching data corresponding to the target material matching scene; expanding characteristic information of each material in each level of materials by utilizing a data generation rule to obtain material characteristic information corresponding to each material; the material characteristic information at least comprises one or more of stock quantity, use priority and material type; and determining the materials at each level and the material characteristic information corresponding to each material in the materials at each level as the material information corresponding to the target material alignment scene.

Description

Data generation method, device, equipment and storage medium
Technical Field
The present disclosure relates to the field of data simulation technologies, and in particular, to a data generating method, device, apparatus, and storage medium.
Background
In industrial production, material alignment is an important step to ensure that the required material is available; the traditional method for solving the problem of material alignment relies on heuristic rules that require a lot of data to perform simulation experiments and parameter adjustments during the design process. However, the amount of real data in industrial production is limited, and it is difficult to acquire, count and sort out these data. At the same time, due to data confidentiality requirements, such data can also be difficult to use. Besides the traditional heuristic method, the machine learning method can also be used for solving the material alignment problem, so that the problem solving efficiency and accuracy are improved. However, the machine learning method is also data driven, which puts higher demands on the amount and quality of data, so that there are problems of insufficient data and influence on the security of real data.
Disclosure of Invention
The embodiment of the application expects to provide a data generation method, device, equipment and storage medium.
The technical scheme of the embodiment of the application is realized as follows:
the embodiment of the application provides a data generation method, which utilizes a data generation rule to determine at least one product corresponding to a target material alignment scene, and expands production materials step by step aiming at each product in the at least one product until the expansion is carried out to a target level, so as to obtain corresponding materials at all levels; the data generation rule is generated based on real material alignment data corresponding to the target material alignment scene;
expanding characteristic information of each material in each level of materials by utilizing the data generation rule to obtain the material characteristic information corresponding to each material; the material characteristic information at least comprises one or more of stock quantity, use priority and material type;
and determining the materials at all levels and the material characteristic information corresponding to the materials in the materials at all levels as the material information corresponding to the target material nesting scene.
The embodiment of the application provides a data generation device, which comprises:
the determining module is used for determining at least one product corresponding to the target material alignment scene by utilizing the data generating rule, and expanding production materials step by step aiming at each product in the at least one product until the expansion is carried out to a target level, so as to obtain corresponding materials at all levels; the data generation rule is generated based on real material alignment data corresponding to the target material alignment scene;
the expansion module is used for expanding the characteristic information of each material in each level of materials by utilizing the data generation rule to obtain the material characteristic information corresponding to each material; the material characteristic information at least comprises one or more of stock quantity, use priority and material type;
the determining module is further configured to determine the materials at each level and the material characteristic information corresponding to each material in the materials at each level as material information corresponding to the target material matching scene.
The embodiment of the application provides a data generation device, which comprises: a processor, a memory, and a communication bus;
the communication bus is used for realizing communication connection between the processor and the memory;
the processor is configured to execute the computer program stored in the memory, so as to implement the data generating method.
Embodiments of the present application provide a computer-readable storage medium storing one or more computer programs executable by one or more processors to implement the above-described data generation method.
Drawings
Fig. 1 is a schematic flow chart of a data generating method according to an embodiment of the present application;
FIG. 2 is a schematic flow chart of an exemplary material expansion provided in an embodiment of the present application;
FIG. 3 is a flow chart illustrating exemplary generation of scene data according to an embodiment of the present application;
FIG. 4 is a schematic diagram of an exemplary order group provided in an embodiment of the present application;
FIG. 5 is a flowchart illustrating an exemplary generation of a data generation rule according to an embodiment of the present application;
FIG. 6 is a second flow chart illustrating an exemplary generation of data generation rules according to an embodiment of the present application;
FIG. 7 is a flow chart of an exemplary model training provided in an embodiment of the present application;
FIG. 8 is a flow chart of an exemplary data screening provided in an embodiment of the present application;
FIG. 9 is a flowchart illustrating exemplary generation of target scene data according to an embodiment of the present application;
FIG. 10 is a flow chart illustrating an exemplary determination of a target solution model provided by embodiments of the present application;
fig. 11 is a schematic structural diagram of a data generating device according to an embodiment of the present application;
fig. 12 is a schematic structural diagram of a data generating device according to an embodiment of the present application.
