CN116882691A - Automatic scheduling processing methods, devices, equipment and readable media for experimental plans - Google Patents

Abstract

The present disclosure relates to an automatic scheduling processing method, device, electronic equipment and computer-readable medium for experimental plans. The method includes: obtaining experimental information corresponding to at least one experimental plan to be processed, the experimental information including a plurality of reaction tasks; determining constraint conditions for its corresponding experimental plan based on the experimental information; determining optimization of the at least one experimental plan Objective; optimize the execution sequence of multiple reaction tasks corresponding to the at least one experimental plan based on the optimization objective and the constraint conditions, and generate an experimental scheduling strategy; automatically call an intelligent laboratory based on the experimental scheduling strategy resources to execute the at least one experimental plan to generate experimental results. The automatic scheduling processing method, device, electronic equipment and computer-readable medium of the experimental plan involved in the present disclosure can perform flexible automated scheduling of chemical experiments with human-machine integration, reduce the operating costs of automated laboratories, and improve work efficiency. Ensure the accurate execution of experimental plans.

Description

Automatic scheduling processing methods, devices, equipment and readable media for experimental plans

Technical field

The present disclosure relates to the field of automatic processing of chemical experiments. Specifically, it relates to an automatic scheduling processing method, device, electronic equipment and computer-readable medium for experimental plans.

Background technique

Automation technology is widely used in the production of petroleum products such as plastics and bulk chemicals such as fertilizers, greatly improving production efficiency. However, it is difficult to directly transfer the experience of chemical industry digitization and automation to chemical laboratory scenarios. This is because an automated assembly line in chemical production is only used to produce one or several commodities, and the tasks of each link are relatively fixed. However, chemistry experiments generally undertake various types of experiments. The procedures of different experiments are also different. Even if it is the same operation link, due to different substances or different reactions, the operation methods are often different. For example, in the feeding process, some substances that react more violently need to be added dropwise, and some substances cannot come into contact with oxygen, so the gas needs to be replaced during the feeding process. Different operations also use different equipment. Due to such diversity, one automated equipment cannot solve all reaction problems, and multiple automated equipment and manual experiments are often required.

The existing laboratory scheduling methods on the market are mainly aimed at automated instruments in the laboratory and do not involve the arrangement of human tasks, so there is no way to arrange the entire experimental task. Methods in the prior art lead to an increase in laboratory costs due to the lack of scheduling of human-machine collaborative automation equipment. Many automation solutions require a large number of robots and transport vehicles with robots to transfer and operate materials. However, the price of robots is not low, which results in the high cost of automated laboratories.

Therefore, a new method, device, electronic device, and computer-readable medium for automatic scheduling of experimental plans are needed to solve the above problems.

The above information disclosed in the Background section is only for enhancement of understanding of the context of the disclosure and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art.

Contents of the invention

In view of this, the present disclosure provides an automatic scheduling processing method, device, electronic equipment and computer-readable medium for experimental plans, which can perform flexible automated scheduling of chemical experiments with human-machine integration and reduce the operating costs of automated laboratories. , improve work efficiency and ensure the accurate execution of the experimental plan.

Additional features and advantages of the disclosure will be apparent from the following detailed description, or, in part, may be learned by practice of the disclosure.

According to one aspect of the present disclosure, a method for automatic scheduling of experimental plans is proposed. The method includes: obtaining experimental information corresponding to at least one experimental plan to be processed, where the experimental information includes multiple reaction tasks; according to the experimental information Determine constraint conditions for its corresponding experimental plan; determine the optimization goal of the at least one experimental plan; optimize the execution sequence of multiple reaction tasks corresponding to the at least one experimental plan based on the optimization goal and the constraint conditions, Generate an experiment scheduling strategy; automatically call resources in the intelligent laboratory based on the experiment scheduling strategy to execute the at least one experiment plan to generate experimental results.

In an exemplary embodiment of the present disclosure, obtaining experimental information corresponding to at least one experimental plan to be processed includes: obtaining an experimental flow chart corresponding to the at least one experimental plan to be processed; obtaining at least one experimental flow chart corresponding to multiple reaction tasks; obtain task information corresponding to the multiple reaction tasks; and generate at least one experimental information through the experimental flow chart, reaction tasks, and task information corresponding to the at least one experimental plan.

In an exemplary embodiment of the present disclosure, determining constraint conditions for its corresponding experimental plan based on experimental information includes: obtaining the execution subject sets of multiple reaction tasks corresponding to the experimental plan from the experimental information and setting the constraint conditions ; Acquire the reaction times of multiple reaction tasks corresponding to the experimental plan from the experimental information and set the constraint conditions; Obtain the reaction sequences of the multiple reaction tasks corresponding to the experimental plan from the experimental information and set the constraint conditions.

In an exemplary embodiment of the present disclosure, obtaining the execution subject sets of multiple reaction tasks corresponding to the experimental plan from the experimental information and setting constraints includes: obtaining the material properties of the reaction tasks from the experimental information and the reaction properties; determine the execution subject of the reaction task according to the material properties and reaction properties; generate the execution subject set corresponding to the experimental plan according to the execution subjects of multiple reaction tasks; for the execution subject set in the execution subject set Each execution subject sets execution constraints.

In an exemplary embodiment of the present disclosure, obtaining the reaction times of multiple reaction tasks corresponding to the experimental plan from the experimental information and setting constraints includes: setting a fixed time for the reaction task according to the execution subject of the reaction task. reaction time and set fixed time constraints; set a prescribed reaction time and set flexible time constraints for the reaction task according to the execution subject of the reaction task.

