Laboratory appointment scheduling method and system
By combining hard constraint screening, soft constraint scoring, and prediction models with the CP-NSGA-III algorithm, a laboratory reservation scheduling scheme is generated, which solves the problems of low efficiency and error-proneness of manual scheduling in laboratory management and achieves efficient and conflict-free scheduling.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-17
- Publication Date
- 2026-03-27
AI Technical Summary
In current laboratory management, manual scheduling is inefficient, error-prone, and inflexible, making it difficult to balance task time requirements and resource utilization, resulting in scheduling conflicts and resource waste.
A list of suitable laboratories is generated through hard constraint screening and soft constraint scoring. Dynamic buffer time and scheduling baseline duration are calculated by combining the prediction model. Candidate scheduling schemes are generated using the CP-NSGA-III hybrid adaptive optimization algorithm. User requests are received and the optimal scheduling scheme is updated.
It automates and optimizes scheduling schemes, improves scheduling reliability and anti-interference capabilities, and ensures conflict-free task assignment.
Smart Images
Figure CN121745528A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of laboratory management, in particular to a laboratory reservation scheduling method and system. BACKGROUND
[0002] In laboratory management, experimental projects need to be carried out on specific laboratory benches, and there is a clear association between projects and laboratories (such as specific instruments and equipment, environmental bench requirements, etc.). At present, most laboratories use manual scheduling: test personnel or inspectors need to manually record project information under each task, laboratory idle time and project estimated duration, and then manually match scheduling in combination with task time requirements. This method has obvious defects: first, it is inefficient, and when facing multiple tasks and multiple projects in parallel, manual information sorting is time-consuming and labor-intensive; second, it is prone to errors, and manual judgment cannot fully consider task time requirements, laboratory idle conflicts and project duration matching, often resulting in scheduling conflicts or resource waste; third, it has poor flexibility, and when tasks are adjusted or laboratory status changes, manual rescheduling response is lagging, affecting experimental progress. SUMMARY
[0003] In view of the above prior art, the present application provides a laboratory reservation scheduling method and system, which mainly solves the technical problems existing in the background art.
[0004] To achieve the above purpose, the technical scheme of the embodiment of the present application is as follows: In a first aspect, the present application provides a laboratory reservation scheduling method, which comprises the following steps: Step S1: According to the attribute information of the experimental project and the resource configuration information of the laboratory, through hard constraint screening and soft constraint scoring, an ordered list of suitable laboratories is generated for each project; Step S2: According to the project attribute information and historical project data, the dynamic buffer time and scheduling reference duration of the project are calculated through a prediction model; Step S3: According to the ordered list of suitable laboratories for the project and the scheduling reference duration, a candidate scheduling scheme set is generated through a CP-NSGA-III hybrid adaptive optimization algorithm; Step S4: According to the candidate scheduling scheme set and its optimization target value, the user's reservation scheduling request is received, the scheduling of the affected projects is recalculated and updated, and the optimal scheduling scheme is generated.
[0005] As a preferred scheme of the present application, the step S1 specifically comprises: The attribute information of the experimental project includes the required instrument and equipment type, technical precision index, and environmental parameter requirement; The resource configuration information includes the instrument and equipment list, its technical state, environmental parameter configuration capability, and cost.
[0006] As a preferred scheme of the present application, the step S1 generates an ordered list of suitable laboratories for each project through hard constraint screening and soft constraint scoring, specifically including: Each mandatory requirement parameter of the experimental project is compared with the corresponding resource configuration parameter of each laboratory one by one, and a hard constraint condition matching operation is performed, and when all of them are matched, the hard constraint condition is satisfied, and a preliminary candidate laboratory set is obtained, which includes all laboratory identifiers that satisfy the hard constraint condition of the experimental project; For each laboratory in the preliminary candidate laboratory set, a soft constraint condition quantitative evaluation operation is performed, including: calculating the matching degree between the optimization requirement parameters of the experimental project and the corresponding resource configuration parameters of the laboratory, and using a weighted summation algorithm to calculate the adaptability score of each laboratory relative to the experimental project, to obtain a candidate laboratory set with adaptability scores.