Detailed Description
The technical solutions in the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. It is to be understood that the specific embodiments described herein are merely illustrative of the application and not limiting of the application. It should be noted that, for convenience of description, only a portion related to the related application is shown in the drawings.
The embodiment of the application provides a data generation method, which is implemented by a data generation device, as shown in fig. 1, and includes the following steps S101 to S103:
step S101, determining at least one product corresponding to a target material alignment scene by utilizing a data generation rule, and expanding production materials step by step aiming at each product in the at least one product until the expansion is carried out to a target level to obtain corresponding materials of all levels; the data generation rule is generated based on real material matching data corresponding to the target material matching scene.
In the embodiment of the present application, the data generating device is an electronic device having a data generating function. The data generating device may be an electronic device such as a computer device, an intelligent terminal device, or the like, for example.
In the embodiment of the application, the target material nesting scene can be a material nesting scene of various production industries and enterprises, and the target material nesting scene can be a scene of food, electronics, automobiles, manufacturing industries and the like by way of example; the data generating device can determine at least one product corresponding to the target material matching scene by utilizing a data generating rule; the data generation rule is generated based on real material alignment data corresponding to the target material alignment scene; for example, if the target material nesting scene is an electronic material nesting scene, the at least one product determined based on the data generation rules may be: a mouse, a keyboard, a host computer, a computer, headphones, and the like.
In the embodiment of the application, after at least one corresponding product is determined aiming at a target material alignment scene, expanding production materials step by step for each product in the at least one product by utilizing a data generation rule until the expansion is carried out to a target level, and obtaining corresponding materials of different levels. Exemplary expansion referring to fig. 2, for expansion of the final product a (product), a first stage is expanded: and then carrying out second-stage expansion on the materials 1-1 and 1-2 expanded at the first stage, wherein the materials 1-1 are expanded with the materials 2-1, the materials 1-2 are expanded with the materials 2-2 and 2-3, and so on to the target level, so that each stage of materials corresponding to the product A can be obtained. Wherein, production dependency exists between each level of materials, see the connecting lines (solid lines and broken lines between materials) in fig. 2; the dashed line illustrates that the hierarchy is newly expanded material.
Step S102, expanding characteristic information of each material in each level of materials by utilizing a data generation rule to obtain material characteristic information corresponding to each material; the material characteristic information includes at least one or more of inventory, usage priority, and material type.
In the embodiment of the application, the data generating device can continue to utilize the data generating rule to expand the characteristic information of each material in each level of material corresponding to each product; wherein the material characteristic information includes at least one or more of inventory, usage priority, and material type.
And step 103, determining the material characteristic information corresponding to each material in each grade of material as the material information corresponding to the target material nesting scene.
In the embodiment of the application, the data generating device determines the materials at each level and the material characteristic information corresponding to each material in the materials at each level as the material information corresponding to the target material alignment scene.
Illustratively, in the material information generation stage, a sub-bill of materials (materials in each stage) of a specific scale is constructed for each final product in units of final products (products). Starting from each final product, the material information is gradually (step by step) expanded through a queuing method. Specifically, the materials with information to be perfected are maintained by using a queue (step by step), the materials at the head of the queue are dequeued, the characteristics (material characteristic information) such as the stock quantity and the type of the materials are determined according to a preset data generation rule (data generation rule), sub-materials required by the production of the materials are generated (continuous expansion is carried out), the newly generated sub-materials are added into the queue for information perfection, and iterative material information expansion is carried out continuously until the data with the specified scale are obtained (until the data are expanded to a target level). A schematic flow diagram of an exemplary ground object expansion is shown with reference to fig. 2.
Compared with the data acquisition difficulty and the data confidentiality aiming at the target material nesting scene in the related art, the method and the device can generate the data generation rule for representing the scene characteristics based on the real material nesting data of the target material nesting scene, further generate the simulation data conforming to the target material nesting scene based on the data generation rule, reduce the data acquisition difficulty and improve the safety of the real material nesting data.
In some embodiments, the data generating apparatus may further perform the following steps S301 to S303:
step S301, generating at least one order aiming at a target material nesting scene by utilizing a data generation rule, and generating corresponding order characteristic information for each order in the at least one order; the order may be: formal, stock, or forecast orders; the order characteristic information includes at least the required materials of the order.
