An experimental procedure intelligent processing method and system
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- NANJING EUROSMART INTELLIGENT TECH RES INST CO LTD
- Filing Date
- 2021-05-13
- Publication Date
- 2026-06-26
AI Technical Summary
Existing technologies are insufficient to effectively manage the orderly and unpredictable needs of multiple experimental operations, resulting in inefficient automated experimental processes that cannot meet the management requirements of continuous or sudden experiments.
An intelligent experimental process management method is adopted, which optimizes resource matching and step sequencing based on the influence factor model through data entry, data update, data analysis and instruction output, thereby realizing intelligent management of the experimental process.
It improved experimental efficiency, ensured the orderly execution of procedures and the efficient use of resources, met the continuous and emergency management needs of multiple sets of experiments, and reduced time costs.
Smart Images
Figure QLYQS_7 
Figure QLYQS_8
Abstract
Description
Technical Field
[0001] This invention belongs to the technical field of experimental management, and in particular relates to an intelligent processing method and system for experimental procedures. Background Technology
[0002] Whether it's a biological experiment, a chemical experiment, a materials experiment, or any other experiment, the actual operation consists of at least one step. The steps involved in different experimental projects vary, and the instruments and time required for each step also differ. Sometimes, the order of adjacent steps cannot be reversed.
[0003] However, due to the widespread use of automated experiments, computers struggle to manage multiple experimental operations and each step of any experimental operation in an orderly manner. They can only perform single, repetitive operations according to the pre-entered experimental procedures, which cannot meet the needs of continuous or sudden experimental management. Summary of the Invention
[0004] To address the technical problems existing in the background art described above, the present invention provides an intelligent processing method and system for experimental procedures.
[0005] This invention adopts the following technical solution: an intelligent processing method for experimental procedures, the method comprising:
[0006] Data entry: Provide the required set of experiments, each set of experiments in the set including at least one step; define all unexecuted steps in the set of experiments as a set of steps; store the types and corresponding quantities of configured resources in the original database;
[0007] Data update: When executing a step that is in the first order in the step set, the corresponding step in the step set is removed to obtain the updated step set. At the same time, the types and corresponding quantities of resources in the original database are updated to obtain the available resource set.
[0008] Data analysis: Based on the impact factor model, determine whether the set of available resources meets the resource requirements for executing one or more steps in the set of update steps; output instructions based on the analysis results;
[0009] Instruction output: If the conditions are not met, the resource set and the updated step set can be maintained in their current state, and the corresponding steps can be executed until they are finished before data updates and data analysis are performed; if the conditions are met, data updates and data analysis are performed; this process is repeated until the step set is empty.
[0010] If one or more sets of experiments are suddenly inserted, the experiment set is updated first, and the corresponding set of steps is updated. The updated set of steps includes the previously incomplete steps and the newly added steps. Then, data updates and data analysis are performed.
[0011] In a further embodiment, the time period for executing the current step is used as a unit, and the start of the execution step is defined as the first time node, and the end of the execution step is defined as the second time node;
[0012] The set of steps and the set of available resources are updated twice, at the first time node and the second time node, respectively.
[0013] In a further embodiment, the resources are defined as the hardware devices and software processes required for the step;
[0014] The set of available resources includes resources that are available for use, and the number of resources in each available state.
[0015] In a further embodiment, an experiment set C is defined, C = {c1, c2, ..., c...} n}, where n is an integer, representing the number of experiments;
[0016] Define a set of steps D, D = {d} t1 d t2 , ...,d tj}, where j is an integer, representing that j steps have not yet been executed at time t; the influencing factors for each step are D(N). tr ,R);
[0017] Define a set of available resources S, S = {s} t1 s t2 , ..., s tr}, where N tr This indicates the type and quantity of resources required for the execution step. R is a predefined function (input into the system in advance) representing the execution conditions, and r is the resource number.