[0007] As a preferred scheme of the present application, the step S2 calculates the dynamic buffer time of the project, specifically including: Extract static feature parameters from the attribute information, including project type code, technical complexity level, and required equipment type identifier; Extract dynamic feature parameters from the historical project data, including the experience weight value of the project leader and the average time between failures of the target equipment; Combine the static feature parameters and dynamic feature parameters to form a project feature vector; and input it into a prediction model, which takes the historical actual execution time as a target variable to predict the execution time of the current project, and outputs a time length prediction distribution curve; According to the time length prediction distribution curve, calculate the prediction uncertainty index, and then calculate the dynamic buffer time parameter of the project according to the uncertainty index.
[0008] As a preferred scheme of the present application, the scheduling reference time length of the project is calculated, specifically including: Extract key quantile values from the time length prediction distribution curve, including the most likely time length corresponding to the P50 quantile and the conservative estimated time length corresponding to the P90 quantile; Take the most likely time length as a reference comparison benchmark, add the conservative estimated time length to the dynamic buffer time parameter to obtain the scheduling reference time length.
[0009] As a preferred scheme of the present application, the step S3 generates a candidate scheduling scheme set through a CP-NSGA-III hybrid adaptive optimization algorithm according to the ordered list of suitable laboratories for the project and the scheduling reference time length, specifically including: According to the ordered list of suitable laboratories and the scheduling reference time length, an initial laboratory allocation scheme is randomly generated; constructing a multi-objective constrained optimization function, including maximizing total fitness score, minimizing total completion time and minimizing total buffer time; According to the multi-objective constrained optimization function, the target function value of each randomly generated initial laboratory allocation scheme is calculated, the parent individual is selected by the NSGA-III algorithm according to the target function value, the genetic operation is performed to generate offspring, and the feasible project start time is calculated for each allocation scheme by the CP-SAT solver, and a completely feasible initial population is obtained; According to the initial population, a new generation population is selected by non-dominated sorting and reference point correlation analysis; According to the new generation population, the Pareto optimal solution set is calculated, and the laboratory allocation scheme is fixed, and the candidate scheduling scheme set is output.
[0010] As a preferred scheme of the application, the step S4 specifically comprises: The user request is subjected to semantic analysis and standardization processing, the core elements of the request are extracted, the core elements include target project identifier, adjustment type, adjustment parameter, and user scheduling adjustment instruction is generated; Based on the user scheduling adjustment instruction, and according to the currently selected scheduling scheme, the target project parameters affected by the adjustment are analyzed, and the adjacent project parameters affected by the adjustment are identified through the dependency relationship propagation algorithm, and an impact domain analysis report is obtained; Based on the impact domain analysis report, a local reconstruction optimization model is established, the scheduling projects are divided into fixed domain and decision domain, the project parameters of the fixed domain are kept unchanged, the project parameters of the decision domain are adjusted, and a local optimization scheme set is generated; The objective function values of each project in the local optimization scheme set are calculated, the Pareto optimality sorting is performed according to the objective function values, and the optimal scheduling scheme meeting the user request is generated.
[0011] As a preferred scheme of the application, the step S4 further comprises: Detecting potential conflicts with fixed domain project parameters, when boundary conflicts are detected, performing conflict detection on the local optimization scheme set, specifically including time conflict detection, resource conflict detection and dependency conflict detection; The time conflict detection includes detecting the time period overlap conflict of the decision domain project and the fixed domain project in the same laboratory, the resource conflict detection includes detecting the laboratory capacity overrun and equipment occupation conflict, and the dependency conflict detection includes detecting whether the timing dependency relationship between the project parameters is destroyed; The structures of the three kinds of conflict detection are prioritized to obtain a conflict list with priority weight, and the local optimization scheme set is updated according to the conflict list.
