Task management method and project management system for scientific research platform

Abstract

The invention provides a task management method and a project management system for a scientific research platform, and relates to the technical field of data processing, and the method comprises the steps: obtaining a to-be-allocated task in the scientific research platform; splitting the to-be-allocated task into a plurality of sub-tasks according to an execution time sequence; the planned completion time of each subtask is distributed; extracting a feature vector of each subtask; obtaining the feature vector of each person; according to the feature vector of each sub-task and the feature vector of each person, distributing a plurality of execution candidates for each sub-task in combination with a collaborative filtering algorithm; determining a final executor of each sub-task from the execution candidates through a multi-objective optimization algorithm by taking minimization of task completion time and minimization of task failure factors as targets; in the execution process, the task execution progress is monitored according to the planned completion time. The task allocation efficiency can be improved, the task allocation personnel rationality is improved, and the scientific research task completion efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a task management method and a project management system for a scientific research platform. Background Art

[0002] A scientific research platform is an integrated system environment that is usually used to support the design, implementation, management and collaboration of scientific research projects. The platform provides researchers with a unified workspace and technical support by integrating computing resources, data management tools, collaboration tools and task management functions. For example, it can provide paper submission, achievement transformation, technology transactions, scientific research paper tutoring services, etc. Scientific research platforms are widely used in various scientific research fields, including biomedicine, materials science, artificial intelligence, environmental science, etc., aiming to improve scientific research efficiency, promote interdisciplinary cooperation and accelerate the output of scientific research results.

[0003] In the scientific research platform, task management is of strategic significance. Through efficient task management, the scientific research platform can provide systematic support for the scientific research team, optimize resource allocation, and improve scientific research efficiency and collaboration effects. It guarantees the quality and progress of scientific research work, enables the scientific research team to advance the project more efficiently and accurately, and promotes the transformation and output of scientific research results.

[0004] At present, many scientific research platforms still use manual task allocation, which is inefficient, experience-dependent, and lacks intelligence. Some scientific research platforms have introduced some intelligent technologies and use static rules for allocation, such as allocation based on priority or first-come-first-served. This method has low flexibility and cannot adapt to the diverse needs of complex scientific research tasks. It is easy to lead to low suitability of personnel for task allocation, affect task progress, and reduce the efficiency of scientific research task completion. Summary of the invention

[0005] In order to solve the technical problems existing in the prior art of manually allocating tasks, which is inefficient, relies on experience, lacks intelligence, uses static rules for allocation, has low flexibility, cannot adapt to the diverse needs of complex scientific research tasks, easily leads to low suitability of personnel assigned to tasks, affects task progress, and reduces the efficiency of completing scientific research tasks, the present invention provides a task management method and project management system for a scientific research platform.

[0006] The technical solution provided by the embodiment of the present invention is as follows:

[0007] First aspect:

[0008] An embodiment of the present invention provides a task management method for a scientific research platform, comprising:

[0009] S1: Obtain the tasks to be assigned in the scientific research platform;

[0010] S2: Split the task to be assigned into multiple subtasks according to the execution time sequence;

[0011] S3: Allocate the planned completion time for each subtask according to its difficulty;

[0012] S4: extracting feature vectors of each of the subtasks;

[0013] S5: Obtain the feature vector of each person;

[0014] S6: allocating multiple execution candidates to each of the subtasks according to the feature vectors of each of the subtasks and the feature vectors of each person in combination with a collaborative filtering algorithm;

[0015] S7: with the goal of minimizing the task completion time and minimizing the task failure factor, determine the final executor of each of the subtasks from the execution candidates through a multi-objective optimization algorithm;

[0016] S8: During the execution process, the progress of the task execution is monitored according to the planned completion time.

[0017] Second aspect:

[0018] An embodiment of the present invention provides a project management system for a scientific research platform, comprising:

[0019] processor;

[0020] A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the task management method for a scientific research platform as described in the first aspect is implemented.