[0018] In a further embodiment, the establishment of the influence factor model is as follows:
[0019] In the set of execution steps D, f(N) tr The steps where R) = 1;
[0020] Where R=1 indicates that the execution conditions for the steps in the set of steps D are ready; conversely, R=0 indicates that the execution conditions for the steps in the set of steps D are lacking.
[0021] In a further embodiment, an experimental sequence is created by effectively sorting the first step of each group of experiments within the experimental set using an experimental priority sorting method, wherein the experimental priority sorting method includes:
[0022] The first step of the nth group of experiments is defined as being based on one or more steps of other experimental groups, meaning that the nth group of experiments partially covers the experiments of other groups.
[0023] Then, the absolute contribution of experimental coverage Where M t This represents the number of other experimental steps covered by each group of experiments, and max{M} is the maximum number of other experimental steps covered in the experimental set.
[0024] The impact of resources on priority Where N t This represents the number of resources used in each group of experiments; max{N} is the number of resources used in the group of experiments that uses the most resources in the experimental set.
[0025] The impact of time on priority Where T 1t T represents the resource runtime used by each experiment, and max{T1} represents the longest resource runtime in the experiment set; 2t This represents the resource waiting time used in each group of experiments, and max{T2} represents the longest resource waiting time in the experimental set.
[0026] Therefore, the experiment preferentially selects value I. t =β1·I1+β2·I2+β3·I3; where β1, β2, and β3 are the weights corresponding to I1, I2, and I3, respectively, and β1, β2, and β3 are adjusted according to experimental requirements.
[0027] In a further embodiment, β1+β2+β3=1.
[0028] In a further embodiment, the sorting method in the first order of the step set is as follows:
[0029] Step coverage of absolute contribution Where M t ' represents the number of other steps covered by each set of steps, and max{M'} is the maximum number of other steps covered in the experimental set;
[0030] The impact of resources on priority Where N t ' represents the number of resource types used in each step; max{N'} is the number of resources in the experiment set that uses the most resources.
[0031] The impact of time on priority Where T 1t ' represents the resource runtime used in each experiment, and max{T1'} represents the longest resource runtime in the experiment set; T 2t' represents the resource waiting time used in each group of experiments, and max{T2'} represents the longest resource waiting time in the experimental set;
[0032] Therefore, the experiment preferentially selects value I. t '=I t ·[β4·I4+β5·I5+β6·I6]; where β4, β5, and β6 are the weights corresponding to I4, I5, and I6, respectively, and β4, β5, and β6 are adjusted according to experimental requirements.
[0033] An intelligent experimental process processing system is provided to implement the intelligent experimental process processing method described above.
[0034] In a further embodiment, it includes:
[0035] The data entry module is configured to store the required set of experiments, each set of experiments in which at least one step is included; store the set of all steps that have not yet been executed; and the original database, which includes: the types of configured resources and the corresponding quantities of resources.
[0036] The data update module is configured to, when executing a step that is in the first order in the step set, remove the corresponding step from the step set to obtain an updated step set, and at the same time update the types and corresponding quantities of resources in the original database to obtain an available resource set.
[0037] The data analysis module is configured to determine, based on an impact factor model, whether the available resource set meets the resource requirements for executing one or more steps in the set of update steps; and output instructions based on the analysis results.
[0038] An execution module is configured to call the corresponding execution module based on the analysis results.
[0039] In a further embodiment, it includes:
[0040] The analysis results include: if the available resource set meets the resource requirements of one or more steps in the updated step set, then the data update module and the data analysis module are invoked;
[0041] If the available resource set does not meet the resource requirements of any step in the update step set, wait for the corresponding step to finish executing before calling the data update module and data analysis module.
[0042] In a further embodiment, the resources are defined as the hardware devices and software processes required for the step;
[0043] The set of available resources includes resources that are available for use, and the number of resources in each available state.