In an exemplary embodiment of the present disclosure, obtaining the reaction sequence of multiple reaction tasks corresponding to the experimental plan from the experimental information and setting constraints includes: extracting an experimental flow chart from the experimental information; according to the The experimental flow chart obtains the reaction order of the multiple reaction tasks; and sets sequence time constraints for the multiple reaction tasks according to the reaction order.

In an exemplary embodiment of the present disclosure, determining the optimization target of the at least one experimental plan includes: determining an end time constraint of the at least one experimental plan; The plan sets an experiment weight; it is determined that the optimization objective of the at least one experiment plan is to minimize the completion time.

In an exemplary embodiment of the present disclosure, optimizing the execution order of multiple reaction tasks corresponding to the at least one experimental plan based on the optimization objective and the constraint conditions, and generating an experiment scheduling strategy includes: A mixed integer linear programming algorithm optimizes the execution sequence of multiple reaction tasks corresponding to the at least one experimental plan based on the optimization objective and the constraint conditions; and/or a constraint programming algorithm based on the optimization objective and the constraints The conditions optimize the execution sequence of multiple reaction tasks corresponding to the at least one experimental plan.

In an exemplary embodiment of the present disclosure, the execution subject of the experimental plan includes an intelligent material transfer vehicle; execution of multiple reaction tasks corresponding to the at least one experimental plan based on the optimization objective and the constraint conditions Optimizing in sequence and generating an experiment scheduling strategy includes: obtaining map information of an intelligent laboratory; optimizing the execution sequence of multiple reaction tasks corresponding to the at least one experimental plan based on the optimization goal and the constraint conditions, and generating Initial scheduling strategy; based on the initial scheduling strategy and the map information, the experimental scheduling strategy is generated in a stepwise and incremental manner combined with the trajectory information of the intelligent material transfer vehicle.

In an exemplary embodiment of the present disclosure, the experimental scheduling strategy is generated based on the initial scheduling strategy and the map information in a stepwise and incremental manner combined with the trajectory information of the intelligent material transfer vehicle, including: Extract the execution order of multiple response tasks from the initial scheduling strategy; extract multiple areas from the map information; add path information of the intelligent material transfer vehicle to each of the multiple areas one by one; The path information of the intelligent material transfer vehicle is optimized in each of the above areas to generate an optimized path; the initial scheduling strategy is updated according to the optimized path to generate the experimental scheduling strategy.

According to one aspect of the present disclosure, an automatic scheduling processing device for experimental plans is proposed. The device includes: an information module for obtaining experimental information corresponding to at least one experimental plan to be processed, and the experimental information includes multiple reactions. Task; constraint module, used to determine constraint conditions for its corresponding experimental plan according to experimental information; target module, used to determine the optimization target of the at least one experimental plan; scheduling module, used to determine the optimization target based on the optimization target and the Constraints optimize the execution sequence of multiple reaction tasks corresponding to the at least one experimental plan and generate an experimental scheduling strategy; an execution module is used to automatically call resources in the intelligent laboratory for execution based on the experimental scheduling strategy The at least one experimental plan generates experimental results.

According to one aspect of the present disclosure, an electronic device is proposed, which includes: one or more processors; a storage device for storing one or more programs; when one or more programs are processed by one or more processors Execution causes one or more processors to implement the method as above.

According to one aspect of the present disclosure, a computer-readable medium is proposed, on which a computer program is stored. When the program is executed by a processor, the method as above is implemented.

According to the automatic scheduling processing method, device, electronic equipment and computer-readable medium of the experimental plan of the present disclosure, experimental information corresponding to at least one experimental plan to be processed is obtained, and the experimental information includes multiple reaction tasks; according to the experimental information Determine constraint conditions for its corresponding experimental plan; determine the optimization goal of the at least one experimental plan; optimize the execution sequence of multiple reaction tasks corresponding to the at least one experimental plan based on the optimization goal and the constraint conditions, Generate an experiment scheduling strategy; automatically call resources in the intelligent laboratory based on the experimental scheduling strategy to execute the at least one experimental plan to generate experimental results, enabling flexible automated scheduling of chemical experiments that combines humans and machines , reduce the operating costs of automated laboratories, improve work efficiency, and ensure the accurate execution of experimental plans.

It should be understood that the above general description and the following detailed description are only exemplary and do not limit the present disclosure.

Description of the drawings

The above and other objects, features and advantages of the present disclosure will become more apparent by describing in detail example embodiments thereof with reference to the accompanying drawings. The drawings described below are only some embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without exerting creative efforts.

FIG. 1 is a schematic diagram of an automatic scheduling processing system for experimental plans according to an exemplary embodiment.

FIG. 2 is a flow chart of an automatic scheduling processing method of an experiment plan according to an exemplary embodiment.

FIG. 3 is a flow chart of an automatic scheduling processing method of an experiment plan according to another exemplary embodiment.

FIG. 4 is a flow chart of an automatic scheduling processing method of an experiment plan according to another exemplary embodiment.

FIG. 5 is a schematic diagram of an automatic scheduling processing method of an experiment plan according to another exemplary embodiment.

FIG. 6 is a schematic diagram of an automatic scheduling processing method of an experiment plan according to another exemplary embodiment.

FIG. 7 is a block diagram of an automatic scheduling processing device for an experiment plan according to an exemplary embodiment.

FIG. 8 is a block diagram of an electronic device according to an exemplary embodiment.

