Method and device for determining plan scheduling, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a plan scheduling determination method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a to-be-processed demand, supply information and material information, determining a material constraint, a capacity constraint and a date constraint according to the material information and the supply information, inputting the to-be-processed demands, the supply of each supply mechanism and the productivity into a pre-trained knowledge reasoning model to obtain bottleneck materials and bottleneck supply mechanisms, grouping and sequencing the to-be-processed demands based on scores corresponding to the bottleneck supply mechanisms to obtain a plurality of sequenced demand subgroups, and aiming at each demand included in the current subgroup, obtaining a plurality of demand subgroups; and determining the weight corresponding to the demand based on the bottleneck material, and performing heuristic solution on the supply plan corresponding to each demand based on the supply information of each supply mechanism by taking the material constraint, the capacity constraint and the date constraint as constraint conditions and taking the demand achievement rate with the weight as an optimization target to obtain the supply plan corresponding to the demand to be processed.

Description

Technical Field

[0001] The present application relates to the field of intelligent production technology, and in particular to a method, device, electronic device and storage medium for determining a plan schedule. Background Art

[0002] Faced with the increasingly fierce market competition environment, enterprises should be able to quickly respond to changes in market demand and achieve effective planning and scheduling. Planning and scheduling refers to outputting executable supply plans that meet various needs under certain resource constraints to achieve supply and demand balance.

[0003] Currently, scheduling systems often focus on production scheduling at the execution level. The research direction is usually efficient and dynamic workshop scheduling or production scheduling. The optimization goal is usually the lowest cost or the shortest completion time, while there is less research on planning scheduling at the planning level. The few existing planning schedulings are also ineffective, with low executability and demand fulfillment rates. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a method, device, electronic device and storage medium for determining a plan schedule, so as to realize a plan schedule with high executability and high achievement rate. The specific technical solution is as follows:

[0005] In a first aspect, an embodiment of the present application provides a method for determining a plan schedule, the method comprising:

[0006] Obtaining the demand to be processed, supply information and material information, wherein the supply information at least includes the supply, production capacity, beat and supply time information of each supply mechanism, and the beat is used to indicate the working hours required for the supply mechanism to provide each material, and / or, to indicate the quantity of each material provided by the supply mechanism in a unit time;

[0007] Determine material constraints according to the demand transmission relationship between the materials identified by the material information, determine capacity constraints according to the capacity and the beat, and determine date constraints according to the supply time relationship of the materials identified by the supply time information, wherein the material constraints are used to represent the dependency relationship between the materials, the capacity constraints are used to represent the ability constraints of the supply agencies to provide the materials, and the date constraints are used to represent the time limits for the supply agencies to provide the materials;

[0008] Input the pending demand, the supply and capacity of each supply mechanism into a pre-trained knowledge reasoning model to obtain the bottleneck material and bottleneck supply mechanism corresponding to the pending demand, wherein the knowledge reasoning model constructs material nodes and supply mechanism nodes based on the material information included in the historical planning and scheduling data and the relationship between each supply mechanism and the material identified by the beat, and characterizes the material nodes, supply mechanism nodes and the edges between the nodes with the demand, supply and capacity included in the historical planning and scheduling data, so as to predict the bottleneck material and bottleneck supply mechanism corresponding to the input demand;

[0009] Based on the scores of the supply mechanism corresponding to the pending demand hitting the corresponding bottleneck supply mechanism, the pending demand is grouped and sorted to obtain a plurality of sorted demand subgroups, wherein the bottleneck supply mechanism is used to indicate that a bottleneck occurs in the material production capacity of the supply mechanism;

[0010] Obtain each demand subgroup in sorted order, and for each demand included in the current subgroup, determine the weight corresponding to the demand based on the number of times the material corresponding to the demand hits the bottleneck material and the score corresponding to the bottleneck material;

[0011] Taking the material constraint, the production capacity constraint and the date constraint as constraint conditions, and the demand fulfillment rate with the weight as the optimization goal, based on the supply information of each supply agency, a heuristic solution is performed on the supply plan corresponding to each demand included in the current subgroup to obtain the supply plan corresponding to the pending demand.

[0012] Optionally, the knowledge reasoning model is constructed by:

[0013] Obtain historical planning and scheduling data, historical bottleneck materials, and historical bottleneck supply organizations;

[0014] Constructing material nodes and supply mechanism nodes according to the material information included in the historical planning and scheduling data and the relationship between each supply mechanism and the material identified by the beat;

[0015] The material nodes, supply mechanism nodes and edges between the nodes are characterized by the demand, supply and capacity included in the historical planning and scheduling data to obtain a heterogeneous directed graph, wherein the edges between material nodes in the heterogeneous directed graph represent the constraint relationship between the materials corresponding to the material nodes, and the edges between material nodes and supply mechanism nodes represent that the materials corresponding to the material nodes can be produced by the supply mechanism corresponding to the supply mechanism node;

[0016] Based on the historical planning and scheduling data, historical bottleneck materials and historical bottleneck supply mechanisms, the heterogeneous directed graph is trained to obtain the knowledge reasoning model.

[0017] Optionally, the step of training the heterogeneous directed graph based on the historical planning and scheduling data, historical bottleneck materials, and historical bottleneck supply mechanisms to obtain the knowledge reasoning model includes:

[0018] Determine the nodes corresponding to the historical bottleneck materials and the nodes corresponding to the historical bottleneck supply mechanisms in the heterogeneous directed graph as positive samples, and determine the nodes other than the positive samples as negative samples;

[0019] The demand and supply included in the historical planning and scheduling data are used as the initial vectors of the material node, the capacity is used as the initial vector of the supply mechanism node, the relationship between the material information is used as the initial vector of the edge between the material node and the material node, and the beat is used as the initial vector of the edge between the material node and the supply mechanism node;

[0020] Based on the positive samples, the negative samples and each initial vector, the heterogeneous directed graph is trained to obtain the knowledge reasoning model.

[0021] Optionally, the step of grouping and sorting the demands to be processed based on the scores of the supply mechanisms corresponding to the demands to be processed hitting the bottleneck supply mechanisms to obtain a plurality of sorted demand subgroups includes:

[0022] For each demand included in each group of demands, determine the supply mechanism corresponding to the demand according to the material information corresponding to the demand and the beat, wherein each group of demands is obtained by grouping the demands to be processed according to priority;

[0023] Divide the demands of the supply mechanism that are the same as the bottleneck supply mechanism into a group of demands to obtain demand subgroups;

[0024] The demand subgroups are sorted according to the scores of the corresponding bottleneck supply mechanisms to obtain a plurality of sorted demand subgroups.

[0025] Optionally, the step of taking the material constraint, the production capacity constraint and the date constraint as constraint conditions, taking the demand fulfillment rate with the weight as the optimization target, and performing a heuristic solution on the supply plan corresponding to each demand included in the current subgroup based on the supply information of each supply organization to obtain the supply plan corresponding to the demand to be processed includes:

[0026] Get a group of requirements with the highest priority as the current group of requirements;

[0027] For the demand subgroups included in the current group of demands, taking the material constraint, the capacity constraint and the date constraint as constraint conditions, taking the weighted demand achievement rate corresponding to the demand subgroups included in the current group of demands as an optimization target, and based on the current supply information of each supply agency, performing a heuristic solution on the supply plan corresponding to the demand subgroups included in the current group of demands, so as to obtain the supply plan corresponding to the current group of demands;

[0028] Deducting the supply information of each supply mechanism required by the supply plan to obtain the current supply information of each supply mechanism;

[0029] Obtain the next set of demands in order of priority from high to low as the current set of demands, and return the demand subgroup included in the current set of demands, with the material constraint, the production capacity constraint and the date constraint as constraints, and the demand fulfillment rate with the weight corresponding to the demand subgroup included in the current set of demands as the optimization target, and perform heuristic solution on the supply plan corresponding to the demand subgroup included in the current set of demands based on the current supply information of each supply agency, to obtain the supply plan corresponding to the current set of demands, until multiple sets of demands are processed.

[0030] Optionally, for the demand subgroup included in the current group demand, taking the material constraint, the production capacity constraint and the date constraint as constraint conditions, taking the weighted demand achievement rate corresponding to the demand subgroup included in the current group demand as an optimization target, and based on the current supply information of each supply agency, performing a heuristic solution on the supply plan corresponding to the demand subgroup included in the current group demand to obtain the supply plan corresponding to the current group demand, comprises:

[0031] For the current group of requirements, obtaining the first requirement subgroup according to the sorting order as the current subgroup;

[0032] For the current subgroup, taking the material constraint, the capacity constraint and the date constraint as constraint conditions, taking the weighted demand fulfillment rate corresponding to the current subgroup as the optimization target, and based on the current supply information of each supply organization, performing a heuristic solution on the supply plan corresponding to the current subgroup to obtain the supply plan corresponding to the current subgroup;

[0033] Deducting the supply information of each supply mechanism required by the supply plan to obtain the current supply information of each supply mechanism;

[0034] Obtain the next demand subgroup in the order as the current subgroup, and return the steps of taking the material constraint, the production capacity constraint and the date constraint as the constraints, taking the weighted demand fulfillment rate corresponding to the current subgroup as the optimization target, performing heuristic solution on the supply plan corresponding to the current subgroup based on the current supply information of each supply agency, and obtaining the supply plan corresponding to the current subgroup, until multiple demand subgroups are processed.

[0035] Optionally, the demand to be processed includes predicted demand;

[0036] Before the step of obtaining the demand, supply information and material information to be processed, the method further includes:

[0037] Acquire historical demand data and switching data of materials, wherein the switching data is material data that changes according to business requirements;

[0038] Constructing a demand sequence for the material according to the time sequence corresponding to the historical demand data and the switching data;

[0039] Extracting features from the demand sequence to obtain sequence features of the demand sequence, and classifying the materials based on the sequence features to obtain multiple categories of materials;

[0040] For each category of materials, a forecasting method that is compatible with the sequence characteristics of the materials in this category is used to forecast the demand for the materials in this category, thereby obtaining the forecast demand for the materials in this category.

[0041] Optionally, the supply of each supply mechanism includes a revised purchase supply;

[0042] Before the step of obtaining the demand, supply information and material information to be processed, the method further includes:

[0043] Acquire historical supply data of the supply mechanism, wherein the historical supply data includes the supply date and supply quantity of each material by each supply mechanism;

[0044] Extracting features from the historical supply data to obtain features of the historical supply data, and classifying each material based on the features to obtain multiple categories of materials;

[0045] For each category of materials, a forecasting method that matches the characteristics of the materials in that category is used to forecast the supply date and supply quantity of the materials in that category, and to obtain a revised procurement supply of the materials in that category.

[0046] Optionally, the supply plan includes an existing supply allocation strategy and / or a new supply plan generated by capacity allocation;

[0047] The allocation strategy of the existing supply includes whether to use the existing supply, the allocation date, the supply selection under the allocation date, and the supply quantity selection under the allocation date;

[0048] The new supply plan generated by the capacity allocation includes the type of planned supply, the date of planned supply, the supply organization of the planned supply and the quantity of planned supply.

[0049] In a second aspect, an embodiment of the present application provides a device for determining a plan schedule, the device comprising:

[0050] An information acquisition module, used to acquire pending demand, supply information and material information, wherein the supply information at least includes the supply, capacity, beat and supply time information of each supply mechanism, and the beat is used to indicate the working hours required for the supply mechanism to provide each material, and / or, to indicate the quantity of each material provided by the supply mechanism in a unit time;

[0051] a constraint determination module, for determining material constraints according to the demand transmission relationship between the materials identified by the material information, determining capacity constraints according to the capacity and the beat, and determining date constraints according to the supply time relationship of the materials identified by the supply time information, wherein the material constraints are used to represent the dependency relationship between the materials, the capacity constraints are used to represent the ability constraints of the supply agencies to provide the materials, and the date constraints are used to represent the time limit for the supply agencies to provide the materials;

[0052] A bottleneck prediction module is used to input the pending demand, the supply and production capacity of each supply mechanism into a pre-trained knowledge reasoning model to obtain the bottleneck material and bottleneck supply mechanism corresponding to the pending demand, wherein the knowledge reasoning model constructs material nodes and supply mechanism nodes based on the material information included in the historical planning and scheduling data and the relationship between each supply mechanism and the material identified by the beat, and characterizes the material nodes, supply mechanism nodes and the edges between the nodes with the demand, supply and production capacity included in the historical planning and scheduling data, so as to predict the bottleneck material and bottleneck supply mechanism corresponding to the input demand;

[0053] A grouping and sorting module is used to group and sort the pending demands based on the scores of the supply mechanisms corresponding to the pending demands hitting the corresponding bottleneck supply mechanisms, so as to obtain a plurality of sorted demand subgroups, wherein the bottleneck supply mechanism is used to indicate that a bottleneck occurs in the material production capacity of the supply mechanism;

[0054] A weight calculation module is used to obtain each demand subgroup in a sorted order, and for each demand included in the current subgroup, determine the weight corresponding to the demand based on the number of times the material corresponding to the demand hits the bottleneck material and the score corresponding to the bottleneck material;

[0055] A supply plan acquisition module is used to use the material constraint, the production capacity constraint and the date constraint as constraint conditions, and the demand fulfillment rate with the weight as the optimization goal. Based on the supply information of each supply agency, a supply plan corresponding to each demand included in the current subgroup is heuristically solved to obtain the supply plan corresponding to the pending demand.