In the embodiment of the application, the data generating device generates at least one order for the target material matching scene based on the data generating rule; the at least one order may include one or more of a formal order, a stock order, a repair order, and a predicted order, and of course, the at least one order may be any of the above types of orders, such as the at least one order is a formal order, a stock order, a repair order, or a predicted order.
In the embodiment of the application, after generating at least one order for the target material matching scene, the data generating device generates corresponding order feature information for each order in the at least one order; the order feature information at least includes required materials of the order, and of course, the order feature information may also include information such as a demand amount, a priority, a completion period, etc., and the specific order feature information may be set according to an application scenario and an actual demand, which is not limited in this application.
Step S302, classifying at least one order according to the required materials to obtain at least one group of orders.
In an embodiment of the present application, after obtaining at least one order, the data generating device classifies the at least one order according to a required material to obtain at least one group of orders, where the required material of each group of orders in the at least one group of orders is the same.
In the embodiment of the present application, after the data generation data generates the material information, the data generation rule is used to generate an order, and then the order is managed in units of groups. In order to facilitate sorting of the orders, the material required by each order is set to be one, and if a certain order needs a plurality of materials, the data generating device splits the order into a plurality of orders, and each order needs only one material. Illustratively, order A requires material B and material C, then order A is split into order A1 and order A2, order A1 requires material B, and order A2 requires material C; the data generating device divides the orders requiring the same material into a group, and then, the materials required by each of the obtained at least one group of orders are the same, as shown in fig. 4, the orders 1, 2, 13 in the order group 1 are the same, and the order characteristic information of each order is included: and the demand quantity, the priority and other characteristic information.
Step S303, according to the required materials of each group of orders in at least one group of orders, carrying out production relation matching on the corresponding materials included in the order and the material information in each group of orders, and generating scene data corresponding to the target material matching scene.
In the embodiment of the application, the data generating device performs production relation matching on each order in each group of orders and corresponding materials included in the material information according to the required materials of each group of orders in at least one group of orders, and generates scene data corresponding to a target material matching scene. For example, assuming that the order group 1 needs the material a, the data generating device establishes a production relationship between the order 13 and the material a to generate scene data corresponding to the target material matching scene with respect to the order 1, the order 2, and the order.
The data generating device performs matching of the generated materials and orders according to the generated materials and orders, wherein a random strategy is used, one material is designated as a target material for each group of orders, and according to scene requirements, a heuristic matching strategy based on characteristics of the materials and the orders can be used for replacing the random strategy.
In some embodiments, the data generating apparatus may further perform the following steps S501 to S503:
and step S501, acquiring real material alignment data.
In an embodiment of the application, the data generating device obtains real material nesting data for a target material nesting scene.
Step S502, analyzing standard data representing the characteristics of the target material matching scene in the real material matching data; the standard data includes at least: one or more of stock distribution of different materials, demand distribution of different orders, probability distribution of different materials, and material distribution required for order production.
In an embodiment of the present application, after acquiring real material alignment data, the data generating device analyzes standard data characterizing a target material alignment scene feature in the real material alignment data, where the standard data at least includes: one or more of stock distribution of different materials, demand distribution of different orders, probability distribution of different materials, and material distribution required for order production.
Illustratively, real data (real material jacket data) is acquired from a material jacket production scene (target material jacket scene) to be simulated, and the data is statistically analyzed to acquire specific statistics (standard data). The statistics to be acquired include: the stock distribution of different types of materials (stock distribution of different materials), the demand distribution of different types of orders (demand distribution of different orders), the distribution of the types of materials required for material production, and the like. Different statistics can be flexibly designed for different scenes to better fit scene features. If the number of the real data accessible to the scene is limited or the scene to be simulated does not generate the real data, various statistical indexes can be approximately obtained through human estimation.
Step S503, generating a data generation rule for the target material complete set scene based on the standard data.
In an embodiment of the present application, the data generating device generates a data generating rule for a target material kit scene based on standard data.
In some embodiments, the data generating rules include at least one or more of data distribution fitting rules, data association fitting rules, and special data generating rules, and performing step S503 described above by the data generating device may include at least one or more of the following steps S601 to S603:
and step S601, generating a data distribution fitting rule based on different distributional data in the standard data by using a distributional generating function.
