Assembly line experiment automatic scheduling method and system and related equipment

Abstract

The invention relates to the technical field of detection experiments, in particular to an automatic scheduling method and system for assembly line experiments and related equipment, and the method comprises the steps: randomly generating a full-permutation array as an initial population, the full-permutation array representing different detection sequences of each detection experiment; taking the initial population as a parent, performing crossover variation by introducing linkage gene probability in biology, determining a target population, and obtaining total detection duration of each individual in the target population; and taking the individual corresponding to the minimum value in the total detection duration as a target individual, and detecting each detection experiment according to the detection sequence corresponding to the target individual. According to the method, the tasks are scheduled and arranged by adopting the genetic algorithm, and the detection efficiency is optimized.

Description

Background Art

[0002] On the laboratory's assembly line testing line, by replacing hands with robotic arms, replacing legs with tracks and transmission systems, and using AI to assist the human brain, the entire testing experiment is made intelligent and automated, providing users with more automatic, smarter, more convenient, and more cost-effective laboratory automation solutions.

[0003] However, the inspection time of each workstation on the existing automated assembly line is inconsistent, and the improper inspection sequence will lead to low efficiency of the assembly line inspection experiment and fail to achieve optimal efficiency. Summary of the invention

[0004] In order to overcome the problems that inconsistent detection time of each workstation on the existing automated assembly line detection line and improper detection sequence will lead to low efficiency of assembly line detection experiments and failure to achieve optimal efficiency, the present invention provides an automatic scheduling method, system and related equipment for assembly line experiments.

[0005] In a first aspect, in order to solve the above technical problems, the present invention provides a method for automatically scheduling a pipeline experiment, comprising: Randomly generate a full permutation array as an initial population, wherein the full permutation array represents different detection orders of each detection experiment; The initial population is used as the parent generation, and crossover mutation is performed by introducing the probability of linked genes in biology to determine the target population, and the total detection time of each individual in the target population is obtained; Individuals that meet the first preset requirement in each total detection time are taken as target individuals, and each detection experiment is tested according to the detection sequence corresponding to the target individuals.

[0006] In a second aspect, the present invention provides an automatic scheduling system for pipeline experiments, comprising: An initial population generation module is used to randomly generate a full permutation array as an initial population, wherein the full permutation array represents different detection orders of various detection experiments; The target population determination module is used to determine the target population by taking the initial population as the parent generation, introducing the probability of linked genes in biology for crossover mutation, and obtaining the total detection time of each individual in the target population; The detection module is used to take the individuals that meet the first preset requirement in each detection total time as the target individuals, and detect each detection experiment according to the detection sequence corresponding to the target individuals.

[0007] In a third aspect, the present invention provides a computing device, including a memory, a processor, and a program stored in the memory and running on the processor, and when the processor executes the program, the steps of the automatic scheduling method for pipeline experiments as described above are implemented.

[0008] In a fourth aspect, the present invention provides a computer-readable storage medium, in which instructions are stored. When the instructions are executed on a terminal device, the terminal device executes the steps of a method for automatic scheduling of pipeline experiments as described above.

[0009] The beneficial effects of the present invention are: by randomly permuting the detection order of each detection experiment, generating a fully permuted array, and by introducing the probability of linked genes in biology for crossover mutation, the target population is optimized, and then the scheduling task is optimized, and finally the optimal detection order (target individual) in the target population is selected for detection, so that the detection experiment efficiency is optimized. The present application uses a genetic algorithm to schedule and arrange tasks, thereby optimizing the detection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0011] Figure 1 A schematic diagram of a flow chart of an automatic scheduling method for pipeline experiments according to an embodiment of the present invention; Figure 2 A Gantt chart of a laboratory test plan for an embodiment of the present invention; Figure 3 The present invention is a schematic diagram of the structure of an automatic scheduling system for assembly line experiments according to an embodiment of the present invention. DETAILED DESCRIPTION

[0012] The following examples are provided to further explain and supplement the present invention and do not constitute any limitation to the present invention.

[0013] The following describes an automatic scheduling method, system and related equipment for pipeline experiments according to an embodiment of the present invention in conjunction with the accompanying drawings.