[0056] In a third aspect, an embodiment of the present application provides an electronic device, including:

[0057] Memory, used to store computer programs;

[0058] The processor is used to implement any method described in the first aspect when executing a program stored in the memory.

[0059] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, any method described in the first aspect is implemented.

[0060] Beneficial effects of the embodiments of the present application:

[0061] The solution provided in the embodiment of the present application, when performing a heuristic solution to the supply plan corresponding to the demand to be processed, not only the dependencies between the materials, the capacity constraints of each supply mechanism to provide each material, and the time limit for each supply mechanism to provide each material are considered, but also the potential bottleneck supply mechanism and bottleneck material are predicted by the pre-trained knowledge reasoning model, and the demand to be processed is grouped and sorted based on the scores corresponding to the bottleneck supply mechanism, each demand subgroup is obtained in the sorting order, the weight of each demand is determined based on the bottleneck material, and the weighted demand achievement rate is used as the optimization target. Therefore, regardless of the demand restricted by the bottleneck material and the bottleneck supply mechanism, or the demand not restricted by the bottleneck material and the bottleneck supply mechanism, a reasonable supply plan can be obtained, so that each supply mechanism can supply reasonably, achieve supply and demand balance, and then achieve a plan scheduling with high executability and high achievement rate. Of course, the implementation of any product or method of the present application does not necessarily require all the advantages described above to be achieved at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application, and for ordinary technicians in this field, other embodiments can also be obtained based on these drawings.

[0063] Figure 1 A flowchart of a method for determining a plan schedule provided in an embodiment of the present application;

[0064] Figure 2 for Figure 1 A specific flow chart of step S104 in the illustrated embodiment;

[0065] Figure 3 for Figure 1 A specific flow chart of step S106 in the illustrated embodiment;

[0066] Figure 4 for Figure 3 A specific flow chart of step S302 in the illustrated embodiment;

[0067] Figure 5 Based on Figure 1 A specific flow chart of constructing a knowledge reasoning model in the illustrated embodiment;

[0068] Figure 6 Based on Figure 5 A schematic diagram of constructing a knowledge reasoning model in the illustrated embodiment;

[0069] Figure 7 for Figure 5 A specific flow chart of step S503 in the illustrated embodiment;

[0070] Figure 8 A specific flow chart for obtaining predicted demand provided in an embodiment of the present application;

[0071] Fig. 9 Based on Figure 8 A schematic diagram of obtaining predicted demand in the illustrated embodiment;

[0072] Fig.10 A specific flow chart for obtaining a revised procurement supply provided in an embodiment of the present application;

[0073] Fig.11 Based on Fig.10 A schematic diagram of obtaining a revised procurement supply in the illustrated embodiment;

[0074] Fig.12 A schematic diagram of a method for determining a plan schedule provided in an embodiment of the present application;

[0075] Fig.13 Based on Fig.12 A schematic diagram of the mechanism model of the illustrated embodiment;

[0076] Fig.14 Based on Fig.12 A schematic diagram of the plan scheduling of the illustrated embodiment;

[0077] Fig.15 A schematic diagram of the structure of a device for determining a plan schedule provided in an embodiment of the present application;

[0078] Fig.16 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0079] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field based on the present application belong to the scope of protection of the present application.

[0080] In order to improve the executability and achievement rate of the plan schedule, the embodiments of the present application provide a method, device, electronic device, computer-readable storage medium and computer program product for determining the plan schedule.

[0081] A method for determining a schedule provided in an embodiment of the present application can be applied to any device that needs to determine a schedule, for example, a processor, a server, a desktop computer, a laptop computer, etc., which is not specifically limited here. For the sake of clarity of description, it is referred to as an electronic device below.

[0082] like Figure 1 As shown, a method for determining a plan schedule includes:

[0083] S101, obtaining demand, supply information and material information to be processed;

[0084] The supply information at least includes the supply, production capacity, rhythm and supply time information of each supply mechanism, and the rhythm is used to indicate the working hours required for the supply mechanism to provide each material, and / or, to indicate the quantity of each material provided by the supply mechanism in a unit time;

[0085] S102, determining material constraints according to the demand transfer relationship between the materials identified by the material information, determining capacity constraints according to the capacity and the beat, and determining date constraints according to the supply time relationship between the materials identified by the supply time information;

[0086] The material constraint is used to indicate the dependency relationship between materials, the capacity constraint is used to indicate the capacity constraint of each supply mechanism in providing each material, and the date constraint is used to indicate the time limit for each supply mechanism to provide each material;

[0087] S103, inputting the demand to be processed, the supply and capacity of each supply mechanism into a pre-trained knowledge reasoning model to obtain the bottleneck material and bottleneck supply mechanism corresponding to the demand to be processed;

[0088] The knowledge reasoning model constructs material nodes and supply mechanism nodes based on the material information included in the historical planning and scheduling data and the relationship between each supply mechanism and the material identified by the beat, and characterizes the material nodes, supply mechanism nodes and the edges between the nodes with the demand, supply and production capacity included in the historical planning and scheduling data, so as to predict the bottleneck materials and bottleneck supply mechanisms corresponding to the input demand;

[0089] S104, grouping and sorting the demands to be processed based on the scores of the supply mechanisms corresponding to the demands to be processed that hit the bottleneck supply mechanism, to obtain a plurality of sorted demand subgroups;

[0090] The bottleneck supply mechanism is used to indicate that a bottleneck occurs in the material production capacity of the supply mechanism;

[0091] S105, obtaining each demand subgroup in a sorted order, and for each demand included in the current subgroup, determining a weight corresponding to the demand based on the number of times the material corresponding to the demand hits the bottleneck material and the score corresponding to the bottleneck material;

[0092] S106, taking the material constraint, the production capacity constraint and the date constraint as constraint conditions, taking the demand fulfillment rate with the weight as the optimization target, based on the supply information of each supply agency, performing a heuristic solution for the supply plan corresponding to each demand included in the current subgroup, and obtaining the supply plan corresponding to the demand to be processed.

[0093] It can be seen that in the solution provided in the embodiment of the present application, when the supply plan corresponding to the demand to be processed is heuristically solved, not only the dependencies between the materials, the capacity constraints of each supply mechanism to provide each material, and the time limit for each supply mechanism to provide each material are considered, but also the potential bottleneck supply mechanism and bottleneck material are predicted by the pre-trained knowledge reasoning model, and the demands to be processed are grouped and sorted based on the scores corresponding to the bottleneck supply mechanism, each demand subgroup is obtained in the sorting order, the weight of each demand is determined based on the bottleneck material, and the weighted demand achievement rate is used as the optimization goal. Therefore, regardless of the demand restricted by the bottleneck material and the bottleneck supply mechanism, or the demand not restricted by the bottleneck material and the bottleneck supply mechanism, a reasonable supply plan can be obtained, so that each supply mechanism can supply reasonably and achieve supply and demand balance, thereby realizing a plan scheduling with high executability and high achievement rate.

[0094] In step S101, the electronic device may obtain pending demands, supply information, and material information. The pending demands may include multiple demands, and the types of demands may be delivery demands, reservation demands, sales demands, transfer demands, forecast demands, etc., which are not specifically limited here. Different types of demands may be set with different priorities according to business logic.

[0095] The supply information at least includes the supply, production capacity, rhythm and supply time information of each supply organization. The production capacity can indicate the upper limit of the quantity of each material provided by the supply organization within a certain period of time, or it can indicate the upper limit of the time for the supply organization to provide each material. The rhythm is used to indicate the working hours required for the supply organization to provide each material. Specifically, it can be the working hours required for the supply organization to provide a unit of material, and / or it indicates the quantity of each material provided by the supply organization within a unit of time. For example, the rhythm is the time required for supply organization A to produce a display. The type of supply can be inventory, procurement, etc., which is not specifically limited here. The supply organization is the supply provider, which can be a supplier, factory, work center, etc., which is not specifically limited here.

[0096] In one implementation, the electronic device can obtain pending demand, supply information, and material information from the business system. The business system stores data related to business demand, such as supply organization, demand, supply, capacity, beat, BOM (bill of material), master data (demand master data and material master data), work calendar, etc. The master data can represent basic attributes of demand and materials.

[0097] For example, demand 1, demand 2, and demand 3 are stored in the business system, and supply organization A, supply organization B, and supply organization C provide the materials required for each demand. The electronic device can obtain demand 1, demand 2, and demand 3 from the business system, and obtain the supply, production capacity, rhythm, and supply time information of supply organization A, supply organization B, and supply organization C for the materials.

[0098] In step S102, the electronic device may determine the material constraint according to the demand transfer relationship between the materials identified by the material information. The material constraint is used to indicate the dependency relationship between the materials. For example, the production of the upper material depends on the lower material. As an implementation method, the electronic device may determine the material constraint according to the relationship between the materials in the BOM. The BOM may show which parts and raw materials a product is composed of, and may show how the time and quantity relationships between these parts are.

[0099] For example, the BOM shows that product A consists of component 1, component 2, and component 3, and component 1 consists of material a and material b, component 2 consists of material b, component 3 consists of material b and material c, and material c consists of material e and material f. In this way, the electronic equipment can determine that the production of component 1 depends on material a and material b, the production of component 2 depends on material b, the production of component 3 depends on material b and material c, and the production of material c depends on material e and material f based on the demand transfer relationship between materials. Therefore, there is a material constraint relationship between each material.

[0100] The electronic device can determine the capacity constraint based on the capacity and beat. Among them, the capacity constraint is used to represent the capacity constraint of each supply mechanism to provide each material. In other words, the electronic device can determine the time and quantity required for each supply mechanism to provide each material. The materials provided by each supply mechanism can be inventory or purchased, which is not specifically limited here. If the materials provided by the supply mechanism are produced, then the capacity constraint can also include the number of staff, etc., which is not specifically limited here.

[0101] For example, the production of product A requires materials a, b, and c. Supply mechanism 1 provides materials a and b, supply mechanism 2 provides materials b and c, and supply mechanism 3 provides materials a, b, and c. Supply mechanism 1 can provide n1 materials a and n2 materials b every day, supply mechanism 2 can provide n3 materials b and n4 materials c within a week, and supply mechanism 3 can provide n3 materials a, n5 materials b, and n6 materials c within three days. In this way, the electronic equipment can determine the quantity of materials a and b that supply mechanism 1 can provide within a certain period of time. Similarly, it can determine the quantity of materials b and c that supply mechanism 2 can provide within a certain period of time, and the quantity of materials a, b, and c that supply mechanism 3 can provide within a certain period of time, that is, determine the capacity constraint.

[0102] The electronic device can determine the date constraint according to the supply time relationship of each material identified by the supply time information. The date constraint is used to indicate the time limit for each supply mechanism to provide each material. That is, the time for each supply mechanism to provide each material may be different. Then, the electronic device can determine the time for each supply mechanism to provide each material to determine the date constraint. The time for each supply mechanism to provide each material may include working days or may not include working days, which all belong to the date constraint.

[0103] For example, the BOM includes materials a, b, and c. The production of material a depends on materials d and e. Supply mechanism 1 provides materials a and b, supply mechanism 2 provides materials b and c, and supply mechanism 3 provides material c. Since the production of material a depends on materials d and e, the production time of material a is constrained by the supply time of materials d and e. The composition of the product is constrained by the time when supply mechanism 1 provides materials a and b, supply mechanism 2 provides materials b and c, and supply mechanism 3 provides material c.

[0104] For another example, the assembly of a computer requires a monitor, a host, a keyboard and a mouse. If supply agency 1 takes 3 days to produce the monitor, supply agency 2 takes 6 days to produce the host, and supply agency 3 takes 2 days to purchase the keyboard and mouse, then the electronic device can determine the date constraints based on the supply time relationship of the monitor, host, keyboard and mouse, and further determine the time when the computer assembly is completed.

[0105] Since potential bottleneck supply mechanisms and bottleneck production capacity may affect the supply plan of the pending demand, the electronic device may consider the bottleneck supply mechanism and bottleneck materials in the pending demand when solving the supply plan corresponding to the pending demand. In step S103, the electronic device may input the pending demand, the supply and production capacity of each supply mechanism into the pre-trained knowledge reasoning model, obtain the bottleneck material and bottleneck supply mechanism corresponding to the pending demand, and obtain the score corresponding to the bottleneck material and the score corresponding to the bottleneck supply mechanism.

[0106] Among them, the knowledge reasoning model constructs material nodes and supply mechanism nodes based on the material information included in the historical planning and scheduling data and the relationship between each supply mechanism and the material identified by the beat, and characterizes the material nodes, supply mechanism nodes and the edges between the nodes with the demand, supply and production capacity included in the historical planning and scheduling data, which is used to predict the bottleneck materials and bottleneck supply mechanisms corresponding to the input demand.

[0107] Bottleneck supply organization is used to indicate that the supply organization has a bottleneck in the material production capacity, that is, the supply organization's ability to produce materials has a bottleneck. For example, when the supply organization is affected by equipment, supply chain, site, etc., the quantity of production materials is limited, and the supply organization is a bottleneck supply organization. Historical planning and scheduling data can include demand, supply, capacity, beat, supply time information and material information of each supply organization.

[0108] For example, the demands to be processed include demands 1, 2, and 3. The materials required for demand 1 include materials a, b, c, and d. The materials required for demand 2 include materials a and c. The materials required for demand 3 include materials c and d. Supply mechanism 1 provides materials a and b, supply mechanism 2 provides materials a and c, and supply mechanism 3 provides materials a, c, and d.

