CN113111479A

CN113111479A - Simulation method and device for warehouse management system and storage medium

Info

Publication number: CN113111479A
Application number: CN202010032826.1A
Authority: CN
Inventors: 朱杰
Original assignee: Shenzhen SF Taisen Holding Group Co Ltd
Current assignee: Shenzhen SF Taisen Holding Group Co Ltd
Priority date: 2020-01-13
Filing date: 2020-01-13
Publication date: 2021-07-13

Abstract

The embodiment of the application provides a simulation method, a simulation device and a storage medium of a warehouse management system, wherein the method comprises the following steps: establishing a plurality of agents according to the composition elements of the warehouse management system, and respectively setting corresponding decision rules and behavior methods for each agent; setting a corresponding decision rule and a corresponding behavior method for each agent, and respectively constructing a multi-agent model for each agent; respectively integrating various agents at the bottom layer of each multi-agent model and decision rules and methods of the agents into different simulation service modules to construct a warehouse system simulation model; and respectively distributing a warehouse task for each intelligent agent in the warehouse system simulation model through the warehouse system simulation model, and outputting the global warehouse task of the warehouse system. The scheme can improve the overall optimization design and the operation efficiency of the warehouse system and improve the comprehensive capability of simulating and analyzing the warehouse system.

Description

Simulation method and device for warehouse management system and storage medium

Technical Field

The embodiment of the application relates to the technical field of warehouse simulation, in particular to a simulation method and device for a warehouse management system and a storage medium.

Background

The warehouse operation system plays a decisive role in modern logistics, if a real-installation test mode is adopted for research, the consumed time, manpower, material resources and risk cost are higher, and the mode of computer modeling and simulation is more scientific. In the existing mechanism, a warehouse operation system is introduced into enterprise logistics, the warehouse operation system is created in a computer modeling and simulation mode, and the logistics task scheduling and the in-warehouse environment in a warehouse of the warehouse operation system are based on. The modeling is carried out aiming at a large and complex system such as a warehouse system, the scale of the composition elements is large, the structure is complex, the behaviors and the interaction among the elements are various, a large amount of intelligent decision requirements exist, and the system efficiency is difficult to be calculated by a traditional mathematical programming model completely by using a mathematical formula. Secondly, the complex behaviors and the interaction relation among all elements in the system at the microscopic level are particularly complex, and the influence on the behaviors at the system level is obvious.

In the research and practice process of the prior art, the inventor of the embodiment of the application finds that for modeling of such a complex dynamic system, it is difficult to realize accurate and accurate simulation of a target system through a traditional modeling mode from top to bottom (such as a discrete event-based simulation method), and differential modeling cannot be performed on individuals in the target system, the model can be simulated to a large extent only according to a preset limited rule, many events and behaviors in the real world evolve after a large amount of microscopic interaction, and a modeler cannot define in advance, so that the model cannot truly reflect the real situation. Therefore, the current model modeling technology is not suitable for warehouse systems with complex and variable environments.

Disclosure of Invention

The embodiment of the application provides a simulation method and device for a warehouse management system and a storage medium, which can improve the overall operation efficiency of the warehouse system and improve the performance of simulating and analyzing the warehouse system.

In a first aspect, an embodiment of the present application provides a simulation method for a warehouse management system, where the method includes:

creating a plurality of intelligent bodies according to the composition elements of the warehouse management system, wherein each intelligent body comprises at least one intelligent body of a channel, a warehouse location, a truck, a production line, a loading area, an inventory unit, a forklift, equipment and a warehouse user;

respectively setting a corresponding decision rule and a corresponding behavior method for each agent;

respectively constructing a multi-agent model for each agent with decision rules and behavior methods;

respectively integrating various agents at the bottom layer of each multi-agent model and decision rules and behavior methods of the agents into different simulation service modules to construct a warehouse system simulation model;

and respectively distributing a warehouse task for each intelligent agent in the warehouse system simulation model through the warehouse system simulation model, and outputting the global warehouse task of the warehouse system.

In one possible design, the creating a plurality of agents from components of a warehouse management system includes:

determining the constituent elements of the warehouse management system;

decomposing the constituent elements of the warehouse management system into a system consisting of various types of individuals according to the attributes of the constituent elements;

different types of individuals are represented by computing entities respectively as agents of the warehouse system.

In one possible design, the multi-agent model includes a production line operational module, in which decision rules and behavior methods for producing agents, forklift agents and SKU agents are integrated; the method further comprises the following steps:

the production intelligent agent produces according to the production plan to generate an SKU intelligent agent;

assigning different attributes to the SKU agent;

the intelligent forklift obtains the SKU intelligent agents from the intelligent agents of all production lines according to the warehouse tasks;

and transporting the SKU intelligent agent to the storage position indicated by the storage task for storage.

In one possible design, after modeling the different types of objects respectively with agent technology as agents of the warehouse system, the method further comprises:

a correspondence between agent types, agent functions, and agent attributes is created.

In one possible design, the setting of the corresponding decision rule and behavior method for each agent respectively includes:

respectively setting corresponding decision rules and behavior methods in each intelligent agent, or respectively establishing an independent rule base or an independent algorithm base for each intelligent agent;

after the corresponding decision rule and behavior method are respectively set in each agent, or after an independent rule base or an independent algorithm base is respectively established for each agent, the method further comprises the following steps:

receiving a modification instruction, wherein the modification instruction carries an agent identifier of an agent to be modified;

determining a target agent corresponding to the entity identification according to the entity identification carried by the modification instruction;

calling a rule base and an algorithm base of the target agent according to the entity identification;

and modifying the rule base and the algorithm base of the target agent.