[0014] like Figure 1 As shown, an embodiment of the present invention provides a method for automatically scheduling a pipeline experiment, comprising: S1. Randomly generate a full permutation array as an initial population, wherein the full permutation array represents different detection orders of each detection experiment.

[0015] S2. Take the initial population as the parent generation, introduce the probability of linked genes in biology to perform crossover mutation, determine the target population, and obtain the total detection time of each individual in the target population.

[0016] S3. The individuals that meet the first preset requirement in each total detection time are taken as target individuals, and each detection experiment is tested according to the detection sequence corresponding to the target individuals.

[0017] In this embodiment, the detection order of each detection experiment is randomly arranged to generate a fully arranged array, and the probability of linked genes in biology is introduced to perform crossover mutation to optimize the target population, thereby optimizing the scheduling task, and finally selecting the optimal detection order (target individual) in the target population for detection, so that the detection experiment efficiency is optimized. This application uses a genetic algorithm to schedule and arrange tasks to optimize the detection efficiency.

[0018] The detection experiment in this embodiment can be applied to all detection items, such as hepatitis B detection, pneumonia detection, virus detection, etc.

[0019] In this embodiment, the detection experiment is an assembly line detection performed on a work station. The work station refers to the detection equipment corresponding to the detection item, such as a pipetting workstation, a film sealing machine, etc.; assembly line detection refers to multiple work stations connected in sequence, and the detection experiment will start from the first work station. After the detection is completed, the robot arm will move to the second work station for detection, and so on, until the last work station is inspected and the detection experiment is completed.

[0020] In addition, since a single workstation can perform multiple detection experiments at the same time, parallel resources can be assigned to a single workstation. Parallel resources refer to the amount of resources consumed by a single workstation to perform detection experiments. For example, detection experiment 1 requires 1 parallel resource, detection experiment 2 requires 1 parallel resource, and detection experiment 3 requires 3 parallel resources. The parallel resources corresponding to a single workstation A are 4. Then workstation A can perform detection experiments 1 and 2, or detection experiments 1 and 3, or detection experiments 2 and 3 at the same time.

[0021] In addition, when testing at each workstation, the following constraints must be met: 1. Each test experiment must be carried out from the first station to the last station in sequence; 2. Each test experiment must be started when the current workstation is idle; 3. If each workstation has extra parallel resources, multiple testing experiments can be carried out in parallel; 4. When the parallel resources consumed by each test experiment are less than the remaining parallel resources of the current workstation, the test can proceed smoothly until the current test is completed.

[0022] 5. The tests run in parallel at each workstation cannot exceed the total parallel resources set for the current workstation.

[0023] In this embodiment, randomly generating a full permutation array refers to randomly permuting the detection order of each detection experiment. For example, there are detection experiments 0, detection experiment 1, detection experiment 2, detection experiment 3, detection experiment 4, and detection experiment 5 (hereinafter replaced by numbers 0-5). Each detection experiment needs to be performed in different workstations in turn. The full permutation array is now obtained as follows: [2,3,0,1,4,5],[2,3,0,1,4,5],[2,3,0,1,4,5],[2,3,0,1,4,5],[2,3,0,1,4,5],[2,3,0,1,4,5],[2,3,0,1,4,5],[2,3,0,1,4,5],[2,3,0,1,4,5].

[0024] Taking [2, 3, 0, 1, 4, 5] as an example, the detection order is detection experiment 2, detection experiment 3, detection experiment 0, detection experiment 1, detection experiment 4, and detection experiment 5.

[0025] In this embodiment, the individuals that meet the first preset requirement refer to one or more individuals in the target population with the shortest total detection time.

[0026] Optionally, the initial population is used as the parent and a new population is determined by a genetic algorithm, including: S11, taking the initial population as the parent generation, generating the first offspring generation through crossover operation; S12, taking the initial population as the parent generation, generating the second offspring generation through mutation operation; S13. Take the first offspring, the second offspring and the parent generation as the new population, and determine the target population by updating the fitness and removing the individuals with poor fitness.

[0027] The genetic algorithm of linked gene probability introduced in this embodiment mainly includes crossover operation and mutation operation, wherein: The crossover operation refers to randomly selecting two genes from an individual and exchanging them, with the resulting individual serving as the new offspring.

[0028] For example, after crossover mutation, [2, 3, 0, 1, 4, 5] becomes [2, 0, 3, 1, 4, 5].