[0044] In a further embodiment, an experiment set C is defined, C = {c1, c2, ..., c...} n}, where n is an integer, representing the number of experiments;
[0045] Define a set of steps D, D = {d} t1 d t2 , ..., d tj}, where j is an integer, representing that j steps have not yet been executed at time t; the influencing factors for each step are D(N). tr ,R);
[0046] Define a set of available resources S, S = {s} t1 s t2 , ..., s tr}, where N tr This indicates the types and quantities of resources required to execute the step, R is a given predefined function representing the execution conditions, and r is the resource number.
[0047] In a further embodiment, the establishment of the influence factor model is as follows:
[0048] In the set of execution steps D, f(N) tr The steps where R) = 1;
[0049] Where R=1 indicates that the execution conditions for the steps in the set of steps D are ready; conversely, R=0 indicates that the execution conditions for the steps in the set of steps D are lacking.
[0050] In a further embodiment, an experimental sequence is created by effectively sorting the first step of each group of experiments within the experimental set using an experimental priority sorting method, wherein the experimental priority sorting method includes:
[0051] The first step of the nth group of experiments is defined as being based on one or more steps of other experimental groups, meaning that the nth group of experiments partially covers the experiments of other groups.
[0052] Then, the absolute contribution of experimental coverage Where M t This represents the number of other experimental steps covered by each group of experiments, and max{M} is the maximum number of other experimental steps covered in the experimental set.
[0053] The impact of resources on priority Where N tThis represents the number of resources used in each group of experiments; max{N} is the number of resources used in the group of experiments that uses the most resources in the experimental set.
[0054] The impact of time on priority Where T 1t T represents the resource runtime used in each experiment set, and max{T1} represents the longest resource runtime used in the experiment set; T 2t This represents the resource waiting time used in each group of experiments, and max{T2} represents the longest resource waiting time in the experimental set.
[0055] Therefore, the experiment preferentially selects value I. t =β1·I1+β2·I2+β3·I3; where β1, β2, and β3 are the weights corresponding to I1, I2, and I3, respectively, and β1, β2, and β3 are adjusted according to experimental requirements.
[0056] In a further embodiment, β1+β2+β3=1.
[0057] In a further embodiment, the sorting method in the first order of the step set is as follows:
[0058] Step coverage of absolute contribution Where M t ' represents the number of other steps covered by each set of steps, and max{M'} is the maximum number of other steps covered in the experimental set;
[0059] The impact of resources on priority Where N t ' represents the number of resource types used in each step; max{N'} is the number of resources in the experiment group that uses the most resources in the experiment set;
[0060] The impact of time on priority Where T 1t ' represents the resource runtime used in each experiment, and max{T1'} represents the longest resource runtime in the experiment set; T 2t ' represents the resource waiting time used in each group of experiments, and max{T2'} represents the longest resource waiting time in the experimental set;
[0061] Therefore, the experiment preferentially selects value I. t '=I t ·[β4·I4+β5·I5+β6·I6]; where β4, β5, and β6 are the weights corresponding to I4, I5, and I6, respectively, and β4, β5, and β6 are adjusted according to experimental requirements.
[0062] The beneficial effects of this invention are as follows: The experimental management process constructed by this invention is based on the matching relationship between the unexecuted steps and the resources required for the executed steps, which are updated in real time, and the currently available resources, thus optimizing management in terms of time. It analyzes from multiple dimensions to determine the optimal next executable step, ensuring that the executed steps conform to the required sequence of the experiment. This improves upon the problem of single, repetitive operations in existing automated experimental processes, while significantly increasing experimental efficiency. Detailed Implementation
[0063] In the following description, numerous specific details are set forth in order to provide a more thorough understanding of the invention. However, it will be apparent to those skilled in the art that the invention can be practiced without one or more of these details. In other instances, certain technical features well-known in the art have not been described in order to avoid obscuring the invention.
[0064] In the existing technology, due to the widespread use of automated experiments, it is difficult for computers to manage multiple experimental operations and each step of any experimental operation in an orderly manner. They can only perform single and repetitive operations according to the pre-input experimental procedure, which cannot meet the needs of continuous or sudden experimental management. Moreover, when multiple sets of experiments are carried out, the efficiency of using the previous single and repetitive operations is extremely low, which cannot meet market or experimental needs and instead increases time costs.