[0021] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0022] In the present invention, the task to be assigned is split into multiple subtasks in order of execution time. According to the feature vectors of each subtask and the feature vectors of each person, combined with a collaborative filtering algorithm, multiple execution candidates are assigned to each subtask. Then, with the goal of minimizing the task completion time and minimizing the task failure factor, the final executor of each subtask is determined from the execution candidates through a multi-objective optimization algorithm, so as to perform flexible task automation allocation without manual allocation, improve task allocation efficiency, adapt to the diverse needs of complex scientific research tasks, improve the rationality of personnel in task allocation, and improve the efficiency of completing scientific research tasks. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 A flowchart of a task management method for a scientific research platform provided by an embodiment of the present invention;

[0025] Figure 2 A schematic diagram of the structure of a project management system for a scientific research platform provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0026] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0027] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0028] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0029] Reference Manual Attached Figure 1 , showing a flow chart of a task management method for a scientific research platform provided by an embodiment of the present invention.

[0030] The embodiment of the present invention provides a processing flow of a task management method for a scientific research platform, which may include the following steps:

[0031] S1: Get the tasks to be assigned in the scientific research platform.

[0032] Among them, the tasks to be assigned can specifically be: paper submission tasks, patent application tasks, results transformation tasks, technology transaction tasks, scientific research paper tutoring service tasks, project funding application tasks, academic cooperation tasks, technical consulting and support tasks, research data analysis service tasks, etc.

[0033] S2: Split the task to be assigned into multiple subtasks according to the execution time sequence.

[0034] For example, for the paper submission task, it can be divided into multiple subtasks in chronological order: (1) selecting a journal and confirming submission requirements; (2) adjusting the paper format and typesetting; (3) polishing and proofreading the paper language; (4) processing charts and data; (5) preparing additional materials (such as cover letters, recommendation letters, etc.); (6) reviewing the paper; (7) revising and improving the paper, etc.

[0035] For another example, for academic cooperation tasks, they can be divided into multiple subtasks in chronological order: (1) determine the cooperation goals and partners; (2) conduct preliminary communication with the target partners, introduce their respective advantages, needs and cooperation expectations, and clarify the feasibility and preliminary framework of the cooperation; (3) the parties to the cooperation jointly formulate a detailed cooperation plan, including the division of responsibilities of each party, execution time nodes and resource allocation; (4) determine the resources that each party needs to invest (such as equipment, data, funds) and allocate resources to ensure that the resources can be in place on time; (5) all parties jointly participate in the formulation of the research plan, discuss details such as experimental design, data collection methods, and analysis methods, and ensure that the research plan is scientific and reasonable; (6) all parties implement the research plan; (7) formulate data collection methods and sharing mechanisms, clarify data formats, sharing frequencies, permission settings, etc., to ensure the security and sharing of data during the cooperation process, etc.

[0036] Furthermore, due to the complexity of the tasks, these subtasks may be completed by multiple different personnel, and during the completion process, the work of the previous person needs to be handed over to the next person.

[0037] S3: Allocate the planned completion time for each subtask based on its difficulty.

[0038] It should be noted that the difficulty of subtasks can be comprehensively evaluated based on task complexity, required skill level, execution time, task dependencies, etc.

[0039] Specifically, the task complexity, required skill level, execution time, and task dependencies of the subtasks can be scored on a difficulty scale of 1-5, with 1 indicating simple and 5 indicating very complex. The scores of each indicator are then weighted and summarized to generate a total difficulty score for the subtask.

[0040] In a possible implementation, S3 specifically includes sub-steps S301 and S302:

[0041] S301: Obtain the planned completion time of the task to be assigned.

[0042] S302: Allocate the planned completion time of each subtask according to the difficulty of each subtask:

[0043]

[0044] Among them, t i represents the planned completion time of the i-th subtask, T represents the planned completion time of the task to be assigned, and α i represents the difficulty value of the i-th subtask, and n represents the total number of subtasks.

[0045] In the present invention, by linking the task completion time with the difficulty coefficient of the subtask, it is ensured that more time is given to high-difficulty tasks, while less time is allocated to simple tasks. In this way, time resources are matched with task complexity, avoiding task failure or quality degradation due to insufficient time for high-difficulty tasks.

[0046] S4: Extract feature vectors for each subtask.