[0109] The electronic device inputs the current group of demands including demand 1, demand 2 and demand 3, supply mechanism 1, supply mechanism 2 and the supply of supply mechanism, as well as the production capacity for material a, material b, material c and material d into the pre-trained knowledge reasoning model, and can obtain that the bottleneck material corresponding to the demand to be processed is material b and the bottleneck supply mechanism is supply mechanism 1.

[0110] After obtaining the bottleneck supply mechanism corresponding to the demand to be processed and the score corresponding to the bottleneck supply mechanism, the electronic device can group and sort the demands to be processed based on the supply mechanism corresponding to the demand to be processed hitting the score corresponding to the bottleneck supply mechanism to obtain multiple sorted demand subgroups, that is, execute step S104.

[0111] In one embodiment, the electronic device may divide the pending demands into multiple demand subgroups according to the bottleneck supply mechanism hit by the supply mechanism corresponding to the pending demands, and then sort the multiple demand subgroups according to the scores of hitting the bottleneck supply mechanism.

[0112] For example, the demands to be processed include demands 1 to 6. The supply agencies corresponding to demands 1 and 6 are supply agency 1 and supply agency 4, the supply agencies corresponding to demands 2 and 5 are supply agency 3, the supply agencies corresponding to demand 3 are supply agency 1 and supply agency 4, and the supply agencies corresponding to demand 4 are supply agency 1 and supply agency 2. The bottleneck supply agencies are supply agency 1, supply agency 2, supply agency 3, and supply agency 4, and the corresponding scores are 8, 5, 3, and 1, respectively.

[0113] The electronic device can divide requirements 1, 3, and 6 into the first subgroup, requirements 2 and 5 into the second subgroup, and requirement 4 into the third subgroup. The score corresponding to the first subgroup is 9, the score corresponding to the second subgroup is 3, and the score corresponding to the third subgroup is 13. Then, the electronic device can obtain a plurality of sorted requirement subgroups, namely, the third subgroup, the first subgroup, and the second subgroup.

[0114] The division of demand subgroups takes into account the bottleneck supply mechanism. For each demand included in the demand subgroup, the bottleneck material included in the demand can be further considered. After obtaining the sorted multiple demand subgroups, the electronic device can obtain each demand subgroup in the sorted order, and for each demand included in the current subgroup, based on the number of times the material corresponding to the demand hits the bottleneck material and the score corresponding to the bottleneck material, determine the weight corresponding to the demand, that is, execute step S105. Among them, the higher the score of hitting the bottleneck material, the greater the weight, which means that there are many bottleneck materials in the demand, which may lead to a low demand fulfillment rate.

[0115] In one implementation, the electronic device may record the number of times each material below the material hits the bottleneck material and the sum of the scores corresponding to the bottleneck material according to the bill of materials of each requirement, and then determine the weight corresponding to each requirement according to the sum of the scores.

[0116] For example, the current subgroup includes demand 1 and demand 2. The bill of materials of material a required by demand 1 includes material b and material c, and the bill of materials of material b includes material d and material e; the bill of materials of material f required by demand 2 includes material b and material g, and the bill of materials of material b includes material d and material e. Among them, material c, material d and material e are bottleneck materials, and the corresponding scores are 5, 3, and 1. Among the materials corresponding to demand 1, material c, material d, and material e are bottleneck materials. The electronic device can determine that the score corresponding to demand 1 is 9, and among the materials corresponding to demand 2, material d and material e are bottleneck materials. The electronic device can determine that the score corresponding to demand 2 is 8. The weight can be determined according to the scores corresponding to demand 1 and demand 2, that is, the weight corresponding to demand 1 is 1, and the weight corresponding to demand 2 is 0.89.

[0117] After determining the weight corresponding to each demand included in the current subgroup, in step S106, the electronic device can use material constraints, production capacity constraints and date constraints as constraints, and the weighted demand fulfillment rate as the optimization goal, and based on the supply information of each supply agency, perform heuristic solution on the supply plan corresponding to each demand included in the current subgroup to obtain the supply plan corresponding to the demand to be processed.

[0118] That is to say, the electronic device can reasonably allocate the supply of each supply organization according to the materials required for each demand, based on the dependency relationship between the materials, the capacity constraints of each supply organization to provide the materials, and the time limit of each supply organization to provide the materials, with the weighted demand fulfillment rate as the optimization target, and obtain the supply plan corresponding to the demand to be processed according to the materials required for each demand. The weight is the weight corresponding to each demand included in the current subgroup.

[0119] Heuristic algorithms are proposed relative to optimization algorithms. The optimization algorithm for a problem is to find the optimal solution for each instance of the problem. Heuristic algorithms can include ant colony algorithms, simulated annealing methods, genetic algorithms, etc. For different heuristic algorithms, the encoding of heuristic solutions is different, and the corresponding encoding needs to be executed according to the heuristic algorithm.

[0120] For example, as a typical heuristic algorithm, the genetic algorithm solves the optimization problem according to the steps of encoding, generating the initial population, selecting, crossing, mutating, and updating the fitness. Specifically, according to the problem to be optimized (i.e., the demand fulfillment rate), the optimization variable (i.e., the supply plan) is encoded to form genes and chromosomes; a certain method (such as random) is used to obtain the initial population, which contains multiple individuals with different genes; the algorithm is iterated, and in one iteration, some individuals are selected from the population as parents, and the genes of the parent individuals are crossed and mutated to obtain the offspring individuals. The fitness values ​​of the parent individuals and the offspring individuals are calculated, and the better individuals are selected from the parent individuals and the offspring individuals according to a certain method (such as elite retention), added to the population, and a new population is formed; the above iterative process is repeated until the algorithm converges or the specified round of iteration ends. Finally, the optimal individual is decoded to obtain the optimal solution corresponding to the optimization problem (i.e., the supply plan corresponding to each demand) and the optimal objective function (i.e., the optimal demand fulfillment rate).

[0121] For example, after determining that the weight corresponding to demand 1 is 1 and the weight corresponding to demand 2 is 0.89, the electronic device can use material constraints, capacity constraints, and date constraints as constraints, and the achievement rate of weighted demand 1 and demand 2 as the optimization target for the demand 1 and demand 2 included in the current subgroup, and based on the supply information of each supply organization, perform heuristic solution on the supply plan corresponding to demand 1 and demand 2 included in the current subgroup to obtain the supply plan corresponding to demand 1 and demand 2. In this way, the demand with a large weight can be given priority, so that the materials and capacity of each supply organization can be reasonably allocated.

[0122] For another example, the current subgroup includes demand 1, and the weight of demand 1 is 0.92. The materials required for demand 1 include 3 materials a, 5 materials b, and 3 materials c. Supply organization 1 provides materials a and b. The production of material a in supply organization 1 depends on materials d and e. Supply organization 2 provides materials b and c. Supply organization 3 provides materials a, b, and c. Among them, material a provided by supply organization 3 is purchased and can be supplied on time. Supply organization 1 can provide 1 material a and 2 materials b every day if materials d and e are sufficient. Supply organization 2 can provide 6 materials b and 10 materials c within five days. Supply organization 3 can provide 3 materials a, 3 materials b, and 1 material c within three days.

[0123] Since the supply of material a by supply organization 1 is subject to the supply time constraints of material d and material e, material a can be provided by supply organization 3. Supply organization 1 can provide 6 materials b within three days, which is less time than supply organization 2 to provide 6 materials b, that is, the date on which supply organization 1 provides material b is earlier than that of supply organization 2. Similarly, the date on which supply organization 2 provides material c can be earlier than that of supply organization 3. Therefore, under the constraints of material constraints, production capacity constraints, and date constraints, and the weighted demand 1 achievement rate as the optimization target, the electronic equipment performs a heuristic solution for the supply plan corresponding to demand 1 based on the supply information of each supply organization, and obtains that the supply plan corresponding to demand 1 can be that supply organization 1 provides material b, supply organization 2 provides material c, and supply organization 3 provides material a.

[0124] In one embodiment, after the electronic device obtains the supply plan corresponding to the demand to be processed, it can modify the supply plan according to business needs to obtain a modified supply plan, and then store the modified supply plan in the business system to implement the modified supply plan.

[0125] In the scheme of this embodiment, when the supply plan corresponding to the demand to be processed is heuristically solved, not only the dependencies between the materials, the capacity constraints of each supply mechanism to provide each material, and the time limit for each supply mechanism to provide each material are considered, but also the pre-trained knowledge reasoning model predicts the potential bottleneck supply mechanism and bottleneck material, and the demands to be processed are grouped and sorted based on the scores corresponding to the bottleneck supply mechanism, each demand subgroup is obtained in the sorting order, the weight of each demand is determined based on the bottleneck material, and the weighted demand achievement rate is used as the optimization goal. Therefore, regardless of the demand restricted by the bottleneck material and the bottleneck supply mechanism, or the demand not restricted by the bottleneck material and the bottleneck supply mechanism, a reasonable supply plan can be obtained, so that each supply mechanism can supply reasonably and achieve supply and demand balance, thereby realizing a plan scheduling with high executability and high achievement rate.

[0126] As an implementation method of the present application, Figure 2 As shown, the step of grouping and sorting the demands to be processed based on the scores of the supply mechanisms corresponding to the demands to be processed hitting the bottleneck supply mechanisms to obtain a plurality of sorted demand subgroups may include:

[0127] S201, for each demand included in each demand group, determine the supply mechanism corresponding to the demand according to the material information corresponding to the demand and the beat;

[0128] Each group of requirements is obtained by grouping the requirements to be processed according to priority.

[0129] Different types of demands have different priorities, and the pending demands may include demands of different priorities. The electronic device may group demands of the same priority into a group, and sort the demands of each group in order of priority from high to low or from low to high, so that the priorities of each group of demands are different, and the priorities of each demand within the group are the same.

[0130] Since the beat is used to indicate the working hours required for the supply mechanism to provide each material, and / or is used to indicate the quantity of each material provided by the supply mechanism in a unit time, that is, there is a corresponding relationship between the supply mechanism and the material, the electronic device can determine the supply mechanism that provides the material based on the material. For each demand included in each group of demands, the electronic device can determine the supply mechanism corresponding to the demand based on the material corresponding to the demand and the beat of each supply mechanism included in the supply information.

[0131] For example, for demand 1 in the current group of demands, the materials required for demand 1 are material a and material b. According to the beat, it can be determined that supply mechanism 1 provides material a and supply mechanism 2 provides material b, that is, the supply mechanisms corresponding to demand 1 are supply mechanism 1 and supply mechanism 2.

[0132] For another example, for demand 1 and demand 2 in the current group of demands, the material required for demand 1 is material a, and the material required for demand 2 is material b. According to the rhythm, it can be determined that supply mechanism 1 provides material a, and supply mechanism 2 provides material b, that is, the supply mechanism corresponding to demand 1 is supply mechanism 1, and the supply mechanism corresponding to demand 2 is supply mechanism.

[0133] S202, dividing the demands of the supply mechanism and the bottleneck supply mechanism that are the same into a group of demands to obtain demand subgroups;

[0134] In one embodiment, for each group of demands, after the electronic device determines the supply mechanism corresponding to each demand included in the group of demands, the demands with the same supply mechanism as the bottleneck supply mechanism can be divided into one group, and other demands can be divided into one group, so that multiple demand subgroups can be obtained.

[0135] For example, the current group of demands includes demands 1 to 10, the material required for demands 1 and 2 is material a, the material required for demands 3 and 6 is material b, the material required for demand 5 is material c, the material required for demands 4 and 7 is material d, and the material required for demands 8 to 10 is material e. Supply mechanism 1 provides material c, supply mechanism 2 provides material e, supply mechanism 3 provides material b, and supply mechanism 4 provides material a and material d. The bottleneck supply mechanisms are supply mechanism 2 and supply mechanism 4. The electronic device can group demands with the same supply mechanism as the bottleneck supply mechanism into one group, that is, group demands 1, 2, 4, and 7 into one group, group demands 8 to 10 into one group, and group demands 3, 5, and 6 into one group.

[0136] In another implementation, for the current group of demands, after the electronic device determines the supply mechanism corresponding to each demand, the demands with the same supply mechanism can be grouped into one group to obtain multiple demand subgroups.

[0137] For example, the current group of demands includes demands 1 to 10, the material required for demands 1 and 6 is material a, the material required for demands 2 and 5 is material b, the material required for demands 3 and 9 is material c, the material required for demands 4 and 7 is material d, the material required for demand 8 is material e, and the material required for demand 10 is material f. Supply mechanism 1 provides material a and material c, supply mechanism 2 provides material b and material d, supply mechanism 3 provides material e, and supply mechanism 4 provides material f. Electronic devices can be grouped into one group with demands of the same supply mechanism, that is, demands 1, 3, 6, and 9 are grouped into one group, demands 2, 4, 5, and 7 are grouped into one group, demand 8 is grouped into one group, and demand 10 is grouped into one group.

[0138] S203, sorting the demand subgroups according to the scores of the corresponding bottleneck supply mechanisms to obtain a plurality of sorted demand subgroups.

[0139] Different bottleneck supply mechanisms indicate the degree to which different supply mechanisms become bottlenecks. In one embodiment, the electronic device may set different scores for different bottleneck supply mechanisms, sort the demand subgroups from high to low according to the scores of the corresponding bottleneck supply mechanisms, and obtain a plurality of sorted demand subgroups. The first demand subgroup obtained by the electronic device is the demand subgroup with the highest score.