[0029] Mutation operation refers to the use of the concept of linked genes in biological genetics to improve the hybridization algorithm and obtain new offspring.

[0030] In this embodiment, a genetic algorithm is used to schedule and arrange tasks to optimize detection efficiency.

[0031] Optionally, the initial population is used as the parent generation, and a second generation is generated through mutation operations, including: Pair any two individuals in the initial population and determine the paired individuals; For each paired individual, multiple linked genes are determined recursively; For each paired individual, one of the genes is selected from each linked gene as the target gene to generate individuals of the second offspring generation.

[0032] In this embodiment, linked genes refer to genes located on the same chromosome, which tend to be inherited together to the offspring. By introducing the probability of linked genes into the genetic algorithm in this embodiment, it is ensured that genes with excellent fitness are inherited to the next generation.

[0033] In this embodiment, the linked genes can be genes at relative positions or adjacent positions, or genes with other special requirements. For example, any two individuals in the initial population are paired to obtain paired individuals, namely P1 and P2. The corresponding linked genes can be found from the two parents in a recursive manner, that is, {{P2(x1)…, P1(y1)…}, {P2(x2)…, P1(y2)…}, …{P2(x n )…, P1(y n )…}}, x n and n That is the gene at the relative position (nth position).

[0034] Through hybridization, the offspring can randomly select the corresponding linked gene {P2(x n )…, P1(y n )…}, and the probability is 50%; that is, P2(x n ), or P1(y n ), which ensures that all genes of offspring come from their parents and that different combinations of genes can appear in the offspring.

[0035] Let's take another example to illustrate: p1= [1, 5, 3, 4, 8, 7, 6, 2, 9]; p2= [5, 1, 4, 3, 7, 6, 8, 9, 2]; P1 and P2 are the parents; The corresponding linked genes are positions 1-2, 3-4, 5-7, and 8-9: {{1, 5}, {5, 1}}, {{3, 4}, {4, 3}}, {{8, 7, 6}, {7, 6, 8}}, {{2, 9}, {9, 2}}.

[0036] The corresponding offspring individuals are: C = [{{1, 5}, {5, 1}}*0.5 probability, {{3, 4}, {4, 3}}*0.5 probability, {{8, 7, 6}, {7, 6, 8}}*0.5 probability, {{2, 9}, {9, 2}}*0.5 probability].

[0037] The target genes in the individuals of the final offspring generation are {1, 5}, {4, 3}, {8, 7, 6} and {2, 9} respectively, that is, the offspring can be: [1, 5, 4, 3, 8, 7, 6, 2, 9].

[0038] Optionally, the first offspring, the second offspring and the parent generation are used as a new population, and the target population is determined by updating the fitness and removing individuals with poor fitness, including: The first offspring, the second offspring and the parent generation are regarded as the new population; According to the detection time and parallel resources of each detection experiment at each workstation, calculate the total detection time of each individual in the new population; If the total detection time of each individual in the new population meets the second preset requirement, the new population is used as the target population.

[0039] In this embodiment, the second preset requirement can be met when the total detection time of each individual is less than the preset threshold, or when the total detection time of more than n% (n is a positive integer from 0 to 100) of the total number of individuals is less than the preset threshold, or when the total detection time of any individual is less than the preset threshold. It can be set according to actual conditions.

[0040] For example, suppose there are 6 test experiments, namely test experiment 0, test experiment 1, test experiment 2, test experiment 3, test experiment 4 and test experiment 5 (corresponding to 0-5 in the test sequence respectively), and 5 workstations are set up, among which: The detection order is [2, 0, 5, 4, 3, 1].

[0041] The inspection time of each inspection experiment at each workstation is: the inspection time s0=[8, 14, 35, 9, 80] for each workstation of inspection experiment 0, the inspection time s1=[8, 22, 35, 9, 60] for each workstation of inspection experiment 1, the inspection time s2=[4, 7, 22, 7, 120] for each workstation of inspection experiment 2, the inspection time s3=[8, 22, 22, 9, 75] for each workstation of inspection experiment 3, the inspection time s4=[12, 33, 22, 11, 120] for each workstation of inspection experiment 4, and the inspection time s5=[4, 11, 35, 7, 120] for each workstation of inspection experiment 5. Taking s0=[8, 14, 35, 9, 80] as an example, it means that the inspection time of inspection experiment 0 at 5 workstations is 8 minutes, 14 minutes, 35 minutes, 9 minutes and 80 minutes respectively.