[0047] Optionally, the feature vector of the subtask includes: task domain, task difficulty, required skills, preset completion time, task priority, and task dependency.

[0048] S5: Obtain the feature vector of each person.

[0049] Optionally, the characteristic vector of the personnel includes: professional field, work experience, skill level, historical completion time, task success rate and collaboration smoothness rate.

[0050] It should be noted that the task domain of the subtask matches the professional domain of the personnel. By matching the requirements of the subtask with the characteristics of the personnel, it is ensured that each task is assigned to the most suitable person. For example, the matching of the task domain and the professional domain ensures that the task is assigned to the person who has expertise in the field, thus improving the accuracy of task completion.

[0051] The difficulty of the subtask matches the work experience of the personnel. The difficulty of the subtask matches the work experience of the personnel, ensuring that high-difficulty tasks are assigned to experienced personnel, reducing task completion time and improving work efficiency.

[0052] The skills required for subtasks match the skill levels of personnel. The skills required for subtasks match the skill levels of personnel to ensure that the skill requirements of the task are met, thereby avoiding knowledge gaps in the progress of the task and improving completion efficiency.

[0053] The preset completion time of the subtask matches the historical completion time of the personnel. The preset completion time of the subtask matches the historical completion time of the personnel, ensuring that the task is assigned to the person who can complete the task efficiently within the expected time, making reasonable use of time resources, and avoiding delays caused by improper time allocation.

[0054] The task priority of the subtask is matched with the task success rate of the personnel. High-priority tasks are assigned to personnel with high task success rates to ensure the completion quality and success rate of key tasks and reduce the risks caused by task failure.

[0055] The task dependency of subtasks matches the smooth collaboration rate of personnel. The task dependency of subtasks matches the smooth collaboration rate of personnel, ensuring that tasks requiring collaboration are assigned to personnel with higher collaboration capabilities, reducing collaboration barriers and improving the completion rate of multi-party tasks.

[0056] S6: According to the feature vectors of each subtask and each person, combined with the collaborative filtering algorithm, multiple execution candidates are assigned to each subtask.

[0057] In a possible implementation, S6 specifically includes sub-steps S601 to S605:

[0058] S601: Calculate the weighted cosine similarity between the feature vector of the current subtask and the feature vector of each person according to the feature vector of the current subtask and the feature vector of each person:

[0059]

[0060] Among them, σ j represents the weighted cosine similarity between the current subtask and the jth person, ω k represents the weight coefficient of the kth eigenvalue, x k represents the kth feature value of the current subtask, y ik represents the kth feature value of the jth person, and K represents the total number of features.

[0061] It should be noted that the characteristic value of the current subtask here can be the score of the task field, task difficulty, required skills, preset completion time, task priority and task dependency mentioned above. The characteristic value of the personnel can be the score of the professional field, work experience, skill level, historical completion time, task success rate and collaboration smoothness rate mentioned above.

[0062] In the present invention, by calculating the weighted cosine similarity of the feature vectors of the current subtask and each candidate, the matching degree between the task requirements and personnel capabilities can be accurately measured, ensuring that the selected candidates have professional skills and work experience that are highly matched with the task requirements.

[0063] S602: Calculate the weighted cosine similarity between the current subtask and the historical subtask:

[0064]

[0065] Among them, δ urepresents the weighted cosine similarity between the current subtask and the u-th historical subtask, y uk represents the kth feature value of the uth historical subtask.

[0066] S603: According to the similarity between the current subtask and the historical subtasks, combined with the execution of the historical subtasks by each person, determine the collaborative recommendation index for each person in the current subtask:

[0067]

[0068] Among them, ρ j represents the collaborative recommendation index for the jth person in the current subtask, z ju represents the execution result of the jth person for the uth historical subtask. When the jth person successfully executes the uth historical subtask, z ju = 1, when the jth person fails to perform the uth historical subtask z ju =0.

[0069] In the present invention, based on the idea of ​​collaborative filtering, by referring to candidates who have performed well in similar tasks, the system can automatically select personnel who have performed well in completing similar tasks in the past, ensuring that the current task is assigned to an executor with relevant experience, thereby reducing the risk of task failure.