[0140] For example, the electronic device obtains multiple demand subgroups, which are demand subgroups including demand 1, demand 2, demand 4, and demand 7, demand subgroups including demand 8 to demand 10, and demand subgroups including demand 3, demand 5, and demand 6. The scores of supply mechanism 2 and supply mechanism 4 are 5 and 3, respectively, and the score of the demand subgroup that does not include the bottleneck supply mechanism is 0. The electronic device can determine the score of the bottleneck supply mechanism corresponding to each demand subgroup, the score of the demand subgroup including demand 1, demand 2, demand 4, and demand 7 is 5, the score of the demand subgroup including demand 8 to demand 10 is 3, and the score of the demand subgroup including demand 6 and demand 7 is 0, and then the three demand subgroups are sorted according to the scores of the corresponding bottleneck supply mechanisms to obtain multiple sorted demand subgroups.

[0141] In another embodiment, the electronic device may sort the demand subgroups from high to low according to the scores of different supply mechanisms becoming bottleneck supply mechanisms, thereby obtaining a plurality of sorted demand subgroups.

[0142] For example, the electronic device obtains multiple demand subgroups, including demand 1, demand 3, demand 6 and demand 9, demand subgroup including demand 2, demand 4, demand 5 and demand 7, demand subgroup including demand 8, and demand subgroup including demand 10. The scores of supply agencies 1-4 becoming bottleneck supply agencies are 10, 8, 5, and 3. The electronic device can sort the demand subgroups according to the bottleneck supply agency scores corresponding to the supply agencies to obtain multiple sorted demand subgroups.

[0143] It can be seen that in this embodiment, for each demand included in each group of demands, the electronic device can determine the supply mechanism corresponding to the demand according to the material information and beat corresponding to the demand, divide the demands with the same supply mechanism and bottleneck supply mechanism into a group of demands to obtain demand subgroups, and sort the demand subgroups according to the scores of the corresponding bottleneck supply mechanisms to obtain a plurality of sorted demand subgroups. Since the bottleneck supply mechanism is taken into account when grouping and sorting each demand subgroup, the demand subgroup with a high score of the bottleneck supply mechanism can be processed first, so that each supply mechanism can achieve a reasonable allocation of materials and production capacity.

[0144] As an implementation method of the present application, Figure 3 As shown, the above-mentioned step of taking the material constraint, the capacity constraint and the date constraint as constraint conditions, taking the demand fulfillment rate with the weight as the optimization target, performing heuristic solution on the supply plan corresponding to each demand included in the current subgroup based on the supply information of each supply organization, and obtaining the supply plan corresponding to the demand to be processed may include:

[0145] S301, obtaining a group of requirements with the highest priority as the current group of requirements;

[0146] In one embodiment, in order to promptly process high-priority demands, the electronic device may obtain a group of demands with the highest priority as the current group of demands. For example, if the demands to be processed include 3 groups and the highest priority is 1, the electronic device may obtain a group of demands with the priority of 1 as the current group of demands.

[0147] S302, for the demand subgroup included in the current group demand, taking the material constraint, the capacity constraint and the date constraint as constraint conditions, taking the demand achievement rate with the weight corresponding to the demand subgroup included in the current group demand as an optimization target, and based on the current supply information of each supply agency, performing a heuristic solution on the supply plan corresponding to the demand subgroup included in the current group demand to obtain the supply plan corresponding to the current group demand;

[0148] After the electronic device obtains the current group demand, it can target the demand subgroups included in the current group demand, based on the dependencies between the materials in the current group demand, the capacity constraints of each supply agency in providing each material, and the time limit for each supply agency to provide each material. It can use the weighted demand fulfillment rate corresponding to the demand subgroups included in the current group demand as the optimization target, and reasonably allocate the supply of each supply agency according to the materials required for the current group demand to obtain the supply plan corresponding to the current group demand.

[0149] For example, the current group demand includes demand subgroup 1, demand subgroup 2 and demand subgroup 3. Demand subgroup 1 includes demand 1, demand subgroup 2 includes demand 2, and demand subgroup 3 includes demand 3. The weights of demand 1, demand 2 and demand 3 are 1, 0.89 and 0.95 respectively. The materials required by demand subgroup 1 include material a, material b, material c and material d. The materials required by demand subgroup 2 include material a and material c. The materials required by demand subgroup 3 include material c and material d. The production of material b depends on material d. Supply organization 1 provides material a and material b, supply organization 2 provides material b and material c, and supply organization 3 provides material a, material c and material d.

[0150] The electronic device can, for demand subgroup 1, demand subgroup 2, and demand subgroup 3 included in the current group demand, according to the dependency relationship between materials a, material b, material c, and material d, the capacity constraints of supply mechanism 1, supply mechanism 2, and supply mechanism 3 in providing the corresponding materials a, material b, material c, and material d, and the time limit for supply mechanism 1, supply mechanism 2, and supply mechanism 3 to provide the corresponding materials a, material b, material c, and material d, take the weighted demand fulfillment rate corresponding to demand subgroup 1, demand subgroup 2, and demand subgroup 3 included in the current group demand as the optimization target, and reasonably allocate the supply of supply mechanism 1, supply mechanism 2, and supply mechanism 3 according to the materials required by demand subgroup 1, demand subgroup 2, and demand subgroup 3, to obtain the supply plan of the current group demand, that is, the supply plan corresponding to demand 1 is that supply mechanism 2 provides material b, and supply mechanism 3 provides material a, material c, and material d, the supply plan corresponding to demand 2 is that supply mechanism 1 and supply mechanism 3 provide material a, and supply mechanism 2 provides material c, and the supply plan corresponding to demand 3 is that supply mechanism 3 provides material c and material d.

[0151] S303, deducting the supply information of each supply mechanism required by the supply plan to obtain the current supply information of each supply mechanism;

[0152] After the electronic device reasonably allocates the supply of each supply organization according to the materials required by the demand sub-groups included in the current group demand, the supply of each supply organization is reduced accordingly. The electronic device can deduct the supply information of each supply organization required by the supply plan to obtain the current supply information of each supply organization.

[0153] For example, the current group demand includes demand subgroup 1, demand subgroup 2 and demand subgroup 3, demand subgroup 1 includes demand 1, demand subgroup 2 includes demand 2, demand subgroup 3 includes demand 3, the materials required for demand 1 include n1 materials a, n2 materials b, n3 materials c and n2 materials d, the materials required for demand 2 include n4 materials a and n5 materials c, and the materials required for demand 3 include n1 materials c and n2 materials d. Supply mechanism 1 can provide N1 materials a and N2 materials b, supply mechanism 2 can provide N3 materials b and N4 materials c, and supply mechanism 3 can provide N5 materials a, N6 materials c and N7 materials d.

[0154] The supply plan corresponding to demand 1 is that supply organization 2 provides material b, and supply organization 3 provides material a, material c, and material d. The supply plan corresponding to demand 2 is that supply organization 1 provides material a, and supply organization 2 provides material c. The supply plan corresponding to demand 3 is that supply organization 3 provides material c and material d.

[0155] After the electronic equipment reasonably allocates the supplies of supply mechanism 1, supply mechanism 2 and supply mechanism 3 according to the materials required by demand subgroup 1, demand subgroup 2 and demand subgroup 3, the electronic equipment can deduct the supply information of supply mechanism 1, supply mechanism 2 and supply mechanism 3 required by the supply plan to obtain the current supply information of each supply mechanism, that is, supply mechanism 1 can provide N1-n4 materials a and N2 materials b, supply mechanism 2 can provide N3-n2 materials b and N4-n5 materials c, and supply mechanism 3 can provide N5-n1 material a, N6-n3-n1 material c and N7-n2-n2 material d.

[0156] S304, obtaining the next set of demands in descending order of priority as the current set of demands, and returning the demand subgroup included in the current set of demands, taking the material constraint, the production capacity constraint and the date constraint as constraint conditions, taking the demand fulfillment rate with the weight corresponding to the demand subgroup included in the current set of demands as the optimization target, performing heuristic solution on the supply plan corresponding to the demand subgroup included in the current set of demands based on the current supply information of each supply agency, and obtaining the supply plan corresponding to the current set of demands, until multiple sets of demands are processed.

[0157] After the electronic device has processed the current group of demands, it can continue to process the next group of demands, that is, obtain the next group of demands in order of priority from high to low as the current group of demands, and then for the demand subgroups included in this group of demands, use material constraints, production capacity constraints and date constraints as constraints, and take the weighted demand fulfillment rate corresponding to the demand subgroups included in the current group of demands as the optimization target. Based on the current supply information of each supply agency, perform heuristic solution on the supply plan corresponding to the demand subgroups included in the current group of demands, and obtain the steps of the supply plan corresponding to the current group of demands until multiple groups of demands are processed.

[0158] For example, the demands to be processed include three groups of demands. After the electronic device processes a group of demands with a priority of 1, it can obtain a group of demands with a priority of 2, and use this group of demands as the current group of demands. The current group of demands includes demand subgroup 4 and demand subgroup 5. For this group of demands, the dependency relationship between the materials in demand subgroup 4 and demand subgroup 5, the capacity constraints of each supply agency to provide each material, and the time limit for each supply agency to provide each material are taken as the optimization target. The weighted demand fulfillment rate corresponding to demand subgroup 4 and demand subgroup 5 is taken as the optimization target. Based on the current supply information of each supply agency, the supply plan corresponding to demand subgroup 4 and demand subgroup 5 is heuristically solved to obtain the supply plan corresponding to the current group of demands until all three groups of demands are processed.

[0159] It can be seen that in this embodiment, the electronic device can process each group of demands according to the priority of each group of demands in order from high to low priority. For the demand subgroups included in the current group of demands, the material constraints, production capacity constraints and date constraints are used as constraints, and the weighted demand achievement rate corresponding to the demand subgroups included in the current group of demands is used as the optimization target. Based on the current supply information of each supply agency, the supply plan corresponding to the demand subgroup included in the current group of demands is heuristically solved to obtain the supply plan corresponding to the current group of demands until multiple groups of demands are processed. In this way, for the planning field, highly executable supply plans are output for various types of demands, so that each supply agency can supply reasonably and achieve supply and demand balance, thereby improving the executability and achievement rate of the plan scheduling.

[0160] As an implementation method of the present application, Figure 4 As shown, for the demand subgroup included in the current group demand, the material constraint, the capacity constraint and the date constraint are used as constraint conditions, the demand achievement rate with the weight corresponding to the demand subgroup included in the current group demand is used as an optimization target, and based on the current supply information of each supply agency, the supply plan corresponding to the demand subgroup included in the current group demand is heuristically solved to obtain the supply plan corresponding to the current group demand, which may include:

[0161] S401, for the current group of requirements, obtaining the first requirement subgroup according to the sorting order as the current subgroup;

[0162] In order to reasonably allocate the supply of each supply mechanism, the demand with high score of the bottleneck supply mechanism can be given priority. For the current group of demands, the electronic device can obtain the first demand subgroup in the sorting order as the current subgroup, that is, the demand subgroup with high score of the bottleneck supply mechanism is given priority.

[0163] For example, the current group of requirements includes requirements 1, 2, 3, and 4. The current group of requirements includes three requirement subgroups, wherein requirements 1 and 2 are the first requirement subgroup, requirement 3 is the second requirement subgroup, and requirement 4 is the third requirement subgroup. The electronic device can obtain the first requirement subgroup in sequence, that is, obtain requirements 1 and 2, and then use requirements 1 and 2 as the current subgroup.

[0164] S402, for the current subgroup, taking the material constraint, the capacity constraint and the date constraint as constraint conditions, taking the weighted demand fulfillment rate corresponding to the current subgroup as an optimization target, and based on the current supply information of each supply organization, performing a heuristic solution on the supply plan corresponding to the current subgroup to obtain the supply plan corresponding to the current subgroup;

[0165] For example, the current subgroup includes demand 1 and demand 2. The corresponding weights of demand 1 and demand 2 are 1 and 0.89 respectively. The materials required for demand 1 include material a, material b and material c. The materials required for demand 2 include material c and material d. The production of material a depends on materials b and c. Supply organization 1 provides material a and material b, supply organization 2 provides material c, and supply organization 3 provides material b and material d.

[0166] The electronic device can, for demand 1 and demand 2 included in the current subgroup, according to the dependency relationship between materials a, material b, material c and material d, the capacity constraints of supply organization 1, supply organization 2 and supply organization 3 in providing corresponding materials a, material b, material c and material d, and the time limit for supply organization 1, supply organization 2 and supply organization 3 to provide corresponding materials a, material b, material c and material d, take the achievement rate of demand 1 and demand 2 with weights as the optimization target, and reasonably allocate the supply of supply organization 1, supply organization 2 and supply organization 3 according to the materials required for demand 1 and demand 2, so as to obtain the supply plan corresponding to demand 1 and demand 2, that is, the supply plan corresponding to demand 1 is that supply organization 1 provides materials a and material b, and supply organization 2 provides material c, and the supply plan corresponding to demand 2 is that supply organization 2 provides material c, and supply organization 3 provides material d.

[0167] For another example, the current subgroup includes demand 1, demand 2, demand 3, and demand 4, and the weights of demand 1, demand 2, demand 3, and demand 4 are obtained. The material required for demand 1 is material a, and the production of material a depends on material b and material c. The material required for demand 2 is material d. The material required for demand 3 is material e, and the production of material e depends on materials b and f. The material required for demand 4 is material g. Supply organization 1 provides material a, material b, and material g, supply organization 2 provides material c, material d, and material e, and supply organization 3 provides material f.