[0012] Secondly, the present invention also provides a laboratory appointment scheduling system, the system comprising: The matching list generation module is used to generate an ordered list of matching laboratories for each project based on the attribute information of the experimental project and the resource configuration information of the laboratory, through hard constraint filtering and soft constraint scoring. The prediction module is used to calculate the dynamic buffer time and scheduling baseline duration of a project based on project attribute information and historical project data through a prediction model. The candidate scheduling scheme generation module is used to generate a set of candidate scheduling schemes based on the ordered list of project-adaptive laboratories and the scheduling baseline duration, using the CP-NSGA-III hybrid adaptive optimization algorithm. The optimal scheduling scheme generation module is used to receive users' appointment scheduling requests based on the candidate scheduling scheme set and its optimization target value, recalculate and update the schedule of affected projects, and generate the optimal scheduling scheme.
[0013] The beneficial effects of this invention are as follows: The laboratory scheduling method and system provided by this invention first screens available laboratories associated with the project, accurately estimates the project execution duration through a predictive model, and dynamically allocates buffer time, thereby improving the reliability and anti-interference capability of the scheduling scheme. Secondly, within the time frame required by the task, it allocates continuous time periods based on the project duration, and through the fusion of the constrained programming algorithm CP-SAT and the NSGA-III algorithm, it finally generates a conflict-free scheduling scheme that meets the task requirements, thus automating and rationalizing the scheduling process. Attached Figure Description
[0014] Figure 1 This invention provides a flowchart illustrating the steps of a laboratory appointment scheduling method. Figure 2 This is a schematic diagram of a laboratory reservation and scheduling system provided by the present invention. Detailed Implementation
[0015] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. In the following description, the expression "some embodiments" refers to a subset of all possible embodiments; however, it should be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with each other without conflict.
[0016] 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.
[0017] It should be understood that the present invention can be embodied in various forms and should not be construed as being limited to the embodiments set forth herein. Rather, providing these embodiments will make the disclosure thorough and complete, and will fully convey the scope of the invention to those skilled in the art. Furthermore, the terminology used herein is intended only to describe particular embodiments and is not intended to limit the invention. When used herein, the singular forms “a,” “an,” and “the” are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the terms “compose” and / or “comprising,” when used in this specification, identify the presence of the stated features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups. When used herein, the term “and / or” includes any and all combinations of the associated listed items.
[0018] It should also be noted that when an element is referred to as being "fixed to" another element, it can be directly attached to the other element or there may be an intervening element. When an element is referred to as being "connected to" another element, it can be directly connected to the other element or there may be an intervening element. The terms "vertical," "horizontal," "inner," "outer," "left," "right," and similar expressions used herein are for illustrative purposes only and do not represent the only possible implementation.
[0019] To fully understand this invention, a detailed structure will be presented in the following description to illustrate the technical solution proposed by this invention. Optional embodiments of the invention are described in detail below; however, in addition to these detailed descriptions, the invention may have other embodiments.
[0020] Firstly, please refer to the attached document. Figure 1 This invention provides a laboratory appointment scheduling method, the method comprising the following steps: Step S1: Based on the attribute information of the experimental project and the resource configuration information of the laboratory, generate an ordered list of suitable laboratories for each project through hard constraint screening and soft constraint scoring. Step S2: Based on project attribute information and historical project data, calculate the project's dynamic buffer time and scheduling baseline duration using a predictive model; Step S3: Based on the ordered list of project-adaptive laboratories and the scheduling baseline duration, generate a set of candidate scheduling schemes using the CP-NSGA-III hybrid adaptive optimization algorithm; Step S4: Based on the candidate scheduling scheme set and its optimization target value, receive the user's appointment scheduling request, recalculate and update the schedule of the affected projects, and generate the optimal scheduling scheme.
[0021] As a preferred embodiment of the present invention, step S1 specifically includes: The attribute information of the experimental project includes the required instrument and equipment type, technical accuracy indicators, and environmental parameter requirements; The resource allocation information includes a list of instruments and equipment and their technical status, environmental parameter configuration capabilities, and costs.