In one possible design, after the building the warehouse system simulation model, the method further includes:

monitoring the behavior of each agent based on the multi-agent model, controlling communication interaction among agents, and controlling interaction between agents and the warehouse environment;

acquiring behavior information of each agent, communication interaction information among agents and change state information of the warehouse environment;

generating a warehouse operation strategy according to the behavior information of the agents, the communication interaction information among the agents and the change state information;

when the environment in the warehouse system changes, each agent generates a warehouse operation scheme for the environment in the warehouse system according to the warehouse operation strategy, and executes the action and strategy corresponding to the changed environment according to the warehouse operation strategy.

In one possible design, after the building of the warehouse system simulation model, the method further comprises at least one of:

the intelligent agent in the warehouse system performs communication interaction with the intelligent agent in the warehouse system through the warehouse system simulation model according to corresponding decision rules and behavior methods;

or the agents in the warehouse system cooperate with the agents in the warehouse system through the warehouse system simulation model according to corresponding task assignment and driving paths;

or, the agent in the warehouse system acquires the warehouse environment within a preset range, and executes the behavior and the strategy corresponding to the warehouse environment within the preset range through the warehouse system simulation model according to the corresponding decision rule and behavior method.

And monitoring the behaviors of the agents in the warehouse system and the interaction state or the cooperation state among the agents based on the warehouse system simulation model.

monitoring the behaviors of all agents in the warehouse system and the interaction state or the cooperation state among all agents on the basis of the warehouse system simulation model;

and generating a warehouse environment log according to the behaviors of the agents and the interaction state or the cooperation state among the agents.

In a second aspect, an embodiment of the present application provides a warehouse simulation apparatus having a function of implementing a simulation method corresponding to the warehouse management system provided in the first aspect. The functions can be realized by hardware, and the functions can also be realized by executing corresponding software by hardware. The hardware or software includes one or more modules corresponding to the above functions, which may be software and/or hardware.

In one possible design, the warehouse simulation apparatus includes:

the warehouse management system comprises an input and output module, a storage management module and a management module, wherein the input and output module is used for creating a plurality of intelligent agents according to the constituent elements of the warehouse management system, and each intelligent agent comprises at least one intelligent agent of a channel, a warehouse location, a truck, a production line, a loading area, an inventory unit, a forklift, equipment and a warehouse user;

the processing module is used for respectively setting a corresponding decision rule and a corresponding behavior method for each agent; respectively constructing a multi-agent model for each agent with decision rules and behavior methods; respectively integrating various agents and behavior methods of the agents at the bottom layer of each multi-agent model into different simulation service modules to construct a warehouse system simulation model; and respectively distributing a warehouse task for each intelligent agent in the warehouse system simulation model through the warehouse system simulation model, and outputting the global warehouse task of the warehouse system.

In one possible design, the input-output module is specifically configured to:

determining the constituent elements of the warehouse management system;

In one possible design, the multi-agent model includes a production line operational module, in which decision rules and behavior methods for producing agents, forklift agents and SKU agents are integrated; the processing module is further configured to:

assigning different attributes to the SKU agent;

In one possible design, the processing module is further configured to:

In one possible design, the processing module is specifically configured to:

the processing module is further used for receiving a modification instruction through the input/output module, wherein the modification instruction carries the agent identifier of the agent to be modified;

and modifying the rule base and the algorithm base of the target agent.

In one possible design, after the processing module constructs the warehouse system simulation model, the processing module is further configured to:

In one possible design, after the building of the warehouse system simulation model, the processing module is further configured to perform at least one of the following operations:

A further aspect of the embodiments of the present application provides a computer device, which includes at least one connected processor, a memory and a transceiver, wherein the memory is used for storing a computer program, and the processor is used for calling the computer program in the memory to execute the method of the first aspect.

Yet another aspect of the embodiments of the present application provides a computer-readable storage medium, which includes instructions that, when executed on a computer, cause the computer to perform the method of the first aspect.

Compared with the prior art, in the scheme provided by the embodiment of the application, the corresponding decision rule and behavior method are respectively set for each intelligent agent in the warehouse system; setting a corresponding decision rule and a corresponding behavior method for each agent, and respectively constructing a multi-agent model for each agent; respectively integrating various agents and behavior methods of the agents at the bottom layer of each multi-agent model into different simulation service modules to construct a warehouse system simulation model; and respectively distributing warehouse tasks for each intelligent agent in the warehouse system simulation model through the warehouse system simulation model. The scheme can improve the overall operation efficiency of the warehouse system and improve the performance of the simulation and analysis warehouse system.

Drawings

FIG. 1 is a schematic modeling flow diagram in an embodiment of the present application;

fig. 2 is a schematic flow chart of a simulation method of the warehouse management system in the embodiment of the present application;

FIG. 3 is a schematic diagram illustrating a correspondence between Agent types, Agent functions, and Agent attributes in an embodiment of the present application;

FIG. 4 is a schematic diagram of an application architecture of a warehouse system simulation model in an embodiment of the present application;

FIG. 5a is a schematic diagram of a CAD drawing plan of an enterprise warehouse system in an embodiment of the present application;

FIG. 5b is an interface schematic diagram of a 1:1 warehouse system simulation model of an enterprise warehouse system and a visual simulation interface module in the warehouse system simulation model in an embodiment of the present application;

FIG. 6 is a schematic simulation diagram of a warehouse system simulation model in an embodiment of the present application;

fig. 7 is a schematic structural diagram of a warehouse simulation apparatus in an embodiment of the present application;

fig. 8 is a schematic structural diagram of an entity device that executes a simulation method of the warehouse management system in the embodiment of the present application.