[0042] The parallel resources required to be consumed by each workstation for each detection experiment are: the parallel resources x0=[1, 1, 2, 1, 1] required for each workstation corresponding to detection experiment 0, the parallel resources x1=[1, 1, 2, 1, 1] required for each workstation corresponding to detection experiment 1, the parallel resources x2=[1, 1, 1, 1, 1] required for each workstation corresponding to detection experiment 2, the parallel resources x3=[1, 1, 2, 1, 1] required for each workstation corresponding to detection experiment 3, the parallel resources x4=[1, 1, 3, 1, 1] required for each workstation corresponding to detection experiment 4, and the parallel resources x5=[1, 1, 1, 1, 1] required for each workstation corresponding to detection experiment 5. Taking x0=[1, 1, 2, 1, 1] as an example, it means that the parallel resources consumed by detection experiment 0 at the 5 workstations are 1, 1, 2, 1, 1 respectively. In this embodiment, the total parallel resources of each workstation need to be set in advance, for example, c=[1, 1, 4, 1, 4], which means that the total parallel resources of workstations 1-5 are 1, 1, 4, 1, 4 respectively, where 1 means that the corresponding workstation only allows one detection experiment to be performed, and 4 means that the corresponding workstation allows up to 4 detection experiments to be performed simultaneously.

[0043] Taking the detection time of each detection experiment at each workstation, the parallel resources consumed by each detection experiment at each workstation, the total parallel resources of workstations 1-5 and the constraints mentioned above as an example, the above data is input into the PyCharm software for simulation experiments, and the start time of each detection experiment (arranged according to the detection order) at each workstation corresponding to the detection order [2, 0, 5, 4, 3, 1] can be obtained as follows: The start time of test experiment 2 at each workstation: [0, 4, 11, 33, 40]; The start time of test 0 at each station: [4, 12, 26, 61, 70]; The start time of test experiment 5 at each workstation: [12, 26, 27, 72, 79]; The start time of test experiment 4 at each workstation: [16, 37, 70, 92, 103]; The start time of test experiment 3 at each workstation: [28, 70, 92, 114, 150]; The start time of the detection experiment 1 at each workstation: [36, 92, 114, 149, 160].

[0044] According to the detection order, it can be seen that detection experiment 2 is first carried out at workstation 1, and the start time is the 0th minute. The detection time of detection experiment 2 at each workstation is s1=[4, 7, 22, 7, 120]. The start time of detection experiment 2 at workstations 1 to 5 is the 0th minute, the 4th minute, the 11th minute, the 33rd minute and the 40th minute ([0, 4, 11, 33, 40]), respectively. The end time of detection experiment 2 should be the 160th minute (40+120=160).

[0045] In addition, the total parallel resource of workstation 1 is 1, and the parallel resource consumed by test experiment 2 at workstation 1 is 1. Therefore, workstation 1 can only start the next test experiment after test experiment 2 is completed. According to the test order, it can be seen that workstation 1 starts to test test experiment 0 after test experiment 1 is completed, and the start time is exactly when test experiment 2 ends. Therefore, the start time of test experiment 2 at workstation 1 is the 4th minute.

[0046] Secondly, since the total parallel resources of workstation 3 and workstation 5 are 4, workstation 3 and workstation 5 allow up to 4 detection experiments to be tested simultaneously. Taking detection experiment 0, detection experiment 2 and workstation 3 as an example, the start time of detection experiment 2 at workstation 3 is 11, and the detection time required for detection experiment 2 at workstation 3 is 22 minutes. If workstation 3 only allows one detection experiment to be tested, then detection experiment 0 should be tested at workstation 3 at the 33rd minute (workstation 3 will just complete detection of detection experiment 2 at the 33rd minute). However, since workstation 3 allows up to 4 detection experiments to be tested, after detection experiment 0 is completed at workstation 2 at the 26th minute (12+14=26), it can be directly tested at workstation 3, that is, the start time of detection experiment 0 at workstation 3 is the 26th minute, and it is tested at the same time as detection experiment 2.