[0022] In a preferred embodiment of the present invention, step S1 generates an ordered list of suitable laboratories for each project through hard constraint screening and soft constraint scoring, specifically including: Each mandatory requirement parameter of the experimental project is compared with the corresponding resource configuration parameters of each laboratory one by one. A hard constraint matching operation is performed. Only when all parameters match can the hard constraint be satisfied, and a preliminary candidate laboratory set is obtained. The set includes the identifiers of all laboratories that meet the hard constraint conditions of the experimental project.
[0023] In this embodiment, the mandatory requirements parameters include: experimental equipment specifications, environmental conditions such as temperature, humidity, safety level requirements, and professional qualification requirements; the laboratory resource configuration parameters include: existing equipment technical parameters, environmental control capabilities, safety certification level, and qualification certification status.
[0024] The hard constraint matching operation is as follows: An item-by-item comparison algorithm is used to make the following judgments for each laboratory: Check whether the laboratory has the necessary equipment for the experimental project, and whether the technical parameters of the equipment are not lower than the minimum specifications required by the project. Verify whether the laboratory's environmental control capabilities fully cover the temperature and humidity range required by the project; Confirm whether the laboratory's safety level meets or exceeds the safety standards required by the project. Verify whether the laboratory possesses the professional qualifications and certifications required for the project.
[0025] A laboratory is marked as matching the hard constraints only if all mandatory requirement parameters are met. Then, all laboratory identifiers that pass the hard constraint screening are collected to generate an initial candidate laboratory set.
[0026] For each laboratory in the preliminary candidate laboratory set, a soft constraint quantitative evaluation operation is performed, including: calculating the matching degree between the optimization requirement parameters of the experimental project and the corresponding resource configuration parameters of the laboratory, and using a weighted summation algorithm to calculate the fitness score of each laboratory relative to the experimental project, thereby obtaining a candidate laboratory set with fitness scores.
[0027] In this embodiment, the soft constraints include optimization requirements parameters such as equipment performance matching degree, resource utilization balance degree, geographical location convenience, and usage cost economy.
[0028] The specific quantitative assessment process includes the following steps: First, the matching degree of equipment performance parameters is calculated. The performance parameters of laboratory equipment are normalized with the performance parameters required by the project, and the matching degree of equipment is calculated by weighted geometric mean method.
[0029] Next, the resource utilization load balancing is calculated. The current load rate is obtained by the ratio of the current reservations to the total capacity of the laboratory. Then, the load balancing score is calculated based on the deviation from the ideal load rate.
[0030] Then, a location convenience score is calculated. Based on the actual travel distance between the project execution location and the laboratory location, an exponential decay function is applied to calculate the location convenience.
[0031] Finally, the cost-effectiveness score is calculated. Combining the matching relationship between laboratory usage fees and project budget, the cost-effectiveness score is obtained through a comprehensive calculation of cost fit and cost-performance indicators.
[0032] Based on the obtained matching scores, a weighted summation algorithm is used to calculate the overall fitness score. The results are then sorted in descending order of fitness score to generate a priority list of laboratory recommendations.
[0033] As a preferred embodiment of the present invention, the calculation of the dynamic buffer time of the project in step S2 specifically includes: Static feature parameters are extracted from the attribute information, including project type code, technical complexity level, and required equipment type identifier; Dynamic feature parameters are extracted from the historical project data, including the experience weight value of the project leader and the average failure interval of the target equipment. The static and dynamic feature parameters are combined to form a project feature vector; this vector is then input into a prediction model, which uses the historical actual execution time as the target variable to predict the probability distribution of the execution time of the current project and outputs a duration prediction distribution curve. In this embodiment, the prediction model used is a gradient decision tree regression model. The project feature vector is input into the gradient decision tree-based regression model, which is trained using the historical actual execution time as the target variable. This model can predict the probability distribution of the execution time of the current project. The resulting time prediction distribution curve represents the cumulative probability distribution of the project's completion at different time points.
[0034] Based on the duration prediction distribution curve, the prediction uncertainty index is calculated, and then the dynamic buffer time parameter of the project is calculated based on the uncertainty index.