Figure 9 is a block diagram of a computer-readable medium according to an exemplary embodiment.

Detailed ways

Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in various forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concepts of the example embodiments. To those skilled in the art. The same reference numerals in the drawings represent the same or similar parts, and thus their repeated description will be omitted.

Furthermore, the described features, structures or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to provide a thorough understanding of embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other instances, well-known methods, apparatus, implementations, or operations have not been shown or described in detail to avoid obscuring aspects of the present disclosure.

The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and/or processor devices and/or microcontroller devices. entity.

The flowcharts shown in the drawings are only illustrative, and do not necessarily include all contents and operations/steps, nor must they be performed in the order described. For example, some operations/steps can be decomposed, and some operations/steps can be merged or partially merged, so the actual order of execution may change according to the actual situation.

It will be understood that, although the terms first, second, third, etc. may be used herein to describe various components, these components should not be limited by these terms. These terms are used to distinguish one component from another component. Accordingly, a first component discussed below may be termed a second component without departing from the teachings of the presently disclosed concepts. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.

Those skilled in the art can understand that the accompanying drawings are only schematic diagrams of exemplary embodiments, and the modules or processes in the accompanying drawings are not necessarily necessary to implement the present disclosure, and therefore cannot be used to limit the scope of protection of the present disclosure.

The applicant in this case found through research on existing technologies that in chemical experiment scenarios, automated equipment is difficult to handle the uncertainty in chemical operations, and that in actual production, the cost of some automated equipment is too high. The efficiency gains are not as great as hiring people to perform them. Therefore, in the scenario of human-machine integration, it is not enough to schedule the experimental equipment alone.

If only chemical equipment is scheduled, the execution efficiency will be reduced. Since the arrangement of machines does not take human tasks into consideration, the execution time or execution status of tasks is often uncertain. Especially tasks performed by humans will lead to situations where humans are waiting for machines or machines are waiting for humans (for example, when a certain task has already been completed) start time, but the task performed by the preceding human has not yet been completed). Scheduling only chemical equipment can also cause task interruptions: for example, a task that is performed by a machine but needs to be started by a human must start when the human is performing other tasks.

In view of the technical shortcomings in the existing technology, this application proposes an automatic scheduling processing method that can meet the uncertainty and diversity needs in chemical experiment scenarios. It takes into account manual operations and machine equipment to schedule experiments. , to meet the needs in actual operations and greatly improve the experimental efficiency.

FIG. 1 is a schematic diagram of an automatic scheduling processing system for experimental plans according to an exemplary embodiment.

As shown in Figure 1, a chemical experiment scenario can include smart containers, weighing equipment, reactors, post-processing reactors, and automatic analyzers. It can also include auxiliary equipment such as material transfer vehicles and robotic arms.

Among them, smart containers are used to load reaction substrates;

Weighing equipment is used to obtain a preset amount of reaction substrate. Weighing equipment can also include automatic weighing equipment, micro-automatic weighing equipment, manual weighing equipment, etc.

The reactor is used to carry reaction substrates, conduct experimental reactions, and generate reaction results. More specifically, automatic reactors, traditional reaction vessels, stirrers, etc. may be included.

An automatic analyzer is used to analyze intermediate reactants and generate analysis results.

The post-processing module is used to perform subsequent operations or processing on the intermediate products or reaction results of chemical reactions. It is worth mentioning that the processing of subsequent reactions can also continue in the reactor.

Material transfer vehicles are used to automatically send materials to corresponding devices according to different process steps;

A mechanical arm may also be included for grabbing reaction substrates or transferring materials to corresponding devices.

In the specific application scenario as shown in Figure 1, when the user submits one or more experimental plans, the method in this application can automatically estimate the reaction time in one or more experimental plans, and then perform intelligent experiments The operation sequence and time of the equipment or execution subjects (machines or people) in the room are sequenced, and operation instructions are generated so that the execution subjects can perform chemical reaction operations according to the instructions.

After one or more experimental plans are started, the system controls the smart container to take out the raw material bottles required for the experiment, and the robotic arm of the smart container places them on a picking table.

Afterwards, the materials can be transported to the batching area by the material transfer vehicle;

The weighing operation is completed by automatic weighing equipment or humans depending on the nature of the substance.

The material transfer vehicle then transports the materials to the reaction area and returns the raw material bottles to the smart container for storage.

Select the appropriate reactor according to the type of reaction, and the robotic arm completes the feeding operation.

After the reaction is completed, the robotic arm samples and automatically preprocesses the reacted mixed solution for automatic analysis.

Send materials to each subsequent execution entity according to the operating steps and experimental scheduling strategy in the flow chart corresponding to the experimental plan;

Finally, the material transfer vehicle delivers the product to the smart container for warehousing operation.

FIG. 2 is a flow chart of an automatic scheduling processing method of an experiment plan according to an exemplary embodiment. The automatic scheduling processing method 20 of the experimental plan includes at least steps S202 to S208.

As shown in Figure 2, in S202, experimental information corresponding to at least one experimental plan to be processed is obtained, and the experimental information includes multiple reaction tasks. For example, the experimental flow chart corresponding to the at least one experimental plan to be processed can be obtained; multiple reaction tasks corresponding to the at least one experimental flow chart can be obtained; task information corresponding to the multiple reaction tasks can be obtained; and the at least one experimental plan can be used to correspond to The experimental flow chart, reaction task, and task information generate at least one experimental information.

In this application, reactions may include combination reactions, decomposition reactions, displacement reactions, metathesis reactions, etc., and an experimental plan may include one or more reaction tasks. The reaction task information can indicate the reaction conditions, environmental information, reaction time, etc. required for the reaction.