[0070] S604: Calculate the comprehensive recommendation index for each person in the current subtask based on the weighted cosine similarity between the feature vector of the current subtask and the feature vector of each person and the collaborative recommendation index for each person in the current subtask:

[0071]

[0072] Among them, η j Represents the comprehensive recommendation index for the jth person in the current subtask.

[0073] In this invention, the comprehensive recommendation index takes into account both the matching degree between the current subtask and personnel characteristics and the collaborative recommendation index, ensuring that the recommendation results not only focus on the current task requirements, but also consider the personnel's actual execution capabilities. This dual recommendation mechanism can maximize the selection of executors who meet the task requirements and perform reliably, ensuring the reliability and stability of the task.

[0074] S605: Sort the personnel in descending order according to the comprehensive recommendation index, and select a preset number of personnel with the highest ranking as candidates for executing the subtask.

[0075] Among them, those skilled in the art can set the size of the preset number according to actual conditions, and the present invention does not limit it.

[0076] Optionally, the preset number is 5 persons.

[0077] S7: With the goal of minimizing the task completion time and minimizing the task failure factor, the final executor of each subtask is determined from the execution candidates through a multi-objective optimization algorithm.

[0078] In a possible implementation, S7 specifically includes sub-steps S701 and S702:

[0079] S701: Construct a multi-objective optimization objective function with the goal of minimizing the task completion time and minimizing the task failure factor.

[0080] Optionally, a multi-objective optimization objective function:

[0081]

[0082] Where f represents the multi-objective optimization objective function, X represents the task allocation scheme, TFF represents the task failure factor, FT represents the task completion time, and λ 1 represents the weight coefficient of the task failure factor, λ 2 The weight coefficient representing the task completion time.

[0083] Among them, those skilled in the art can set the weight coefficient λ of the task failure factor according to actual conditions. 1 and the weight coefficient λ of the task completion time 2 The present invention does not limit the size.

[0084] In the present invention, in the multi-objective optimization objective function, minimizing the task failure factor helps to improve the task success rate, while minimizing the task completion time ensures that the task is completed on time. Through the weight adjustment of the two, the scientific research platform can strike a balance between the quality and efficiency of task completion. Not only does it improve the success rate and time efficiency of task completion, it can also enhance the intelligence of the system, support the improvement of team capabilities and the rational allocation of resources, and provide a solid foundation for the long-term development of the scientific research platform.

[0085] Optionally, the task failure factor is:

[0086]

[0087] Where TFF represents the task failure factor, g i represents the task failure rate of the executor corresponding to the i-th subtask, γ i Indicates the difficulty coefficient of the i-th subtask, ET i represents the execution time of the ith subtask, v i represents the collaboration failure rate between the executor corresponding to the i-1th subtask and the executor corresponding to the i-th subtask, CTi represents the collaboration time of the ith subtask, and n represents the total number of subtasks.

[0088] It should be noted that the task failure factor can measure the failure risk of a task at the level of multiple subtasks. The task failure factor is divided into two parts, one is the task failure item and the other is the collaboration failure item. The task failure item evaluates the complexity of the subtask itself and the personnel risk of the task, combining the difficulty of executing the subtask with the risk factor. High-difficulty and long-duration tasks usually have larger values ​​in this part, indicating a higher risk of failure. The collaboration failure item evaluates the risk of failure caused by poor collaboration during task execution, and is particularly suitable for tasks with strong dependencies between multiple executors. If the collaboration between subtasks is not smooth or the collaboration time is long, the value of this part will be larger, indicating a higher risk of failure caused by collaboration.

[0089] Optionally, the task completion time is:

[0090]

[0091] Among them, FT represents the task completion time, ET i represents the execution time of the ith subtask, CT i represents the collaboration time of the i-th subtask.

[0092] S702: According to the multi-objective optimization objective function, the final executor of each subtask is determined from the execution candidates through the firefly combined with the genetic optimization algorithm.

[0093] Specifically, the multi-objective optimization objective function can be used as the fitness function of the firefly combined with genetic optimization algorithm.