In an embodiment of the present application, the data generating device may generate the data distribution fitting rule based on different distribution data in the standard data using a distribution generating function. Illustratively, a data distribution fitting (data distribution fitting rule) design generation process uses a distribution generation function, such as a material kind probability distribution, a material stock quantity distribution, and the like, to align the generated simulation distribution with the true distribution.
Step S602, generating a data association fitting rule based on association relations among different distributive data in the standard data.
In an embodiment of the present application, the data generating device generates the data association fitting rule based on association relations between different distributive data in the standard data. Illustratively, the data association fit (data association fit rule) studies the association between different distributive indicators, such as: the association of the material category with the number of material categories required for its production to model the association information of the real scene.
Step S603, setting a special data generation rule based on the distribution situation of the abnormal data in the standard data.
In the embodiment of the present application, the data generating apparatus sets the special data generating rule based on the distribution situation of the abnormal data in the standard data. Illustratively, special data generation (special data generation rules) studies marginal distributions in a scene, such as orders with abnormally high or abnormally low demand, to include special cases in a target material nested scene.
In the embodiment of the present application, the rules included in the data generation rule may be flexibly adjusted according to the scene feature and the simulation requirement, which is not limited in this application.
In some embodiments, the data generating apparatus may include the following steps when performing the above step S102: according to the data distribution fitting rule, determining initial material characteristic information of each material; according to the data association fitting rule, carrying out association adjustment on the initial material characteristic information of each material to obtain adjustment material characteristic information of each material in each level of materials; and generating special data for the material characteristic information of each material according to the special data generation rule to obtain material characteristic information corresponding to each material.
In the embodiment of the application, the data generating device determines initial material characteristic information of each material according to the data distribution fitting rule, and then carries out association adjustment on the generated initial material characteristic information according to the data association fitting rule to obtain adjusted material characteristic information, and finally carries out special data generation according to the special data generating rule to obtain corresponding material characteristic information.
In some embodiments, the data generating apparatus may include the following steps when performing the above step S301: according to the data distribution fitting rule, determining initial order feature information of each order; according to the data association fitting rule, carrying out association adjustment on the initial order feature information of each order to obtain adjustment order feature information of each order; and generating special data for the adjustment order characteristic information of each order according to the special data generation rule to obtain the order characteristic information of each order.
In the embodiment of the application, the data generating device determines initial order feature information of each order according to the data distribution fitting rule, then carries out association adjustment on the generated initial order feature information according to the data association fitting rule to obtain adjustment order feature information, and finally carries out special data generation according to the special data generating rule to obtain corresponding order feature information.
In the embodiment of the application, in order to ensure that the generated simulation sample can be used for optimizing the solving effect of the heuristic method and the machine learning method and ensure the generation quality of data, a three-stage simulation sample construction mode is provided: first, simulated material information is generated (see step S101 to step S103 described above); thereafter, simulation order information is generated (see steps S301 to 302 described above); finally, the two are matched (see step S303 described above). As such, the present application uses three aspects of scene alignment methods, data distribution fitting, data correlation fitting, and special data generation. On the premise of ensuring confidentiality of real data, the method ensures that the generated data has the characteristics of specific real production scenes.
In some embodiments, after performing the above step S303, the data generating apparatus may further perform the following steps S701 to S703:
and step 701, establishing a mixed integer programming problem model aiming at scene data, and calling a solver to solve the mixed integer programming problem model to obtain an optimal solution.
In an embodiment of the application, the data generating device builds a mixed integer programming problem model (Mix Integer Programming, MIP) for the scene data and invokes a solver (Solving Constraint Integer Programs, SCIP) to solve the mixed integer programming problem model to obtain an optimal solution.
Step S702, screening the scene data with the time length within the target solving time length range for solving the mixed integer programming problem model as target scene data.
In the embodiment of the application, the data generating device screens the scene data with the time length for solving the mixed integer programming problem model being in the target solving time length range as target scene data. To solve the degradation problem in the generated simulation samples (scene data), data filtering is required, for example, see fig. 8, in the following manner: modeling the simulation samples (scene data) 81 as a mixed integer programming problem model (MIP samples) 83 using a MIP modeling module 82; problem solving of the MIP samples is performed using a mathematical programming solver (MIP solver) 84, and a solution time period 85 is recorded; according to the upper and lower bounds (target solution duration range) of the preset desired solution time, the data (data filtering) 86 whose solution duration exceeds the bounds are removed, and the required simulation data (target scene data) 87 is obtained.