[0168] The electronic device can provide the corresponding capacity constraints of materials a, materials b, materials c, materials d, materials e, materials f and materials g for the requirements 1, requirements 2, requirements 3 and requirements 4 included in the current subgroup according to the dependency relationship between materials a, materials b, materials c, materials d, materials e, materials f and materials g, and the time limits of materials a, materials b, materials c, materials d, materials e, materials f and materials g provided by the supply mechanism 1, supply mechanism 2 and supply mechanism 3, so as to realize the weighted requirements 1, requirements 2, requirements 3 and requirements 4. Taking the achievement rate as the optimization goal, the supply of supply organization 1, supply organization 2 and supply organization 3 is reasonably allocated according to the materials required for demand 1, demand 2, demand 3 and demand 4, and the supply plans for demand 1, demand 2, demand 3 and demand 4 are obtained. That is, the supply plan corresponding to demand 1 is that supply organization 1 provides materials a and material b, and supply organization 2 provides material c. The supply plan corresponding to demand 2 is that supply organization 2 provides material d. The supply plan corresponding to demand 3 is that supply organization 2 provides material e, supply organization 1 provides material b, and supply organization 3 provides material f. The supply plan corresponding to demand 4 is that the supply organization provides material f.

[0169] S403, deducting the supply information of each supply mechanism required by the supply plan to obtain the current supply information of each supply mechanism;

[0170] After the electronic device reasonably allocates the supply of each supply mechanism according to the materials required by the current sub-group, the supply of each supply mechanism is reduced accordingly. The electronic device can deduct the supply of each supply mechanism required by the supply plan to obtain the current supply of each supply mechanism.

[0171] For example, the current subgroup includes demand 1 and demand 2. The materials required for demand 1 include n1 material a, n2 material b, and n3 material c. The materials required for demand 2 include n4 material c and n5 material d. Supply organization 1 can provide N1 material a and N2 material b, supply organization 2 can provide N3 material c, and supply organization 3 can provide N4 material b and N5 material d. The supply plan corresponding to demand 1 is that supply organization 1 provides material a and material b, and supply organization 2 provides material c. The supply plan corresponding to demand 2 is that supply organization 2 provides material c, and supply organization 3 provides material d.

[0172] After the electronic equipment reasonably allocates the supplies of supply mechanism 1, supply mechanism 2 and supply mechanism 3 according to demand 1 and demand 2, the electronic equipment can deduct the supply information of supply mechanism 1, supply mechanism 2 and supply mechanism 3 required by the supply plan to obtain the current supply information of each supply mechanism, that is, supply mechanism 1 can provide N1-n1 materials a and N2-n2 materials b, supply mechanism 2 can provide N3-n3-n4 materials c, and supply mechanism 3 can provide N4 materials b and N5-n5 materials d.

[0173] For another example, the current subgroup includes demand 1, demand 2, demand 3, and demand 4. The materials required to complete demand 1 include n1 materials a, n2 materials b, and n3 materials c. The materials required to complete demand 2 include n4 materials d. The materials required to complete demand 3 include n5 materials e, n6 materials b, and n7 materials f. The materials required to complete demand 4 include n8 materials g. Supply organization 1 can provide N1 materials a, N2 materials b, and N3 materials g. Supply organization 2 can provide N4 materials c, N5 materials d, and N6 materials e. Supply organization 3 can provide N7 materials f. The supply plan corresponding to demand 1 is provided by supply organization 1 with materials a and material b, and supply organization 2 with material c. The supply plan corresponding to demand 2 is provided by supply organization 2 with material d. The supply plan corresponding to demand 3 is provided by supply organization 2 with material e, supply organization 1 with material b, and supply organization 3 with material f. The supply plan corresponding to demand 4 is provided by supply organization f.

[0174] After the electronic equipment reasonably allocates the supplies of supply mechanism 1, supply mechanism 2 and supply mechanism 3 according to demand 1, demand 2, demand 3 and demand 4, the electronic equipment can deduct the supply information of supply mechanism 1, supply mechanism 2 and supply mechanism 3 required by the supply plan to obtain the current supply information of each supply mechanism, that is, supply mechanism 1 can provide N1-n1 material a, N2-n2-n6 material b, N3-n8 material g, supply mechanism 2 can provide N4-n3 material c, N5-n4 material d, N6-n5 material e, and supply mechanism 3 can provide N7-n7 material f.

[0175] S404, obtaining the next demand subgroup in the order as the current subgroup, and returning the step of obtaining the supply plan corresponding to the current subgroup by heuristically solving the supply plan corresponding to the current subgroup based on the current supply information of each supply agency, with the material constraint, the production capacity constraint and the date constraint as constraint conditions, and the weighted demand fulfillment rate corresponding to the current subgroup as the optimization target, until multiple demand subgroups are processed.

[0176] After the electronic device has processed the current subgroup, it can continue to process the next subgroup, that is, obtain the next subgroup in sequence as the current subgroup, and then for this subgroup, use material constraints, production capacity constraints and date constraints as constraints, and the weighted demand fulfillment rate corresponding to the current subgroup as the optimization goal. Based on the current supply information of each supply agency, the supply plan corresponding to the current subgroup is heuristically solved to obtain the steps of the supply plan corresponding to the current subgroup until multiple demand subgroups are processed.

[0177] For example, the current group demand includes 3 demand subgroups. After the electronic device processes the first demand subgroup, it can obtain the demand subgroup ranked second and use this demand subgroup as the current subgroup. The current subgroup includes demand 3. For this demand subgroup, the dependency relationship between the materials in demand 3, the capacity constraints of each supply agency to provide each material, and the time limit for each supply agency to provide each material, the weighted demand 3 achievement rate is used as the optimization target, and based on the current supply information of each supply agency, the supply plan corresponding to demand 3 is heuristically solved to obtain the supply plan corresponding to demand 3 until all 3 demand subgroups are processed.

[0178] It can be seen that in this embodiment, the electronic device can process each demand subgroup according to the arrangement order of each demand subgroup. For the current subgroup, the material constraint, production capacity constraint and date constraint are used as constraint conditions, and the weighted demand achievement rate corresponding to the current subgroup is used as the optimization target. Based on the current supply information of each supply agency, the supply plan corresponding to the current subgroup is heuristically solved to obtain the supply plan corresponding to the current subgroup until multiple demand subgroups are processed. In this way, a highly executable supply plan is output for each type of demand in the planning field, so that each supply agency can supply reasonably, achieve supply and demand balance, and thus improve the executability and achievement rate of the plan scheduling.

[0179] As an implementation method of the present application, Figure 5 As shown, the construction method of the above knowledge reasoning model may include:

[0180] S501, obtaining historical planning and scheduling data, historical bottleneck materials, and historical bottleneck supply organizations;

[0181] S502, constructing a material node and a supply mechanism node according to the material information included in the historical planning and scheduling data and the relationship between each supply mechanism and the material identified by the beat;

[0182] In order to build a knowledge reasoning model, the electronic device can obtain historical planning and scheduling data, historical bottleneck materials, and historical bottleneck supply agencies. The historical planning and scheduling data may include demand, supply, production capacity, beat, supply time information, and material information of each supply agency, which are not specifically limited here.

[0183] In this way, the electronic device can construct two types of nodes included in the heterogeneous directed graph, namely material nodes and supply mechanism nodes, based on the material information included in the historical planning and scheduling data and the relationship between each supply mechanism and the material identified by the beat.

[0184] S503, characterizing the material nodes, supply mechanism nodes and edges between nodes based on the demand, supply and capacity included in the historical planning and scheduling data to obtain a heterogeneous directed graph;

[0185] Among them, the edges between material nodes in the heterogeneous directed graph represent the constraint relationship between the materials corresponding to the material nodes, and the edges between the material nodes and the supply mechanism nodes represent that the materials corresponding to the material nodes can be produced by the supply mechanism corresponding to the supply mechanism nodes.

[0186] In one embodiment, the electronic device characterizes the material nodes, supply mechanism nodes, and edges between nodes using the demand, supply, and capacity included in the historical planning and scheduling data to obtain a directed heterogeneous graph. The heterogeneous directed graph includes two types of edges, namely, the edges between material nodes and the edges between material nodes and supply mechanism nodes. The edges between material nodes represent the constraint relationship between the materials corresponding to the material nodes. The direction of the edge can represent the dependency relationship between the materials. For example, the node corresponding to the upper material in the bill of materials points to the node corresponding to the lower material, indicating that the upper material depends on the lower material.

[0187] The edge between the material node and the supply mechanism node indicates that the material corresponding to the material node can be produced by the supply mechanism corresponding to the supply mechanism node. The direction of the edge is from the material node to the supply mechanism node, which is a working time transfer relationship. The material corresponding to the material node is produced by the supply mechanism corresponding to the supply mechanism node.

[0188] For example, Figure 6As shown, on the graph construction side, the historical planning and scheduling data includes two BOMs. The first BOM includes material A, material B, material C, material D, and material E, where the production of material A depends on material B and material C, and the production of material B depends on material D and material E. The second BOM includes material F, material B, material G, material D, and material E. Wherein, the production of material F depends on material B and material G, and the production of material B depends on material D and material E. The beat identification supply mechanism W1 can produce material A, supply mechanism W2 can produce material A and material F, and supply mechanism W3 can produce material F.

[0189] The electronic device can construct material nodes and supply mechanism nodes of a directed heterogeneous graph according to the relationship between each supply mechanism and the material identified by the BOM and the beat included in the historical planning and scheduling data, and characterize the material nodes, supply mechanism nodes and the edges between the nodes according to the demand, supply and capacity included in the historical planning and scheduling data to obtain a heterogeneous directed graph 601. Among them, the material nodes are F, A, G, B, C, D, E, and the supply mechanism nodes are W1, W2, W3. The directed arrows between the material nodes represent the dependency relationship between the materials, and the directed arrows between the material nodes and the supply mechanism nodes represent the materials produced by the supply mechanism.

[0190] S504, based on the historical planning and scheduling data, historical bottleneck materials and historical bottleneck supply mechanisms, the heterogeneous directed graph is trained to obtain the knowledge reasoning model.

[0191] After constructing the heterogeneous directed graph, the electronic device can train the heterogeneous directed graph based on historical planning and scheduling data, historical bottleneck materials, and historical bottleneck supply agencies to obtain a knowledge reasoning model.

[0192] For example, Figure 6 As shown, on the training and knowledge reasoning side, the electronic device can input the demand, supply of each supply mechanism, production capacity, historical bottleneck materials and historical bottleneck supply mechanism included in the historical planning and scheduling data into the heterogeneous directed graph 601 until the loss function converges, and the knowledge reasoning model can be obtained. After the electronic device inputs the pending demand, the supply of each supply mechanism and production capacity into the knowledge reasoning model, the potential bottleneck materials and potential bottleneck supply mechanism corresponding to the pending demand can be obtained, and the scores corresponding to the bottleneck materials and bottleneck supply mechanism can be obtained.

[0193] It can be seen that in this embodiment, historical planning and scheduling data, historical bottleneck materials and historical bottleneck supply mechanisms are obtained, and material nodes and supply mechanism nodes are constructed according to the material information included in the historical planning and scheduling data and the relationship between each supply mechanism and the material identified by the beat. The material nodes, supply mechanism nodes and the edges between the nodes are characterized by the demand, supply and production capacity included in the historical planning and scheduling data to obtain a heterogeneous directed graph. Based on the historical planning and scheduling data, historical bottleneck materials and historical bottleneck supply mechanisms, the heterogeneous directed graph is trained to obtain a knowledge reasoning model, so that the knowledge reasoning model can be used to predict potential bottleneck materials and bottleneck supply mechanisms, and the scores corresponding to the bottleneck materials and bottleneck supply mechanisms can be obtained, so that the information of bottleneck materials and bottleneck supply mechanisms can be fully utilized to achieve a reasonable allocation of materials and production capacity for each supply mechanism.

[0194] As an implementation method of the present application, Figure 7 As shown, the step of training the heterogeneous directed graph based on the historical planning and scheduling data, historical bottleneck materials, and historical bottleneck supply mechanisms to obtain the knowledge reasoning model may include:

[0195] S701, determining nodes corresponding to historical bottleneck materials and nodes corresponding to historical bottleneck supply mechanisms in the heterogeneous directed graph as positive samples, and determining nodes other than the positive samples as negative samples;

[0196] After constructing the heterogeneous directed graph, the electronic device can construct positive and negative samples for the material nodes or supply mechanism nodes of the heterogeneous directed graph based on the historical bottleneck materials and the historical bottleneck supply mechanisms. In one embodiment, the electronic device can determine the nodes corresponding to the historical bottleneck materials and the nodes corresponding to the historical bottleneck supply mechanisms in the heterogeneous directed graph as positive samples, and determine the nodes other than the positive samples as negative samples.

[0197] For example, the historical bottleneck materials are material B and material A, and the historical bottleneck supply mechanism is supply mechanism W2. Figure 6 As shown, on the training and knowledge reasoning side, the electronic device can determine the node B corresponding to material B, the node A corresponding to material A, and the node W2 corresponding to the supply mechanism W2 in the heterogeneous directed graph 601 as positive samples, and determine the material nodes F, G, C, D, E and the supply mechanism nodes W1 and W3 as negative samples.