[0094] Initialize the population, which contains multiple individuals. Each individual represents a feasible task allocation scheme. Each individual has multiple components, and each component represents the allocation of a subtask.

[0095] An elite selection strategy is adopted to remove the 30% of individuals with the lowest fitness values ​​to form the first population.

[0096] It should be noted that the elite strategy retains high-quality individuals and further avoids interference from individuals with poor fitness, making the optimization process more efficient.

[0097] Perform a crossover operation on the individuals in the first population to form a second population:

[0098]

[0099]

[0100] Among them, Y1 , Y 2 represents a new individual, X 1 Indicates the first parent, X 2 Represents the second parent, and rand represents a random number between 0 and 1.

[0101] Perform mutation operations on individuals in the second population to form a third population:

[0102]

[0103] Among them, Y 3 represents a new individual, X 3 Indicates the parent, X max represents the individual with the largest fitness value, X min represents the individual with the smallest fitness value, and rand represents a random number between 0 and 1.

[0104] The positions of individuals in the third population are updated according to the firefly optimization algorithm to form the fourth population:

[0105]

[0106] in, represents the position of the i-th firefly individual at the t+1th iteration, ω t represents the adaptive inertia weight coefficient at the tth iteration, represents the position of the i-th firefly individual at the t-th iteration, represents the position of the j-th firefly individual at the t-th iteration, β represents the attraction, α represents the step factor, r represents a random number in the range of 0 to 1, and Levy represents the random step of Levy flight.

[0107] Optionally, the adaptive inertia weight coefficient is specifically:

[0108]

[0109] Among them, T m Indicates the maximum number of iterations.

[0110] It should be noted that larger weights in the early stage make individuals move more drastically in the global scope, which helps to explore more potential solutions and avoid falling into local optimality too early.

[0111] Optionally, the attraction is specifically:

[0112]

[0113] Among them, β 0represents the attraction between two fireflies when the distance between them is 0, exp represents the exponential function with the natural constant e as the base, γ represents the light intensity attraction coefficient, r ij represents the Euclidean distance between the i-th firefly individual and the j-th firefly individual.

[0114] Optionally, the Levy flight random step size is specified as:

[0115]

[0116] Among them, u obeys The normal distribution of v follows The normal distribution of , λ represents the exponential parameter.

[0117]

[0118]

[0119] Among them, τ is the standard Gamma function.

[0120] It should be noted that Levy flight increases the randomness of the search process, allowing the algorithm to escape from the local optimum and expand the search space, thereby increasing the possibility of finding the global optimal solution.

[0121] It should be noted that the combination of crossover and mutation of the genetic algorithm and position update of the firefly algorithm enables the algorithm to adaptively adjust strategies at different stages and handle complex task allocation problems. This combined optimization method enhances the adaptability and robustness of the algorithm to complex multi-objective problems.

[0122] The third and fourth populations are merged to form the fifth population.

[0123] Determine whether the current number of iterations has reached the maximum number of iterations; if so, output the 3D printing parameter set representing the firefly individual with the highest fitness in the fifth population; otherwise, return to continue iterating.

[0124] In the present invention, by using the firefly combined with the genetic optimization algorithm and the task allocation method with the multi-objective optimization objective function as the fitness function, the scientific research platform can intelligently and automatically determine the task allocation scheme. This method has significant advantages in the balance between global and local search, the balance between task completion time and failure rate, flexibility and adaptability, enabling the scientific research platform to perform task allocation more scientifically and efficiently, and improve the overall efficiency of task management and resource utilization.

[0125] S8: During the execution process, the progress of the task execution is monitored according to the planned completion time.

[0126] In a possible implementation, S8 specifically includes sub-steps S801 to S803:

[0127] S801: During the execution process, obtain the current task execution progress.

[0128] S802: Compare the current task execution progress with the expected execution progress and determine the progress deviation:

[0129]

[0130] Among them, β represents the progress deviation, a r Indicates the current task execution progress, a p Indicates the expected execution progress.

[0131] S803: When the progress deviation exceeds the preset deviation, an alarm is issued.

[0132] Among them, those skilled in the art can set the size of the preset deviation according to actual conditions, and the present invention does not limit it.

[0133] In the present invention, through the combination of progress monitoring, progress deviation calculation and early warning mechanism, the scientific research platform can control the task execution in real time, find problems in time and adjust the task arrangement. This can not only ensure the timely and high-quality completion of tasks, but also provide support for team collaboration, data accumulation and future management. It is a scientific and intelligent task management method.

[0134] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0135] In the present invention, the task to be assigned is split into multiple subtasks in order of execution time. According to the feature vectors of each subtask and the feature vectors of each person, combined with the collaborative filtering algorithm, multiple execution candidates are assigned to each subtask. Then, with the goal of minimizing the task completion time and minimizing the task failure factor, the final executor of each subtask is determined from the execution candidates through a multi-objective optimization algorithm, so as to perform flexible task automation allocation without manual allocation, improve the task allocation efficiency, adapt to the diverse needs of complex scientific research tasks, improve the rationality of personnel in task allocation, and improve the efficiency of scientific research task completion.

[0136] Reference Manual Attached Figure 2 , showing a structural schematic diagram of a project management system for a scientific research platform provided by the present invention.

[0137] The present invention further provides a project management system 20 for a scientific research platform, which is applied to the above-mentioned task management method for a scientific research platform, comprising:

[0138] Processor 201.

[0139] The memory 202 stores computer-readable instructions, and when the computer-readable instructions are executed by the processor 201, a task management method for a scientific research platform as described in the method embodiment is implemented.

[0140] The project management system 20 for a scientific research platform provided by the present invention can execute the above-mentioned task management method for a scientific research platform and achieve the same or similar technical effects. To avoid repetition, the present invention will not go into details.

[0141] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0142] In the present invention, the task to be assigned is split into multiple subtasks in order of execution time. According to the feature vectors of each subtask and the feature vectors of each person, combined with a collaborative filtering algorithm, multiple execution candidates are assigned to each subtask. Then, with the goal of minimizing the task completion time and minimizing the task failure factor, the final executor of each subtask is determined from the execution candidates through a multi-objective optimization algorithm, so as to perform flexible task automation allocation without manual allocation, improve task allocation efficiency, adapt to the diverse needs of complex scientific research tasks, improve the rationality of personnel in task allocation, and improve the efficiency of completing scientific research tasks.

[0143] It should be understood that the processor in the embodiment of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0144] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0145] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0146] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0147] In the present invention, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0148] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0149] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0150] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0151] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0152] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0153] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0154] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0155] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the task management method for a scientific research platform as described in the method embodiment.

[0156] A computer-readable storage medium provided by the present invention can implement the steps and effects of the task management method for a scientific research platform of the above-mentioned method embodiment. To avoid repetition, the present invention will not go into details.

[0157] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0158] In the present invention, the task to be assigned is split into multiple subtasks in order of execution time. According to the feature vectors of each subtask and the feature vectors of each person, combined with a collaborative filtering algorithm, multiple execution candidates are assigned to each subtask. Then, with the goal of minimizing the task completion time and minimizing the task failure factor, the final executor of each subtask is determined from the execution candidates through a multi-objective optimization algorithm, so as to perform flexible task automation allocation without manual allocation, improve task allocation efficiency, adapt to the diverse needs of complex scientific research tasks, improve the rationality of personnel in task allocation, and improve the efficiency of completing scientific research tasks.

[0159] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0160] There are a few points to note:

[0161] (1) The drawings of the embodiments of the present invention only involve structures related to the embodiments of the present invention. Other structures may refer to conventional designs.

[0162] (2) For the sake of clarity, in the drawings used to describe the embodiments of the present invention, the thickness of layers or regions is exaggerated or reduced, that is, these drawings are not drawn according to the actual scale. It is understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element or there may be intermediate elements.

[0163] (3) In the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other to obtain new embodiments.