And step 703, performing model training on the to-be-trained solution model of the target material matching scene by using the target scene data and the optimal solution to obtain a target solution model, so as to solve the real data in the target material matching scene by using the target solution model.
In the embodiment of the application, after obtaining the target scene data and the optimal solution for the target scene data, the data generating device performs model training on a solution model to be trained of the target material nesting scene by using the target scene data and the optimal solution to obtain a target solution model, so that real data in the target material nesting scene is solved by using the target solution model.
As shown in fig. 9, a specific flowchart of generating target scene data is further provided for the embodiment of the present application. As shown in fig. 9, exemplary generation of the target scene data includes the following steps S901 to S904:
step S901, rule setting for aligning real data features.
As shown in fig. 9, the data generating apparatus extracts features characterizing a target material jacket scene from the acquired real data (real material jacket data), sets a corresponding rule (data generation rule) 90; wherein the data generation rule includes: a data distribution fit 91, a data association fit 92, and a feature data generation rule 93.
And step S902, generating a material complete set simulation sample.
As shown in fig. 9, the data generating apparatus performs material-kit simulation sample (scene data) 94 generation based on the data generating rule 90 set in step S901 described above. Illustratively, the material information 96 is generated by the material information generating module 95 and the order information 98 is generated by the order information generating module 97, and then the matching of the material and order production relationship is performed by the material-order matching module 99, so as to generate the material set simulation sample 94.
And step S903, screening the materials Ji Taoshu.
As shown in fig. 9, the data generating device may use the MIP modeling module 910 to build a mixed integer programming problem model on the generated material complete set simulation sample 94, and call the solver to solve, and further use the data filtering module 911 to remove the data with the solution time exceeding the upper and lower bounds of the preset expected solution time, and filter the data with the solution time being within the upper and lower bounds of the preset expected solution time.
Step S904, obtaining target scene data.
As shown in fig. 9, the target scene data obtained by screening has confidentiality and can be desensitized with real data; the simulation performance is realized, and the characteristic of the material alignment sleeve problem can be embodied; the data obtained after degradation is screened out with high quality.
Illustratively, as shown in FIG. 10, the implementation of determining the target solution model may be: embedding a material alignment problem simulation sample (target scene data) 11 into a graph convolution neural network 12, identifying to obtain a neural network prediction result 13, performing MIP modeling on the material alignment problem simulation sample 11, calling a MIP solver 14 to solve an optimal solution label (optimal solution) 15, further calculating loss information 16 between the neural network prediction result 13 and the optimal solution label 15, and further performing model training on a solution model to be trained based on the loss information 16 to obtain a target solution model, so as to solve real data in a target material alignment scene by using the target solution model. Thus, the simulation sample generation method (data generation method) provided by the application fills the defects of the existing data generation method, and can construct high-quality material alignment problem simulation data. The model enhancement method provided by the patent can utilize the generated simulation data to optimize model parameters, improves problem solving efficiency, has important significance for decision maker optimizing problem solving algorithm and improving production plan formulation, and can improve the utilization rate and satisfaction of production resources.
In an embodiment of the present application, the simulation data generated by the data generating apparatus may be used for training a machine learning model, and a model enhancement process (determining a target solution model) is shown in fig. 10. First, mixed integer programming modeling is performed on simulation data (target scene data), and training labels (optimal solutions) are acquired by using a mathematical programming solver SCIP. And then, inputting the simulation data into a machine learning model (to-be-trained solving model) to obtain an output result (neural network prediction result) of the model. And calculating loss by using the training labels and model output, updating model parameters, repeating the process until model training is completed, and solving a material alignment problem by using the obtained machine learning model (target solving model), thereby improving the solving efficiency.
The embodiment of the application provides a data generation method, which utilizes a data generation rule to determine at least one product corresponding to a target material alignment scene, and expands production materials step by step aiming at each product in the at least one product until the expansion reaches a target level, so as to obtain corresponding materials of all levels; the data generation rule is generated based on real material matching data corresponding to the target material matching scene; expanding characteristic information of each material in each level of materials by utilizing a data generation rule to obtain material characteristic information corresponding to each material; the material characteristic information at least comprises one or more of stock quantity, use priority and material type; and determining the materials at each level and the material characteristic information corresponding to each material in the materials at each level as the material information corresponding to the target material alignment scene. According to the data generation method, the data generation rule for representing the scene characteristics can be generated based on the real material nesting data of the target material nesting scene, so that the simulation data conforming to the target material nesting scene is generated based on the data generation rule, the difficulty in data acquisition is reduced, and the safety of the real material nesting data is improved.