Detailed Description

The terms "first," "second," and the like in the description and in the claims of the embodiments of the application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprise" and "have," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or modules is not necessarily limited to those steps or modules expressly listed, but may include other steps or modules not expressly listed or inherent to such process, method, article, or apparatus, such that the division of modules presented in the present application is merely a logical division and may be implemented in a practical application in a different manner, such that multiple modules may be combined or integrated into another system or some features may be omitted or not implemented, and such that couplings or direct couplings or communicative connections shown or discussed may be through interfaces, indirect couplings or communicative connections between modules may be electrical or the like, the embodiments of the present application are not limited. Moreover, the modules or sub-modules described as separate components may or may not be physically separated, may or may not be physical modules, or may be distributed in a plurality of circuit modules, and some or all of the modules may be selected according to actual needs to achieve the purpose of the embodiments of the present application.

Aiming at introducing a warehouse operation system into enterprise logistics in the existing mechanism, the warehouse operation system is established by adopting a computer modeling and simulation mode and is based on logistics task scheduling and in-warehouse environment in a warehouse of the warehouse operation system. The modeling is carried out aiming at a large and complex system such as a warehouse system, the scale of the composition elements is large, the structure is complex, the behaviors and the interaction among the elements are various, a large amount of intelligent decision requirements exist, and the system efficiency is difficult to be calculated by a traditional mathematical programming model completely by using a mathematical formula. Secondly, the complex behaviors and the interaction relation among all elements in the system at the microscopic level are particularly complex, and the influence on the behaviors at the system level is obvious. For modeling of such complex dynamic systems, it is difficult to realize accurate and accurate simulation of a target system through a traditional top-down modeling manner (such as a discrete event-based simulation method), and it is also impossible to perform differentiated modeling of individuals in the target system, the model can be simulated to a large extent only according to preset limited rules, and many events and behaviors in the real world evolve after a large number of microscopic interactions, which is that a modeler cannot define in advance, so that the model cannot truly reflect the real situation.

Currently, two main simulation techniques are mainly adopted for modeling and planning a warehouse system: system dynamics simulation and discrete event simulation.

(1) Technical characteristics of system dynamics simulation method

The warehouse system is abstracted to a combination of flow and inventory for simulation, and single individuals (goods, machines, people) in the warehouse system are not specifically modeled, but are uniformly represented as one set number (i.e., abstract modeling). The evolution behavior of a warehouse system is determined by the relationship of changes between multiple inventories, the flow between which is controlled by the flow rate, and thus, a series of factors affect the rate of flow. The system dynamics is a very abstract modeling method, differential modeling cannot be performed on individuals in the system, and attribute differences among the individuals cannot be reflected (such as working time and task allocation differences of each device in a warehouse system). The system dynamics modeling necessarily involves the following strong assumptions based on static parameters: we have 120 developers and can design about 20 new products each year, the monthly delivery is rated and 5% of the vehicles need to be replaced each year. The above parameters in a real system all change with time.

(2) The discrete event simulation method has the technical characteristics that:

simulating a warehouse system as a network consisting of a series of activities and queues; individual objects or persons in the warehouse system are called entities (entitys) and assigned attributes; a list of events arranged in chronological order of the model's operation; all elements describing the structure of the system (such as events, activities and flows) are defined in advance by the modeler.

Discrete events are only suitable for emphasizing process-driven systems (such as systems with queuing properties in factories, railway stations, shop shopping and the like), and are a top-down modeling mode, modelers need to define and describe various activities and processes in the systems in advance, models can be simulated only according to set limited rules, and a large number of events and behaviors in the real world evolve autonomously after a large number of microscopic interactions, so that the modelers cannot define in advance, and the models cannot truly reflect the real situation of a warehouse system.

However, both of the above simulation techniques ignore the uniqueness of the individual existence in the warehouse system and the interaction thereof with each other. For example, a customer may consult a family member before making a purchase decision, and the availability of a single aircraft depends on the rigid maintenance schedule of the crew. Therefore, the current modeling technology is not suitable for a warehouse system with complex and dynamically variable environment.

Based on this, the embodiment of the application provides a simulation method and device for a warehouse management system and a storage medium, which can be used for warehouse system simulation and planning. Specifically, a plurality of agents are created based on individual elements in a warehouse system, modeling is performed based on the plurality of agents, and a decision rule and an action method of each Agent are created. The Agent in the modeling model can directly interact with the warehouse environment and capture and learn the change of the environment, and more information reflecting the microscopic change of the warehouse system is obtained when the simulation is run. In addition, the model of the embodiment of the application also focuses on the behaviors of single agents and the interaction relation among the agents, and each agent has an autonomous behavior and decision mode and can perform communication interaction and cooperation with other agents in the system. Compared with the existing mechanism that simulation can be performed only according to well-defined limited rules, the method and the system for simulating the warehouse environment can reflect the real situation of the warehouse environment based on a large number of events and behaviors evolved after microscopic interaction. Furthermore, the model based on the multi-Agent technology in the embodiment of the application can enable each individual element in the warehouse system to take active action and strategy according to the environmental feedback in a large scale. And finally, a decision rule and a behavior method of each Agent are created when modeling is carried out based on multiple agents, so that even under the condition of a large number of agents and behaviors, the complexity or difference of the internal structure of the agents is not needed to be worried about, and the decision rule and the behavior method are convenient to modify and manage.