[0164] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A task management method for a scientific research platform, characterized in that: include: S1: Obtain the tasks to be assigned in the scientific research platform; S2: Split the task to be assigned into multiple subtasks according to the execution time sequence; S3: Allocate the planned completion time for each subtask according to its difficulty; S4: extracting feature vectors of each of the subtasks; S5: Obtain the feature vector of each person; S6: allocating multiple execution candidates to each of the subtasks according to the feature vectors of each of the subtasks and the feature vectors of each person in combination with a collaborative filtering algorithm; S7: with the goal of minimizing the task completion time and minimizing the task failure factor, determine the final executor of each of the subtasks from the execution candidates through a multi-objective optimization algorithm; S8: During the execution process, the progress of the task execution is monitored according to the planned completion time.

2. The task management method for a scientific research platform according to claim 1, characterized in that: The S3 specifically includes: S301: Obtaining the planned completion time of the task to be assigned; S302: Allocate a planned completion time for each subtask according to the difficulty of each subtask.

3. The task management method for a scientific research platform according to claim 1, characterized in that: The feature vector of the subtask includes: task domain, task difficulty, required skills, preset completion time, task priority and task dependency; The characteristic vector of the personnel includes: professional field, work experience, skill level, historical completion time, task success rate and collaboration smoothness rate; The task areas of the subtasks match the professional areas of the personnel; The difficulty of the subtasks matches the work experience of the personnel; The skills required for the subtasks match the skill levels of the personnel; The preset completion time of the subtask matches the historical completion time of the personnel; The task priority of the subtask has a matching relationship with the task success rate of the personnel; The task dependency of subtasks has a matching relationship with the smooth collaboration rate of personnel.

4. The task management method for a scientific research platform according to claim 1, characterized in that: The S6 specifically includes: S601: Calculate the weighted cosine similarity between the feature vector of the current subtask and the feature vector of each person according to the feature vector of the current subtask and the feature vector of each person; S602: Calculate the weighted cosine similarity between the current subtask and the historical subtask; S603: Determine the collaborative recommendation index for each person in the current subtask based on the similarity between the current subtask and the historical subtask and the execution status of each person in the historical subtask; S604: Calculate a comprehensive recommendation index for each person in the current subtask according to the weighted cosine similarity between the feature vector of the current subtask and the feature vector of each person and the collaborative recommendation index for each person in the current subtask; S605: Sort the personnel in descending order according to the comprehensive recommendation index, and select a preset number of personnel with the highest ranking as candidates for executing the subtask.

5. The task management method for a scientific research platform according to claim 4, characterized in that: The preset number is 5 persons.

6. The task management method for a scientific research platform according to claim 1, characterized in that: The S7 specifically includes: S701: Construct a multi-objective optimization objective function with the goal of minimizing task completion time and minimizing task failure factor; S702: According to the multi-objective optimization objective function, the final executor of each subtask is determined from the execution candidates by combining Firefly with genetic optimization algorithm.

7. The task management method for a scientific research platform according to claim 6, characterized in that: Multi-objective optimization objective function: ， Where f represents the multi-objective optimization objective function, X represents the task allocation scheme, TFF represents the task failure factor, FT represents the task completion time, λ1 represents the weight coefficient of the task failure factor, and λ2 represents the weight coefficient of the task completion time.

8. The task management method for a scientific research platform according to claim 7, characterized in that: The task failure factors are specifically: ， Where TFF represents the task failure factor, g i represents the task failure rate of the executor corresponding to the i-th subtask, γ i Indicates the difficulty coefficient of the i-th subtask, ET i represents the execution time of the ith subtask, v i represents the collaboration failure rate between the executor corresponding to the i-1th subtask and the executor corresponding to the i-th subtask, CT i represents the collaboration time of the ith subtask, and n represents the total number of subtasks; The task completion time is specifically: ， Among them, FT represents the task completion time, ET i represents the execution time of the ith subtask, CT i represents the collaboration time of the i-th subtask.

9. The task management method for a scientific research platform according to claim 1, characterized in that: The S8 specifically includes: S801: During the execution process, obtain the current task execution progress; S802: Compare the current task execution progress with the expected execution progress to determine the progress deviation; S803: When the progress deviation exceeds a preset deviation, an alarm is issued.

10. A project management system for a scientific research platform, characterized in that: include: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the task management method for a scientific research platform as described in any one of claims 1 to 9 is implemented.

Images