It is worth mentioning that in this application, the experimental flow chart corresponds to the chemical experimental flow chart. It refers to a directed graph constructed from tasks and task sequences in chemical experiments. Each node represents a chemical experiment task (picking, weighing, and reaction in Figure 1). A simple arrow means to do the previous task first, and then perform the next task after completing it. Parallel tasks controlled by the parallel task switch: Indicates that the process between the start of the parallel task and the end of the parallel task is carried out simultaneously.

In S204, constraints are determined for its corresponding experiment plan based on the experimental information. For example, the execution subject sets of multiple reaction tasks corresponding to the experimental plan are obtained from the experimental information and the constraint conditions are set; the reaction times of the multiple reaction tasks corresponding to the experimental plan are obtained from the experimental information and the constraint conditions are set; The reaction order of multiple reaction tasks corresponding to the experimental plan is obtained from the experimental information and constraint conditions are set.

The details of "determining constraints for its corresponding experimental plan based on experimental information" will be described in the corresponding embodiment of FIG. 3 .

In S206, the optimization target of the at least one experimental plan is determined. The end time constraint of the at least one experiment plan can be determined; an experiment weight can be set for each experiment plan in the at least one experiment plan; and the optimization goal of the at least one experiment plan can be determined to minimize the completion time.

The details of "determining the optimization target of the at least one experimental plan" will be described in the corresponding embodiment of FIG. 3 .

In S208, the execution order of multiple reaction tasks corresponding to the at least one experiment plan is optimized based on the optimization target and the constraint conditions, and an experiment scheduling strategy is generated. For example, a mixed integer linear programming algorithm may be used to optimize the execution sequence of multiple reaction tasks corresponding to the at least one experimental plan based on the optimization objective and the constraint conditions; or for example, a constraint programming algorithm may be used based on the optimization The goal and the constraint condition optimize the execution sequence of multiple reaction tasks corresponding to the at least one experimental plan.

More specifically, the optimization algorithms described in this application may include MILP, CP-SAT, and available solvers include but are not limited to commercial solvers such as Gurobi, CPLEX, and XPress, and open source solvers such as SCIP and CBC.

In S210, resources in the intelligent laboratory are automatically called based on the experiment scheduling policy to execute the at least one experiment plan to generate experimental results.

According to the automatic scheduling processing method of the experimental plan of the present disclosure, experimental information corresponding to at least one experimental plan to be processed is obtained, and the experimental information includes a plurality of reaction tasks; constraints are determined for the corresponding experimental plan according to the experimental information; Determine the optimization goal of the at least one experimental plan; optimize the execution sequence of multiple reaction tasks corresponding to the at least one experimental plan based on the optimization goal and the constraint conditions, and generate an experiment scheduling strategy; based on the experiment The scheduling strategy automatically calls up resources in the intelligent laboratory to execute the at least one experiment plan to generate experimental results. It can conduct flexible automated scheduling of chemical experiments that combines humans and machines, reduce the operating costs of the automated laboratory, and improve Work efficiency and ensure the accurate execution of experimental plans.

It should be clearly understood that this disclosure describes how to make and use specific examples, but that the principles of the disclosure are not limited to any details of these examples. Rather, these principles can be applied to many other embodiments based on the teachings of this disclosure.

FIG. 3 is a flow chart of an automatic scheduling processing method of an experiment plan according to another exemplary embodiment. The process 30 shown in Figure 3 is a detailed description of S204 "Determining constraints for its corresponding experimental plan based on the experimental information" in the process shown in Figure 2 .

As shown in Figure 3, in S302, constraints are determined for its corresponding experiment plan based on the experimental information.

For example, suppose there are m experimental flow charts that need to be arranged:

fl ₁ , fl ₂ ,..., fl _m ;

For process fl _i, there are several tasks on the flow chart:

In S304, a set of execution subjects of multiple response tasks corresponding to the experiment plan is obtained from the experiment information and constraints are set. For example, the material properties and reaction properties of the reaction task can be obtained from the experimental information; the execution subject of the reaction task can be determined according to the material properties and reaction properties; and the experimental plan corresponding to the execution subjects of multiple reaction tasks can be generated. The set of execution subjects; and setting execution constraints for each execution subject in the set of execution subjects.

In this application, reactions in the same experimental plan can be performed by different automated equipment or people. For example, the same reaction can be performed using microwave reactors, normal temperature reactors, flow reactors and other equipment. The choice of equipment type is usually based on the nature of the reaction or substance. For example, in reactions, microwave reactors are selected for non-dangerous high-temperature reactions (properties of reactions); automatic weighing equipment is used for liquids with good fluidity (properties of substances), etc.

In the flowchart, select the available equipment or operators for each task.

For task t _ij , a user-configurable rule engine is used to define which automation equipment can be executed based on the nature of the material and the nature of the reaction. The l _ij operators of the executable task are defined as variables. Among them, o _ijc indicates whether the c-th operator performs task t _ij .

There is an equation

In S306, the reaction times of multiple reaction tasks corresponding to the experiment plan are obtained from the experimental information and constraint conditions are set. A fixed reaction time and fixed time constraints can be set for the reaction task according to the execution subject of the reaction task; a prescribed reaction time and flexible time constraints can be set for the reaction task according to the execution subject of the reaction task.