[0065] The applicant provides an intelligent processing method for experimental procedures, including:
[0066] Data entry: Provide the required set of experiments, each set of experiments including at least one step; define all unexecuted steps within the set of experiments as a step set; store the types and corresponding quantities of configured resources in the original database; the resources are defined as the hardware devices and software processes required for the steps; specifically, hardware devices are the equipment, tools, or instruments used when executing the steps. Software processes refer to the behaviors of computer computing power, algorithms, etc., dependent on the medium.
[0067] Data Update: When executing a step that is in the first priority of the step set, the corresponding step is removed from the step set to obtain an updated step set. Simultaneously, the types and quantities of resources in the original database are updated to obtain a set of available resources. This set of available resources includes resources that are available and their corresponding quantities. Only resources within the available resource set are in an idle state, meaning they can be used for other necessary steps at the current moment.
[0068] Data analysis: Based on the impact factor model, determine whether the set of available resources meets the resource requirements for executing one or more steps in the set of update steps; output instructions based on the analysis results;
[0069] Output instructions: If the conditions are not met, the available resource set and the updated step set remain unchanged, waiting for the corresponding step to finish execution before performing data updates and data analysis; if the conditions are met, data updates and data analysis are performed; this process is repeated until every step in the experimental set is completed. Specifically, taking the time period of executing the current step as a unit, the time of starting the step is defined as the first time node, and the time of ending the step is defined as the second time node; then the step set and the available resource set are updated twice, at the first time node and the second time node respectively.
[0070] To facilitate understanding, let's take a common experiment as an example: There are three sets of experiments. The first set of experiments includes the following steps: preparing raw materials, ultrasonic dispersion, water bath heating, and filtration; the second set of experiments includes the following steps: preparing raw materials, water bath heating, and drying; and the third set of experiments includes: preparing raw materials, water bath stirring, and filtration separation.
[0071] In this embodiment, the experimental set includes the first group of experiments, the second group of experiments, and the third group of experiments. Before execution, the set of steps includes: in the first group of experiments: preparing raw materials, ultrasonic dispersion, water bath heating, and filtration; in the second group of experiments: preparing raw materials, water bath heating, and drying; and in the third group of experiments: preparing raw materials, water bath stirring, and filtration separation. The order of each step in the first, second, and third groups of experiments is preset. Simultaneously, the models and corresponding quantities of the beakers, dispersers, water baths, and drying ovens configured at this time are recorded and stored in the original database.
[0072] Experimental sequences are created by prioritizing experiments. The first step in the first group of experiments, raw material preparation, is executed. While this step is being performed, the system removes the raw material preparation steps from the first group of experiments. The updated step set then includes: ultrasonic dispersion, water bath heating, and filtration in the first group; raw material preparation, water bath heating, and drying in the second group; and raw material preparation, water bath stirring, and filtration separation in the third group. Simultaneously, the categories and quantities of instruments required for raw material preparation, such as beakers, keys, and balances, are temporarily deleted from the original database, and the database is updated. After this, the resources in the database are matched with the resources required for the updated step set. Based on the influence factor model, steps executable with available resources are selected. It is found that all resources for raw material preparation are occupied, so other steps cannot be executed. Therefore, the database is updated after the raw material preparation for the first group of experiments is completed, and the resources used for raw material preparation are added to the database. Then, the resources in the database are matched with the resources required for the updated set of steps. Based on the impact factor model, steps that can be executed based on existing resources are selected. The following steps can be executed: The first priority step in the first group of experiments: ultrasonic dispersion; the first priority step in the second group of experiments: raw material preparation; or the first priority step in the third group of experiments: raw material preparation. One or two of the above steps are selected as first priority based on the impact factor model and operated on. When executing this step, the system can remove the corresponding step from the set of steps. The updated set of steps then includes: water bath heating and filtration in the first group of experiments; water bath heating and drying in the second group of experiments; and raw material preparation, water bath stirring, and filtration separation in the third group of experiments. Simultaneously, the categories and quantities of dispersers, beakers, keys, balances, etc., in the original database are temporarily deleted, and the database is updated. This process is repeated until each step is completed.