In some embodiments, a modeling process based on multi-Agent modeling may refer to a modeling process as shown in fig. 1, where the modeling process includes three phases. The following are introduced separately:

in the first stage, cut-in is performed from the individual microscopic level of the warehouse system, all individuals existing in the warehouse system are determined, and then the individuals in the warehouse system are classified according to individual types, so that a system (represented by Agent types) consisting of various types of individuals is obtained. Different types of individuals in the warehouse system are represented by a computing entity, an Agent, which results in multiple computing entities present in the warehouse system and which are used as objects for modeling in the second phase.

In the second stage, the behavior and method represented by the Agent is built in each Agent model, the behavior and method can also be standardized, a rule base or an Algorithm base of an independent module is established, the Agent can call and load a related Algorithm through an interface to realize more complex behavior (for example, in the model, a forklift Agent calls a path optimization Algorithm (Dijkstra _ Algorithm) in an Algorithm module when planning a driving line, and an independent behavior method is respectively established for each type of Agent through the calling of the rule and the Algorithm base.

In the third stage, modeling is respectively carried out on the relevant characteristics of each Agent type to obtain a multi-Agent model corresponding to each Agent, and then the multi-Agent models corresponding to the agents of each type are integrated in a simulation system module to obtain a final warehouse system simulation model. For example, in a production line operation module, three Agent models of a production line, a forklift and a SKU and decision rules and methods related to the three Agent models are integrated.

Wherein the agent comprises at least one agent of a channel, a storage location, a truck, a production line, a loading area, an inventory unit, a forklift, equipment, and a warehouse user. Any independent entity that is capable of thinking and that can interact with the environment can be abstracted as an agent. An Agent refers to a computing entity (e.g., a software or hardware entity capable of autonomous activities) that is resident in a dynamic environment, can continuously and autonomously perform functions, and has four major characteristics of activity, responsiveness, autonomy, and sociality. An agent may also be referred to as an agent, an agent, an agent, etc., and the name of the agent is not limited in the embodiments of the present application.

When the intelligent agent is applied to the warehouse system planning in the embodiment of the application, the intelligent agent mainly has the following characteristics and advantages:

(1) autonomy (Autonomy) an intelligent agent can automatically adjust own behaviors and states according to changes of external environments, but not only passively receives external stimulation, and has the capacity of self-management and self-regulation.

(2) Social (Social) agents have the ability to collaborate with other agents or people, and different agents can interact with other agents according to their own intentions to achieve the goal of solving problems.

Because the Agent has the characteristics of autonomy and sociality, when the Agent with the characteristics of autonomy and sociality is applied to the embodiment of the application, the Agent has certain autonomous decision-making and cooperation capacity. Particularly, the warehouse system is a dynamic and complex environment, the requirement for building a simulation model is higher and higher, and because the Agent has the characteristics of autonomous learning, intelligent decision making, information interaction capacity and the like, the Agent can be used as an Agent (such as a forklift, a warehouse location and workers) for core elements of the system, can directly interact with the warehouse environment and capture and learn the change of the environment, so that more information about reflecting the microscopic change of the warehouse system can be obtained during operation simulation, and the warehouse operation system can be simulated more accurately and more efficiently; and the agents can be coordinated and cooperated with each other, so that the complex warehouse system can be effectively decomposed and subjected to distributed modeling and control in the modeling process, and the overall modeling difficulty is reduced.

(3) Proactive (Proactive) the ability of an intelligent entity to actively take action in response to changes in the external environment. Specifically, the Agent has the initiative and the capability of actively completing the target during the operation. In a constantly changeable warehouse operation environment, the Agent can provide timely decision for warehouse operation, so that a timely and reliable operation decision scheme can be provided for a manager in the constantly changeable warehouse environment.

(4) Reactive refers to the ability to respond to an external stimulus. Because the modeling mode of multiple agents is adopted in the embodiment of the application, independent and differentiated reaction standards and reaction capacities of large-scale groups (such as each forklift) can be broken through, each individual element can adopt active behaviors and strategies according to environment feedback (for example, the forklift dynamically plans a driving path based on the current own environment and condition), and compared with the system dynamics that all employees and facility equipment are abstracted into a unified set, the reaction performance of the agents in the embodiment of the application can more accurately simulate the microscopic differences of the individual in the reaction coping capacity in a real system.

(5) The property of the mixture: the intelligence can accumulate or learn experience and knowledge and modify its behavior to adapt to the new environment. Based on the evolution type of the Agent, the Agent in the embodiment of the application configures a flexible organization framework and an evolution mechanism. Therefore, when modeling is carried out based on the Agent, the method has a potential computing mechanism for flexibly forming, maintaining, evolving and disassembling the modeling system, and is particularly suitable for solving the flexible organization and scheduling problems of operators and resources in the warehouse operating system along with different work tasks.

In the embodiment of the present application, a multi-agent system is formed based on a plurality of agents in a warehouse system, and the multi-agent system is a set of a plurality of agents, and the aim of the multi-agent system is to construct a large and complex system into a small system which is mutually communicated and coordinated and is easy to manage. Its research involves the agent's knowledge, goals, skills, planning, and how to get the agent to take coordinating actions to solve the problem. Researchers mainly research the aspects of interactive communication, coordination and cooperation, conflict resolution and the like among the agents, emphasize the close group cooperation among a plurality of agents rather than the autonomy and exertion of individual capacity, and mainly explain how to analyze, design and integrate a plurality of agents to form a mutual cooperation system.

In summary, the multi-agent modeling mode is a flexible and distributed modeling technology, and can realize the autonomous control and operation of individual elements and more intelligent decision in a modeling system. The influence of microscopic behaviors and decisions on macroscopic phenomena and laws is revealed in a bottom-up cooperative autonomous mode by a plurality of agents. A brand-new technical scheme can be provided for constructing a warehouse system planning system by adopting a multi-agent modeling mode.