[0035] In this embodiment, the duration values corresponding to key quantiles are extracted from the duration prediction distribution curve, the coefficient of variation and skewness index are calculated, and a comprehensive uncertainty index is obtained through weighted fusion. The comprehensive uncertainty index is multiplied by the adjustment parameter to obtain the dynamic buffer time parameter.
[0036] As a preferred embodiment of the present invention, calculating the scheduling baseline duration of the project specifically includes: Key quantile values are extracted from the duration prediction distribution curve, including the most likely duration corresponding to the P50 quantile and the conservative estimated duration corresponding to the P90 quantile. In this embodiment, the P50 quantile in the distribution curve is first identified, and the duration corresponding to this point is the most likely completion time of the project, denoted as T_P50. Then, the P90 quantile is identified, and the duration corresponding to this point is the conservatively estimated duration, denoted as T_P90. These two key duration parameters represent the most likely duration reflecting a typical scenario and the conservatively estimated duration considering uncertainties, respectively.
[0037] Using the most probable duration as a reference comparison benchmark, the conservative estimated duration is added to the dynamic buffer time parameter to obtain the baseline duration for scheduling.
[0038] As a preferred embodiment of the present invention, step S3 generates a set of candidate scheduling schemes based on the ordered list of project-adaptive laboratories and the scheduling baseline duration using the CP-NSGA-III hybrid adaptive optimization algorithm, specifically including: An initial laboratory allocation scheme is randomly generated based on the ordered list of suitable laboratories and the scheduling baseline duration. Construct a multi-objective constrained optimization function, including maximizing the total fitness score, minimizing the total completion time, and minimizing the total buffer time; In this embodiment, based on the mathematical model of the multi-objective constrained optimization problem, two types of decision variables are defined: one is the binary decision variable for laboratory allocation. , indicating project Assigned to the laboratory The decision state; the second is to define the integer decision variable at the start time. , indicating project The start time is based on the scheduling baseline duration. Through relational formulas + By deriving the termination time variable, the constructed multi-objective optimization function is as follows:
[0039] In the formula, This represents maximizing the total fitness score. Indicates the total completion time. This indicates the total buffer time. Represents the collection of all items. Indicates project An ordered list of compatible laboratories. Indicates project In the laboratory fitness score Indicates project Dynamic buffer time, Indicates project The proportion of buffer time used.
[0040] For each randomly generated initial laboratory allocation scheme based on the multi-objective constraint optimization function, the objective function value is calculated. Based on the objective function value, the parent individuals are selected using the NSGA-III algorithm, genetic operations are performed to generate offspring, and the feasible project start time for each allocation scheme is calculated using the CP-SAT solver to obtain a fully feasible initial population. Based on the initial population, a new generation of population is selected through non-dominated ordination and reference point correlation analysis; In this embodiment, individuals in the population are divided into different Pareto front ranks by non-dominated ordination; reference point association analysis is used to selectively retain individuals in the same front rank based on their association with the reference point.
[0041] Based on the new generation population, calculate the Pareto optimal solution set, fix the laboratory allocation scheme, and output the candidate scheduling scheme set.
[0042] As a preferred embodiment of the present invention, step S4 specifically includes: The system performs semantic parsing and standardization on user requests, extracts the core elements of the requests, including the target project identifier, adjustment type, and adjustment parameters, and generates user scheduling adjustment instructions. In this embodiment, natural language processing technology is used to identify key elements in the request, and the unstructured request is transformed into a structured scheduling adjustment instruction through a semantic standardization module.
[0043] Based on the user's scheduling adjustment instructions and according to the currently selected scheduling scheme, the target project parameters affected by the adjustment are analyzed, and the parameters of the indirectly affected adjacent projects are identified through the dependency propagation algorithm to obtain an impact domain analysis report. In this embodiment, the target project parameters directly affected by the adjustment are first identified; then, the parameters of adjacent projects indirectly affected are recursively identified based on the temporal dependencies, resource sharing relationships, and logical constraints between projects using a dependency propagation algorithm; finally, an impact domain analysis report containing the scope of direct and indirect impacts is generated.