[0198] S702, using the demand and supply included in the historical planning and scheduling data as the initial vector of the material node, the capacity as the initial vector of the supply mechanism node, the relationship between the material information as the initial vector of the edge between the material node and the material node, and the beat as the initial vector of the edge between the material node and the supply mechanism node;

[0199] Electronic equipment can determine the initial vector of a heterogeneous directed graph based on demand, supply, production capacity, rhythm and material information included in historical planning and scheduling data, that is, using demand and supply as the initial vectors of material nodes, production capacity as the initial vector of supply mechanism nodes, the relationship between material information as the initial vector of the edges between material nodes, and rhythm as the initial vector of the edges between material nodes and supply mechanism nodes.

[0200] S703: Based on the positive samples, the negative samples and the initial vectors, the heterogeneous directed graph is trained to obtain the knowledge reasoning model.

[0201] In one embodiment, after the electronic device determines the positive samples, negative samples and each initial vector, the positive samples, negative samples and each initial vector can be input into a heterogeneous directed graph, and the heterogeneous directed graph can be trained until the loss function converges to obtain a knowledge reasoning model, thereby predicting the bottleneck materials and bottleneck supply mechanisms, and obtaining the corresponding scores of the bottleneck materials and bottleneck supply mechanisms.

[0202] It can be seen that in this embodiment, the electronic device can determine the nodes corresponding to the historical bottleneck materials and the nodes corresponding to the historical bottleneck supply mechanisms in the heterogeneous directed graph as positive samples, and determine the nodes other than the positive samples as negative samples, and use the demand and supply included in the historical planning and scheduling data as the initial vectors of the material nodes, the production capacity as the initial vector of the supply mechanism nodes, the relationship between the material information as the initial vector of the edges between the material nodes, and the beat as the initial vector of the edges between the material nodes and the supply mechanism nodes. Based on the positive samples, negative samples and each initial vector, the heterogeneous directed graph is trained to obtain a knowledge reasoning model, which can then realize the prediction of potential bottleneck materials and bottleneck supply mechanisms.

[0203] As an implementation method of the embodiment of the present application, the above-mentioned demand to be processed includes predicted demand;

[0204] like Figure 8 As shown, before the step of obtaining the demand, supply information and material information to be processed, the method may further include:

[0205] S801, obtain historical demand data and switching data of materials;

[0206] The switching data is material data that changes according to business requirements.

[0207] The pending demand can include forecast demand, which is a forecast of the potential material demand in the future. Forecast demand can be regarded as a type of demand. In this way, when the supply plan of forecast demand is obtained, the staff can replenish the material demand according to the supply plan and meet the forecast demand in time when it occurs.

[0208] The electronic device can obtain the historical demand data and switching data of materials. The switching data is the material data that changes according to business needs. The historical demand data can be data stored in the business system. For example, for product a, the market includes the original model A and the new model B. The electronic device can obtain the historical demand data of the materials required by the original model A and the material data required by the new model B, that is, the switching data.

[0209] In one implementation, after the electronic device obtains the historical demand data and switching data of the material, the historical demand data and switching data may be cleaned and sorted, such as processing abnormal values.

[0210] S802, constructing a demand sequence for the material according to the time sequence corresponding to the historical demand data and the switching data;

[0211] After the electronic device obtains the historical demand data and switching data, it can construct a demand sequence for the material according to the time sequence corresponding to the historical demand data and switching data. For example, according to the historical demand data, the demand data of material a, material b, material c, material d, and material e are obtained; according to the historical switching data, the switching time t1 of material a and material c, and the switching time t2 of material d and material e are obtained. Then the demand sequence of the material is determined, which are demand sequence 1, demand sequence 2, and demand sequence 3. Demand sequence 1 contains material c, and the demand quantity is the sum of the demand quantities of material a and material c at the same time point. Demand sequence 2 contains material b, and demand sequence 3 contains material e, and the demand quantity is the sum of the demand quantities of material d and material e at the same time point.

[0212] S803, extracting features from the demand sequence to obtain sequence features of the demand sequence, and classifying the materials based on the sequence features to obtain multiple categories of materials;

[0213] In one implementation, after constructing the material demand sequence, the electronic device may extract features from the demand sequence to obtain sequence features of the demand sequence, and classify the materials using a clustering algorithm based on the sequence features to obtain multiple categories of materials.

[0214] For example, following the example in step S802, after the electronic device constructs demand sequence 1, demand sequence 2 and demand sequence 3, it can respectively extract features from demand sequence 1, demand sequence 2 and demand sequence 3 to obtain sequence features of each demand sequence, and use a clustering algorithm to classify material b, material c and material e based on the sequence features to obtain two categories of materials, category 1 including material b and material e, and category 2 including material c.

[0215] S804, for each category of materials, using a forecasting method that is compatible with the sequence characteristics of the category of materials, forecasting the demand for the category of materials, and obtaining the forecast demand for the category of materials.

[0216] For different categories of materials, the electronic device may use different prediction algorithms for prediction. In one embodiment, for each category of materials, the electronic device may use a prediction method that is compatible with the sequence characteristics of the materials in that category to predict the demand for the materials in that category, thereby obtaining the predicted demand for the materials in that category. The prediction method may be a machine learning algorithm, a deep learning algorithm, etc., which are not specifically limited here.

[0217] For example, for material b in category 1, the electronic device can use a deep learning algorithm that is compatible with the sequence characteristics of materials in this category to predict material b and obtain the predicted demand for material b. If the predicted demand for material b increases, material b can be appropriately replenished to meet the demand for material b in a timely manner when the demand for material b arises.

[0218] In one embodiment, the electronic device can pre-build a demand forecasting model, and when the historical demand data and switching data of the material are input into the demand forecasting model, the forecast demand of each category of material can be output. Fig. 9 As shown, the demand forecasting model includes three parts: feature engineering, material clustering, and machine learning / deep learning algorithm training and reasoning. Feature engineering can realize feature extraction of demand sequences, material clustering can realize material classification, and machine learning / deep learning algorithm training and reasoning can adopt a prediction method that is compatible with the sequence characteristics of each category of materials to predict the demand for each category of materials. When the electronic device inputs the acquired historical demand data of materials and the material switching data into the demand forecasting model, the predicted demand for each category of materials can be output.

[0219] It can be seen that in this embodiment, the electronic device can obtain the historical demand data and switching data of the material, construct the demand sequence of the material according to the time sequence corresponding to the historical demand data and the switching data, extract features of the demand sequence, obtain the sequence features of the demand sequence, and classify the materials based on the sequence features to obtain multiple categories of materials. For each category of materials, a forecasting method that is compatible with the sequence features of the materials in that category is used to forecast the demand for the materials in that category and obtain the forecasted demand for the materials in that category. In this way, the forecasted demand can be considered when the materials and production capacity of each supply organization are reasonably allocated, and the staff can be guided to replenish the materials related to the supply plan according to the supply plan of the forecasted demand. When the forecasted demand occurs, the materials required for the forecasted demand can be provided in time, thereby improving the executability and achievement rate of the planning and scheduling.

[0220] As an implementation method of the embodiment of the present application, the supply of each supply mechanism mentioned above includes a revised purchase supply;

[0221] like Fig.10 As shown, before the step of obtaining the demand, supply information and material information to be processed, the method may further include:

[0222] S1001, obtaining historical supply data of the supply organization;

[0223] The historical supply data includes the supply date and supply quantity of each material by each supply mechanism.

[0224] Since the supply capacity of the selected supply mechanism is not fixed, the supply capacity of the selected supply mechanism can be evaluated. In one embodiment, the electronic device can evaluate the accuracy of the supply date and supply quantity of the procurement supply provided by the supply mechanism based on the historical supply data of each supply mechanism, that is, if the supply date and supply quantity of the material change, the supply date and supply quantity are corrected.

[0225] The electronic device can obtain the historical supply data of the supply mechanism. The historical supply data includes the supply date and supply quantity of each material by each supply mechanism. For example, the selected supply mechanism includes supply mechanism 1, supply mechanism 2 and supply mechanism 3, and the electronic device can obtain the historical supply data of supply mechanism 1, supply mechanism 2 and supply mechanism 3. The historical supply data includes the supply date and supply quantity of material a and material b by supply mechanism 1, the supply date and supply quantity of material b and material c by supply mechanism 2, and the supply date and supply quantity of material d by supply mechanism 3.

[0226] In one implementation, after the electronic device acquires the historical supply data of the supply mechanism, the historical supply data may be cleaned and sorted, such as processing abnormal values.

[0227] S1002, extracting features from the historical supply data to obtain features of the historical supply data, and classifying each material based on the features to obtain multiple categories of materials;

[0228] After the electronic device obtains the historical supply data, it can extract features from the historical supply data to obtain features of the historical supply data, and classify each material using a clustering method based on the extracted features, thereby obtaining multiple categories of materials. For example, following the example in step S1001, the electronic device can extract features from the historical supply data to obtain features of the historical supply data, and classify materials a, b, c, and d based on the features to obtain three categories, namely, category 1 includes materials a and b provided by supply mechanism 1, and material b provided by supply mechanism 2, category 2 includes material c provided by supply mechanism 2, and category 3 includes material d provided by supply mechanism 3.

[0229] S1003, for each category of materials, a forecasting method adapted to the characteristics of the category of materials is used to forecast the supply date and supply quantity of the category of materials, and a revised procurement supply of the category of materials is obtained.

[0230] For different categories of materials, the electronic device can use different prediction algorithms for prediction. In one embodiment, for each category of materials, the electronic device can use a prediction method that is compatible with the characteristics of the category to predict the supply date and supply quantity of the category of materials, and then obtain the revised purchase supply of the category of materials. Among them, the prediction method can be a machine learning algorithm, a deep learning algorithm, etc., which is not specifically limited here.

[0231] For example, for material d provided by supply mechanism 3 in category 3, the electronic device can use a deep learning algorithm that is adapted to the characteristics of this category to predict the supply date and supply quantity of material d. If the supply date and supply quantity of material d are different from those provided in the historical supply data of supply mechanism 3, the supply date and supply quantity of material d by supply mechanism 3 will be corrected.

[0232] In one embodiment, the electronic device can pre-build a supply mechanism capability assessment model, and when the supply mechanism's historical supply data is input into the supply mechanism capability assessment model, the revised procurement supply of each category of materials can be output. Fig.11As shown, the supply agency capacity assessment model includes three parts: feature engineering, material clustering, and machine learning / deep learning algorithm training and reasoning. Feature engineering can realize feature extraction of historical supply data, material clustering can realize classification of each material, and machine learning / deep learning algorithm training and reasoning can adopt a prediction method that is compatible with the characteristics of each category of materials to predict the supply date and supply quantity of each category of materials. When the electronic device obtains the historical supply data of the supply agency and inputs it into the supply agency capacity assessment model, it can output the supply date and supply quantity of each category of materials provided by the supply agency.

[0233] It can be seen that in this embodiment, the electronic device can obtain the historical supply data of the supply mechanism, extract the features of the historical supply data, obtain the features of the historical supply data, and classify each material based on the features to obtain multiple categories of materials. For each category of materials, a prediction method that matches the features of the materials of the category is used to predict the supply date and supply quantity of the materials of the category to obtain the revised purchase supply of the materials of the category. In this way, the supply date and supply quantity of each category of materials are corrected, thereby improving the executability and achievement rate of the planning and scheduling.

[0234] As an implementation method of the embodiment of the present application, the above supply plan may include an existing supply allocation strategy and / or a new supply plan generated by capacity allocation;

[0235] The allocation strategy of the existing supply includes whether to use the existing supply, the allocation date, the supply selection under the allocation date, and the supply quantity selection under the allocation date; the new supply plan generated by the capacity allocation includes the type of planned supply, the date of planned supply, the supply organization of the planned supply, and the quantity of planned supply.

[0236] The supply plan for the pending demand obtained by the electronic device may include the allocation strategy of the existing supply and / or the new supply plan generated by the capacity allocation. In other words, the supply plan may include how to allocate the existing supply of each supply mechanism and / or how to allocate the capacity of each supply mechanism to generate a new planned supply.

[0237] In one embodiment, the allocation strategy of the existing supply may include whether to use the existing supply, the allocation date, the supply selection under the allocation date, and the supply quantity selection under the allocation date. The new supply plan generated by the capacity allocation may include the type of planned supply, the date of planned supply, the supply organization of the planned supply, and the quantity of planned supply. Among them, the type of planned supply may include procurement and inventory.

[0238] For example, the supply plan for demand 1 of the electronic device includes the allocation strategy of the existing supply and the new supply plan generated by the capacity allocation. Among them, the allocation strategy of the existing supply includes using the existing supply, the allocation date is 2023-10-09, the supply under the allocation date selects the supply of material a by supply agency 1, and the supply quantity under the allocation date selects quantity n1. The new supply plan generated by the capacity allocation may include the type of planned supply as procurement, the date of planned supply as 2023-10-10, the supply agency of the planned supply as supply agency 2, and the quantity of planned supply as n2.

[0239] It can be seen that in this embodiment, the allocation strategy of the existing supply may include whether to use the existing supply, the allocation date, the supply selection under the allocation date, and the supply quantity selection under the allocation date. The new supply plan generated by the capacity allocation may include the type of planned supply, the date of planned supply, the supply organization of the planned supply, and the quantity of planned supply. In this way, after obtaining the supply plan for the demand to be processed, the staff can use the supply plan as auxiliary information for various decisions, effectively assist the staff in making decisions, reduce workload, and improve the quality of demand delivery.