[0047] To summarize, the start times of detection experiments 0 to 5 at workstation 5 are the 70th minute, 160th minute, 40th minute, 150th minute, 103rd minute and 79th minute respectively, and the detection times of detection experiments 0 to 5 at workstation 5 are 80 minutes, 60 minutes, 120 minutes, 75 minutes, 120 minutes and 120 minutes respectively. The end times of detection experiments 0 to 5 are the 150th minute, 220th minute, 160th minute, 225th minute, 223rd minute and 199th minute respectively. It can be seen that the total detection time obtained according to the detection order [2, 0, 5, 4, 3, 1] is 225 minutes.

[0048] Optionally, if the total detection time of each individual in the new population meets the second preset requirement, the new population is used as the target population, further comprising: If the total detection time of each individual in the new population does not meet the second preset requirement, the new population is used as a new initial population, and S11-S13 are repeatedly executed.

[0049] In this embodiment, the fitness is updated through multiple cycles until the total detection time of each individual in the new population meets the second preset requirement, thereby obtaining the arrangement order of the optimal solution and improving the efficiency of the detection experiment.

[0050] In this embodiment, fitness refers to the total detection time of each individual in the population.

[0051] Optionally, another embodiment is used to illustrate a method for automatically scheduling a pipeline experiment, as follows: A total of 6 test experiments are set up, namely test experiment 0, test experiment 1, test experiment 2, test experiment 3, test experiment 4 and test experiment 5, and 5 workstations are set up, among which: Randomly generate a fully permuted array as the initial population and obtain {[2, 3, 0, 1, 4, 5], [2, 3, 0, 1, 4, 5], [2, 3, 0, 1, 4, 5], [2, 3, 0, 1, 4, 5], [2, 3, 0, 1, 4, 5], [2, 3, 0, 1, 4, 5], [2, 3, 0, 1, 4, 5], [2, 3, 0, 1, 4, 5]}.

[0052] The detection time of each detection experiment at each workstation is: the detection time of each workstation corresponding to detection experiment 0 is s0=[8, 14, 35, 9, 80], the detection time of each workstation corresponding to detection experiment 1 is s1=[8, 22, 35, 9, 60], the detection time of each workstation corresponding to detection experiment 2 is s2=[4, 7, 22, 7, 120], the detection time of each workstation corresponding to detection experiment 3 is s3=[8, 22, 22, 9, 75], the detection time of each workstation corresponding to detection experiment 4 is s4=[12, 33, 22, 11, 120], and the detection time of each workstation corresponding to detection experiment 5 is s5=[4, 11, 35, 7, 120].

[0053] The parallel resources required to be consumed by each workstation for each detection experiment are: the parallel resources x0=[1, 1, 2, 1, 1] required for each workstation corresponding to detection experiment 0, the parallel resources x1=[1, 1, 2, 1, 1] required for each workstation corresponding to detection experiment 1, the parallel resources x2=[1, 1, 1, 1, 1] required for each workstation corresponding to detection experiment 2, the parallel resources x3=[1, 1, 2, 1, 1] required for each workstation corresponding to detection experiment 3, the parallel resources x4=[1, 1, 3, 1, 1] required for each workstation corresponding to detection experiment 4, and the parallel resources x5=[1, 1, 1, 1, 1] required for each workstation corresponding to detection experiment 5.

[0054] The total parallel resources of each workstation are c = [1, 1, 4, 1, 4].

[0055] By using the genetic algorithm in this embodiment, the initial population is subjected to crossover, mutation and loop operations, and the target population can be obtained as {[2,0,5,4,3,1], [2,5,3,4,0,1], [2,3,5,4,0,1], [2,0,4,5,3,1], [2,5,0,4,1,3], [2,5,0,4,3,1], [2,0,5,4,1,3], [2,5,1,4,0,3], [2,0,4,5,1,3], [2,1,5,4,0,3]}.