[0073] When the experiment is more complex, or when the experiment is in other fields such as biology or materials, the same processing method is used: data entry, data update, data analysis, and instruction output.
[0074] To facilitate better judgment, an impact factor model is established in this embodiment. First, define the experimental set C, C = {c1, c2, ..., c...} n}, where n is an integer, representing the number of experiments;
[0075] Define a set of steps D, D = {d} t1 d t2 , ..., d tj}, where j is an integer, representing that j steps have not yet been executed at time t; the influencing factors for each step are D(N). tr,R); Define a set of available resources S, S={s t1 s t2 , ..., s tr The set S is updated based on the start and end times of the steps. Where N... tr This represents the types and quantities of resources required for the execution step, where R is a given predetermined function representing the execution conditions, and r is the resource number. In this embodiment, the execution conditions refer to whether the required resources, raw materials, or other components are ready. This is represented by R=1 indicating that the execution conditions for a step that has not yet been executed are ready; conversely, R=0 indicates that the execution conditions for a step that has not yet been executed are not ready.
[0076] To ensure the feasibility and orderly execution of the steps considering factors such as time, resources, and conditions, this embodiment constructs an impact factor model:
[0077] In the set of execution steps D, f(N) tr The steps where R) = 1;
[0078] Where R=1 indicates that the execution conditions for the steps in the set of steps D are ready; conversely, R=0 indicates that the execution conditions for the steps in the set of steps D are lacking.
[0079] A step can only be executed if the types and quantities of resources required for its execution are within the scope of the current step and are ready. If none of these conditions are met, another step should be selected for execution, or the process should wait.
[0080] In this embodiment, an experimental sequence is created by effectively sorting the first step of each group of experiments within the experimental set using an experimental priority sorting method. The experimental priority sorting method includes:
[0081] The first step of the nth group of experiments is defined as being based on one or more steps of other experimental groups, meaning that the nth group of experiments partially covers the experiments of other groups.
[0082] Then, the absolute contribution of experimental coverage Where M t This represents the number of other experimental steps covered by each group of experiments, and max{M} is the maximum number of other experimental steps covered in the experimental set.
[0083] The impact of resources on priority Where N t This represents the number of resources used in each group of experiments; max{N} is the number of resources used in the group of experiments that uses the most resources in the experimental set.
[0084] The impact of time on priority Where T 1t T represents the resource runtime used in each experiment set, and max{T1} represents the longest resource runtime used in the experiment set; T 2t This represents the resource waiting time used in each group of experiments, and max{T2} represents the longest resource waiting time in the experimental set.
[0085] Therefore, the experiment preferentially selects value I. t =β1·I1+β2·I2+β3·I3; where β1, β2, and β3 are the weights corresponding to I1, I2, and I3, respectively, and β1, β2, and β3 are adjusted according to experimental requirements. β1+β2+β3=1.
[0086] In a further embodiment, the sorting method for the first order in the step set is as follows: Step coverage absolute contribution. Where M t ' represents the number of other steps covered by each set of steps, and max{M'} is the maximum number of other steps covered in the experimental set;
[0087] The impact of resources on priority Where N t ' represents the number of resource types used in each step; max{N'} is the number of resources in the experiment group that uses the most resources in the experiment set;
[0088] The impact of time on priority Where T 1t ' represents the resource runtime used in each experiment, and max{T1'} represents the longest resource runtime in the experiment set; T 2t ' represents the resource waiting time used in each group of experiments, and max{T2'} represents the longest resource waiting time in the experimental set;
[0089] Therefore, the experiment preferentially selects value I. t '=I t ·[β4·I4+β5·I5+β6·I6]; where β4, β5, and β6 are the weights corresponding to I4, I5, and I6, respectively, and β4, β5, and β6 are adjusted according to experimental requirements. β4+β5+β6=1.