[0240] Fig.12 A schematic diagram of a method for determining a schedule provided in an embodiment of the present application. Fig.12 The method for determining the schedule provided in the embodiment of the present application is introduced by way of example. Fig.12 As shown, the method for determining the plan and schedule provided in the embodiment of the present application is designed with the agent and environment interaction framework as the core, and the framework includes the following parts: mechanism model, prediction unit, knowledge reasoning and plan and schedule.

[0241] The environment includes a mechanism model and a prediction unit. The mechanism model can determine material constraints, capacity constraints, and date constraints. The prediction unit can perform demand forecasting and supply organization evaluation. The results obtained by the mechanism model and the prediction unit can be input into the environment to be transmitted to the agent for processing, that is, to achieve relevant state input. The agent includes knowledge reasoning and planning and scheduling. Knowledge reasoning can realize the identification of bottleneck materials and bottleneck supply organizations. Planning and scheduling can realize demand grouping and weighting, supply allocation, and capacity allocation. After the agent processes based on the relevant state, it can obtain decision-making behavior, that is, to achieve decision-making behavior output.

[0242] The mechanism model can organize various basic data according to business logic to provide a unified data base for other parts. The data base is an infrastructure platform with data storage, management, calculation and distribution capabilities. In this way, electronic equipment can obtain the demand, supply information and material information to be processed from the mechanism model.

[0243] like Fig.13As shown in the figure, the mechanism model construction can extract data such as supply organization, demand, supply, capacity, beat, BOM, master data, work calendar, etc. from the business system. The demand side includes various types of demand in the business system (such as delivery demand, reserved demand, sales demand, transfer demand, etc.), as well as the potential forecast demand output by the forecast unit through demand forecasting. The supply side includes various types of supply in the business system (such as inventory, production orders, etc.), as well as the revised procurement supply (such as purchase orders) output by the forecast unit through the supply organization capacity assessment. The master data includes demand master data and material master data, which can represent the basic attributes of demand and materials. BOM is used to form material constraint relationships, beat and capacity are used to guide the formation of capacity constraint relationships, and work calendars are used to guide the formation of date constraint relationships. Supply organizations can share a global work calendar, or different supply organizations have separate work calendars. BOM, beat, and capacity can also be used as inputs to the knowledge reasoning model, and knowledge reasoning can output bottleneck materials and bottleneck supply organizations.

[0244] Planning and scheduling can be targeted at pending demands, with material constraints, production capacity constraints and date constraints as constraints, and demand fulfillment rate as the optimization goal. Based on the supply information of each supply organization, the supply plan corresponding to the pending demand can be heuristically solved to obtain the supply plan corresponding to the pending demand and realize planned supply.

[0245] like Fig.14 As shown, in the process of implementing planning and scheduling, the demand to be processed may include multiple groups of demands with priorities, from the highest priority demand group to the lowest priority demand group. For the highest priority demand group, the demand group includes demand 1, demand 2, demand 3 and demand 4. Knowledge reasoning outputs bottleneck supply mechanisms and their scores and bottleneck materials and their scores. The electronic device can group and sort the demands according to the bottleneck supply mechanisms and their scores, dividing demands 1 and demand 3 into one demand subgroup, dividing demand 2 into one demand subgroup, and dividing demand 4 into one demand subgroup. The electronic device can assign weights to the demands according to the bottleneck materials and their scores.

[0246] For the first demand subgroup, that is, the demand subgroup consisting of demand 1 and demand 3, electronic equipment can use material constraints, production capacity constraints and date constraints as constraints, and weighted demand fulfillment rate as the optimization goal. Based on the supply information of each supply agency, the supply plan corresponding to demand 1 and demand 3 included in the demand subgroup is heuristically solved to obtain the supply plan corresponding to demand 1 and demand 3.

[0247] The supply plan may include the supply plan of the existing supply allocation and the supply plan generated by the capacity allocation. The supply plan of the supply allocation may include 1) date decision, 2) supply decision, and 3) quantity decision. For demand 1, existing supply 1, existing supply 2, and planned supply 1 may be generated. Among them, the existing supply 2 refers to the result of the supply organization's capacity assessment. The supply plan of the capacity allocation includes 1) date decision, 2) supply decision, and 3) quantity decision. For demand 1, planned supply 2 and planned supply 3 may be generated. Planned supply 1, planned supply 2, and planned supply 3 may realize the planned output. Similarly, for each other demand, the corresponding supply plan may be obtained.

[0248] It can be seen that in the solution provided in the embodiment of the present application, when the supply plan corresponding to the demand to be processed is heuristically solved, not only the dependencies between the materials, the capacity constraints of each supply mechanism to provide each material, and the time limit for each supply mechanism to provide each material are considered, but also the potential bottleneck supply mechanism and bottleneck material are predicted by the pre-trained knowledge reasoning model, and the demands to be processed are grouped and sorted based on the scores corresponding to the bottleneck supply mechanism, each demand subgroup is obtained in the sorting order, the weight of each demand is determined based on the bottleneck material, and the weighted demand achievement rate is used as the optimization goal. Therefore, regardless of the demand restricted by the bottleneck material and the bottleneck supply mechanism, or the demand not restricted by the bottleneck material and the bottleneck supply mechanism, a reasonable supply plan can be obtained, so that each supply mechanism can supply reasonably and achieve supply and demand balance, thereby realizing a plan scheduling with high executability and high achievement rate.

[0249] Corresponding to the above-mentioned method for determining a plan schedule, an embodiment of the present application further provides a device for determining a plan schedule. The following is an introduction to a device for determining a plan schedule provided in an embodiment of the present application.

[0250] like Fig.15 As shown, a device for determining a plan schedule, the device comprising:

[0251] The information acquisition module 1510 is used to acquire the demand to be processed, supply information and material information, wherein the supply information at least includes the supply, capacity, beat and supply time information of each supply mechanism, and the beat is used to indicate the working hours required for the supply mechanism to provide each material, and / or, to indicate the quantity of each material provided by the supply mechanism in a unit time;

[0252] The constraint determination module 1520 is used to determine the material constraint according to the demand transmission relationship between the materials identified by the material information, determine the capacity constraint according to the capacity and the beat, and determine the date constraint according to the supply time relationship of the materials identified by the supply time information, wherein the material constraint is used to indicate the dependency relationship between the materials, the capacity constraint is used to indicate the ability constraint of the supply agencies to provide the materials, and the date constraint is used to indicate the time limit for the supply agencies to provide the materials;

[0253] The bottleneck prediction module 1530 is used to input the pending demand, the supply and production capacity of each supply mechanism into a pre-trained knowledge reasoning model to obtain the bottleneck material and bottleneck supply mechanism corresponding to the pending demand, wherein the knowledge reasoning model constructs material nodes and supply mechanism nodes based on the material information included in the historical planning and scheduling data and the relationship between each supply mechanism and the material identified by the beat, and characterizes the material nodes, supply mechanism nodes and the edges between the nodes with the demand, supply and production capacity included in the historical planning and scheduling data, so as to predict the bottleneck material and bottleneck supply mechanism corresponding to the input demand, wherein the bottleneck supply mechanism is used to characterize that the supply mechanism has a bottleneck in the production capacity of the material;

[0254] A grouping and sorting module 1540 is used to group and sort the demands to be processed based on the scores of the supply mechanisms corresponding to the demands to be processed hitting the bottleneck supply mechanisms, so as to obtain a plurality of sorted demand subgroups;

[0255] The weight calculation module 1550 is used to obtain each demand subgroup in a sorted order, and for each demand included in the current subgroup, determine the weight corresponding to the demand based on the number of times the material corresponding to the demand hits the bottleneck material and the score corresponding to the bottleneck material;

[0256] The supply plan acquisition module 1560 is used to use the material constraint, the production capacity constraint and the date constraint as constraint conditions, and the demand fulfillment rate with the weight as the optimization goal. Based on the supply information of each supply agency, the supply plan corresponding to each demand included in the current subgroup is heuristically solved to obtain the supply plan corresponding to the pending demand.

[0257] It can be seen that in the solution provided in the embodiment of the present application, when the supply plan corresponding to the demand to be processed is heuristically solved, not only the dependencies between the materials, the capacity constraints of each supply mechanism to provide each material, and the time limit for each supply mechanism to provide each material are considered, but also the potential bottleneck supply mechanism and bottleneck material are predicted by the pre-trained knowledge reasoning model, and the demands to be processed are grouped and sorted based on the scores corresponding to the bottleneck supply mechanism, each demand subgroup is obtained in the sorting order, the weight of each demand is determined based on the bottleneck material, and the weighted demand achievement rate is used as the optimization goal. Therefore, regardless of the demand restricted by the bottleneck material and the bottleneck supply mechanism, or the demand not restricted by the bottleneck material and the bottleneck supply mechanism, a reasonable supply plan can be obtained, so that each supply mechanism can supply reasonably and achieve supply and demand balance, thereby realizing a plan scheduling with high executability and high achievement rate.

[0258] As an implementation of the embodiment of the present application, the above-mentioned device may further include a knowledge reasoning model construction module, and the knowledge reasoning model construction module is used to construct a knowledge reasoning model, which may include:

[0259] The first acquisition submodule is used to acquire historical planning and scheduling data, historical bottleneck materials, and historical bottleneck supply organizations;

[0260] A node construction submodule, used to construct material nodes and supply mechanism nodes according to the material information included in the historical planning and scheduling data and the relationship between each supply mechanism and the material identified by the beat;

[0261] A heterogeneous directed graph acquisition submodule is used to characterize the material nodes, supply mechanism nodes and the edges between the nodes according to the demand, supply and capacity included in the historical planning and scheduling data to obtain a heterogeneous directed graph, wherein the edges between material nodes in the heterogeneous directed graph represent the constraint relationship between the materials corresponding to the material nodes, and the edges between the material nodes and the supply mechanism nodes represent that the materials corresponding to the material nodes can be produced by the supply mechanism corresponding to the supply mechanism node;

[0262] The second acquisition submodule is used to train the heterogeneous directed graph based on the historical planning and scheduling data, historical bottleneck materials and historical bottleneck supply agencies to obtain the knowledge reasoning model.

[0263] As an implementation of an embodiment of the present application, the second acquisition submodule may include:

[0264] A positive and negative sample determination unit, used to determine the nodes corresponding to the historical bottleneck materials and the nodes corresponding to the historical bottleneck supply mechanisms in the heterogeneous directed graph as positive samples, and determine the nodes other than the positive samples as negative samples;

[0265] An initial vector determination unit, used to use the demand and supply included in the historical planning and scheduling data as the initial vector of the material node, the capacity as the initial vector of the supply mechanism node, the relationship between the material information as the initial vector of the edge between the material node and the material node, and the beat as the initial vector of the edge between the material node and the supply mechanism node;

[0266] A knowledge reasoning model acquisition unit is used to train the heterogeneous directed graph based on the positive samples, the negative samples and each initial vector to obtain the knowledge reasoning model.

[0267] As an implementation of the embodiment of the present application, the above-mentioned group sorting module 1540 may include:

[0268] A supply mechanism determination submodule is used to determine the supply mechanism corresponding to each demand included in each group of demands according to the material information corresponding to the demand and the beat, wherein each group of demands is obtained by grouping the demands to be processed according to priority;

[0269] A demand subgroup acquisition submodule is used to divide the demands of the supply mechanism and the bottleneck supply mechanism into a group of demands to obtain demand subgroups;

[0270] The sorting demand subgroup acquisition submodule is used to sort the demand subgroups according to the scores of the corresponding bottleneck supply mechanisms to obtain a plurality of sorted demand subgroups.

[0271] As an implementation of the embodiment of the present application, the supply plan acquisition module 1560 may include:

[0272] The current group requirement acquisition submodule is used to obtain a group of requirements with the highest priority as the current group requirements;

[0273] A supply plan acquisition submodule is used to perform a heuristic solution on the supply plan corresponding to the demand subgroup included in the current group demand, based on the current supply information of each supply agency, with the material constraint, the capacity constraint and the date constraint as constraint conditions, and the demand achievement rate with the weight corresponding to the demand subgroup included in the current group demand as an optimization target, so as to obtain the supply plan corresponding to the current group demand;

[0274] A current supply information acquisition submodule, used to deduct the supply information of each supply mechanism required by the supply plan to obtain the current supply information of each supply mechanism;

[0275] A submodule for completing the processing of multiple groups of demands is used to obtain the next group of demands in order of priority from high to low as the current group of demands, and return the demand subgroup included in the current group of demands, with the material constraint, the production capacity constraint and the date constraint as constraints, and the demand fulfillment rate with the weight corresponding to the demand subgroup included in the current group of demands as the optimization target. Based on the current supply information of each supply agency, the supply plan corresponding to the demand subgroup included in the current group of demands is heuristically solved to obtain the supply plan corresponding to the current group of demands, until multiple groups of demands are processed.

[0276] As an implementation method of the embodiment of the present application, the supply plan acquisition submodule may include:

[0277] A current subgroup determining unit, configured to obtain, for the current group demand, a first demand subgroup according to the sorting order as the current subgroup;

[0278] a supply plan acquisition unit, configured to perform a heuristic solution on the supply plan corresponding to the current subgroup based on the current supply information of each supply agency, with the material constraint, the capacity constraint and the date constraint as constraint conditions, with the weighted demand fulfillment rate corresponding to the current subgroup as an optimization target, and obtain the supply plan corresponding to the current subgroup;

[0279] A current supply information acquisition unit, used to deduct the supply information of each supply mechanism required by the supply plan to obtain the current supply information of each supply mechanism;

[0280] The demand subgroup processing completion unit is used to obtain the next demand subgroup in the order as the current subgroup, and return the steps of obtaining the supply plan corresponding to the current subgroup by heuristically solving the supply plan corresponding to the current subgroup based on the current supply information of each supply agency, with the material constraint, the production capacity constraint and the date constraint as the constraint conditions and the weighted demand fulfillment rate corresponding to the current subgroup as the optimization target, until multiple demand subgroups are processed.