[0044] Based on the influence domain analysis report, a local reconstruction optimization model is established, which divides the scheduling items into fixed domains and decision domains. The item parameters of the fixed domains are kept unchanged, while the item parameters of the decision domains are adjusted to generate a set of local optimization schemes. In this embodiment, the scheduling items are divided into fixed domains, which are items that are not affected by adjustments or are not allowed to be adjusted, and decision domains, which are items that are allowed to be adjusted. Then, calculate the objective function values of each item in the local optimization scheme set, sort them according to Pareto optimality based on the objective function values, and generate the optimal scheduling scheme that meets the user's request.
[0045] As a preferred embodiment of the present invention, step S4 further includes: Detect potential conflicts with fixed domain project parameters. When a boundary conflict is detected, perform conflict detection on the local optimization scheme set, specifically including time conflict detection, resource conflict detection, and dependency conflict detection. The time conflict detection includes detecting the overlap of decision domain items and fixed domain items in the same laboratory during time periods; the resource conflict detection includes detecting laboratory capacity exceeding limits and equipment occupancy conflicts; and the dependency conflict detection includes detecting whether the temporal dependency relationship between item parameters has been broken. In this embodiment, for time conflict detection, firstly, a time interval comparison database is established, extracting the start and end time parameters of the projects assigned to each laboratory to form a complete set of time intervals. Secondly, according to the time overlap detection algorithm, all project combinations within each laboratory are compared pairwise, and the existence of overlapping time periods is detected through time interval intersection operations. Specifically, when two different projects are assigned to the same laboratory, the relationship between the maximum start time and the minimum end time of their time intervals is calculated. If the maximum start time is less than the minimum end time, a time conflict is determined. Finally, the severity of the conflict is quantitatively assessed. Based on the ratio of the overlap time length to the project's baseline duration, the conflict is classified into three levels: severe conflict, moderate conflict, and mild conflict.
[0046] For resource conflict detection, firstly, the number of projects allocated to each laboratory at consecutive time points is statistically calculated, and a capacity over-limit detection algorithm is used to identify time periods when the number of projects exceeds the laboratory's maximum capacity. Secondly, equipment occupancy conflicts are detected by scanning the occupancy status of each equipment type at all time points to detect whether there are conflicts where the same equipment is occupied by multiple projects during the same time period. Specific detection methods include equipment occupancy time interval comparison and equipment type matching verification. Finally, special resource conflict detection is carried out, and compliance verification is performed for special constraints such as environmental parameter requirements, consumable resource requirements, and personnel allocation requirements to ensure that all special resource requirements are met.
[0047] For dependency conflict detection, firstly, compliance checks are performed on all time-series constraints defined in the dependency graph. This includes verifying start-to-start, end-to-start, end-to-end, and start-to-end dependencies to ensure that time lag parameters in all dependencies are met. Secondly, logical dependency verification is performed, checking logical constraints such as resource dependencies and spatial dependencies to verify compliance with constraints on resource usage order and spatial relationships between projects.
[0048] The three conflict detection structures are prioritized to obtain a conflict list with priority weights, and the local optimization scheme set is updated based on the conflict list.
[0049] Secondly, the present invention also provides a laboratory reservation and scheduling system, please refer to the appendix. Figure 2 The system includes: The matching list generation module is used to generate an ordered list of matching laboratories for each project based on the attribute information of the experimental project and the resource configuration information of the laboratory, through hard constraint filtering and soft constraint scoring. The prediction module is used to calculate the dynamic buffer time and scheduling baseline duration of a project based on project attribute information and historical project data through a prediction model. The candidate scheduling scheme generation module is used to generate a set of candidate scheduling schemes based on the ordered list of project-adaptive laboratories and the scheduling baseline duration, using the CP-NSGA-III hybrid adaptive optimization algorithm. The optimal scheduling scheme generation module is used to receive users' appointment scheduling requests based on the candidate scheduling scheme set and its optimization target value, recalculate and update the schedule of affected projects, and generate the optimal scheduling scheme.