[0056] The total detection time is: [2, 0, 5, 4, 3, 1], total detection time = 225 minutes; [2, 5, 3, 4, 0, 1], total detection time = 230 minutes; [2, 3, 5, 4, 0, 1], total detection time = 231 minutes; [2, 0, 4, 5, 3, 1], total detection time = 232 minutes; [2, 5, 0, 4, 1, 3], total detection time = 235 minutes; [2, 5, 0, 4, 3, 1], total detection time = 235 minutes; [2, 0, 5, 4, 1, 3], total detection time = 235 minutes; [2, 5, 1, 4, 0, 3], total detection time = 235 minutes; [2, 0, 4, 5, 1, 3], total detection time = 235 minutes; [2, 1, 5, 4, 0, 3], total detection time = 235 minutes.

[0057] That is, [2, 0, 5, 4, 3, 1] can be used as the target individual, and the five detection experiments are tested according to the detection order corresponding to [2, 0, 5, 4, 3, 1].

[0058] like Figure 2 As shown in the figure, it is a Gantt chart of the laboratory test plan completed in the order of testing corresponding to the target individuals. The horizontal axis represents time and the vertical axis represents each workstation, including influenza virus testing, hepatitis B testing, fungal testing, parainfluenza virus testing, pneumonia virus testing and Mycobacterium tuberculosis testing. Figure 2It can be seen that influenza virus detection is the first virus detected, and its time in each station (vertical coordinates A1-A5 represent 5 stations respectively) can refer to the horizontal coordinate. Influenza A&B-4 virus was detected in the first station, influenza A&B-7 virus was detected in the second station, influenza A&B-22 virus was detected in the third station, influenza A&B-7 virus was detected in the fourth station, and influenza A&B-120 virus was detected in the fifth station. At the same time, influenza virus detection was paralleled with hepatitis B detection and fungal detection at the third station, paralleled with fungal detection at the fourth station, and paralleled with hepatitis B detection, fungal detection, parainfluenza virus detection and pneumonia virus detection at the fifth station (parallel detection means there is an overlapping area on the horizontal coordinate). By analogy, the detection mechanisms of hepatitis B detection, fungal detection, parainfluenza virus detection, pneumonia virus detection, Mycobacterium tuberculosis detection and influenza virus detection are the same, so they are not described in detail.

[0059] like Figure 3 As shown, an embodiment of the present invention provides an automatic scheduling system for pipeline experiments, including: An initial population generation module is used to randomly generate a full permutation array as an initial population, wherein the full permutation array represents different detection orders of various detection experiments at various workstations; The target population determination module is used to determine the target population by taking the initial population as the parent generation, introducing the probability of linked genes in biology for crossover mutation, and obtaining the total detection time of each individual in the target population; The detection module is used to take the individuals that meet the first preset requirement in each detection total time as the target individuals, and detect each detection experiment according to the detection sequence corresponding to the target individuals.

[0060] Optionally, the target population determination module is specifically used to: Take the initial population as the parent generation and generate the first offspring generation through crossover operation; The initial population is used as the parent generation, and the second generation is generated through mutation operation; The first offspring, the second offspring and the parent generation are taken as the new population, and the target population is determined by updating the fitness and removing the individuals with poor fitness.

[0061] Optionally, the target population determination module includes: Pair any two individuals in the initial population and determine the paired individuals; For each paired individual, multiple linked genes are determined recursively; For each paired individual, one of the genes is selected from each linked gene as the target gene to generate individuals of the second offspring generation.

[0062] Optionally, the target population determination module includes: A new population determination module, used for taking the first offspring, the second offspring and the parent generation as new populations; The total detection time calculation module is used to calculate the total detection time of each individual in the new population according to the detection time and parallel resources of each detection experiment at each workstation; The judgment module is used to take the new population as the target population if the total detection time of each individual in the new population meets the second preset requirement.

[0063] Optionally, the target population determination module further includes: The loop module is used to use the new population as a new initial population and repeatedly execute the corresponding function of the target population determination module if the total detection time of each individual in the new population does not meet the second preset requirement.

[0064] An embodiment of the present invention also provides a computing device, including a memory, a manager, and a program stored in the memory and running on the manager. When the manager executes the program, some or all steps of the above-mentioned automatic scheduling method for pipeline experiments are implemented.

[0065] Among them, the computing device can be a computer, and correspondingly, its program is computer software. The above-mentioned parameters and steps in the computing device of the present invention can refer to the parameters and steps in the embodiment of an automatic scheduling method for assembly line experiments mentioned above, and will not be repeated here.

[0066] Those skilled in the art know that the present invention can be implemented as a system, method or computer program product. Therefore, the present disclosure can be specifically implemented in the following forms, namely: it can be complete hardware, it can be complete software (including firmware, resident software, microcode, etc.), or it can be a combination of hardware and software, generally referred to as "circuit", "module" or "system" herein. In addition, in some embodiments, the present invention can also be implemented in the form of a computer program product in one or more computer-readable media, and the computer-readable medium contains computer-readable program code. Computer-readable storage media can be, for example, but not limited to - electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above.

[0067] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0068] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A method for automatic scheduling of pipeline experiments, characterized in that: include: Randomly generate a full permutation array as an initial population, wherein the full permutation array represents different detection orders of each detection experiment; Taking the initial population as the parent generation, performing crossover mutation by introducing the probability of linked genes in biology, determining the target population, and obtaining the total detection time of each individual in the target population; Individuals that meet the first preset requirement in each of the total detection time periods are taken as target individuals, and each detection experiment is tested according to the detection sequence corresponding to the target individuals.

2. The method according to claim 1, characterized in that The initial population is used as a parent generation, and crossover mutation is performed by introducing the probability of linked genes in biology to determine the target population, including: S11, taking the initial population as the parent generation, generating the first offspring generation through a crossover operation; S12, using the initial population as a parent generation, and generating a second offspring generation through a mutation operation; S13. Take the first offspring, the second offspring and the parent generation as the new population, and determine the target population by updating the fitness and removing the individuals with poor fitness.

3. The method according to claim 2, characterized in that The initial population is used as a parent generation, and a second generation is generated through a mutation operation, including: Pairing any two individuals in the initial population to determine paired individuals; For each paired individual, multiple linked genes are determined recursively; For each paired individual, one of the genes is selected from each linked gene as the target gene to generate individuals of the second offspring generation.

4. The method according to claim 3, characterized in that The first offspring, the second offspring, and the parent generation are taken as the new population. By updating the fitness and removing the individuals with poor fitness, the target population is determined, including: The first offspring, the second offspring and the parent generation are regarded as the new population; Calculate the total detection time of each individual in the new population according to the detection time and parallel resources of each detection experiment at each workstation; If the total detection time of each individual in the new population meets the second preset requirement, the new population is used as the target population.

5. The method according to claim 4, characterized in that If the total detection time of each individual in the new population meets the second preset requirement, the new population is used as the target population, further comprising: If the total detection time of each individual in the new population does not meet the second preset requirement, the new population is used as a new initial population, and S11-S13 are repeatedly executed.

6. An automatic scheduling system for assembly line experiments, characterized in that: include: An initial population generation module, used to randomly generate a full permutation array as an initial population, wherein the full permutation array represents different detection orders of various detection experiments at various workstations; A target population determination module is used to determine the target population by taking the initial population as the parent generation, introducing the probability of linked genes in biology to perform crossover mutation, and obtaining the total detection time of each individual in the target population; The detection module is used to take the individuals that meet the first preset requirement in each of the total detection time as target individuals, and detect each detection experiment according to the detection sequence corresponding to the target individuals.

7. The system according to claim 6, characterized in that The target population determination module is specifically used for: Taking the initial population as the parent generation, generating the first offspring generation through a crossover operation; Taking the initial population as the parent generation, generating the second offspring generation through mutation operation; The first offspring, the second offspring and the parent generation are taken as the new population, and the target population is determined by updating the fitness and removing the individuals with poor fitness.

8. The system according to claim 7, characterized in that Target population determination module, including: Pairing any two individuals in the initial population to determine paired individuals; For each paired individual, multiple linked genes are determined recursively; For each paired individual, one of the genes is selected from each linked gene as the target gene to generate individuals of the second offspring generation.

9. A computing device comprising a memory, a processor, and a program stored in the memory and running on the processor, characterized in that: When the processor executes the program, the steps of the automatic scheduling method for pipeline experiments as described in any one of claims 1 to 5 are implemented.

10. A computer-readable storage medium, characterized in that: Instructions are stored in a computer-readable storage medium. When the instructions are executed on a terminal device, the terminal device executes the steps of a method for automatically scheduling a pipeline experiment as described in any one of claims 1 to 5.

Images