The following describes a simulation method, apparatus, server and storage medium of a warehouse management system provided in an embodiment of the present invention. The following describes a simulation method of a warehouse management system provided in an embodiment of the present application, where the simulation method is performed by a server, and the server may be an independent server, or a server network or a server cluster composed of servers, for example, the server described in the embodiment of the present invention includes, but is not limited to, a computer, a network host, a single network server, a plurality of network server sets, or a cloud server composed of a plurality of servers. Among them, the Cloud server is constituted by a large number of computers or web servers based on Cloud Computing (Cloud Computing). The number, the deployment mode, the application scene and the application environment of the servers are not limited in the embodiment of the application. The warehouse management system may also include one or more other services, which are not particularly limited herein. The warehouse management system and the scenario described in the embodiment of the present application are for more clearly illustrating the technical solution of the embodiment of the present application, and do not constitute a limitation to the technical solution provided in the embodiment of the present application, and as a person having ordinary skill in the art knows, along with the evolution of the warehouse management system and the appearance of a new business scenario, the technical solution provided in the embodiment of the present application is also applicable to similar technical problems.

Referring to a flow diagram of a simulation method of a warehouse management system shown in fig. 2, the simulation method of the warehouse management system includes:

201. a plurality of agents are created from the constituent elements of the warehouse management system.

The following describes the process of creating multiple agents:

cutting into from the individual microscopic level of the warehouse system, identifying all individuals existing in the warehouse system, and then classifying the individuals in the warehouse system according to individual types to obtain a system (which can be represented by Agent types) consisting of various types of individuals. Different types of individuals in the warehouse system are represented by a computing entity, namely an Agent, so that a plurality of agents existing in the warehouse system are obtained, and the agents are used as objects for subsequent modeling, namely, the relevant characteristics of each Agent type are modeled.

In some embodiments, a plurality of agents are created from the components of the warehouse management system by:

determining the constituent elements of the warehouse management system;

and modeling different types of objects by using intelligent agent technology respectively to serve as intelligent agents of the warehouse system.

Correspondingly, a corresponding relationship among the Agent type, the Agent function and the Agent attribute is created, and the corresponding relationship can also be called description information. In some embodiments, the correspondence between the Agent type, the Agent function, and the Agent attribute may refer to a schematic diagram as shown in fig. 3.

For example, the table shown in FIG. 3 describes the types of Agents and associated functions and attributes that exist in the warehouse simulation world. In fig. 3, Agent types, Agent functions, and Agent attributes are defined, and the Agent types include a library Agent, a fixed-point Agent, a SKU Agent, a forklift Agent production line Agent, a loading area Agent, and a truck Agent. Taking the Agent type as the stock location Agent as an example, the corresponding Agent function is 'representing various stock location types and being responsible for managing the stock stored, including recording SKU material number types, storage quantity, stock-in time, stock-out time and dynamic information, and sending signals, broadcasting requirements and other Agent behaviors aiming at the stock-in operation and the stock-out operation', and the corresponding Agent attribute is 'coordinate position, stock capacity constraint, maximum SKU detail, current stock SKU detail, subordinate stock area and stacker crane number'.

202. And respectively setting corresponding decision rules and behavior methods for each agent.

For example, a corresponding decision rule and a corresponding behavior method are set for each Agent for description and modeling, such as how the forklift Agent runs in a warehouse, how a route is planned, and how a task is assigned. The decision and behavior of this part can be modeled in two ways, a and b:

a. modeling within Agent intelligence, respectively, is generally standardized or simpler behavior.

b. And a rule base or an algorithm base of an independent module is established, and the Agent can call and load a related algorithm through an interface to realize more complex behaviors. For example, in the model, the forklift Agent calls a path optimization algorithm in the algorithm module when planning a driving route. The method b has the advantages that the method can be used for independently modeling more complex behaviors and algorithms, does not need to worry about the difference of the internal structure of the Agent, and is convenient for modifying and managing large-scale rules.

In some embodiments, relatively complex behaviors and algorithms may also be modeled separately to facilitate modification and management of large-scale rules. Specifically, a corresponding decision rule and a corresponding behavior method are respectively set in each intelligent agent, or an independent rule base or an independent algorithm base is respectively established for each intelligent agent; the rule base and the algorithm base can be called by each multi-agent model.

and modifying the rule base and the algorithm base of the target agent.

Therefore, by adopting the mode, the large-scale rules can be efficiently modified and managed without considering the difference between the internal structures of the agents, and the warehouse management efficiency and the modification timeliness are improved.

203. And respectively constructing a multi-agent model for each agent with the decision rule and the behavior method.

Wherein the multi-agent model is used for monitoring the change state of the corresponding agent and the interaction state with other agents in the warehouse system.

In some embodiments, in order to facilitate centralized management and embody the correlation characteristics such as the superior-inferior relationship, the collaborative relationship, and the like between the agents from a macroscopic perspective, in the embodiments of the present application, when a plurality of agents in a warehouse system are separately modeled, a distributed modeling manner may be adopted, the agents correspond to one multi-agent model separately, and the multi-agent models corresponding to the plurality of agents constitute one modeling system. By adopting a distributed modeling mode, the autonomous control and operation of the building individual elements (namely single intelligent agents) and more intelligent decision can be realized in the modeling system. The influence of microscopic behaviors and decisions on macroscopic phenomena and laws is revealed in a bottom-up cooperative autonomous mode of each agent.

204. And respectively integrating various agents of each multi-agent model and decision rules and behavior methods of the agents into different simulation service modules to construct a warehouse system simulation model.