[0050] Thirdly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the above-described laboratory reservation scheduling method.
[0051] In this embodiment, the computer-readable storage medium may be a non-transitory computer-readable storage medium, such as a read-only memory (ROM), random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device.
[0052] Fourthly, embodiments of this application also provide an electronic device, including a processor and a memory, wherein the memory stores a plurality of instructions; the processor loads instructions from the memory to execute steps in any of the laboratory appointment scheduling methods provided in embodiments of this application.
[0053] Fifthly, embodiments of this application also provide a computer program product, including a computer program / instructions, which, when executed by a processor, implement the steps in any of the laboratory appointment scheduling methods provided in embodiments of this application.
[0054] In this embodiment, those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be accomplished by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.
[0055] Therefore, embodiments of this application provide a computer-readable storage medium storing a plurality of instructions that can be loaded by a processor to execute steps in any of the laboratory appointment scheduling methods provided in embodiments of this application.
[0056] It should be noted that, through the above description of the implementation methods, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.
[0057] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. The scope of protection of the present invention should be determined by the scope of the claims.
Claims
1. A laboratory appointment scheduling method, characterized in that, The method includes the following steps: Step S1: Based on the attribute information of the experimental project and the resource configuration information of the laboratory, generate an ordered list of suitable laboratories for each project through hard constraint screening and soft constraint scoring. Step S2: Based on project attribute information and historical project data, calculate the project's dynamic buffer time and scheduling baseline duration using a predictive model; Step S3: Based on the ordered list of project-adaptive laboratories and the scheduling baseline duration, generate a set of candidate scheduling schemes using the CP-NSGA-III hybrid adaptive optimization algorithm; Step S4: Based on the candidate scheduling scheme set and its optimization target value, receive the user's appointment scheduling request, recalculate and update the schedule of the affected projects, and generate the optimal scheduling scheme.
2. The laboratory reservation and scheduling method according to claim 1, characterized in that, Step S1 specifically includes: The attribute information of the experimental project includes the required instrument and equipment type, technical accuracy indicators, and environmental parameter requirements; The resource allocation information includes a list of instruments and equipment and their technical status, environmental parameter configuration capabilities, and costs.
3. The laboratory reservation and scheduling method according to claim 2, characterized in that, In step S1, an ordered list of suitable laboratories is generated for each project through hard constraint screening and soft constraint scoring, specifically including: The mandatory requirements parameters of the experimental project are compared one by one with the corresponding resource configuration parameters of each laboratory. A hard constraint matching operation is performed. Only when all of them match can the hard constraint be satisfied, and a preliminary candidate laboratory set is obtained. The set includes the identifiers of all laboratories that satisfy the hard constraint conditions of the experimental project. For each laboratory in the preliminary candidate laboratory set, a soft constraint quantitative evaluation operation is performed, including: calculating the matching degree between the optimization requirement parameters of the experimental project and the corresponding resource configuration parameters of the laboratory, and using a weighted summation algorithm to calculate the fitness score of each laboratory relative to the experimental project, thereby obtaining a candidate laboratory set with fitness scores.
4. The laboratory reservation and scheduling method according to claim 3, characterized in that, The calculation of the project's dynamic buffer time in step S2 specifically includes: Static feature parameters are extracted from the attribute information, including project type code, technical complexity level, and required equipment type identifier; Dynamic feature parameters are extracted from the historical project data, including the experience weight value of the project leader and the average failure interval of the target equipment. The static and dynamic feature parameters are combined to form a project feature vector; this vector is then input into a prediction model, which uses the historical actual execution time as the target variable to predict the probability distribution of the execution time of the current project and outputs a duration prediction distribution curve. Based on the duration prediction distribution curve, the prediction uncertainty index is calculated, and then the dynamic buffer time parameter of the project is calculated based on the uncertainty index.
