CN113793203A - Order processing method and device - Google Patents

Order processing method and device Download PDF

Info

Publication number
CN113793203A
CN113793203A CN202111122414.8A CN202111122414A CN113793203A CN 113793203 A CN113793203 A CN 113793203A CN 202111122414 A CN202111122414 A CN 202111122414A CN 113793203 A CN113793203 A CN 113793203A
Authority
CN
China
Prior art keywords
order
orders
target
tree
scoring
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
CN202111122414.8A
Other languages
Chinese (zh)
Inventor
张昌文
范伟
宋天恒
孙赞
袁浩
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.)
Lenovo Beijing Ltd
Original Assignee
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 Lenovo Beijing Ltd filed Critical Lenovo Beijing Ltd
Priority to CN202111122414.8A priority Critical patent/CN113793203A/en
Publication of CN113793203A publication Critical patent/CN113793203A/en
Pending legal-status Critical Current

Links

Images

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
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
    • G06Q30/0635—Processing of requisition or of purchase orders
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/12—Computing arrangements based on biological models using genetic models
    • G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
    • 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
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • 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
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • 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)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Development Economics (AREA)
  • Health & Medical Sciences (AREA)
  • Biophysics (AREA)
  • Tourism & Hospitality (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Software Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Quality & Reliability (AREA)
  • Accounting & Taxation (AREA)
  • Artificial Intelligence (AREA)
  • Finance (AREA)
  • Educational Administration (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Biomedical Technology (AREA)
  • Primary Health Care (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Computer Hardware Design (AREA)
  • Geometry (AREA)
  • Manufacturing & Machinery (AREA)
  • Mathematical Physics (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)

Abstract

The application provides an order processing method and an order processing device, wherein the method comprises the following steps: obtaining a plurality of orders to be processed; according to various attribute characteristics of the order, constructing an order scoring tree which accords with a genetic programming algorithm, wherein the order scoring tree comprises a logical operation relation among the various attribute characteristics; determining order scoring of the order according to the logical operation relationship among various attribute characteristics in the order scoring tree; determining order ranks of the orders according to the order scores of the orders; carrying out material matching and index scoring simulation operation on the plurality of orders based on order sequencing and configured material configuration information and evaluation index information to obtain comprehensive index scores of the plurality of orders; and optimizing the logical operation relationship in the order scoring tree by adopting a genetic programming algorithm with the optimal comprehensive index score as a target until the comprehensive index score is optimal to obtain the target order sequence under the condition of the optimal comprehensive index score. The scheme of the application can determine the optimal order sequencing more accurately and reliably.