An embodiment of the present application provides a data generating apparatus, as shown in fig. 11, including:
the determining module 1101 is configured to determine at least one product corresponding to the target material matching scene by using a data generating rule, and perform expansion of production materials step by step for each product in the at least one product until the expansion reaches a target level, so as to obtain corresponding materials at each level; the data generation rule is generated based on real material matching data corresponding to the target material matching scene;
the expansion module 1102 is configured to expand characteristic information of each material in each level of material by using a data generation rule, so as to obtain material characteristic information corresponding to each material; the material characteristic information at least comprises one or more of stock quantity, use priority and material type;
the determining module 1101 is further configured to determine each level of material, and material characteristic information corresponding to each material in each level of material as material information corresponding to a target material nesting scene
In an embodiment of the present application, the determining module 1101 is further configured to generate at least one order for the target material set scene by using a data generating rule, and generate corresponding order feature information for each order in the at least one order; the order may be: formal, stock, or forecast orders; the order characteristic information at least comprises the required materials of the order; classifying at least one order according to the required materials to obtain at least one group of orders; and according to the required materials of each group of orders in at least one group of orders, carrying out production relation matching on the corresponding materials included in the order and the material information in each group of orders, and generating scene data corresponding to the target material matching scene.
In an embodiment of the present application, the data generating device further includes a generating module (not shown in the figure) configured to obtain real material alignment data; analyzing standard data representing characteristics of a target material alignment scene in real material alignment data; the standard data includes at least: one or more of stock distribution of different materials, demand distribution of different orders, probability distribution of different materials, and material distribution required for order production; based on the standard data, generating a data generation rule for the target material matching scene.
In an embodiment of the present application, the data generation rule at least includes one or more of a data distribution fitting rule, a data association fitting rule, and a special data generation rule; the generation module is also used for generating a data distribution fitting rule based on different distributional data in the standard data by using a distributional generation function; generating a data association fitting rule based on association relations among different distributive data in the standard data; and setting a special data generation rule based on the distribution condition of the abnormal data in the standard data.
In an embodiment of the present application, the determining module 1101 is further configured to determine initial material characteristic information of each material according to a data distribution fitting rule; according to the data association fitting rule, carrying out association adjustment on the initial material characteristic information of each material to obtain adjustment material characteristic information of each material in each level of materials; and generating special data for the material characteristic information of each material according to the special data generation rule to obtain material characteristic information corresponding to each material.
In an embodiment of the present application, the determining module 1101 is further configured to determine initial order feature information of each order according to a data distribution fitting rule; according to the data association fitting rule, carrying out association adjustment on the initial order feature information of each order to obtain adjustment order feature information of each order; and generating special data for the adjustment order characteristic information of each order according to the special data generation rule to obtain the order characteristic information of each order.
In an embodiment of the present application, the data generating device further includes a training module (not shown in the figure) configured to build a mixed integer programming problem model for the scene data, and call a solver to solve the mixed integer programming problem model to obtain an optimal solution; screening scene data with the time length within the target solving time length range for solving the mixed integer programming problem model into target scene data; and carrying out model training on a to-be-trained solution model of the target material matching scene by utilizing the target scene data and the optimal solution to obtain a target solution model, so as to solve the real data of the target material matching scene by utilizing the target solution model.
The embodiment of the application provides a data generating device, as shown in fig. 12, the data generating device includes: a processor 1201, a memory 1202, and a communication bus 1203;
a communication bus 1203 for implementing a communication link between processor 1201 and memory 1202;
a processor 1201 for executing computer programs stored in the memory 1202 to implement the data generation method described above.