5. A laboratory reservation and scheduling method according to claim 4, characterized in that, The base duration for project scheduling is calculated, specifically including: Key quantile values are extracted from the duration prediction distribution curve, including the most likely duration corresponding to the P50 quantile and the conservative estimated duration corresponding to the P90 quantile. Using the most probable duration as a reference comparison benchmark, the conservative estimated duration is added to the dynamic buffer time parameter to obtain the baseline duration for scheduling.
6. The laboratory reservation and scheduling method according to claim 5, characterized in that, In step S3, based on the ordered list of project-suitable laboratories and the scheduling baseline duration, a set of candidate scheduling schemes is generated using the CP-NSGA-III hybrid adaptive optimization algorithm. Specifically, this includes: An initial laboratory allocation scheme is randomly generated based on the ordered list of suitable laboratories and the scheduling baseline duration. Construct a multi-objective constrained optimization function, including maximizing the total fitness score, minimizing the total completion time, and minimizing the total buffer time; For each randomly generated initial laboratory allocation scheme based on the multi-objective constraint optimization function, the objective function value is calculated. Based on the objective function value, the parent individuals are selected using the NSGA-III algorithm, genetic operations are performed to generate offspring, and the feasible project start time for each allocation scheme is calculated using the CP-SAT solver to obtain a fully feasible initial population. Based on the initial population, a new generation of population is selected through non-dominated ordination and reference point correlation analysis; Based on the new generation population, calculate the Pareto optimal solution set, fix the laboratory allocation scheme, and output the candidate scheduling scheme set.
7. A laboratory reservation and scheduling method according to claim 6, characterized in that, Step S4 specifically includes: The system performs semantic parsing and standardization on user requests, extracts the core elements of the requests, including the target project identifier, adjustment type, and adjustment parameters, and generates user scheduling adjustment instructions. Based on the user's scheduling adjustment instructions and according to the currently selected scheduling scheme, the target project parameters affected by the adjustment are analyzed, and the parameters of the indirectly affected adjacent projects are identified through the dependency propagation algorithm to obtain an impact domain analysis report. Based on the influence domain analysis report, a local reconstruction optimization model is established, which divides the scheduling items into fixed domains and decision domains. The item parameters of the fixed domains are kept unchanged, while the item parameters of the decision domains are adjusted to generate a set of local optimization schemes. Then, calculate the objective function values of each item in the local optimization scheme set, sort them according to Pareto optimality based on the objective function values, and generate the optimal scheduling scheme that meets the user's request.
8. A laboratory reservation and scheduling method according to claim 7, characterized in that, Step S4 further includes: Detect potential conflicts with fixed domain project parameters. When a boundary conflict is detected, perform conflict detection on the local optimization scheme set, specifically including time conflict detection, resource conflict detection, and dependency conflict detection. The time conflict detection includes detecting the overlap of decision domain items and fixed domain items in the same laboratory during time periods; the resource conflict detection includes detecting laboratory capacity exceeding limits and equipment occupancy conflicts; and the dependency conflict detection includes detecting whether the temporal dependency relationship between item parameters has been broken. The three conflict detection structures are prioritized to obtain a conflict list with priority weights, and the local optimization scheme set is updated based on the conflict list.
9. A laboratory reservation and scheduling system, characterized in that, The system includes: The matching list generation module is used to generate an ordered list of matching laboratories for each project based on the attribute information of the experimental project and the resource configuration information of the laboratory, through hard constraint filtering and soft constraint scoring. The prediction module is used to calculate the dynamic buffer time and scheduling baseline duration of a project based on project attribute information and historical project data through a prediction model. The candidate scheduling scheme generation module is used to generate a set of candidate scheduling schemes based on the ordered list of project-adaptive laboratories and the scheduling baseline duration, using the CP-NSGA-III hybrid adaptive optimization algorithm. The optimal scheduling scheme generation module is used to receive users' appointment scheduling requests based on the candidate scheduling scheme set and its optimization target value, recalculate and update the schedule of affected projects, and generate the optimal scheduling scheme.