Description

Order processing method and device
Technical Field
The present application relates to the field of data processing technologies, and in particular, to an order processing method and apparatus.
Background
With the rapid development of socio-economic, many manufacturing enterprises have a large number of orders to be processed at the same time. Because enterprise material supplies are typically limited, the enterprise needs to prioritize orders to decide which orders can use material preferentially.
Because there is competition of material resources among the orders, there is also a change in the manner in which the material is allocated to the orders when the orders are prioritized. The distribution of materials to orders affects the overall yield, delivery achievement rate, profit and other key indicators corresponding to the orders. However, under the condition of a large number of orders, the combination modes of the order priority ordering are also more, and it is difficult to find the order priority ordering which makes the key index better through a traversal mode, so how to determine the order priority ordering which can optimize the whole key index is a technical problem which needs to be solved urgently by a person skilled in the art.
Disclosure of Invention
The application provides an order processing method and device.
The order processing method comprises the following steps:
obtaining a plurality of orders to be processed, wherein each order comprises characteristic values of various attribute characteristics;
according to the multiple attribute characteristics, constructing an order scoring tree which accords with a genetic programming algorithm, wherein the order scoring tree comprises the logical operation relation among the multiple attribute characteristics;
determining the order score of the order according to the characteristic values of the various attribute characteristics of the order and the logical operation relationship among the various attribute characteristics in the order score tree;
determining order ranks of the orders according to the order scores of the orders;
carrying out material matching and index scoring simulation operation on the plurality of orders based on the order sequencing and the configured material configuration information and evaluation index information to obtain comprehensive index scores of the plurality of orders;
and optimizing the logical operation relationship in the order scoring tree by adopting a genetic programming algorithm with the optimal comprehensive index score as a target until the comprehensive index score is optimal to obtain target order sequencing under the condition of optimal comprehensive index score.
In a possible implementation manner, the constructing an order scoring tree conforming to a genetic programming algorithm according to the plurality of attribute features includes:
determining at least one first attribute feature of the plurality of attribute features that is numerical and at least one second attribute feature that is not numerical;
combining the at least one attribute feature and the at least one second attribute feature to construct an order scoring tree conforming to a genetic programming algorithm, wherein the order scoring tree comprises a logic operation relation which is a multiplied logic type branch tree and a numerical type branch tree, the logic type branch tree comprises the logic operation relation of the at least one first attribute feature, and the numerical type branch tree comprises the logic operation relation of the at least one second attribute feature;
and optimizing the logical operation relationship in the order scoring tree by adopting a genetic programming algorithm by taking the optimal comprehensive index scoring as a target, wherein the method comprises the following steps:
and optimizing the logical operation relationship in the logic type branch tree and the numerical type branch tree by adopting a genetic programming algorithm with the optimal comprehensive index score as a target.
In yet another possible implementation, the plurality of attribute characteristics of the order include a customer level of the order;
the determining at least one first attribute characteristic belonging to a numerical type and at least one second attribute characteristic not belonging to a numerical type of the plurality of attribute characteristics includes:
determining at least one first attribute characteristic outside the customer level and belonging to a numerical type and at least one second attribute characteristic outside the customer level and not belonging to a numerical type from the plurality of attribute characteristics;
the order scoring tree includes: a first scoring tree adapted to be below a set level at a customer level and a second scoring tree adapted to be not below the set level at the customer level, the first scoring tree including a first logical type branch tree and a first numerical type branch tree, the second scoring tree including a second logical type branch tree and a second numerical type branch tree, the first logical type branch tree and the second logical type branch tree each including a logical operation relationship of at least one first attribute feature, the first numerical type branch tree and the second numerical type branch tree each including a logical operation relationship of at least one second attribute feature;
determining the order score of the order based on the characteristic values of the multiple attribute characteristics of the order and according to the logical operation relationship among the multiple attribute characteristics in the order score tree, wherein the determining comprises the following steps:
if the customer level of the order is lower than the set level, determining the order score of the order based on the characteristic value of at least one first attribute characteristic and the characteristic value of at least one second attribute characteristic of the order and according to the logical operation relationship between a first logical type branch tree and a first numerical type branch tree in the first scoring tree;
and if the customer level of the order is not lower than the set level, determining the order score of the order based on the characteristic value of at least one first attribute characteristic and the characteristic value of at least one second attribute characteristic of the order and according to the logical operation relationship between a second logic type branch tree and a second numerical type branch tree in the second scoring tree.
In another possible implementation manner, the method further includes:
acquiring a corresponding comprehensive index score when the comprehensive index score is optimal, and outputting the comprehensive index score;
and obtaining an order scoring tree obtained when the comprehensive index score is optimal, and outputting a structure diagram of the order scoring tree.
In another possible implementation manner, the characteristic values of the plurality of attribute characteristics of the order include: the product production quantity of the production product corresponding to the order and the income characteristic of the order;
the order further comprises at least one batch feature;
the method further comprises the following steps:
determining at least one target batch characteristic according to which batch processing of a plurality of orders is required;
respectively determining an order set of each target batch characteristic from the plurality of orders based on at least one batch characteristic included in the orders, wherein the order set of the target batch characteristic includes at least one order matched with the target batch characteristic;
determining the total order number, the total product production number and the total order income of the orders by combining the product production number and income characteristics of the orders;
determining a batch priority score of an order set corresponding to the target batch characteristic according to the product production quantity and income characteristic of each order in the order set of the target batch characteristic and the order quantity of the orders in the order set, and by combining the total order quantity, the total product production quantity and the total order income;
and determining the batch priority corresponding to the order set of the at least one target batch characteristic according to the batch priority score of the order set.
In another possible implementation manner, after the ranking of the target orders under the condition that the obtained composite index score is optimal, the method further includes:
obtaining scheduling data of the plurality of orders, where the scheduling data is scheduling result data obtained by scheduling a plurality of work orders split from the plurality of orders in combination with the target order ranking, and the scheduling data includes: information of work orders required to be executed by different production lines in each sub-period of the target planning period;
displaying a rearrangement adjustment interface based on the scheduling data, the rearrangement adjustment interface at least comprising: a work order schedule chart and a rearrangement setting area, wherein the work order schedule chart comprises an indication chart of work orders planned to be produced by each production line in each sub-period of the target planning period;
acquiring rearrangement range constraint data set in the rearrangement setting area by a user, wherein the rearrangement range constraint data comprises: at least one scheduling constraint parameter for adjusting the scheduling data;
determining at least one candidate production line to which the target work order can be adjusted and at least one candidate sub-period in the candidate production line based on a target work order selected by a user in a work order schedule chart, the at least one scheduling constraint parameter and scheduling data;
identifying candidate sub-slots in the at least one candidate production line in the work order schedule;
and adjusting the target work order to the target candidate sub-time interval in the target candidate production line based on the target candidate sub-time interval in the target candidate production line selected by the user in the work order schedule diagram so as to complete the re-arrangement process of the target work order and obtain re-arrangement process data corresponding to the schedule data.
Wherein, an order processing apparatus includes:
the order obtaining unit is used for obtaining a plurality of orders to be processed, and each order comprises characteristic values of various attribute characteristics;
the genetic tree construction unit is used for constructing an order scoring tree which accords with a genetic programming algorithm according to the multiple attribute characteristics, and the order scoring tree comprises the logical operation relation among the multiple attribute characteristics;
the order scoring unit is used for determining order scoring of the order based on the characteristic values of the various attribute characteristics of the order and according to the logical operation relation among the various attribute characteristics in the order scoring tree;
the order sorting unit is used for determining the order sorting of the orders according to the order scores of the orders;
the simulation operation unit is used for carrying out simulation operation of material matching and index scoring on the orders based on the order sorting and the configured material configuration information and evaluation index information to obtain comprehensive index scores of the orders;
and the comprehensive optimization unit is used for optimizing the logical operation relation in the order scoring tree by adopting a genetic programming algorithm with the optimal comprehensive index score as a target until the comprehensive index score is optimal, so as to obtain the target order sequence under the condition of optimal comprehensive index score.
As can be seen from the above, in the present application, an order scoring tree conforming to a genetic programming algorithm is constructed according to various attribute features of orders, order scores of the orders can be determined by using the order scoring tree, and order ranks of the orders are determined based on the order scores. On the basis, simulation operation of material and index scoring is carried out based on order sorting, and comprehensive index scoring obtained through simulation operation is determined, so that the influence generated by material distribution under the order sorting can be reflected by the comprehensive index scoring.
Moreover, the method and the device can continuously optimize the logical operation relationship in the order scoring tree by using a genetic programming algorithm so as to continuously re-optimize the order sequencing of a plurality of orders until the comprehensive index score reaches the optimum, thereby synthesizing the influence of material distribution under different order sequencing on index optimization, finally determining the order sequencing which enables the comprehensive index score to be optimum, and further more accurately and reliably determining the optimum order sequencing.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on the provided drawings without creative efforts.
FIG. 1 is a flow chart illustrating an order processing method according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram illustrating a structure of an order scoring tree conforming to a genetic programming algorithm according to an embodiment of the present application;
FIG. 3 is a schematic flow chart illustrating an order processing method according to an embodiment of the present application;
FIG. 4 is a schematic diagram illustrating another structure of an order scoring tree conforming to a genetic programming algorithm provided by an embodiment of the present application;
FIG. 5 is a schematic flow chart illustrating the determination of order batches in the order processing method according to the embodiment of the present application;
FIG. 6 is a flow chart illustrating the work order rescheduling in the order processing method according to the embodiment of the present application;
FIG. 7 illustrates a schematic view of a rearrangement adjustment interface provided in an embodiment of the present application;
FIG. 8 is a schematic diagram of an operation interface for work order rescheduling provided in the embodiments of the present application;
FIG. 9 is a schematic diagram of an interface for adjusting work order schedules according to an embodiment of the present application;
fig. 10 is a schematic structural diagram illustrating a component of an order processing apparatus according to an embodiment of the present application;
fig. 11 shows a schematic diagram of a component architecture of an electronic device according to an embodiment of the present application.
Detailed Description
The scheme of the application is applicable to the processing of some orders existing in a manufacturing enterprise, such as the processing of a plurality of orders of different customers by a supplier.
In the present application, the processing of the order may involve determining order ranking that optimizes the overall evaluation index, and may also involve determining the batch of the order, scheduling and rescheduling of work orders divided from the order, and the like.
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without inventive step, are within the scope of the present disclosure.
As shown in fig. 1, which shows a flowchart of an order processing method according to the present application, the method of the present embodiment can be applied to any electronic device with data processing capability.
The method of the embodiment may include:
s101, obtaining a plurality of orders to be processed.
Wherein each order includes feature values for a plurality of attribute features.
It is understood that the order is provided by the customer to the supplier to request the supplier for the corresponding product, but other orders are possible without limitation. For example, an order may be an order issued by a customer to a supplier that requires the production or manufacture of a related product.
The attribute features of the order refer to information related to content and source of the order. In general, orders have a plurality of attribute features with different dimensions, and the feature value of an attribute feature is a specific value under the attribute feature.
For example, the attribute characteristics of an order may include: one or more of the creation date of the order, the delivery time of the order, the income of the order, the profit of the order, the customer type of the order and the like.
It will be appreciated that the orders to be ordered are typically of the same type, such as orders that require the use of the same plant or that require the production of the same product, and therefore, the type of attribute characteristics that each order has are the same.
And S102, constructing an order scoring tree according with a genetic programming algorithm according to the various attribute characteristics.