[0090] In a further embodiment, a software-based experimental workflow management system includes:
[0091] The data entry module is configured to store the required set of experiments, each set of experiments in which at least one step is included; store the set of all steps that have not yet been executed; and store the original database, which includes: the types and corresponding quantities of configured resources.
[0092] The data update module is configured to, when executing a step that is in the first order in the step set, remove the corresponding step from the step set to obtain an updated step set, and at the same time update the types and corresponding quantities of resources in the original database to obtain an available resource set.
[0093] The data analysis module is configured to determine, based on an impact factor model, whether the available resource set meets the resource requirements for executing one or more steps in the set of update steps; and output instructions based on the analysis results.
[0094] An execution module is configured to call the corresponding execution module based on the analysis results.
[0095] In a further embodiment, the analysis results include: if the available resource set meets the resource requirements of one or more steps in the updated step set, then the data update module and the data analysis module are invoked; if the available resource set does not meet the resource requirements of any step in the updated step set, the execution of the corresponding step is waited for to finish before the execution of the data update module and the data analysis module are invoked.
[0096] To facilitate better judgment, an impact factor model is established in this embodiment. First, define the experimental set C, C = {c1, c2, ..., c...} n}, where n is an integer representing n sets of experiments; define a set of steps D, D = {d t1 d t2 , ..., d tj}, where j is an integer, representing that j steps have not yet been executed at time t; the influencing factors for each step are D(N). tr ,R); Define a set of available resources S, S={s t1 s t2 , ..., s tr}, where N tr This represents the types and quantities of resources required for the execution step, where R is a given predetermined function representing the execution conditions, and r is the resource number. In this embodiment, the execution conditions refer to whether the required resources, raw materials, or other components are ready. This is represented by R=1 indicating that the execution conditions for a step that has not yet been executed are ready; conversely, R=0 indicates that the execution conditions for a step that has not yet been executed are not ready.
[0097] This embodiment constructs an impact factor model: The establishment of the impact factor model:
[0098] In the set of execution steps D, f(N) tr The steps where R) = 1;
[0099] Where R=1 indicates that the execution conditions for the steps in the set of steps D are ready; conversely, R=0 indicates that the execution conditions for the steps in the set of steps D are lacking.
[0100] A step can only be executed if the types and quantities of resources required for its execution are within the scope of the current step and are ready. If none of these conditions are met, another step should be selected for execution, or the process should wait.
[0101] As described above, although the invention has been shown and described with reference to specific preferred embodiments, it should not be construed as limiting the invention itself. Various changes in form and detail may be made without departing from the spirit and scope of the invention as defined in the appended claims.
Claims
1. An intelligent processing method for experimental procedures, characterized in that, The method includes: Data entry: Provide the required set of experiments, each set of experiments in the set including at least one step; define all unexecuted steps in the set of experiments as a set of steps; store the types and corresponding quantities of configured resources in the original database; Data update: When executing a step that is in the first order in the step set, the corresponding step in the step set is removed to obtain the updated step set. At the same time, the types and corresponding quantities of resources in the original database are updated to obtain the available resource set. Data analysis: Based on the impact factor model, determine whether the set of available resources meets the resource requirements for executing one or more steps in the set of update steps; output instructions based on the analysis results; Instruction output: If the conditions are not met, the resource set and the updated step set can be maintained to maintain the status quo, waiting for the corresponding step to finish execution, and then data update and data analysis can be performed; if the conditions are met, data update and data analysis can be performed; this process is repeated until the step set is empty. Define the experiment set C, ,in n If it is an integer, it means that there is n Group experiment; Define a set of steps D, D = ,in The integer represents the condition at time t. j Several steps have not yet been executed; the influencing factors for each step are: D ( ,R ); Define a set of available resources S, S = ,in This indicates the types and quantities of resources required for the execution step, where R is a given predefined function representing the execution conditions, and r is the resource number. The impact factor model is established as follows: ; Execution steps set D Steps; in, This indicates that the execution conditions for the steps in the set of steps D are ready; otherwise, R... This indicates that the execution conditions for the steps in the set of steps D are missing.