As shown in fig. 4, the warehouse system includes a plurality of business processes, for example, the business processes include an shelving process, a shipping process, and a replenishment process. The warehouse system simulation model constructed based on the warehouse system can comprise various agent modules (also called agent modules) which are really existing in the warehouse system, an algorithm strategy module, a system module and a visual simulation interface module.

The intelligent modules are used for constructing various types of intelligent bodies in the corresponding simulation world of the warehouse system.

The system modules include modules for constructing and managing each business process in the warehouse system, for example, three agents of a production line, a forklift and a Stock Keeping Unit (SKU) are integrated in the production line operation modules, and respective behaviors and decisions of the production line, the forklift and the SKU. The production line agents produce according to the production plan generated by the production line agents, and the SKU agents are generated from the production line and are endowed with different attributes. And the fork truck agents acquire the SKU agents from the agents of all the production lines according to the task assignment, and transport the SKU agents to the designated storage positions for storage.

The algorithm strategy module provides various algorithm supports for Agent behavior decision.

The simulation interface module provides parameter adjusting function and simulation index analysis for the model.

205. And respectively distributing a warehouse task for each intelligent agent in the warehouse system simulation model through the warehouse system simulation model, and outputting the global warehouse task of the warehouse system.

The warehouse task refers to an operation planned and executed by the intelligent agent in the warehouse system, for example, the intelligent agent is a forklift, the warehouse task for planning the forklift can be operations of loading and unloading, stacking, short-distance transportation and the like of goods, and the warehouse task is time-efficient and has a certain path planning.

Compared with the existing mechanism that a single individual (enterprise, machine and human) in the warehouse system is not specifically modeled, but is uniformly represented as a set number in the warehouse system, in this way, the individual of the warehouse system cannot be modeled differentially. The Agent in the modeling model can directly interact with the warehouse environment and capture and learn the change of the environment, and more information reflecting the microscopic change of the warehouse system is obtained when the simulation is run.

In addition, the model of the embodiment of the application also focuses on the behaviors of single agents and the interaction relation among the agents, and each agent has an autonomous behavior and decision mode and can perform communication interaction and cooperation with other agents in the system. Compared with the existing mechanism that simulation can be performed only according to well-defined limited rules, the method and the system for simulating the warehouse environment can reflect the real situation of the warehouse environment based on a large number of events and behaviors evolved after microscopic interaction. Furthermore, according to the Agent-based model, each individual element in the warehouse system can take active actions and strategies according to environment feedback in a large scale. And finally, a decision rule and a behavior method of each Agent are created when modeling is carried out based on multiple agents, so that even under the condition of a large number of agents and behaviors, the complexity or difference of the internal structure of the agents is not needed to be worried about, and the decision rule and the behavior method are convenient to modify and manage.

The Agent of the embodiment of the application is finer in granularity and comprehensive, and can simulate a finer-granularity running state by performing simulation modeling based on all real individuals such as each equipment assembly, the position of the equipment assembly, the control point of the equipment assembly, the user participating in the warehouse system and the like in the warehouse system, and further perform modeling and judgment aiming at the situation that whether interaction exists among the equipment assemblies, the interaction situation among the equipment assemblies is tracked in real time, and the change generated by the equipment assemblies after the interaction, so that various hidden and undefined change situations in the warehouse environment can be captured, and the purpose of realizing the mutual coordination and mutual cooperation of the fine-granularity individuals can be achieved.

Optionally, in some embodiments of the present application, because complex behaviors and interaction relationships between the agents in the warehouse system at the micro level are relatively complex, the complex behaviors and interaction relationships between the agents at the micro level have a relatively obvious influence on the behaviors at the system level. Therefore, the present application further considers the uniqueness of the individuals in the warehouse system, such as the agents, and the interaction state of the agents, and after the warehouse system simulation model is constructed, the method further includes:

Therefore, the intelligent agent in the embodiment of the application can directly interact with the warehouse environment and capture and learn the change of the environment, so that more information reflecting the microscopic change of the warehouse system can be obtained during operation simulation, and the warehouse operation system can be simulated more accurately and more efficiently; and the agents can coordinate and cooperate with each other, so that the decomposition, distributed modeling and control can be effectively carried out on the complex warehouse system in the modeling process, and the overall modeling difficulty is reduced.

In addition, the multi-agent model focuses on the behavior of the agent individuals and the interaction relationship among the agents, and can be regarded as a group of interaction objects which naturally reflect various relationships in the real world, so that the warehouse environment with higher complexity can be accurately understood, the dynamic and nonlinear states of the warehouse system can be captured, and compared with the existing mechanism, the scheme of the embodiment of the application can obviously improve the efficiency of warehouse management and capture the real warehouse state.

For the convenience of understanding, the simulation process of the entire warehouse system is described below by taking a specific application scenario as an example. The above shelving process, shipping process and replenishment process are examples. The following are introduced separately:

(1) the racking process refers to a process of taking and placing off-line products into corresponding storage positions, and mainly relates to the steps of generating a racking task by a task manager, waiting for the task to trigger and executing the racking task.

The execution of the racking task comprises:

find the appropriate fork/forklift worker to receive the task

Production line outlet corresponding to task of forklift

Forklift loading (production line export unloading)

Fork truck opens to finished product storehouse position that task corresponds

Forklift unloading (finished goods warehouse position loading)

Fork lift truck returns to default position or stands by in situ

(2) The delivery process refers to a process of taking the goods out of a warehouse location or taking the goods out of a production line exit and transporting the goods to a truck parking space.

a. The simulation process of the transportation from the warehouse location to the parking location comprises the steps that the task manager generates a transportation task, waits for the triggering of the task and executes the transportation task.