The order scoring tree comprises a logical operation relation among various attribute characteristics.
The genetic programming algorithm is an optimization algorithm, and the comprehensive evaluation index is optimized by using a tree structure of the genetic programming algorithm.
Based on this, the order scoring tree in the present application is a tree structure under the genetic programming algorithm, but the attribute features of each order in the order scoring tree and the nodes of different attribute features establish association through logical operators, so that the order scoring tree can represent the logical relationship among various attribute features of the order. It can be seen that an order scoring tree represents a function between attribute features in an order.
Fig. 2 is a schematic diagram illustrating a structure of the order scoring tree according to the present application.
As can be seen from fig. 2, the bottom layer of the order scoring tree is a plurality of attribute feature nodes 201, each attribute feature node represents an attribute feature of the order, and two attribute features are linked by a logical operation relationship, for example, an operation node 202 marked with "operation" in the order scoring tree in the figure represents a logical operation relationship, and the logical operation relationships corresponding to different operation nodes are different, for example, the logical operation relationship may include: various mathematical operations such as multiplication, division, and addition, etc., which are not limited in this regard.
It can be understood that the logical operation relationship of each operation node in the initially constructed order scoring tree may be randomly set, and the logical operation relationship represented by each operation node is continuously adjusted in the continuous optimization process, so as to obtain the order scoring tree capable of accurately evaluating order scoring.
S103, determining order scores of the orders according to the characteristic values of the various attribute characteristics of the orders and the logical operation relation among the various attribute characteristics in the order score tree.
It can be understood that the order scoring tree is characterized by a function, and under the condition that various attribute features in the function and the logical operation relationship thereof are determined, if feature values in various attribute features are obtained, the output result of the order scoring tree can be finally obtained.
Correspondingly, the method and the device input the characteristic values of the attribute characteristics of the order into the corresponding nodes in sequence according to the node distribution of the attribute characteristics in the order scoring tree, and finally obtain a score output by the order scoring tree through the logical relation operation of each layer in the order scoring tree.
As in the order scoring tree in fig. 2, assuming that the leftmost attribute feature node is the delivery date of the order, the specific value of the delivery date of the order needs to be input into the attribute feature node, and other attribute feature nodes are similar. On the basis, the characteristic values of all the attribute characteristics are subjected to multi-level logic operation in the order scoring tree, and finally, the result output by the topmost operation node in the order scoring tree is the order score.
It is understood that, in the present application, the feature value of some attribute features in the order may be a character string value, for example, whether the customer is an important customer or not, in which case, the feature value of the attribute feature may be converted into a logical type value, for example, depending on whether the customer is an important customer or not, the feature value of this attribute feature may be converted into 0 or 1, and for a feature attribute whose date of delivery or other feature value does not belong to a numerical type, the feature value of the attribute feature may also be converted into a logical type value capable of representing the meaning of its feature value according to a set conversion rule.
Of course, if a plurality of orders are obtained in step S101, the feature values of the respective attribute features of the orders have been converted without performing this operation.
And S104, determining order sequence of the orders according to the order scores of the orders.
The order sorting refers to a sorting result of a plurality of orders.
It will be appreciated that order ordering reflects the material allocation sequencing of orders. Considering that most of the material distribution processes are to distribute materials to orders in sequence from the front to the back of the order sorting, the order sorting can be obtained by sorting a plurality of orders according to the order from high to low of the order grade in the application.
Of course, if the materials are distributed in order from back to front, the order may be sorted from low to high according to the order score.
And S105, carrying out material matching and index scoring simulation operation on the plurality of orders based on the order sequencing and the configured material configuration information and the configured evaluation index information to obtain a comprehensive index score of the plurality of orders.
The evaluation index information may include at least one evaluation index, and may further include weight information of the at least one evaluation index. The evaluation index is an evaluation standard for evaluating the completion condition of the multiple orders and is also an optimization parameter index for optimizing the sequencing of the multiple orders.
It can be understood that the evaluation index required to be optimized can be set according to different actual requirements. For example, the evaluation index in the present application may include one or more of key indexes such as delivery achievement rate, total income of the order and total profit of the order. The delivery period achievement rate refers to the proportion of delivery periods of the orders on time. The total revenue of an order refers to the total revenue that can be generated by multiple orders, and the total profit is similar.
It will be appreciated that the manner in which material is dispensed to the various orders will vary due to the order, for example, the top order will have priority over material delivery and dispensing, while the back order may have insufficient material. It can be seen that the different material allocated to the order will affect the actual revenue generated by the order and the delivery achievement rate. Therefore, in order to determine the comprehensive index scores of a plurality of orders in a certain order, the material distribution mode in the order sequence and the scoring condition of each evaluation index in the material distribution mode need to be determined.
Based on this, the present application performs simulation operation in order to finally determine the composite index score. The simulation operation refers to the simulation calculation of distributing materials to the orders based on the order sorting simulation and scoring the evaluation index by combining the materials distributed by the orders.
In one possible implementation, the simulation operation of this step includes: the method comprises two parts of material matching simulation and simulation calculation of comprehensive index scoring.
The material matching simulation can simulate the material matching and distribution of each order in the plurality of orders by combining the material configuration information and the determined order sequence to obtain the material distribution information which can be distributed by each order. The material configuration information may be material information such as material type and quantity available for the plurality of orders.
For example, the order of the materials to be distributed is sequentially determined according to the order sequence by combining the material configuration information, and for the order, the material information capable of being distributed for the order can be determined according to the material demand condition of the order and the remaining available material information until the material distribution of all the orders is completed.
And (3) performing simulation calculation of the comprehensive index score to determine the respective score of at least one evaluation index according to the material information distributed by each order. On the basis, the score of each evaluation index is combined with the weight information of the at least one evaluation index, and a comprehensive index score can be determined.
For example, the total income of the order is taken as an example of the evaluation index, and the total income of the order refers to the total income which can be generated by a plurality of orders determined by combining the material distribution condition of the order under the current order sorting. For example, in conjunction with the allocated materials for each order, and revenue information for each order, the actual revenue for each order placed in the order sequence may be simulated, and then in conjunction with the simulated actual revenue for each order, the total revenue for the plurality of orders may be derived.
Of course, the total order revenue is taken as an example, and if the evaluation index is only one, the total order revenue is the comprehensive evaluation index. If a plurality of different evaluation indexes exist, the weighting summation can be carried out on each evaluation index by combining the weight of each evaluation index to obtain a comprehensive evaluation index.
And S106, optimizing the logical operation relation in the order scoring tree by adopting a genetic programming algorithm with the optimal comprehensive index score as a target until the comprehensive index score is optimal, and obtaining the target order sequence under the condition of optimal comprehensive index score.
It can be understood that the process of optimizing the comprehensive index score is also a process of optimizing the logical operation relationship of the order score tree by using a genetic programming algorithm, recalculating the score of each order by combining the optimized order score tree, and re-optimizing the order sequence.
After the order sorting is re-optimized, the order sorting determined after optimization is required to be combined, the comprehensive index score is re-determined, and if the comprehensive index score reaches the optimum, the order sorting determined for the last time is determined as the optimum order sorting; if the comprehensive index score does not reach the optimum, the logic operation relation in the order scoring tree is still required to be adjusted based on the genetic programming algorithm, the order score is recalculated, the order sorting is optimized, and the like, and the operation is continuously circulated until the comprehensive evaluation index reaches the optimum.
Wherein, the determination of the optimal specific implementation of the comprehensive evaluation index may also have various possibilities.
For example, in one implementation, the overall evaluation index may be determined to be optimal when the overall evaluation index converges, e.g., during continuous multiple cycles, the overall evaluation index score may be kept constant or the variation amplitude may be smaller than a set value.
In yet another possible implementation manner, it may be determined that the comprehensive evaluation index is optimal when the number of times of optimization adjustment (i.e., the number of cycles) reaches the set number of times. If the optimization adjustment times reach the set times, the comprehensive evaluation index is determined to reach the optimum.
As can be seen from the above, in the present application, an order scoring tree conforming to a genetic programming algorithm is constructed according to various attribute features of orders, order scores of the orders can be determined by using the order scoring tree, and order ranks of the orders are determined based on the order scores. On the basis, simulation operation of material and index scoring is carried out based on order sorting, and comprehensive index scoring obtained through simulation operation is determined, so that the influence generated by material distribution under the order sorting can be reflected by the comprehensive index scoring.
Moreover, the method and the device can continuously optimize the logical operation relationship in the order scoring tree by using a genetic programming algorithm so as to continuously re-optimize the order sequencing of a plurality of orders until the comprehensive index score reaches the optimum, thereby synthesizing the influence of material distribution under different order sequencing on index optimization, finally determining the order sequencing which enables the comprehensive index score to be optimum, and further more accurately and reliably determining the optimum order sequencing.
In addition, material configuration information and evaluation index information can be set according to needs, so that a user can configure the material information according to actual production conditions and set evaluation indexes and weight conditions thereof by combining actual requirements, and the scheme can be flexibly applied to different production conditions.
It can be understood that, in the application, in order to enable the user to intuitively know how to specifically grade the optimal target order ranking comprehensive index score, the application may further obtain the comprehensive index score corresponding to the optimal comprehensive evaluation index score, and output the optimal comprehensive index score.
Of course, the method and the device for obtaining the comprehensive index scores can also obtain the scores of all the evaluation indexes when the comprehensive index scores are optimal, and output the scores of all the evaluation indexes corresponding to the optimal comprehensive index scores, so that a user can know the conditions of all the evaluation indexes under the currently determined optimal order ranking in more detail.
It will be appreciated that, in addition to being concerned with the situation of composite index scoring for an optimal order sequence, the user may also wish to understand the specific functional logic and the like for determining the optimal order sequence. Based on this, after determining the optimal target order sequence, the method can further obtain the order scoring tree obtained when the comprehensive evaluation index score is optimal, that is, when determining that the comprehensive evaluation index is optimal, the structure diagram of the order scoring tree obtained by optimization. Correspondingly, the structure diagram of the order scoring tree obtained through final optimization can be output, so that a user can determine and obtain information such as a specific implementation principle of the optimized target order sequencing according to the structure diagram.
It can be understood that some of the attribute features of the order are numerical attribute features, and some of the attribute features are non-numerical attribute features, and due to the difference of the feature values of the two types of attribute features, if the two types of attribute features are mixed to perform a logical relationship operation, the accuracy of order scoring is likely to be affected.
In order to further accurately determine the order score representing the ordering order suitable for the order, in the application, the order score tree constructed may include a branch tree suitable for the attribute feature of the numerical type and a branch tree suitable for the attribute feature of the non-numerical type.
Specifically, after obtaining a plurality of orders, according to a plurality of attribute characteristics of the orders, at least one first attribute characteristic belonging to a numerical type and at least one second attribute characteristic not belonging to the numerical type in the plurality of attribute characteristics can be determined.
Accordingly, an order scoring tree that conforms to a genetic programming algorithm may be constructed in conjunction with the at least one attribute feature and the at least one second attribute feature. The order scoring tree comprises a logic type branch tree and a numerical type branch tree, wherein the logic operation relationship is a multiplied logic type branch tree and the numerical type branch tree, the logic type branch tree comprises the logic operation relationship among the at least one first attribute characteristic, and the numerical type branch tree comprises the logic operation relationship among the at least one second attribute characteristic.
The attribute feature belonging to the numerical type (may also be referred to as an arithmetic attribute feature) is an attribute feature in which the data type of the feature value is a numerical value. For example, when the attribute feature is income or profit, the income or profit takes on a specific data value, and thus, the two attribute features belong to numerical attribute features.