For task t _ij , let its start time be s _ij , the end time of the experiment be e _ij , and the duration of each task be d _ij =e _ij -s _ij (2)

Definable fixed-duration tasks (such as machine tasks)

Let d _ij =c _ij , where c _ij is a constant. (3)

Flexible tasks, such as human-operated tasks. The execution time is between c _ij and between tasks, indicating that the execution time of the task must be greater than a constant c _ij and less than a variable/> If there are no subsequent tasks scheduled, the execution time of the task can be extended (for example, if the response reaches 3 a.m., it does not have to be terminated immediately, and the stirring can be continued until the next day for processing).

make

In S308, the reaction order of multiple reaction tasks corresponding to the experiment plan is obtained from the experimental information and constraint conditions are set. For example, an experimental flow chart can be extracted from the experimental information; the reaction order of the multiple reaction tasks can be obtained according to the experimental flow chart; and sequential time constraints can be set for the multiple reaction tasks according to the reaction order.

For two adjacent tasks t _ij and t _ik on the same flow chart;

t _ij executes e _ik = s _ij (5) immediately after ti _ik ends.

t _ij and t _ik start at the same time s _ik =s _ij (6)

t _ij starts within a certain range of time after the start of t _ik :

s _ik +l _lb ≤s _Ij <s _ik +l _ub , where l _lb and l _ub are constants. (7)

t _ij starts within a certain range of time after the end of t _ik :

e _ik +l _lb ≤s _ij <e _ik +l _ub , where l _lb and l _ub are constants. (8)

On the same operation object c, tasks do not overlap:

make

s _ij ≥e _i′j′ -M ₁ ×y _iji′j′ -M ₂ ×(2-o _ijc -o _i′j′c ) (9)

s _i′j′ ≥e _ij -M ₁ ×(1-y _iji′j′ )-M ₂ ×(2-o _ijc -o _i′j′c ) (10)

Among them, M ₁ and M ₂ are very large constants, which can be taken as 10 ⁶ in practice.

Optimization goal: The last task of each experiment can be The corresponding end time is/> Add constraints on the end time of each experiment:

obj＝minimize∑ _i z _i (12)

Where w _i is the weight of the experiment, z _i is the completion time of each experiment with weight. This optimization goal aims to minimize the completion time of all experiments. The experimental algorithm with a higher weight will induce the end as much as possible.

FIG. 4 is a flow chart of an automatic scheduling processing method of an experiment plan according to another exemplary embodiment. The process 40 shown in Figure 4 is when the execution subject of the experimental plan includes an intelligent material transfer vehicle, "optimizing the execution sequence of multiple reaction tasks corresponding to the at least one experimental plan based on the optimization objective and the constraint conditions" , generate a detailed description of the experimental scheduling strategy.

When it is necessary to optimize the schedule of intelligent material transfer vehicles, the factors of intelligent material transfer vehicles can be added to the optimization model above. Since the walking time of intelligent material transfer vehicles between different work areas is uncertain, intelligent The movement of the material transfer vehicle must consider two factors at the same time:

1. The shortest path traveled by the intelligent material transfer vehicle

2. Arrangement of tasks.

As shown in Figure 4, in S402, map information of the smart laboratory is obtained. The map information of the laboratory can be shown in Figure 5.

Assume that the laboratory has work areas: w ₁ , w ₂ ,..., w _m , and the walking time of the intelligent material transfer vehicle between the work areas wi _and w _j is d _ij .

Assume that there are six work areas a, b, c, d, e, and f. Among them, the three work areas a, b, and c are relatively close to each other, and the three work areas d, e, and f are relatively close to each other. But there is a long distance between the two.

As shown in Figure 6, assuming that only scheduling is considered and the order of tasks is a, e, b, f, c, g, then the transportation distance of the intelligent material transfer vehicle is relatively long, which wastes a lot of time. If only the shortest journey of the intelligent material transfer vehicle is considered, tasks in the work area may be idle due to waiting for the intelligent material transfer vehicle, resulting in a delay in task completion time.

In S404, the execution order of multiple reaction tasks corresponding to the at least one experimental plan is optimized based on the optimization target and the constraint conditions, and an initial scheduling strategy is generated. The execution sequence of reaction tasks can be optimized through the method described in Figure 2 to generate an initial scheduling strategy.

In S406, the experimental scheduling strategy is generated based on the initial scheduling strategy and the map information in a stepwise and incremental manner combined with the trajectory information of the intelligent material transfer vehicle.

In one embodiment, for example, the execution order of multiple reaction tasks can be extracted from the initial scheduling policy; multiple regions can be extracted from the map information; and each of the multiple regions can be extracted one by one. Add the path information of the intelligent material transfer vehicle; optimize the path information of the intelligent material transfer vehicle in each area to generate an optimized path; update the initial scheduling strategy according to the optimized path to generate the experimental schedule process strategy.

For any two tasks t _ij , t _i′j′ that may be transported by intelligent material transfer vehicles, since t _ij , t _i′j′ may be arranged in different work areas, it can be made:

s _ij ≥e _i′j′ +d _ww′ -M ₃ ×y _iji′j′ -M ₄ ×(2-a _ijc - _i′j′c )(13)

s _i′j′ ≥e _ij +d _ww′ -M ₃ ×(1-y _iji′j′ )

-M ₄ ×(2-o _ijc - _i′j′c ) (14)

Among them, M ₃ and M ₄ are very large constants, which can be taken as 10 ⁶ in practice.

Type 9 and Type 10 are very similar in form, but the tasks in the same work area are limited within a certain range, but the tasks in any two different work areas may be arranged to be executed one after another, thus being used by the intelligent material transfer vehicle. transportation. Therefore, the complexity introduced by equations 13 and 14 will be much greater than that of equations 9 and 10.

Direct solution after the introduction of intelligent material transfer vehicles will greatly increase the solution time of the algorithm. After the algorithm obtains a solution based on the current situation of the laboratory, the actual situation of the laboratory may have changed significantly, and the solution of the algorithm cannot be applied to actual laboratory scheduling.

In this application, this complex problem is solved in two steps.

Let’s ignore the problem of intelligent material transfer vehicles and solve the laboratory scheduling algorithm.

Repeat the following process:

The tasks corresponding to the obtained solution are arranged in order of start and end time: The corresponding workspace is/>

Add constraints to the model in 1 in order of regions

Try to find new solutions.

If there is no feasible solution and no solution that meets the requirements has been obtained before, replace equation 15 with

where d ^* is a variable and will Add optimization goals. Since d ^* =0 must be a solution that satisfies the constraints. This problem must have an optimal solution. Find the corresponding /> in the optimal solution tasks, eliminate problems with t _i and its subsequent tasks (that is, the intelligent material transfer vehicle does not transport the materials of the experiment in this problem, but will be transported in the next round. In actual operations, it can also be carried out by human operators. complete the job).

If there is a feasible solution, assuming the latest completion time obj _p (12) corresponding to the feasible solution, then add constraints to the optimization objective

obj _p ＞minimize∑ _i Z _i (17)

Try to solve again. If a feasible solution is obtained, repeat the operation of (a). If there is no feasible solution, then the current solution is the optimal solution.

Using this algorithm greatly reduces the complexity of the solution. Compared with equations 13 and 14, equation 15 avoids using the double big M method, and the number of equations is reduced from O(n ² ) to O(n), n is The number of tasks.

The optimization method in this application innovatively proposes starting from only considering laboratory tasks and not material transportation, and gradually adding material transportation constraints to the model. Since there are no material transportation constraints at the beginning, there are no constraints between work areas. The distance is considered to be 0. When the distance between partial workspaces is added, the process of solving Equation 17 will gradually transform a problem that only considers scheduling, not paths, into a problem that considers both scheduling and paths, driving the model To find a better path to iterate over the current solution. Until the remaining solution, even if other paths are considered to be time-consuming, will not make the solution better.

Those skilled in the art can understand that all or part of the steps for implementing the above-described embodiments are implemented as computer programs executed by a CPU. When the computer program is executed by the CPU, the above-mentioned functions defined by the above-mentioned method provided by the present disclosure are performed. The program can be stored in a computer-readable storage medium, which can be a read-only memory, a magnetic disk or an optical disk.

Furthermore, it should be noted that the above-mentioned drawings are only schematic illustrations of processes included in the methods according to the exemplary embodiments of the present disclosure, and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal sequence of these processes. In addition, it is also easy to understand that these processes may be executed synchronously or asynchronously in multiple modules, for example.

The following are device embodiments of the present disclosure, which can be used to perform method embodiments of the present disclosure. For details not disclosed in the device embodiments of the disclosure, please refer to the method embodiments of the disclosure.

FIG. 7 is a block diagram of an automatic scheduling processing device for an experiment plan according to an exemplary embodiment. As shown in Figure 7, the automatic scheduling processing device 70 of the experimental plan includes: an information module 702, a constraint module 704, a target module 706, a scheduling module 708, and an execution module 710.

The information module 702 is used to obtain experimental information corresponding to at least one experimental plan to be processed, and the experimental information includes multiple reaction tasks; the information module 702 is also used to obtain the experimental flow chart corresponding to the at least one experimental plan to be processed. ; Obtain multiple reaction tasks corresponding to at least one experimental flow chart; Obtain task information corresponding to the multiple reaction tasks; Generate at least one experimental information through the experimental flow chart, reaction tasks, and task information corresponding to the at least one experimental plan.

The constraint module 704 is used to determine constraint conditions for its corresponding experimental plan based on the experimental information; the constraint module 704 is also used to obtain the execution subject sets of multiple reaction tasks corresponding to the experimental plan from the experimental information and combine to set the constraint conditions; The reaction times of multiple reaction tasks corresponding to the experimental plan are obtained from the experimental information and constraint conditions are set; the reaction sequences of the multiple reaction tasks corresponding to the experimental plan are obtained from the experimental information and constraint conditions are set.

The goal module 706 is used to determine the optimization goal of the at least one experimental plan; the goal module 706 is also used to determine the end time constraints of the at least one experimental plan; and set experiments for each experimental plan in the at least one experimental plan. Weight; determine that the optimization objective of the at least one experimental plan is to minimize the completion time.

The scheduling module 708 is used to optimize the execution sequence of multiple reaction tasks corresponding to the at least one experimental plan based on the optimization goal and the constraint conditions, and generate an experimental scheduling strategy; the scheduling module 708 is also used to use the mixing An integer linear programming algorithm optimizes the execution sequence of multiple reaction tasks corresponding to the at least one experimental plan based on the optimization objective and the constraint conditions; and/or a constraint programming algorithm based on the optimization objective and the constraint conditions Optimize the execution sequence of multiple reaction tasks corresponding to the at least one experimental plan.

The execution module 710 is configured to automatically call resources in the intelligent laboratory based on the experiment scheduling policy to execute the at least one experiment plan to generate experimental results.

According to the automatic scheduling processing device of the experimental plan of the present disclosure, the experimental information corresponding to at least one experimental plan to be processed is obtained, and the experimental information includes a plurality of reaction tasks; and the constraint conditions are determined for the corresponding experimental plan according to the experimental information; Determine the optimization goal of the at least one experimental plan; optimize the execution sequence of multiple reaction tasks corresponding to the at least one experimental plan based on the optimization goal and the constraint conditions, and generate an experiment scheduling strategy; based on the experiment The scheduling strategy automatically calls up resources in the intelligent laboratory to execute the at least one experiment plan to generate experimental results. It can conduct flexible automated scheduling of chemical experiments that combines humans and machines, reduce the operating costs of the automated laboratory, and improve Work efficiency and ensure the accurate execution of experimental plans.

FIG. 8 is a block diagram of an electronic device according to an exemplary embodiment.

An electronic device 800 according to this embodiment of the present disclosure is described below with reference to FIG. 8 . The electronic device 800 shown in FIG. 8 is only an example and should not bring any limitations to the functions and usage scope of the embodiments of the present disclosure.

As shown in Figure 8, electronic device 800 is embodied in the form of a general computing device. The components of the electronic device 800 may include, but are not limited to: at least one processing unit 810, at least one storage unit 820, a bus 830 connecting different system components (including the storage unit 820 and the processing unit 810), a display unit 840, and the like.

Wherein, the storage unit stores program code, and the program code can be executed by the processing unit 810, so that the processing unit 810 performs the steps described in this specification according to various exemplary embodiments of the present disclosure. For example, the processing unit 810 can perform the steps shown in Figure 2, Figure 3, and Figure 4.

The storage unit 820 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 8201 and/or a cache storage unit 8202, and may further include a read-only storage unit (ROM) 8203.

The storage unit 820 may also include a program/utility 8204 having a set of (at least one) program modules 8205 including, but not limited to: an operating system, one or more applications, other program modules, and programs. Data, each of these examples or some combination may include an implementation of a network environment.

Bus 830 may be a local area representing one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, a graphics acceleration port, a processing unit, or using any of a variety of bus structures. bus.

The electronic device 800 may also communicate with one or more external devices 800' (e.g., a keyboard, a pointing device, a Bluetooth device, etc.) so that the user can communicate with the device that the electronic device 800 interacts with, and/or the electronic device 800 can communicate with a Any device (such as a router, modem, etc.) with which multiple other computing devices communicate. This communication may occur through input/output (I/O) interface 850. Furthermore, the electronic device 800 may also communicate with one or more networks (eg, a local area network (LAN), a wide area network (WAN), and/or a public network, such as the Internet) through a network adapter 860. Network adapter 860 may communicate with other modules of electronic device 800 via bus 830. It should be understood that, although not shown in the figures, other hardware and/or software modules may be used in conjunction with electronic device 800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives And data backup storage system, etc.

Through the above description of the embodiments, those skilled in the art can easily understand that the example embodiments described here can be implemented by software, or can be implemented by software combined with necessary hardware. Therefore, as shown in Figure 9, the technical solution according to the embodiment of the present disclosure can be embodied in the form of a software product. The software product can be stored in a non-volatile storage medium (which can be a CD-ROM, U disk, mobile hard disk etc.) or on a network, including several instructions to cause a computing device (which may be a personal computer, a server, a network device, etc.) to execute the above method according to an embodiment of the present disclosure.

The software product may take the form of any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: electrical connection with one or more conductors, portable disk, hard disk, random access memory (RAM), read only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.

The computer-readable storage medium may include a data signal propagated in baseband or as part of a carrier wave carrying readable program code therein. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A readable storage medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transport the program for use by or in connection with an instruction execution system, apparatus, or device. Program code contained on a readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

Program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., as well as conventional procedures programming language - such as "C" or a similar programming language. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server execute on. In situations involving remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device, such as provided by an Internet service. (business comes via Internet connection).

The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by a device, the computer-readable medium realizes the following functions: obtaining experimental information corresponding to at least one experimental plan to be processed, The experimental information includes a plurality of reaction tasks; determines constraint conditions for its corresponding experimental plan according to the experimental information; determines the optimization goal of the at least one experimental plan; and determines the at least one experimental plan based on the optimization goal and the constraint conditions. The execution order of multiple reaction tasks corresponding to the experimental plan is optimized to generate an experimental scheduling strategy; resources in the intelligent laboratory are automatically called based on the experimental scheduling strategy to execute the at least one experimental plan to generate experimental results.

Those skilled in the art can understand that the above-mentioned modules can be distributed in devices according to the description of the embodiments, or can be modified accordingly in one or more devices that are only different from this embodiment. The modules of the above embodiments can be combined into one module, or further divided into multiple sub-modules.

Through the description of the above embodiments, those skilled in the art can easily understand that the example embodiments described here can be implemented by software, or can be implemented by software combined with necessary hardware. Therefore, the technical solution according to the embodiment of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, U disk, mobile hard disk, etc.) or on the network , including several instructions to cause a computing device (which may be a personal computer, a server, a mobile terminal, a network device, etc.) to execute a method according to an embodiment of the present disclosure.

The exemplary embodiments of the present disclosure have been specifically shown and described above. It is to be understood that the present disclosure is not limited to the details of construction, arrangements, or implementations described herein; on the contrary, the present disclosure is intended to cover various modifications and equivalent arrangements included within the scope of the appended claims.

Claims (13)

1. An automatic scheduling method for an experimental plan, comprising:

acquiring experimental information corresponding to at least one experimental plan to be processed, wherein the experimental information comprises a plurality of reaction tasks;

determining constraint conditions for the corresponding experiment plans according to the experiment information;

determining an optimization objective of the at least one experimental plan;

optimizing the execution sequence of a plurality of reaction tasks corresponding to the at least one experiment plan based on the optimization target and the constraint condition to generate an experiment scheduling strategy;

and automatically invoking resources in an intelligent laboratory based on the experiment scheduling policy to execute the at least one experiment plan to generate an experiment result.

2. The method of claim 1, wherein obtaining experimental information corresponding to at least one experimental plan to be processed comprises:

acquiring an experimental flow chart corresponding to the at least one experimental plan to be processed;

Acquiring a plurality of reaction tasks corresponding to at least one experimental flow chart;

task information corresponding to a plurality of reaction tasks is obtained;

and generating at least one piece of experimental information through the experimental flow chart, the reaction task and the task information corresponding to the at least one experimental plan.

3. The method of claim 1, wherein determining constraints for its corresponding experimental plan based on experimental information comprises:

acquiring an execution main body set of a plurality of reaction tasks corresponding to an experiment plan from the experiment information and setting constraint conditions;

obtaining reaction time of a plurality of reaction tasks corresponding to an experiment plan from the experiment information and setting constraint conditions;

and obtaining the reaction sequence of a plurality of reaction tasks corresponding to the experiment plan from the experiment information and setting constraint conditions.

4. The method of claim 3, wherein obtaining the execution subject set of the plurality of reaction tasks corresponding to the experiment plan from the experiment information and setting the constraint condition comprises:

acquiring material properties and reaction properties of a reaction task from the experimental information;

determining an execution main body of the reaction task according to the material property and the reaction property;

Generating the execution subject set corresponding to the experiment plan according to the execution subjects of the plurality of reaction tasks;

setting execution constraints for each execution body in the set of execution bodies.

5. The method of claim 3, wherein obtaining reaction times of a plurality of reaction tasks corresponding to an experiment plan from the experiment information and setting constraints comprises:

setting fixed reaction time and fixed time constraint conditions for the reaction task according to an execution main body of the reaction task;

and setting a specified reaction time and an elastic time constraint condition for the reaction task according to the execution main body of the reaction task.

6. The method of claim 3, wherein obtaining the reaction sequence of the plurality of reaction tasks corresponding to the experiment plan from the experiment information and setting the constraint condition comprises:

extracting an experimental flow chart from the experimental information;

obtaining the reaction sequence of the plurality of reaction tasks according to the experimental flow chart;

and setting sequence time constraint conditions for the plurality of reaction tasks according to the reaction sequence.

7. The method of claim 1, wherein determining the optimization objective of the at least one experimental plan comprises:

Determining an end time constraint of the at least one experimental plan;

setting an experimental weight for each of the at least one experimental plan;

an optimization objective of the at least one experimental plan is determined to minimize the completion time.

8. The method of claim 1, wherein optimizing the order of execution of the plurality of reaction tasks corresponding to the at least one experimental plan based on the optimization objective and the constraint condition, generating an experimental scheduling policy, comprises:

optimizing the execution sequence of a plurality of reaction tasks corresponding to the at least one experimental plan based on the optimization target and the constraint condition through a mixed integer linear programming algorithm; and/or

And optimizing the execution sequence of a plurality of reaction tasks corresponding to the at least one experiment plan based on the optimization target and the constraint condition through a constraint planning algorithm.

9. The method of claim 1, wherein the subject of execution of the experiment plan comprises an intelligent material transfer cart;

optimizing the execution sequence of a plurality of reaction tasks corresponding to the at least one experiment plan based on the optimization target and the constraint condition, and generating an experiment scheduling strategy, wherein the method comprises the following steps:

Acquiring map information of an intelligent laboratory;

optimizing the execution sequence of a plurality of reaction tasks corresponding to the at least one experiment plan based on the optimization target and the constraint condition, and generating an initial scheduling strategy;

and generating the experimental scheduling strategy by combining the track information of the intelligent material transfer vehicle in a gradual increasing mode based on the initial scheduling strategy and the map information.

10. The method of claim 9, wherein generating the experimental scheduling strategy based on the initial scheduling strategy and the map information in a stepwise increasing manner in combination with trajectory information of an intelligent material transfer vehicle comprises:

extracting the execution sequence of a plurality of reaction tasks from the initial scheduling strategy;

extracting a plurality of areas from the map information;

adding path information of the intelligent material transfer vehicle to each of the plurality of areas one by one;

optimizing the path information of the intelligent material transfer vehicle in each area to generate an optimized path;

and updating the initial scheduling strategy according to the optimized path to generate the experimental scheduling strategy.

11. An automated scheduling apparatus for an experimental plan, comprising:

The information module is used for acquiring experimental information corresponding to at least one experimental plan to be processed, wherein the experimental information comprises a plurality of reaction tasks;

the constraint module is used for determining constraint conditions for the corresponding experiment plans according to the experiment information;

a goal module for determining an optimization goal of the at least one experimental plan;

the scheduling module is used for optimizing the execution sequence of a plurality of reaction tasks corresponding to the at least one experiment plan based on the optimization target and the constraint condition, and generating an experiment scheduling strategy;

and the execution module is used for automatically calling resources in the intelligent laboratory based on the experiment scheduling strategy to execute the at least one experiment plan to generate an experiment result.

12. An electronic device, comprising:

one or more processors;

a storage means for storing one or more programs;

when executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1-10.

13. A computer readable medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any of claims 1-10.