Wherein, executing the shipping task comprises:

find the appropriate fork/forklift worker to receive the task

Fork truck opens to finished product storehouse position that task corresponds

Forklift loading (finished product warehouse location unloading)

Forklift driving departure parking space corresponding to task

Forklift unloading (loading in parking space)

Fork lift truck returns to default position or stands by in situ

b. The simulation process of the production line export delivery to the parking space comprises the steps of generating a delivery task by a task manager, waiting for the task to trigger and executing the delivery task.

Wherein performing the shipping task comprises finding a suitable forklift/forklift worker to receive the task

Production line outlet corresponding to task of forklift

Forklift loading (production line export unloading)

Forklift driving departure parking space corresponding to task

Forklift unloading (loading in parking space)

Fork lift truck returns to default position or stands by in situ

(3) The replenishment process refers to optimization of current stock location conditions (litter size) or minimization of picking paths based on future orders (SKU ABC classification adjustment, etc.), and the system determines whether SKU placement between stock locations needs to be adjusted.

The simulation process of the replenishment process comprises the steps that the stock position manager triggers a replenishment task and transmits the replenishment task to the task manager, the task manager generates the replenishment task, and the task is waited to trigger and execute the replenishment task.

Wherein, carry out the replenishment task and include:

find the appropriate fork/forklift worker to receive the task

Starting finished product storage position corresponding to forklift driving task

Forklift loading (initial finished goods warehouse position unloading)

Target finished product warehouse position corresponding to forklift driving task

Forklift unloading (target finished goods warehouse loading)

Fork lift truck returns to default position or stands by in situ

Based on the scheme about the warehouse system simulation model in the embodiments corresponding to fig. 2 to fig. 4, a visual, easy-to-operate and flexible-configuration warehouse simulation environment can be constructed. Fig. 5a is a schematic CAD plan drawing of an enterprise warehouse system, and fig. 5b is a schematic 1:1 warehouse system simulation model of an enterprise warehouse system and an interface diagram of a visual simulation interface module in the warehouse system simulation model. Because the warehouse system simulation model shown in fig. 5b is accurately restored in a ratio of 1:1 according to the CAD drawing of the warehouse system, and the simulation environment of the entire warehouse system is presented in a visual interface manner, a user can intuitively observe the complete business process and the warehouse operation state of the warehouse simulation operation based on fig. 5 b. Meanwhile, the model provides a series of operation index calculations and statistics, and a simulation result as shown in fig. 6 is obtained after the warehouse system is simulated based on the warehouse system simulation model shown in fig. 4. From the index of simulation result statistics, the simulation model almost perfectly reproduces the actual operation state of the target client warehouse system. The warehouse throughput of 12 months and 1 days actually recorded on site has high similarity with the throughput simulated by the model, and the reduction degree is as high as 99.3%, so that the real environment of the warehouse system can be accurately simulated by adopting the mode of constructing the warehouse system simulation model based on the multi-agent in the embodiment of the application, and a user can take the warehouse system simulation model as a Digital Twin (Digital Twin) to perform a series of experimental analysis in a simulation virtual space parallel to a real physical space, so that the overall operation efficiency of the warehouse system is improved.

Any technical feature mentioned in the embodiment corresponding to any one of fig. 1 to 6 is also applicable to the embodiments corresponding to fig. 7 and 8 in the embodiment of the present application, and the details of the subsequent similarities are not repeated.

In the above description, a simulation method of a warehouse management system in the embodiment of the present application is described, and a device for executing the simulation method of the warehouse management system is described below.

Referring to fig. 7, a schematic structural diagram of a warehouse simulation apparatus 70 shown in fig. 7 may be applied to a warehouse system. The warehouse simulation apparatus 70 in the embodiment of the present application can implement the steps of the simulation method corresponding to the warehouse management system executed in the embodiment corresponding to any one of fig. 1 to 6. The functions realized by the warehouse simulation device can be realized by hardware, and can also be realized by executing corresponding software by hardware. The hardware or software includes one or more modules corresponding to the above functions, which may be software and/or hardware. The warehouse simulation apparatus may include a processing module 701 (which may also be decomposed into a determining module, a constructing module, a distributing module, and the like, which is not limited in this embodiment) and an input/output module 702, where the functional implementation of the processing module 701 and the input/output module 702 may refer to the operation performed in any one of the embodiments corresponding to fig. 1 to fig. 6, and details are not described here. For example, the processing module may be used to control the operations of the input/output module 702 such as obtaining, transceiving, and the like.

In some embodiments, the processing module 701 may be configured to create a plurality of agents from the components of the warehouse management system, the agents including at least one agent of a aisle, a bay, a truck, a production line, a loading area, an inventory unit, a forklift, a device, and a warehouse user;

the processing module 701 may also be configured to set a corresponding decision rule and a corresponding behavior method for each agent; respectively constructing a multi-agent model for each agent with decision rules and behavior methods; respectively integrating various agents at the bottom layer of each multi-agent model and decision rules and behavior methods of the agents into different simulation service modules to construct a warehouse system simulation model; and respectively distributing a warehouse task for each intelligent agent in the warehouse system simulation model through the warehouse system simulation model, and outputting the global warehouse task of the warehouse system.

In this embodiment of the application, the processing module 701 sets a corresponding decision rule and a corresponding behavior method for each agent in the warehouse system; setting a corresponding decision rule and a corresponding behavior method for each agent, and respectively constructing a multi-agent model for each agent; respectively integrating various agents and behavior methods of the agents at the bottom layer of each multi-agent model into different simulation service modules to construct a warehouse system simulation model; and respectively distributing warehouse tasks for each intelligent agent in the warehouse system simulation model through the warehouse system simulation model. The scheme can improve the overall operation efficiency of the warehouse system and improve the performance of the simulation and analysis warehouse system.

In some embodiments, the input-output module 702 is specifically configured to:

determining the constituent elements of the warehouse management system;

different types of individuals are respectively represented by agents as agents of the warehouse system.

In some embodiments, the multi-agent model includes a production line operational module that integrates decision rules and behavioral methods for production agents, forklift agents, and SKU agents; the processing module 701 is further configured to:

assigning different attributes to the SKU agent;

In some embodiments, the processing module 701 represents different types of individuals with agents, respectively, to serve as agents of the warehouse system, and then further:

In some embodiments, the processing module 701 is specifically configured to:

respectively setting corresponding decision rules and behavior methods in each agent, or respectively setting each agent;

receiving a modification instruction through the input/output module 702, where the modification instruction carries an agent identifier of an agent to be modified;

and modifying the rule base and the algorithm base of the target agent.

In some embodiments, after the processing module 701 constructs the warehouse system simulation model, it is further configured to:

In some embodiments, after the building of the warehouse system simulation model, the processing module 701 is further configured to perform at least one of the following operations:

The above describes the warehouse simulation apparatus 70 in the present embodiment from the perspective of a modular functional entity, and the following describes computer devices that execute the simulation method of the warehouse management system in the present embodiment from the perspective of hardware processing. The warehouse simulation apparatus 70 shown in fig. 7 may have a structure as shown in fig. 8, when the warehouse simulation apparatus 70 shown in fig. 7 has a structure as shown in fig. 8, the processor and the transceiver in fig. 8 can implement the same or similar functions as the processing module 701 and the input/output module 702 provided in the apparatus embodiment corresponding to the warehouse simulation apparatus 70, and the central storage in fig. 8 stores a computer program that the processor needs to call when executing the simulation method of the warehouse management system. In the embodiment of this application, an entity device corresponding to the input/output module 702 in the embodiment shown in fig. 7 may be an input/output unit, an input/output interface, or a transceiver, and an entity device corresponding to the processing module 701 may be a processor.

In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system, the apparatus and the module described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the several embodiments provided in the embodiments of the present application, it should be understood that the disclosed system, apparatus, and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical division, and in actual implementation, there may be other divisions, for example, multiple modules or components may be combined or integrated into another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or modules, and may be in an electrical, mechanical or other form.

The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.

In addition, functional modules in the embodiments of the present application may be integrated into one processing module, or each module may exist alone physically, or two or more modules are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may be stored in a computer readable storage medium.

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may 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. The procedures or functions described in accordance with the embodiments of the present application are generated in whole or in part when the computer program is loaded and executed on a computer. The computer may be a general purpose computer, a special purpose computer, a network of computers, 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, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can store or a data storage device, such as a server, a data center, etc., that is integrated with one or more available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.

The technical solutions provided by the embodiments of the present application are introduced in detail, and the principles and implementations of the embodiments of the present application are explained by applying specific examples in the embodiments of the present application, and the descriptions of the embodiments are only used to help understanding the method and core ideas of the embodiments of the present application; meanwhile, for a person skilled in the art, according to the idea of the embodiment of the present application, there may be a change in the specific implementation and application scope, and in summary, the content of the present specification should not be construed as a limitation to the embodiment of the present application.

Claims

1. A method of simulating a warehouse management system, the method comprising:

2. The method of claim 1, wherein creating a plurality of agents from components of a warehouse management system comprises:

determining the constituent elements of the warehouse management system;

decomposing the constituent elements of the warehouse management system into a system consisting of various types of objects according to the attributes of the constituent elements;

3. The method of claim 2, wherein said multi-agent model comprises a line operations module that integrates decision rules and behavior methods for production agents, forklift agents, and SKU agents;

assigning different attributes to the SKU agent;

4. The method according to any one of claims 1-3, wherein the setting of the corresponding decision rule and behavior method for each agent respectively comprises:

determining a target agent corresponding to the agent identifier according to the agent identifier carried by the modification instruction;

and modifying the rule base and the algorithm base of the target agent.

5. The method of claim 3, wherein after the building the warehouse system simulation model, the method further comprises:

6. The method of claim 5, wherein after the building of the warehouse system simulation model, the method further comprises at least one of:

7. The method of claim 6, wherein after the building the warehouse system simulation model, the method further comprises:

8. A warehouse simulation apparatus, comprising:

the system comprises a processing module, a warehouse management system and a storage management module, wherein the processing module is used for creating a plurality of intelligent bodies according to the constituent elements of the warehouse management system, and each intelligent body comprises at least one intelligent body of a channel, a warehouse location, a truck, a production line, a loading area, an inventory unit, a forklift, equipment and a warehouse user;

the processing module is also used for respectively setting a corresponding decision rule and a corresponding behavior method for each intelligent agent; respectively constructing a multi-agent model for each agent with decision rules and behavior methods; respectively integrating various agents at the bottom layer of each multi-agent model and decision rules and behavior methods of the agents into different simulation service modules to construct a warehouse system simulation model; respectively distributing warehouse tasks to each intelligent agent in the warehouse system simulation model through the warehouse system simulation model;

and the input and output module is used for outputting the global warehouse task of the warehouse system.

9. A computer device, characterized in that the computer device comprises:

at least one processor, memory, and transceiver;

wherein the memory is for storing a computer program and the processor is for calling the computer program stored in the memory to perform the method of any one of claims 1-7.

10. A computer-readable storage medium comprising instructions which, when executed on a computer, cause the computer to perform the method of any of claims 1-7, in that it comprises instructions.