The attribute feature belonging to the non-numerical type refers to an attribute feature in which the data type of the feature value is not a numerical value that characterizes the data size. If the attribute feature is whether the client is an important client, the feature value of the attribute feature may be yes or no, or a logical value 0 or 1 indicating whether the client is an important client, and the attribute feature is a non-numeric data feature. For another example, if the attribute feature is a date of delivery, the feature value of the attribute feature may be in the form of a character string, and even if the date of delivery in the form of a character string is converted into a numeric form, the feature value belongs to a logical numeric value rather than a numeric value capable of representing a magnitude relationship.
For the sake of convenience of distinction, the present application refers to an attribute feature belonging to a numerical type as a first attribute feature, and an attribute feature not belonging to a numerical type as a second attribute feature.
It is understood that the nodes of the attribute features contained in the logical branch tree are different from those contained in the numerical branch tree, and the logical operation relationship between the different logical features contained in the two branch trees is also different.
In this case, when the order score tree is optimized using the genetic programming algorithm with the goal of the optimal composite index score, the logical operation relationships in the logical type branch tree and the numerical type branch tree may be optimized, respectively.
Further, considering that there is an influence on the order sorting order for customers with different degrees of importance, the order scoring tree can be constructed and the order sorting can be optimized by combining the customer levels. The following is a description with reference to the flowchart.
As shown in fig. 3, which shows another flowchart of the order processing method provided in the embodiment of the present application, the method of the present embodiment may include:
s301, a plurality of orders to be processed are obtained.
Wherein each order includes feature values for a plurality of attribute features.
The various attribute characteristics of the order in this application include at least the customer level of the order.
It is understood that the client level may represent the importance of the client in practical applications, and the number of levels of the client level may be set as desired, for example, if the client is divided into important clients and non-important clients, the client level may be set to two levels of a low level and a high level.
S302, at least one first attribute characteristic which is out of the client level and belongs to the numerical type and at least one second attribute characteristic which is out of the client level and does not belong to the numerical type are determined from the multiple attribute characteristics.
In the embodiment of the present application, the customer level is used as a special attribute feature and does not participate in the classification of the numerical attribute feature and the non-numerical attribute feature, and then the processing of order scoring and the like is constructed and performed according to the attribute feature of the customer level, which is not described herein again.
S303, combining the at least one attribute feature and the at least one second attribute feature to construct an order scoring tree conforming to the genetic programming algorithm.
Wherein, order score tree includes: the first grading tree is suitable for the customer level lower than the set level, and the second grading tree is suitable for the customer level not lower than the set level.
Wherein the first scoring tree includes a first logical type branch tree and a first numerical type branch tree. The second scoring tree includes: a second logical type branch tree and a second numerical type branch tree.
For the first and second score trees, the first and second logical branch trees each include at least one logical operation relationship of the first attribute feature, and the first and second numerical branch trees each include at least one logical operation relationship of the second attribute feature.
It can be seen that the first score tree and the second score tree have similar composition structures, but the nodes and logical operation relations of the attribute features contained in the logic type branch tree and the numerical type branch tree in different score trees are different.
For ease of understanding, reference may be made to fig. 4, which shows a schematic diagram of another structure of an order scoring tree according to the present application.
As can be seen from fig. 4, in the order scoring tree structure, two scoring trees are connected by an addition node 400, and the left scoring tree 401 may be considered as a scoring tree suitable for a more important customer level, while the right scoring tree 402 may be considered as a scoring tree suitable for a less important customer level.
As can be seen from fig. 4, the left and right scoring trees each include a logical type branching tree and a numerical type branching tree, respectively.
The structure of the logical branch tree and the numerical branch tree in each score tree can be referred to the related description of the previous embodiments, and will not be described herein. In fig. 4, to facilitate distinguishing the logical operation relationship between the logical type branch tree and the numerical type branch tree, the logical operation L in the logical type branch tree is used to represent the logical operation relationship in the logical type branch tree, and the logical operation a in the numerical type branch tree is used to represent the logical operation relationship in the numerical type branch tree.
S304, if the customer level of the order is lower than the set level, determining the order score of the order based on the characteristic value of at least one first attribute characteristic and the characteristic value of at least one second attribute characteristic of the order and according to the logical operation relationship between the first logical type branch tree and the first numerical type branch tree in the first score tree.
S305, if the customer level of the order is not lower than the set level, determining the order score of the order based on the characteristic value of at least one first attribute characteristic and the characteristic value of at least one second attribute characteristic of the order and according to the logical operation relationship in a second logic type branch tree and a second numerical type branch tree in a second score tree.
The setting level may be set according to the type of the customer level and the actual requirement, which is not limited herein.
In the present application, for each order, a scoring tree to be utilized for evaluating the order score of the order is determined according to the attribute feature of the customer level in the order, so that for an order, only step S304 or step S305 needs to be executed according to the customer level.
After the score tree for the order is determined, the process of determining the score of the order using the score tree is the same as that of the previous embodiment, and is not described herein again.
As described with reference to fig. 4, if the customer level of an order is higher than the set level, the order score of the order may be determined using the scoring tree 401 on the left side in fig. 4, in this case, since there is no input of the value of the attribute feature in the scoring tree 402 on the right side and the output value of the scoring tree on the right side is 0, the output result of the order scoring tree is the order score output by the scoring tree 401 on the left side.
S306, combining the order scores of the orders, and determining the order sequence of the orders.
S307, carrying out material matching and index scoring simulation operation on the plurality of orders based on order sequencing and configured material configuration information and evaluation index information to obtain comprehensive index scores of the plurality of orders.
And S308, optimizing the logical operation relations among the logical branch trees and the numerical branch trees in the first scoring tree and the second scoring tree by adopting a genetic programming algorithm with the optimal comprehensive index score as a target until the comprehensive index score is optimal, and obtaining the target order sequence under the condition of optimal comprehensive index score.
The specific implementation process of steps S306 to S308 is similar to that of the previous embodiment, and is not described herein again.
Of course, in this embodiment, the optimal composite index score corresponding to the target order sequence and the structure diagram of the corresponding order score tree may also be output, which is specifically described above and will not be described herein again.
It will be appreciated that in practice, the processing of orders may also involve the scheduling of orders to determine which orders to place as a batch on the same production line. In order placement involves determining the batches of orders and the priority of each order batch. The batching of orders is the determination of which orders to process as a batch, and the priority of the orders for each batch.
It can be understood that, for different specific contents of the orders, the batching of the orders may be performed after the target order ranks corresponding to the determined multiple orders are determined, or may be performed before the target order ranks of the multiple orders are determined, which is determined comprehensively according to the specific contents of the orders, the production scenario, and the like.
For example, if the material required for an order is a product that needs to be produced, then a batch-like production operation for generating related materials for the plurality of orders may be determined based on the order rankings after the order rankings for the plurality of orders are determined. Of course, this is merely an example, and the present application is not limited to the order of the order and the execution order of the order.
In this application, if the order processing involves determining batches of a plurality of orders, the characteristic values of the plurality of attribute characteristics of the orders may include at least: the product production quantity of the produced product corresponding to the order and the income characteristics of the order.
The income characteristic of the order can be the income value generated by the order completion; but also a parameter characteristic that enables revenue values to be determined, such as unit price per product in an order, and the like.
It will be appreciated that when an order is batched, the batching characteristics upon which the batching is based may be set, the batching characteristics characterizing the batch characteristics that the order of the same batch needs to satisfy. For example, the batch characteristics upon which the batches are based may include: order delivery priority (or delivery deadline), readiness of resources required by the order, type of product produced by the production line, and the like.
Similarly, each order also has a batch characteristic for characterizing which batches the order is applicable to, and the batch characteristics of the order are similar to the batch characteristics optionally set, and are not described herein again.
The following describes an implementation process for determining order batch in the order processing method provided by the present application with reference to a flowchart.
As shown in fig. 5, which shows a flowchart of an implementation of determining order allocation provided in an embodiment of the present application, a method of this embodiment may include:
s501, at least one target batch characteristic required by batch processing of a plurality of orders is determined.
Wherein, the characteristic value of the attribute characteristic of the order comprises: the product production quantity of the produced product corresponding to the order and the revenue characteristics of the order.
Each order also has at least one batch feature. The batch characteristic of the order is a basis for determining the batch of the order in which the order is located. For example, the batch features of an order may include: urgent order, delivery priority, preparation state of resources required by the order, types of products required to be produced by the order and the like.
It is understood that, in order to determine which orders can be divided into several batches and which orders can be divided into the same batch, a batch characteristic according to which the order batches are divided may be set, and the batch characteristic according to which the batch processing is based is referred to as a target batch characteristic in order to distinguish from the batch characteristic that the orders themselves have. The target batch characteristics may be referred to above and will not be described in further detail herein.
S502, based on at least one batch characteristic included in the order, an order set of each target batch characteristic is determined from the plurality of orders respectively.
Wherein the set of orders for the target batch trait includes at least one order matching the target batch trait.
For example, assuming that the target batch characteristic is a product type produced by a production line, the order set corresponding to the target batch characteristic may include orders for which the desired product type is the product type in the target batch characteristic.
For another example, assuming the target batch characteristic is resource preparation complete, the marked batch characteristic including orders that have completed the required associated resource preparation may be determined to be orders in the order set corresponding to the target batch characteristic.
For another example, assuming the target batch characteristic is order delivery priority, orders with marked batch characteristics as urgent orders and delivery deadline nearing may be determined as orders in the order set corresponding to the target batch characteristic.
Of course, the above is exemplified by several possible cases, and in practical applications, the target batch feature may have other possibilities, which is not limited to this.
And S503, determining the total order number, the total product production number and the total order income of the orders by combining the product production number and income characteristics of the orders.
For example, the income characteristic of an order is the unit price of a single product produced by the order, and on the basis, the income of the order can be determined by combining the production quantity of the product which can be produced by each order and the income characteristic, and on the basis, the income of all orders is counted to obtain the total income of the orders of a plurality of orders.
For another example, the income characteristic of the order is the income generated by the order, and then the income of all orders can be directly counted to obtain the total income of the order.
The total number of product production may be counted for all orders.
S504, determining the batch priority score of the order set corresponding to the target batch characteristic according to the product production quantity and income characteristic of each order in the order set of the target batch characteristic and the order quantity of the orders in the order set, and combining the total order quantity, the product production quantity and the total order income.
It will be appreciated that the order set for each target batch characteristic is a defined order batch, however, the priority of different order batches may need to be determined in combination with the characteristics of the orders in the different order sets.
As can be appreciated, the batch priority score for an order set is used to characterize the order of priority in which the corresponding batch of the order set is placed into production. In practical application, key indexes of each batch production sequence can be set according to actual requirements, and on the basis, the batch priority scores are determined by combining the order sets and the characteristics of the above dimensions of a plurality of orders.
In one possible implementation, the order set with the least number of orders may be executed first, and the priority with higher key index score may be executed first. E.g. the batch priority Score of the order set Di for a certain target batch feature iDiCan be determined by the following formula:
Figure BDA0003277429540000181
wherein TD is the total number of orders, TP is the total number of product production, and TR is the total income of orders. N is a radical ofDiThe number of orders in an order set Di is obtained; rDiFor revenue of orders in order set Di, RDiThe method can be determined according to the income characteristics of each order in the order set Di; pDiThe total product production for all orders in order set Di can be obtained by counting the product production quantities in each order in the order set.
Wherein the value of i is from 1 to m, and m is the total number of the target batch characteristics.
Among them, by the above formula, the higher the key indexes such as revenue and profit, the higher the batch priority score of the order set.
Of course, the above description is given by taking one implementation of determining the batch priority score of an order set of a target batch characteristic as an example, and other implementations are also applicable to the present embodiment.
And S505, determining the batch priority corresponding to the order set of at least one target batch characteristic according to the batch priority score of the order set.
For example, the order sets of the at least one target batch characteristic are sorted in order of their batch priority scores from high to low, with the order position of the order set representing their batch priority.
According to the scheme, the order can be batched and the priority of each batch can be determined only by pre-configuring the target batching characteristics, so that a user can set the target batching characteristics according to actual business requirements if special conditions occur in the production process of an enterprise, the order can be batched in a targeted mode, the scheme is suitable for various batching scenes, the universality is high, corresponding batching programs do not need to be developed every time, the flexibility of order batching is improved, and the convenience is improved.
In an alternative manner, in this step S504, if the user sets the priorities of different target feature batches, the priority of target feature matching set by the user is used as the standard. For example, if the current comparison focuses on order delivery dimensions, then batches with tight order delivery may be prioritized. The method and the device can provide the function of configurable batch order priority, and a user can adjust the batch order priority according to the batch priority required by the current business.
It will be appreciated that, in practice, the batch characteristics or other characteristics of an order tag may cause an order to match multiple target batch characteristics, such that an order may belong to a corresponding order set of multiple target batch characteristics. On the basis, in order to determine the order set to which the order belongs more reasonably, after determining the batch priority corresponding to the order set of at least one target batch characteristic, if the order is determined to belong to the order sets corresponding to the multiple target batch characteristics, determining the target order set with the highest batch priority from the order set of the multiple target batch characteristics to which the order belongs, determining the order as the order in the target order set, and deleting the orders in other order sets except the target order set.
It will be appreciated that after the batch priorities for the plurality of order sets are determined, the production may be ranked according to the batch priorities of the individual order sets.
In order to facilitate the user to intuitively know the scheduling result, the scheduling result can be displayed in a Gantt chart mode.
It can be understood that products of large-scale manufacturing enterprises continuously exhibit the characteristics of short life cycle, urgent delivery date, small-batch customization and the like, and the large production scale of the products enables the organization of work fragmentation and mass production in the production process, the dimensionality and space of production decision factors are increased rapidly, and the production efficiency and stability need to be ensured by advanced production scheduling solutions more and more. The processing of orders in this application may also involve the scheduling of orders.
It is understood that the product to be produced in an order may involve multiple parts or steps, and therefore, when an order is scheduled, a work order for the order is typically determined and scheduled. By scheduling work orders, it is possible to determine which work orders are suitable to be put together for execution through a production line to improve efficiency.
The scheduling of work orders is typically after the prioritization and production of the orders. It is understood that there are many possibilities for specific scheduling of work orders, which is not limited by the present application.
However, the production process usually belongs to a dynamic time-varying system, and various variables from internal processes (such as scheduling change, labor change, equipment failure and maintenance, production resource state change, and the like) and external environments (such as order urgency, order cancellation, market change, and the like) continuously disturb the conversion rate from the original scheduling plan to the actual manufacturing execution. Therefore, the scheduling result needs to be continuously corrected to adapt to the actual production environment. The process of revising the work order schedule is referred to as a re-scheduling process.
Traditional re-arrangement is realized by manual modification and simulation, but the complexity of modern manufacturing process is such that re-arrangement is no longer a problem which can be processed by professional skill and experience. Rescheduling with poor adjustment results is likely to violate some production constraints and lose the optimization of the targets brought by the original scheduling. The time consumption of the rearrangement process of part of enterprises is even longer than that of the original edition scheduling, so that the labor intensity of production scheduling planning personnel is overlarge, and the effect and the significance of the rearrangement process are greatly reduced due to the lack of quick corresponding capacity.
Based on this, the order processing method of the application also relates to the re-scheduling of the work orders, so as to improve the convenience and efficiency of the re-scheduling. The following is a description with reference to the flowchart.
As shown in fig. 6, which shows a schematic flow chart of rescheduling work orders related to orders in the order processing method provided by the present application, the flow of this embodiment may include:
s601, obtaining the scheduling data of a plurality of orders.
The scheduling data is scheduling result data obtained by scheduling a plurality of work orders split from a plurality of orders in combination with target order sequencing.
The scheduling data includes: information of work orders required to be executed by different production lines in each sub-period of the target planning period.
The target planning time interval is a calculation time interval in which the production schedule is completed, and if work order scheduling needs to be performed on each production line from 12 o 'clock to 15 o' clock on a certain day, the target calculation time interval is from 12 o 'clock to 15 o' clock.
The sub-period of the target planning period is each time period divided by the target planning period, and each time period can be processed by one work order.
S602, displaying a rearrangement adjustment interface based on the scheduling data.
Wherein the rearrangement adjustment interface at least comprises: a work order schedule chart and a rearrangement setting area.
The work order schedule includes an indication of the work orders that each production line plans to produce during each sub-period of the target planning period.
As shown in fig. 7, a schematic diagram of a rearrangement adjustment interface in the present application is shown, and a work order schedule display area 701 is included in the rearrangement adjustment interface.
The work order schedule display area presents a work order schedule, and the specific work order schedule can be shown in FIG. 8.
FIG. 8 is a schematic diagram of a work order schedule displayed in the rescheduling interface.
As can be seen from FIG. 8, the work order schedule for a plurality of production lines is shown in the work order schedule diagram, for example, the work order schedule for production line 1 is work order a, work order b and work order c. In the work order schedule of each production line in fig. 8, the work order positioned at the forefront and with the bold line frame represents the work order being executed (or in production), the schedule of these work orders cannot be adjusted, and the work orders with the bold line frame represent the work orders that can still be rearranged.
Meanwhile, a target planning period is shown in fig. 8, i.e., the target planning period includes at least a period from 12 o 'clock to 16:00 o' clock. In order to facilitate the determination of different sub-periods corresponding to different work orders on each production line, the target planning period is indicated by one time every half hour, so that the sub-period in which each work order is located in each production line can be determined. It can be seen from fig. 8 that the sub-periods corresponding to different work orders on the same production line are different, and the durations of the sub-periods corresponding to different work orders are also different.
In the present application, the rearrangement setting region is an operation region provided for the user to perform rearrangement related setting. The setting operation performed in the rearrangement setting region will be described later, and will not be described herein again.
It is understood that, in order to enable the user to more fully understand the information of the various work orders and production lines involved in the scheduling and re-scheduling process, a work order information area and a production line information area may be provided in the re-scheduling adjustment interface.
The work order information area may display detailed information of each work order, such as an order to which the work order belongs, information related to a product to be produced by the work order, and the like, which is not limited herein.
The production line information area may display information related to each production line, such as the products that the production line can produce and the production capacity.
As shown in fig. 7, a rearrangement setting area 702 is displayed in the rearrangement adjustment interface. In the interface shown in fig. 7, a work order information area 703 is included. A "setup" button is displayed in the work order information area, and when the "setup" button is clicked by the user, the production line information area 704 and the corresponding re-scheduling setting area 702 are displayed. Of course, fig. 7 is only an example, and in practical applications, the rearrangement setting area, the work order information area, and the production line information area may be displayed on the rearrangement adjustment interface at the same time.
It is understood that, in practical applications, the rearrangement adjustment interface may also be displayed with a key indicator display area, as shown in fig. 7, and the interface is presented with a key indicator display area 705. The key indicator display area may display specific values of each key indicator on the premise of the determined scheduling data. Of course, after re-ranking the data, the values of the key indicators may be re-calculated and the displayed values of the key indicators may be updated.
S603, acquiring rearrangement process constraint data set in the rearrangement setting area by the user.
The re-range constraint data includes: at least one scheduling constraint parameter for adjusting the scheduling data.
The scheduling constraint parameter may relate to a constraint parameter of the production line, and may also relate to a constraint parameter of at least one work order that needs to be rescheduled. For example, the scheduling constraint parameters may include: the number of work orders in the production line is limited by data, work fixture limiting parameters, delay accumulation errors and other parameters, and the number of work orders can also comprise time window constraints of the work orders and other constraint parameters.
S604, based on the target work order selected by the user in the work order schedule chart, the at least one scheduling constraint parameter and the scheduling data, at least one candidate production line to which the target work order can be adjusted and at least one candidate sub-period in the candidate production line are determined.
In one implementation, at least one candidate production line to which the target work order is suitable and optionally adjustable and at least one candidate sub-period suitable for processing the target work order in the adjustable production line can be determined through logic simulation according to the set scheduling constraint parameters, the related information of the target work order and the work order condition on each production line in the scheduling data.
For example, a scheduling simulation may be performed by combining the production planning schedule in the Advanced Planning System (APS) with the scheduling constraint parameters, the information of the target work order, and the scheduling data to determine at least one candidate production line to which the target work order can be adjusted and at least one candidate sub-period selectable in the candidate production line.
S605, at least one candidate sub-period in the candidate production line is marked in the work order schedule chart.
For example, referring to fig. 8, the target work order selected by the user is the work order d in the production line 4, as indicated by the bold line in fig. 4, and on this basis, the candidate production lines to which the work order is adjustable and the corresponding candidate sub-periods thereof can be presented in the work order schedule, as indicated by the arrows drawn from the work order d in fig. 8.
S606, based on the target candidate sub-time interval in the target candidate production line selected by the user in the work order schedule diagram, the target work order is adjusted to the target candidate sub-time interval in the target candidate production line to complete the re-arrangement process of the target work order, and the re-arrangement process data corresponding to the schedule data is obtained.
It can be understood that, according to the adjustment operation of the target work order by the user, the production line and the sub-period to which the target work order is adjusted can be determined, and accordingly, the production line and the sub-period in which the target work order is located in the scheduling data can be updated, so as to obtain the rescheduling data.
As shown in fig. 9, a schematic diagram of the rearrangement process after the adjustment of the work order d in the production line 4 is shown. As can be understood from a comparison of fig. 8 and 9, after the user selects the sub-period after the adjustment of the work order d to the work order c in the production line 1, the work order d is rearranged to the work order c in the production line 1 and then executed.
As can be seen from the above, in the present application, only the user needs to select the work order to be rescheduled in the rescheduling operation interface and set the corresponding constraint condition, so as to display at least one candidate production line suitable for the adjustment of the work order and at least one candidate sub-period selectable in the candidate production lines in real time. On the basis, a user can select and adjust the work order to a candidate sub-time period of a certain candidate production line according to needs, so that the rearrangement process of the work order can be completed, and the convenience of the rearrangement process is improved; and because the user can see the information such as the production line and the like which can be selected in the rescheduling, the interactivity is improved, and the rescheduling mode can be more reasonably selected and arranged by the user.
It can be understood that, in order to enable the user to know the key index conditions after the rearrangement process in time, the total work order index score of each work order required to be executed in the target planning time period can be determined by combining the rescheduling data after the target work order is adjusted to the target candidate sub-time period in the target candidate production line. Meanwhile, historical work order index scores before the target work order rearrangement process can be obtained. On the basis, the total work order index score and the historical work order index score can be displayed.
Wherein, the total work order index score is at least one index score of all the work orders after rescheduling. For example, the total work order score may include one or more of total revenue, completion rate by date, profit, and the like, and may be a composite score of multiple metrics.
It is understood that after re-scheduling, there may be some production lines remaining unscheduled time slots in the target planning time slot, and based on this, in order to optimize scheduling, so as to make it possible to schedule more work orders in the target planning time slot to the maximum, the present application may also perform capacity optimization.
Specifically, in the present application, the re-scheduling adjustment interface may further display a capacity optimization button. As shown in FIG. 8 or 9, there may be a button 800 in the interface area of the work order schedule for optimizing capacity.
Correspondingly, the touch of the capacity optimization key is detected, and the unscheduled residual work order information and the residual available sub-time periods of different production lines in the target planning time period are obtained. The remaining sub-period is a period in which no work order is scheduled in the production line, such as a period in which the last part of each production line is left vacant in fig. 8 and 9.
On the basis, the method and the system can combine the information of the remaining work orders and the remaining sub-time periods corresponding to different production lines, and determine at least one candidate work order which can be scheduled in the remaining sub-time period corresponding to each production line by using the trained optimization model. Then, the information of at least one candidate work order which can be scheduled in the remaining sub-time period corresponding to the production line can be displayed, so that the user can add the work order which needs to be scheduled to the remaining sub-time period corresponding to the production line.
The optimization model is based on the work order data of a plurality of work order training samples and the data of the available time periods of a plurality of production line samples, and is obtained by training through an unsupervised learning algorithm with the index scores of the plurality of work order training samples optimized as a target.
After clicking the capacity optimization button 800, candidate work orders that can be scheduled in the remaining sub-periods of each production line can be presented, and based on this, the user can add the candidate work orders to the remaining sub-periods of the corresponding production line.
The application also provides an order processing device corresponding to the order processing method.
As shown in fig. 10, which shows a schematic structural diagram of an order processing apparatus according to the present application, the apparatus of the present embodiment may include:
an order obtaining unit 1001 configured to obtain a plurality of orders to be processed, where each order includes feature values of a plurality of attribute features;
a genetic tree construction unit 1002, configured to construct an order scoring tree conforming to a genetic programming algorithm according to the multiple attribute features, where the order scoring tree includes logical operation relationships among the multiple attribute features;
the order scoring unit 1003 is configured to determine an order score of the order according to a logical operation relationship among multiple attribute features in the order scoring tree based on feature values of the multiple attribute features of the order;
an order sorting unit 1004 for determining an order sorting of the orders in combination with the order scores of the orders;
a simulation operation unit 1005, configured to perform simulation operation of material matching and index scoring on the multiple orders based on the order ranking and the configured material configuration information and evaluation index information, so as to obtain a comprehensive index score of the multiple orders;
and the comprehensive optimization unit 1006 is configured to optimize the logical operation relationship in the order scoring tree by using the optimal comprehensive index score as a target and using a genetic programming algorithm until the comprehensive index score is optimal, so as to obtain a target order sequence under the condition that the comprehensive index score is optimal.
In one possible implementation, a genetic tree construction unit includes:
an attribute separation subunit, configured to determine at least one first attribute feature belonging to a numerical type and at least one second attribute feature not belonging to the numerical type from the plurality of attribute features;
a genetic tree construction subunit, configured to combine the at least one attribute feature and the at least one second attribute feature to construct an order scoring tree conforming to a genetic programming algorithm, where the order scoring tree includes a logical type branching tree and a numerical type branching tree, where the logical type branching tree includes a logical operation relationship of the at least one first attribute feature, and the numerical type branching tree includes a logical operation relationship of the at least one second attribute feature;
the comprehensive optimization unit is specifically used for optimizing the logical operation relationship in the logical type branch tree and the numerical type branch tree by adopting a genetic programming algorithm with the optimal comprehensive index score as a target.
In an alternative approach:
the plurality of attribute characteristics of the order obtained by the order obtaining unit include a customer level of the order;
the attribute separation subunit is specifically configured to determine, from the plurality of attribute features, at least one first attribute feature that is outside the client level and belongs to a numerical type, and at least one second attribute feature that is outside the client level and does not belong to the numerical type;
correspondingly, the order scoring tree constructed by the genetic tree construction subunit comprises: a first scoring tree adapted to be below a set level at a customer level and a second scoring tree adapted to be not below the set level at the customer level, the first scoring tree including a first logical type branch tree and a first numerical type branch tree, the second scoring tree including a second logical type branch tree and a second numerical type branch tree, the first logical type branch tree and the second logical type branch tree each including a logical operational relationship of at least one first attribute feature, the first numerical type branch tree and the second numerical type branch tree each including a logical operational relationship of at least one second attribute feature;
the order scoring unit may include:
a first scoring unit, configured to determine, if a customer level of the order is lower than the set level, a score of the order based on a feature value of at least one first attribute feature and a feature value of at least one second attribute feature of the order, and according to a logical operation relationship between a first logical type branch tree and a first numerical type branch tree in the first scoring tree;
and the second scoring unit is used for determining the order score of the order based on the characteristic value of at least one first attribute characteristic and the characteristic value of at least one second attribute characteristic of the order and according to the logical operation relationship between a second logic type branch tree in the second scoring tree and a second numerical type branch tree if the customer level of the order is not lower than the set level.
In yet another possible implementation manner, the apparatus further includes:
the comprehensive score output unit is used for obtaining a corresponding comprehensive index score when the comprehensive index score is optimal and outputting the comprehensive index score;
and the structure output unit is used for obtaining the order scoring tree obtained when the comprehensive index score is optimal and outputting the structure chart of the order scoring tree.
In another possible implementation manner, the characteristic values of the plurality of attribute characteristics of the order obtained by the order obtaining unit include: the product production quantity of the production product corresponding to the order and the income characteristic of the order;
the order further comprises at least one batch feature;
in this application, the apparatus further comprises:
a batch characteristic determination unit for determining at least one target batch characteristic according to which the batch processing of the plurality of orders is required;
a set determining unit, configured to determine, based on at least one batch characteristic included in the order, an order set for each target batch characteristic from the plurality of orders, respectively, where the order set for the target batch characteristic includes at least one order matching the target batch characteristic;
the data determining unit is used for determining the total order number, the total product production number and the total order income of the orders by combining the product production number and income characteristics of the orders;
the batch priority rating unit is used for determining the batch priority rating of the order set corresponding to the target batch characteristic according to the product production quantity and income characteristic of each order in the order set of the target batch characteristic and the order quantity of the orders in the order set, and by combining the total order quantity, the total product production quantity and the total order income;
and the batch determining unit is used for determining the batch priority corresponding to the order set of the at least one target batch characteristic according to the batch priority score of the order set.
In one possible implementation, the apparatus further includes:
and the batch optimization unit is used for determining a target order set with the highest batch priority from the order sets of the various target batch characteristics to which the order belongs, determining the order as the order in the target order set, and deleting the orders in other order sets except the target order set if the order belongs to the order sets corresponding to the various target batch characteristics after the batch determination unit determines the batch priority corresponding to the order set of the at least one target batch characteristic.
In one possible implementation, the present application may further include:
a scheduling data obtaining unit, configured to obtain scheduling data of the multiple orders after the comprehensive optimization unit obtains a target order ranking under a condition that a comprehensive index score is optimal, where the scheduling data is scheduling result data obtained by scheduling a plurality of work orders split from the multiple orders in combination with the target order ranking, and the scheduling data includes: information of work orders required to be executed by different production lines in each sub-period of the target planning period;
an interface display unit, configured to display a rearrangement adjustment interface based on the scheduling data, where the rearrangement adjustment interface at least includes: a work order schedule chart and a rearrangement setting area, wherein the work order schedule chart comprises an indication chart of work orders planned to be produced by each production line in each sub-period of the target planning period;
a constraint obtaining unit, configured to obtain rearrangement range constraint data set in the rearrangement setting region by a user, where the rearrangement range constraint data includes: at least one scheduling constraint parameter for adjusting the scheduling data;
a candidate determining unit, configured to determine, based on a target work order selected by a user in a work order schedule, the at least one scheduling constraint parameter, and scheduling data, at least one candidate production line to which the target work order can be adjusted and at least one candidate sub-period in the candidate production line;
a candidate marking unit for marking candidate sub-periods in the at least one candidate production line in the work order schedule;
and the re-arrangement process unit is used for adjusting the target work order to the target candidate sub-time interval in the target candidate production line based on the target candidate sub-time interval in the target candidate production line selected by the user in the work order schedule chart so as to complete the re-arrangement process of the target work order and obtain the re-arrangement process data corresponding to the schedule data.
In one possible implementation, the apparatus further includes:
a total score determining unit, configured to determine, after the re-scheduling unit adjusts the target work order to the target candidate sub-period in the target candidate production line, a total work order index score of each work order that needs to be executed within the target planning time period in combination with the re-scheduling data;
a historical score obtaining unit, configured to obtain a historical work order index score before the target work order re-arrangement process;
and the total score display unit is used for displaying the total work order index score and the historical work order index score.
In an optional manner, the rearrangement adjustment interface further displays a productivity optimization key;
the device also includes:
a residual information determining unit, configured to detect that the capacity optimization key is touched and pressed, and obtain residual work order information that is not scheduled and residual available sub-time periods that remain in the target planning time period for different production lines;
a residual optimization determining unit, configured to determine at least one candidate work order that can be scheduled in a residual sub-time period corresponding to a different production line by using a trained optimization model in combination with the residual work order information and the residual sub-time periods corresponding to the different production lines, where the optimization model is obtained by using unsupervised learning algorithm training with the target of optimizing index scores of a plurality of work order training samples based on work order data of the plurality of work order training samples and data of available time periods of the plurality of production line samples;
and the residual optimization display unit is used for displaying the information of at least one candidate work order which can be scheduled in the residual sub-time period corresponding to the production line, so that a user can add the work order required to be scheduled to the residual sub-time period corresponding to the production line.
In yet another aspect, the present application further provides an electronic device, as shown in fig. 11, which shows a schematic diagram of a constituent structure of the electronic device, where the electronic device may be any type of electronic device, and the electronic device includes at least a memory 1101 and a processor 1102;
wherein the processor 1101 is configured to execute the order processing method in any one of the above embodiments.
The memory 1102 is used to store programs needed for the processor to perform operations.
It is to be understood that the electronic device may further include a display unit 1103 and an input unit 1104.
Of course, the electronic device may have more or less components than those shown in fig. 11, which is not limited thereto.
In another aspect, the present application further provides a computer-readable storage medium, in which at least one instruction, at least one program, a code set, or a set of instructions is stored, and the at least one instruction, the at least one program, the code set, or the set of instructions is loaded and executed by a processor to implement the order processing method according to any of the above embodiments.
The present application also proposes a computer program comprising computer instructions stored in a computer readable storage medium. The computer program is configured to perform the order processing method as in any of the above embodiments when run on an electronic device.
It should be noted that, in the present specification, the embodiments are all described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other. Meanwhile, the features described in the embodiments of the present specification may be replaced or combined with each other, so that those skilled in the art can implement or use the present application. For the device-like embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing is only a preferred embodiment of the present application and it should be noted that those skilled in the art can make several improvements and modifications without departing from the principle of the present application, and these improvements and modifications should also be considered as the protection scope of the present application.

Claims (10)

1. An order processing method, comprising:
obtaining a plurality of orders to be processed, wherein each order comprises characteristic values of various attribute characteristics;
according to the multiple attribute characteristics, constructing an order scoring tree which accords with a genetic programming algorithm, wherein the order scoring tree comprises the logical operation relation among the multiple attribute characteristics;
determining the order score of the order according to the characteristic values of the various attribute characteristics of the order and the logical operation relationship among the various attribute characteristics in the order score tree;
determining order ranks of the orders according to the order scores of the orders;
carrying out material matching and index scoring simulation operation on the plurality of orders based on the order sequencing and the configured material configuration information and evaluation index information to obtain comprehensive index scores of the plurality of orders;
and optimizing the logical operation relationship in the order scoring tree by adopting a genetic programming algorithm with the optimal comprehensive index score as a target until the comprehensive index score is optimal to obtain target order sequencing under the condition of optimal comprehensive index score.
2. The method of claim 1, said constructing an order scoring tree conforming to a genetic programming algorithm according to said plurality of attribute features, comprising:
determining at least one first attribute feature of the plurality of attribute features that is numerical and at least one second attribute feature that is not numerical;
combining the at least one attribute feature and the at least one second attribute feature to construct an order scoring tree conforming to a genetic programming algorithm, wherein the order scoring tree comprises a logic operation relation which is a multiplied logic type branch tree and a numerical type branch tree, the logic type branch tree comprises the logic operation relation of the at least one first attribute feature, and the numerical type branch tree comprises the logic operation relation of the at least one second attribute feature;
and optimizing the logical operation relationship in the order scoring tree by adopting a genetic programming algorithm by taking the optimal comprehensive index scoring as a target, wherein the method comprises the following steps:
and optimizing the logical operation relationship in the logic type branch tree and the numerical type branch tree by adopting a genetic programming algorithm with the optimal comprehensive index score as a target.
3. The method of claim 2, wherein the plurality of attribute characteristics of the order include a customer level of the order;
the determining at least one first attribute characteristic belonging to a numerical type and at least one second attribute characteristic not belonging to a numerical type of the plurality of attribute characteristics includes:
determining at least one first attribute characteristic outside the customer level and belonging to a numerical type and at least one second attribute characteristic outside the customer level and not belonging to a numerical type from the plurality of attribute characteristics;
the order scoring tree includes: a first scoring tree adapted to be below a set level at a customer level and a second scoring tree adapted to be not below the set level at the customer level, the first scoring tree including a first logical type branch tree and a first numerical type branch tree, the second scoring tree including a second logical type branch tree and a second numerical type branch tree, the first logical type branch tree and the second logical type branch tree each including a logical operation relationship of at least one first attribute feature, the first numerical type branch tree and the second numerical type branch tree each including a logical operation relationship of at least one second attribute feature;
determining the order score of the order based on the characteristic values of the multiple attribute characteristics of the order and according to the logical operation relationship among the multiple attribute characteristics in the order score tree, wherein the determining comprises the following steps:
if the customer level of the order is lower than the set level, determining the order score of the order based on the characteristic value of at least one first attribute characteristic and the characteristic value of at least one second attribute characteristic of the order and according to the logical operation relationship between a first logical type branch tree and a first numerical type branch tree in the first scoring tree;
and if the customer level of the order is not lower than the set level, determining the order score of the order based on the characteristic value of at least one first attribute characteristic and the characteristic value of at least one second attribute characteristic of the order and according to the logical operation relationship between a second logic type branch tree and a second numerical type branch tree in the second scoring tree.
4. The method of claim 1, further comprising:
acquiring a corresponding comprehensive index score when the comprehensive index score is optimal, and outputting the comprehensive index score;
and obtaining an order scoring tree obtained when the comprehensive index score is optimal, and outputting a structure diagram of the order scoring tree.
5. The method of claim 1, wherein the characteristic values of the plurality of attribute characteristics of the order comprise: the product production quantity of the production product corresponding to the order and the income characteristic of the order;
the order further comprises at least one batch feature;
the method further comprises the following steps:
determining at least one target batch characteristic according to which batch processing of a plurality of orders is required;
respectively determining an order set of each target batch characteristic from the plurality of orders based on at least one batch characteristic included in the orders, wherein the order set of the target batch characteristic includes at least one order matched with the target batch characteristic;
determining the total order number, the total product production number and the total order income of the orders by combining the product production number and income characteristics of the orders;
determining a batch priority score of an order set corresponding to the target batch characteristic according to the product production quantity and income characteristic of each order in the order set of the target batch characteristic and the order quantity of the orders in the order set, and by combining the total order quantity, the total product production quantity and the total order income;
and determining the batch priority corresponding to the order set of the at least one target batch characteristic according to the batch priority score of the order set.
6. The method of claim 5, after determining a batch priority corresponding to the set of orders for the at least one target batch characteristic, further comprising:
if the order belongs to an order set corresponding to various target batch characteristics, determining a target order set with the highest batch priority from the order set of the various target batch characteristics to which the order belongs, determining the order as the order in the target order set, and deleting the orders in other order sets except the target order set.
7. The method according to claim 1 or 5, further comprising, after the ranking of the target orders under the condition of the optimal composite index score, the following steps:
obtaining scheduling data of the plurality of orders, where the scheduling data is scheduling result data obtained by scheduling a plurality of work orders split from the plurality of orders in combination with the target order ranking, and the scheduling data includes: information of work orders required to be executed by different production lines in each sub-period of the target planning period;
displaying a rearrangement adjustment interface based on the scheduling data, the rearrangement adjustment interface at least comprising: a work order schedule chart and a rearrangement setting area, wherein the work order schedule chart comprises an indication chart of work orders planned to be produced by each production line in each sub-period of the target planning period;
acquiring rearrangement range constraint data set in the rearrangement setting area by a user, wherein the rearrangement range constraint data comprises: at least one scheduling constraint parameter for adjusting the scheduling data;
determining at least one candidate production line to which the target work order can be adjusted and at least one candidate sub-period in the candidate production line based on a target work order selected by a user in a work order schedule chart, the at least one scheduling constraint parameter and scheduling data;
identifying candidate sub-slots in the at least one candidate production line in the work order schedule;
and adjusting the target work order to the target candidate sub-time interval in the target candidate production line based on the target candidate sub-time interval in the target candidate production line selected by the user in the work order schedule diagram so as to complete the re-arrangement process of the target work order and obtain re-arrangement process data corresponding to the schedule data.
8. The method of claim 7, further comprising, after the adjusting the target work order to the target candidate sub-period in the target candidate production line:
determining total work order index scores of all work orders required to be executed in the target planning time period by combining the rescheduling data;
obtaining historical work order index scores before the target work order re-arrangement process;
and displaying the total work order index score and the historical work order index score.
9. The method of claim 7, wherein the rearrangement adjustment interface further displays a capacity optimization button;
the method further comprises the following steps:
detecting that the productivity optimization key is touched and pressed, and obtaining the remaining work order information which is not scheduled and the remaining available sub-time periods of different production lines in the target planning time period;
determining at least one candidate work order which can be scheduled in the remaining sub-time periods corresponding to the production lines by combining the remaining work order information and the remaining sub-time periods corresponding to different production lines and utilizing a trained optimization model, wherein the optimization model is obtained by training through an unsupervised learning algorithm by taking the work order data of a plurality of work order training samples and the data of the available time periods of the plurality of production line samples as targets and optimizing the index scores of the plurality of work order training samples;
and displaying information of at least one candidate work order which can be scheduled in the remaining sub-time period corresponding to the production line, so that a user can add the work order required to be scheduled to the remaining sub-time period corresponding to the production line.
10. An order processing apparatus comprising:
the order obtaining unit is used for obtaining a plurality of orders to be processed, and each order comprises characteristic values of various attribute characteristics;
the genetic tree construction unit is used for constructing an order scoring tree which accords with a genetic programming algorithm according to the multiple attribute characteristics, and the order scoring tree comprises the logical operation relation among the multiple attribute characteristics;
the order scoring unit is used for determining order scoring of the order based on the characteristic values of the various attribute characteristics of the order and according to the logical operation relation among the various attribute characteristics in the order scoring tree;
the order sorting unit is used for determining the order sorting of the orders according to the order scores of the orders;
the simulation operation unit is used for carrying out simulation operation of material matching and index scoring on the orders based on the order sorting and the configured material configuration information and evaluation index information to obtain comprehensive index scores of the orders;
and the comprehensive optimization unit is used for optimizing the logical operation relation in the order scoring tree by adopting a genetic programming algorithm with the optimal comprehensive index score as a target until the comprehensive index score is optimal, so as to obtain the target order sequence under the condition of optimal comprehensive index score.
CN202111122414.8A 2021-09-24 2021-09-24 Order processing method and device Pending CN113793203A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111122414.8A CN113793203A (en) 2021-09-24 2021-09-24 Order processing method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111122414.8A CN113793203A (en) 2021-09-24 2021-09-24 Order processing method and device

Publications (1)

Publication Number Publication Date
CN113793203A true CN113793203A (en) 2021-12-14

Family

ID=79184310

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111122414.8A Pending CN113793203A (en) 2021-09-24 2021-09-24 Order processing method and device

Country Status (1)

Country Link
CN (1) CN113793203A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115345529A (en) * 2022-10-18 2022-11-15 一汽解放汽车有限公司 Assembly production line scheduling method and device, computer equipment and storage medium
CN117035697A (en) * 2023-10-09 2023-11-10 天津云起技术有限公司 ITSM (integrated traffic simulation) platform optimization method and system based on historical dynamic analysis
CN117474444A (en) * 2023-09-27 2024-01-30 广州交通集团物流有限公司 Digital medicine supply chain management platform

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115345529A (en) * 2022-10-18 2022-11-15 一汽解放汽车有限公司 Assembly production line scheduling method and device, computer equipment and storage medium
CN117474444A (en) * 2023-09-27 2024-01-30 广州交通集团物流有限公司 Digital medicine supply chain management platform
CN117035697A (en) * 2023-10-09 2023-11-10 天津云起技术有限公司 ITSM (integrated traffic simulation) platform optimization method and system based on historical dynamic analysis
CN117035697B (en) * 2023-10-09 2023-12-15 天津云起技术有限公司 ITSM (integrated traffic simulation) platform optimization method and system based on historical dynamic analysis

Similar Documents

Publication Publication Date Title
CN113793203A (en) Order processing method and device
US7860737B2 (en) Constraint-based production planning and scheduling
US20200104169A1 (en) Systems and methods of a production environment tool
JPH01265356A (en) Computerized management system
JP4439580B2 (en) Process management support system and simulation method
JP6467264B2 (en) Plan creation support apparatus and plan creation support method
JP2017162044A (en) Production planning device, production planning method and production planning program
CN108475361A (en) The amount of time estimating system and method for project management system
EP3123417A1 (en) A framework to optimize the selection of projects and the allocation of resources within a structured business organization under time, resource and budget constraints
JP2004021364A (en) Management intention decision support system
CN111967766A (en) Performance indicator-based serial task assignment method
US8046252B2 (en) Sales plan evaluation support system
Witt et al. Application of a mathematical model to an intermediate-to long-term real-world steel production planning problem based on standard software
JP2013097625A (en) Task allocation support device, task allocation support method and task allocation support program
Rabbani et al. A novel bi-level hierarchy towards available-to-promise in mixed-model assembly line sequencing problems
WO2022176073A1 (en) Production planning support system
Sawik Multi-objective due-date setting in a make-to-order environment
CN113095704A (en) Production plan scheduling method, device, equipment and medium
JP2004145880A (en) Method of preparing production schedule
JP7163104B2 (en) Supply chain business process optimization device and supply chain business support method
JP7481381B2 (en) Store management system, store management device, server device, and store management method
Stefansson et al. Multi-scale planning and scheduling in the pharmaceutical industry
JP2023132879A (en) Store management system, store management device, and store management method
JP2005284959A (en) Method of preparing production schedule
JP5023714B2 (en) Production plan information output device, production plan information output method, and production management system

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