The embodiment of the application provides data generation equipment, which utilizes data generation rules to determine at least one product corresponding to a target material alignment scene, and expands production materials step by step aiming at each product in the at least one product until the expansion reaches a target level to obtain corresponding materials at all levels; the data generation rule is generated based on real material matching data corresponding to the target material matching scene; expanding characteristic information of each material in each level of materials by utilizing a data generation rule to obtain material characteristic information corresponding to each material; the material characteristic information at least comprises one or more of stock quantity, use priority and material type; and determining the materials at each level and the material characteristic information corresponding to each material in the materials at each level as the material information corresponding to the target material alignment scene. According to the data generation device, the data generation rule for representing the scene characteristics can be generated based on the real material nesting data of the target material nesting scene, and then the simulation data conforming to the target material nesting scene is generated based on the data generation rule, so that the difficulty in data acquisition is reduced, and the safety of the real material nesting data is improved.
Embodiments of the present application provide a computer readable storage medium storing one or more computer programs executable by one or more processors to implement the above-described data generating method. The computer readable storage medium may be a volatile Memory (RAM), such as a Random-Access Memory (RAM); or a nonvolatile Memory (non-volatile Memory), such as a Read-Only Memory (ROM), a flash Memory (flash Memory), a Hard Disk (HDD) or a Solid State Drive (SSD); but may be a respective device, such as a mobile phone, a computer, a tablet device, a personal digital assistant, etc., comprising one or any combination of the above memories.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, magnetic disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing is merely specific embodiments of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions easily conceivable by those skilled in the art within the technical scope of the present application should be covered in the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (10)

1. A method of data generation, the method comprising:
determining at least one product corresponding to a target material alignment scene by utilizing a data generation rule, and expanding production materials step by step aiming at each product in the at least one product until the expansion is carried out to a target level to obtain corresponding materials at all levels; the data generation rule is generated based on real material alignment data corresponding to the target material alignment scene;
expanding characteristic information of each material in each level of materials by utilizing the data generation rule to obtain the material characteristic information corresponding to each material; the material characteristic information at least comprises one or more of stock quantity, use priority and material type;
and determining the materials at all levels and the material characteristic information corresponding to the materials in the materials at all levels as the material information corresponding to the target material nesting scene.
2. The method of claim 1, the method further comprising:
generating at least one order according to the target material matching scene by utilizing the data generation rule, and generating corresponding order characteristic information for each order in the at least one order; the order may be: formal, stock, or forecast orders; the order characteristic information at least comprises required materials of an order;
classifying the at least one order according to the required materials to obtain at least one group of orders;
and according to the required materials of each group of orders in the at least one group of orders, carrying out production relation matching on each order in each group of orders and the corresponding materials included in the material information, and generating scene data corresponding to the target material matching scene.
3. The method of claim 1 or 2, the method further comprising:
acquiring the real material alignment data;
analyzing standard data representing the scene characteristics of the target material alignment sleeve in the real material alignment sleeve data; the standard data at least comprises: one or more of stock distribution of different materials, demand distribution of different orders, probability distribution of different materials, and material distribution required for order production;
and generating the data generation rule for the target material matching scene based on the standard data.
4. A method according to claim 3, the data generation rules comprising at least one or more of data distribution fitting rules, data association fitting rules, and special data generation rules; the generating the data generation rule for the target material matching scene based on the standard data at least comprises one or more of the following:
generating the data distribution fitting rule based on different distributional data in the standard data by using a distributional generating function;
generating the data association fitting rule based on association relations among different distributive data in the standard data;
and setting the special data generation rule based on the distribution condition of the abnormal data in the standard data.
5. The method according to claim 4, wherein the expanding the characteristic information of each material in the materials at each level by using the data generating rule to obtain the material characteristic information corresponding to each material includes one or more of the following:
determining initial material characteristic information of each material according to the data distribution fitting rule;
performing association adjustment on the initial material characteristic information of each material according to the data association fitting rule to obtain adjustment material characteristic information of each material in each level of materials;
and generating special data of the material characteristic information of each material according to the special data generation rule to obtain the material characteristic information corresponding to each material.
6. The method of claim 4, wherein the generating corresponding order characteristic information for each of the at least one order using the data generation rules comprises one or more of:
determining initial order feature information of each order according to the data distribution fitting rule;
performing association adjustment on the initial order feature information of each order according to the data association fitting rule to obtain adjustment order feature information of each order;
and generating special data for the adjustment order characteristic information of each order according to the special data generation rule to obtain the order characteristic information of each order.