[0281] As an implementation method of the embodiment of the present application, the above-mentioned demand to be processed includes predicted demand;

[0282] The above device may also include:

[0283] A data acquisition module, used for acquiring historical demand data and switching data of materials before the step of acquiring the demand to be processed, supply information and material information, wherein the switching data is material data changed according to business requirements;

[0284] A demand sequence building module, used to build the demand sequence of the material according to the time sequence corresponding to the historical demand data and the switching data;

[0285] A first acquisition module is used to extract features from the demand sequence to obtain sequence features of the demand sequence, and classify the materials based on the sequence features to obtain multiple categories of materials;

[0286] The forecast demand acquisition module is used to forecast the demand for each category of materials by using a forecasting method that is compatible with the sequence characteristics of the materials in the category, so as to obtain the forecast demand for the materials in the category.

[0287] As an implementation method of the embodiment of the present application, the supply of each supply mechanism mentioned above includes a revised purchase supply;

[0288] The above device may also include:

[0289] A historical supply data acquisition module, used to acquire historical supply data of supply agencies before the step of acquiring the demand to be processed, supply information and material information, wherein the historical supply data includes the supply date and supply quantity of each material by each supply agency;

[0290] A second acquisition module is used to extract features from the historical supply data to obtain features of the historical supply data, and classify each material based on the features to obtain multiple categories of materials;

[0291] The revised procurement supply acquisition module is used to predict the supply date and supply quantity of each category of materials using a forecasting method that is compatible with the characteristics of the category of materials, and obtain the revised procurement supply of the category of materials.

[0292] As an implementation method of the embodiment of the present application, the supply plan includes an existing supply allocation strategy and / or a new supply plan generated by capacity allocation;

[0293] The allocation strategy of the existing supply includes whether to use the existing supply, the allocation date, the supply selection under the allocation date, and the supply quantity selection under the allocation date;

[0294] The new supply plan generated by the capacity allocation includes the type of planned supply, the date of planned supply, the supply organization of the planned supply and the quantity of planned supply.

[0295] The present application also provides an electronic device, such as Fig.16 As shown, including:

[0296] Memory 1601, used for storing computer programs;

[0297] The processor 1602 is used to implement the steps of the method for determining the schedule described in any of the above embodiments when executing the program stored in the memory 1601.

[0298] In addition, the electronic device may further include a communication bus and / or a communication interface, and the processor 1602, the communication interface, and the memory 1601 communicate with each other via the communication bus.

[0299] It can be seen that in the solution provided in the embodiment of the present application, when the supply plan corresponding to the demand to be processed is heuristically solved, not only the dependencies between the materials, the capacity constraints of each supply mechanism to provide each material, and the time limit for each supply mechanism to provide each material are considered, but also the potential bottleneck supply mechanism and bottleneck material are predicted by the pre-trained knowledge reasoning model, and the demands to be processed are grouped and sorted based on the scores corresponding to the bottleneck supply mechanism, each demand subgroup is obtained in the sorting order, the weight of each demand is determined based on the bottleneck material, and the weighted demand achievement rate is used as the optimization goal. Therefore, regardless of the demand restricted by the bottleneck material and the bottleneck supply mechanism, or the demand not restricted by the bottleneck material and the bottleneck supply mechanism, a reasonable supply plan can be obtained, so that each supply mechanism can supply reasonably and achieve supply and demand balance, thereby realizing a plan scheduling with high executability and high achievement rate.

[0300] The communication bus mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0301] The communication interface is used for communication between the above electronic device and other devices.

[0302] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0303] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0304] In another embodiment provided in the present application, a computer-readable storage medium is provided, in which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned methods for determining the planning schedule are implemented.

[0305] In another embodiment provided by the present application, a computer program product including instructions is also provided, which, when executed on a computer, enables the computer to execute any of the methods for determining a schedule in the above embodiments.

[0306] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a solid-state hard disk (SSD), etc.

[0307] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0308] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, electronic device, computer-readable storage medium, and computer program product embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0309] The above description is only a preferred embodiment of the present application and is not intended to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application are included in the protection scope of the present application.

Claims

1. A method for determining a plan schedule, characterized in that: The method comprises: Obtaining the demand to be processed, supply information and material information, wherein the supply information at least includes the supply, production capacity, beat and supply time information of each supply mechanism, and the beat is used to indicate the working hours required for the supply mechanism to provide each material, and / or, to indicate the quantity of each material provided by the supply mechanism in a unit time; Determine material constraints according to the demand transmission relationship between the materials identified by the material information, determine capacity constraints according to the capacity and the beat, and determine date constraints according to the supply time relationship of the materials identified by the supply time information, wherein the material constraints are used to represent the dependency relationship between the materials, the capacity constraints are used to represent the ability constraints of the supply agencies to provide the materials, and the date constraints are used to represent the time limits for the supply agencies to provide the materials; Input the pending demand, the supply and capacity of each supply mechanism into a pre-trained knowledge reasoning model to obtain the bottleneck material and bottleneck supply mechanism corresponding to the pending demand, wherein the knowledge reasoning model constructs material nodes and supply mechanism nodes based on the material information included in the historical planning and scheduling data and the relationship between each supply mechanism and the material identified by the beat, and characterizes the material nodes, supply mechanism nodes and the edges between the nodes with the demand, supply and capacity included in the historical planning and scheduling data, so as to predict the bottleneck material and bottleneck supply mechanism corresponding to the input demand; Based on the scores of the supply mechanism corresponding to the pending demand hitting the corresponding bottleneck supply mechanism, the pending demand is grouped and sorted to obtain a plurality of sorted demand subgroups, wherein the bottleneck supply mechanism is used to indicate that a bottleneck occurs in the material production capacity of the supply mechanism; Obtain each demand subgroup in sorted order, and for each demand included in the current subgroup, determine the weight corresponding to the demand based on the number of times the material corresponding to the demand hits the bottleneck material and the score corresponding to the bottleneck material; Taking the material constraint, the production capacity constraint and the date constraint as constraint conditions, and the demand fulfillment rate with the weight as the optimization goal, based on the supply information of each supply agency, a heuristic solution is performed on the supply plan corresponding to each demand included in the current subgroup to obtain the supply plan corresponding to the pending demand.

2. The method according to claim 1, characterized in that The construction method of the knowledge reasoning model includes: Obtain historical planning and scheduling data, historical bottleneck materials, and historical bottleneck supply organizations; Constructing material nodes and supply mechanism nodes according to the material information included in the historical planning and scheduling data and the relationship between each supply mechanism and the material identified by the beat; The material nodes, supply mechanism nodes and edges between the nodes are characterized by the demand, supply and capacity included in the historical planning and scheduling data to obtain a heterogeneous directed graph, wherein the edges between material nodes in the heterogeneous directed graph represent the constraint relationship between the materials corresponding to the material nodes, and the edges between material nodes and supply mechanism nodes represent that the materials corresponding to the material nodes can be produced by the supply mechanism corresponding to the supply mechanism node; Based on the historical planning and scheduling data, historical bottleneck materials and historical bottleneck supply mechanisms, the heterogeneous directed graph is trained to obtain the knowledge reasoning model.

3. The method according to claim 2, characterized in that The step of training the heterogeneous directed graph based on the historical planning and scheduling data, historical bottleneck materials, and historical bottleneck supply mechanisms to obtain the knowledge reasoning model includes: Determine the nodes corresponding to the historical bottleneck materials and the nodes corresponding to the historical bottleneck supply mechanisms in the heterogeneous directed graph as positive samples, and determine the nodes other than the positive samples as negative samples; The demand and supply included in the historical planning and scheduling data are used as the initial vectors of the material node, the capacity is used as the initial vector of the supply mechanism node, the relationship between the material information is used as the initial vector of the edge between the material node and the material node, and the beat is used as the initial vector of the edge between the material node and the supply mechanism node; Based on the positive samples, the negative samples and each initial vector, the heterogeneous directed graph is trained to obtain the knowledge reasoning model.

4. The method according to claim 1, characterized in that: The step of grouping and sorting the demands to be processed based on the scores of the supply mechanisms corresponding to the demands to be processed that hit the bottleneck supply mechanisms to obtain a plurality of sorted demand subgroups comprises: For each demand included in each group of demands, determine the supply mechanism corresponding to the demand according to the material information corresponding to the demand and the beat, wherein each group of demands is obtained by grouping the demands to be processed according to priority; Divide the demands of the supply mechanism that are the same as the bottleneck supply mechanism into a group of demands to obtain demand subgroups; The demand subgroups are sorted according to the scores of the corresponding bottleneck supply mechanisms to obtain a plurality of sorted demand subgroups.

5. The method according to claim 4, characterized in that The step of taking the material constraint, the capacity constraint and the date constraint as constraint conditions, taking the demand fulfillment rate with the weight as the optimization target, and performing heuristic solution on the supply plan corresponding to each demand included in the current subgroup based on the supply information of each supply organization to obtain the supply plan corresponding to the demand to be processed includes: Get a group of requirements with the highest priority as the current group of requirements; For the demand subgroups included in the current group of demands, taking the material constraint, the capacity constraint and the date constraint as constraint conditions, taking the weighted demand achievement rate corresponding to the demand subgroups included in the current group of demands as an optimization target, and based on the current supply information of each supply agency, performing a heuristic solution on the supply plan corresponding to the demand subgroups included in the current group of demands, so as to obtain the supply plan corresponding to the current group of demands; Deducting the supply information of each supply mechanism required by the supply plan to obtain the current supply information of each supply mechanism; Obtain the next set of demands in order of priority from high to low as the current set of demands, and return the demand subgroup included in the current set of demands, with the material constraint, the production capacity constraint and the date constraint as constraints, and the demand fulfillment rate with the weight corresponding to the demand subgroup included in the current set of demands as the optimization target, and perform heuristic solution on the supply plan corresponding to the demand subgroup included in the current set of demands based on the current supply information of each supply agency, to obtain the supply plan corresponding to the current set of demands, until multiple sets of demands are processed.

6. The method according to claim 5, characterized in that The step of performing a heuristic solution on the supply plan corresponding to the demand subgroup included in the current group of demands, taking the material constraint, the production capacity constraint and the date constraint as constraint conditions, taking the weighted demand achievement rate corresponding to the demand subgroup included in the current group of demands as an optimization target, and based on the current supply information of each supply agency, obtaining the supply plan corresponding to the current group of demands includes: For the current group of requirements, obtaining the first requirement subgroup according to the sorting order as the current subgroup; For the current subgroup, taking the material constraint, the capacity constraint and the date constraint as constraint conditions, taking the weighted demand fulfillment rate corresponding to the current subgroup as the optimization target, and based on the current supply information of each supply organization, performing a heuristic solution on the supply plan corresponding to the current subgroup to obtain the supply plan corresponding to the current subgroup; Deducting the supply information of each supply mechanism required by the supply plan to obtain the current supply information of each supply mechanism; Obtain the next demand subgroup in the order as the current subgroup, and return the steps of taking the material constraint, the production capacity constraint and the date constraint as the constraints, taking the weighted demand fulfillment rate corresponding to the current subgroup as the optimization target, performing heuristic solution on the supply plan corresponding to the current subgroup based on the current supply information of each supply agency, and obtaining the supply plan corresponding to the current subgroup, until multiple demand subgroups are processed.

7. The method according to any one of claims 1 to 6, characterized in that: The demand to be processed includes predicted demand; Before the step of obtaining the demand, supply information and material information to be processed, the method further includes: Acquire historical demand data and switching data of materials, wherein the switching data is material data that changes according to business requirements; Constructing a demand sequence for the material according to the time sequence corresponding to the historical demand data and the switching data; Extracting features from the demand sequence to obtain sequence features of the demand sequence, and classifying the materials based on the sequence features to obtain multiple categories of materials; For each category of materials, a forecasting method that is compatible with the sequence characteristics of the materials in this category is used to forecast the demand for the materials in this category, thereby obtaining the forecast demand for the materials in this category.

8. The method according to any one of claims 1 to 6, characterized in that: The supply of each supply agency includes the revised procurement supply; Before the step of obtaining the demand, supply information and material information to be processed, the method further includes: Acquire historical supply data of the supply mechanism, wherein the historical supply data includes the supply date and supply quantity of each material by each supply mechanism; Extracting features from the historical supply data to obtain features of the historical supply data, and classifying each material based on the features to obtain multiple categories of materials; For each category of materials, a forecasting method that matches the characteristics of the materials in that category is used to forecast the supply date and supply quantity of the materials in that category, and to obtain a revised procurement supply of the materials in that category.

9. The method according to any one of claims 1 to 6, characterized in that: The supply plan includes an allocation strategy for existing supply and / or a new supply plan generated by capacity allocation; The allocation strategy of the existing supply includes whether to use the existing supply, the allocation date, the supply selection under the allocation date, and the supply quantity selection under the allocation date; The new supply plan generated by the capacity allocation includes the type of planned supply, the date of planned supply, the supply organization of the planned supply and the quantity of planned supply.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

Images