2. The intelligent processing method for experimental procedures according to claim 1, characterized in that, Using the time period of executing the current step as a unit, the time of starting the step is defined as the first time node, and the time of ending the step is defined as the second time node; The set of steps and the set of available resources are updated twice, at the first time node and the second time node, respectively.
3. The intelligent processing method for experimental procedures according to claim 1, characterized in that, The resources are defined as the hardware devices and software processes required for the steps; The set of available resources includes resources that are available for use, and the number of resources in each available state.
4. The intelligent processing method for experimental procedures according to claim 1, characterized in that, The experiment sequence is created by effectively sorting the first step of each group of experiments within the experiment set using an experiment priority sorting method. This experiment priority sorting method includes: The first step of the nth group of experiments is defined as being based on one or more steps of other experimental groups, meaning that the nth group of experiments partially covers the experiments of other groups. Then, the absolute contribution of experimental coverage ,in This indicates the number of experimental steps in other groups that are covered by each group of experiments. This represents the maximum number of experimental steps covered in the experimental set. The impact of resources on priority = ,in This indicates the number of resources used in each group of experiments; This is the number of resources in the group of experiments that consumes the most resources in the experimental set; The impact of time on priority = + ;in This indicates the resource usage and runtime of each experiment group. This indicates the longest runtime in the experimental set that utilizes the most resources. This indicates the resource waiting time used in each group of experiments. This represents the longest resource waiting time in the experimental set; Therefore, the experiment takes priority in selecting values. In the formula They are respectively The corresponding weights Adjustments can be made based on experimental requirements.
5. The intelligent processing method for experimental procedures according to claim 1, characterized in that, The sorting method for the first position in the step set is as follows: Step coverage of absolute contribution ,in This indicates the number of other groups of steps that each group of steps covers. This represents the maximum number of steps covered in the experimental set. The impact of resources on priority ,in This indicates the number of different types of resources used in each set of steps; This is the number of resources in the group of experiments that consumes the most resources in the experimental set; The impact of time on priority = + ;in This indicates the runtime of the resources used in each experiment. This indicates the longest runtime in the experimental set that utilizes the most resources. This indicates the resource waiting time used in each group of experiments. This represents the longest resource waiting time in the experimental set; Therefore, the experiment takes priority in selecting values. In the formula They are respectively The corresponding weights Adjustments can be made based on experimental requirements.
6. An intelligent processing system for experimental procedures, characterized in that, This method is used to implement the intelligent processing method for experimental procedures as described in any one of claims 1 to 5.
7. The intelligent processing system for experimental procedures according to claim 6, characterized in that, include: A data entry module is configured to store a set of experiments, each set of experiments in which at least one step is included; Stores a set of all steps that have not yet been executed, as well as a raw database, which includes: the types of configured resources and the corresponding quantities of resources; The data update module is configured to, when executing a step that is in the first order in the step set, remove the corresponding step from the step set to obtain an updated step set, and at the same time update the types and corresponding quantities of resources in the original database to obtain an available resource set. The data analysis module is configured to determine, based on an impact factor model, whether the available resource set meets the resource requirements for executing one or more steps in the set of update steps; and output instructions based on the analysis results. An execution module is configured to call the corresponding execution module based on the analysis results.
8. The intelligent processing system for experimental procedures according to claim 7, characterized in that, include: The analysis results include: if the available resource set meets the resource requirements of one or more steps in the updated step set, then the data update module and the data analysis module are invoked; If the available resource set does not meet the resource requirements of any step in the update step set, wait for the corresponding step to finish executing before calling the data update module and data analysis module.