7. The method of claim 2, wherein the matching of production relations between the respective orders in each set of orders and the corresponding materials included in the material information is performed according to the required materials in each set of orders, and after generating the scene data corresponding to the target material matching scene, the method further comprises:
establishing a mixed integer programming problem model aiming at the scene data, and calling a solver to solve the mixed integer programming problem model to obtain an optimal solution;
screening the scene data with the time length within the range of the target solving time length for solving the mixed integer programming problem model into target scene data;
and carrying out model training on a to-be-trained solution model of the target material matching scene by utilizing the target scene data and the optimal solution to obtain a target solution model, so as to solve the real data in the target material matching scene by utilizing the target solution model.
8. A data generating apparatus comprising:
the determining module is used for determining at least one product corresponding to the target material alignment scene by utilizing the data generating rule, and expanding production materials step by step aiming at each product in the at least one product until the expansion is carried out to a target level, so as to obtain corresponding materials at all levels; the data generation rule is generated based on real material alignment data corresponding to the target material alignment scene;
the expansion module is used for expanding the characteristic information of each material in each level of materials by utilizing the data generation rule to obtain the material characteristic information corresponding to each material; the material characteristic information at least comprises one or more of stock quantity, use priority and material type;
the determining module is further configured to determine the materials at each level and the material characteristic information corresponding to each material in the materials at each level as material information corresponding to the target material matching scene.
9. A data generating apparatus comprising: a processor, a memory, and a communication bus;
the communication bus is used for realizing communication connection between the processor and the memory;
the processor for executing a computer program stored in the memory to implement the data generation method of any one of claims 1 to 7.
10. A computer readable storage medium storing one or more computer programs executable by one or more processors to implement the data generation method of any of claims 1 to 7.
CN202311632279.0A 2023-11-30 2023-11-30 Data generation method, device, equipment and storage medium Pending CN117592905A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311632279.0A CN117592905A (en) 2023-11-30 2023-11-30 Data generation method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311632279.0A CN117592905A (en) 2023-11-30 2023-11-30 Data generation method, device, equipment and storage medium

Publications (1)

Publication Number Publication Date
CN117592905A true CN117592905A (en) 2024-02-23

Family

ID=89919849

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311632279.0A Pending CN117592905A (en) 2023-11-30 2023-11-30 Data generation method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN117592905A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118469460A (en) * 2024-07-11 2024-08-09 南京达链信息技术有限公司 Material allocation optimization system

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118469460A (en) * 2024-07-11 2024-08-09 南京达链信息技术有限公司 Material allocation optimization system
CN118469460B (en) * 2024-07-11 2024-09-13 南京达链信息技术有限公司 Material allocation optimization system

Similar Documents

Publication Publication Date Title
CN111667267B (en) Block chain transaction risk identification method and device
CN110188910B (en) Method and system for providing online prediction service by using machine learning model
CN107169768B (en) Method and device for acquiring abnormal transaction data
CN108364106A (en) A kind of expense report Risk Forecast Method, device, terminal device and storage medium
CN110852882B (en) Packet consensus method, apparatus, device, and medium for blockchain networks
CN113869521A (en) Method, device, computing equipment and storage medium for constructing prediction model
CN117592905A (en) Data generation method, device, equipment and storage medium
CN103150696A (en) Method and device for selecting potential customer of target value-added service
CN111582341B (en) User abnormal operation prediction method and device
CN113536081A (en) Data center data management method and system based on artificial intelligence
CN115757124A (en) Test case generation method based on neural network
CN113486584A (en) Equipment fault prediction method and device, computer equipment and computer readable storage medium
CN111931848A (en) Data feature extraction method and device, computer equipment and storage medium
CN113344708A (en) Large-scale system production and exercise application evaluation method and system
CN110020728B (en) Service model reinforcement learning method and device
CN108363789B (en) Short-term missing repairing method and device for electricity consumption meter data of industrial and commercial users
CN110633971A (en) Method and device for estimating loss
CN114968933A (en) Method and device for classifying logs of data center
CN115099934A (en) High-latency customer identification method, electronic equipment and storage medium
CN105101475B (en) A kind of method and device of identification WLAN WLAN potential users
CN114661750A (en) Feature derivation method and device, nonvolatile storage medium and electronic equipment
CN114692888A (en) System parameter processing method, device, equipment and storage medium
CN113313615A (en) Method and device for quantitatively grading and grading enterprise judicial risks
CN111984704A (en) Data screening method and device
CN113139563A (en) Optimization method and device of image classification model

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination