Intelligent pipeline operation method and system fusing RPA and AI

Abstract

The application provides a kind of intelligent pipeline operation method and system fusing RPA with AI, it is related to data processing technical field, method includes: the intelligent pipeline operation model based on artificial intelligence AI is built;Obtain the task to be processed;Determine the difficulty of each task to be processed;Determine the production capacity value of each production line;Determine the production efficiency when each production line produces each task to be processed;Determine the estimated completion time when each production line produces each task to be processed;According to the estimated completion time of each task, determine the timeliness of task completion;According to the work load of each production line, determine the fluctuation index of pipeline;Through the intelligent pipeline operation model based on artificial intelligence AI, to improve the timeliness of task completion and reduce the fluctuation index of pipeline as the goal, determine the pipeline operation scheme;Through robot process automation RPA technology, execute pipeline operation scheme.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to an intelligent pipeline operation method and system fusing RPA and AI. BACKGROUND

[0002] Pipeline scheduling ensures that each link in the production process is completed on time and efficiently to meet production targets and delivery deadlines. Reasonable pipeline scheduling can help enterprises maintain competitiveness in modern manufacturing environments while meeting increasing production complexity, customer demand and sustainable development requirements.

[0003] Currently, many enterprises still use manual allocation methods for pipeline scheduling. Workers allocate and schedule tasks based on experience or manual input. This method lacks flexibility, and when the production environment changes, manual scheduling may not be able to adjust in time, resulting in decreased production efficiency. The manual scheduling method often encounters bottlenecks in the production process and cannot achieve accurate task allocation, resulting in uneven production line load and waste of production resources.

[0004] With the rapid development of science and technology, more and more modern technologies are being applied to pipeline scheduling. Common ones include pipeline scheduling based on preset rules, such as longest task first, shortest operation time first, etc. for automatic task allocation and scheduling.

[0005] However, the pipeline scheduling scheme based on preset rules is difficult to cope with complex and variable production environments. When the production environment changes (such as equipment failure, order changes, raw material shortages, etc.), it is difficult to make quick adjustments, affecting production efficiency. At the same time, the pipeline scheduling scheme based on preset rules can usually only optimize one target (such as minimizing task completion time, maximizing resource utilization, etc.), which can easily lead to uneven production line load and ignore the volatility of the production line, i.e. some pipelines may be overloaded, while others are relatively idle, causing unnecessary fluctuations in the production process and affecting the stability of the production line. SUMMARY

[0006] To solve the technical problems of the current pipeline scheduling scheme based on preset rules, which is difficult to cope with complex and variable production environments, and when the production environment changes, it is difficult to make quick adjustments, affecting production efficiency, and can usually only optimize one target, which can easily lead to uneven production line load and ignore the volatility of the production line, i.e. some pipelines may be overloaded, while others are relatively idle, causing unnecessary fluctuations in the production process and affecting the stability of the production line, the present application provides an intelligent pipeline operation method and system fusing RPA and AI.

[0007] The technical solutions provided by the embodiments of the present application are as follows:

[0008] The first aspect is:

[0009] The embodiment of the application provides a kind of intelligent pipeline job method of fusing RPA and AI, applied to memory, comprising:

[0010] S1: construct intelligent pipeline job model based on artificial intelligence AI;

[0011] S2: obtain to be processed task;

[0012] S3: determine the difficulty of each to be processed task;

[0013] S4: determine the production capacity value of each production line;

[0014] S5: the difficulty of task and the production capacity value of production line are matched, and the production efficiency when each production line produces each to be processed task is determined;

[0015] S6: according to the production efficiency when each production line produces each to be processed task, the predicted completion time when each production line produces each to be processed task is determined;

[0016] S7: according to the predicted completion time of each task, the timeliness of task completion is determined;

[0017] S8: according to the work load of each production line, the fluctuation index of pipeline is determined;

[0018] S9: through intelligent pipeline job model based on artificial intelligence AI, to improve the timeliness of task completion and reduce the fluctuation index of pipeline as target, determine pipeline job scheme;

[0019] S10: through robot process automation RPA technology, the pipeline job scheme is executed.

[0020] The second aspect is:

[0021] The embodiment of the application provides a kind of intelligent pipeline job system of fusing RPA and AI, comprising:

[0022] Processor;

[0023] Memory, the computer readable instructions are stored on the memory, the computer readable instructions are executed by the processor, realize the intelligent pipeline job method of fusing RPA and AI as described in the first aspect.

[0024] The third aspect is:

[0025] The embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to realize the intelligent pipeline operation method of fusing RPA and AI.

[0026] The technical scheme provided by the embodiment of the present application has at least the following beneficial effects:

[0027] In the present application, the intelligent pipeline operation model based on artificial intelligence AI is used to dynamically determine the pipeline operation scheme in real time, so that the timeliness of task completion and the fluctuation index of the pipeline are reduced, the production environment can be quickly adjusted in real time when the production environment changes, the production efficiency is improved, the load imbalance of the production line is reduced, the fluctuation of the production line is reduced, and the stability of the production line is improved. BRIEF DESCRIPTION OF DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0029] Figure 1 The flowchart of the intelligent pipeline operation method of fusing RPA and AI provided by the embodiment of the present application is shown in the figure.

[0030] Figure 2 The structure diagram of the intelligent pipeline operation system of fusing RPA and AI provided by the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0031] The technical solutions in the present application will be described below with reference to the drawings.

[0032] In the embodiments of the present application, the words such as "example", "for example" and the like are used to represent as an example, illustration or description. Any embodiment or design scheme described as "example" in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the word "example" is intended to present the concept in a specific manner. In addition, in the embodiments of the present application, the meaning expressed by "and / or" can be both, or can be one of the two.

[0033] In the embodiments of the present application, "image" and "picture" can be used interchangeably, and it should be pointed out that the meanings expressed are consistent when the distinction is not emphasized. "Of", "corresponding" and "corresponding" can be used interchangeably, and it should be pointed out that the meanings expressed are consistent when the distinction is not emphasized.

[0034] In the embodiments of the present application, sometimes the subscript such as W1 can be mistakenly used as a non-subscript such as W1, and the meanings expressed are consistent when the distinction is not emphasized.

[0035] In order to make the technical problems, technical solutions and advantages to be solved by the present application more clear, the following will be described in detail with reference to the drawings and specific embodiments.

[0036] Reference is made to the accompanying drawings and specific embodiments of the present application Figure 1 , a flowchart of a method for intelligent pipeline operation combining RPA and AI is shown.

[0037] The processing flow of the method for intelligent pipeline operation combining RPA and AI provided by the embodiments of the present application can include the following steps:

[0038] S1: Construct an intelligent pipeline operation model based on artificial intelligence (AI).

[0039] S2: Obtain a task to be processed.

[0040] S3: Determine the difficulty of each task to be processed.

[0041] In one possible implementation, S3 is specifically: determining the difficulty of the task to be processed according to the process required by the task to be processed.

[0042] Further, the difficulty of the task to be processed is specifically:

[0043]

[0044] Wherein, W i represents the difficulty of the i-th task, s ij represents the difficulty score of the j-th process of the i-th task, n ij represents the number of executions of the j-th process of the i-th task, J i represents the total number of processes of the i-th task.

[0045] In the present application, by combining the difficulty score of each process of the task with the number of executions, the overall difficulty of the task can be more accurately reflected.

[0046] S4: Determine the production capacity value of each production line.

[0047] In one possible implementation, S4 specifically involves determining the production capacity value of the production line based on its performance when processing standard processes.

[0048] Furthermore, the specific production capacity value of the production line is as follows:

[0049]

[0050] Among them, A k Let η represent the production capacity value of the k-th production line, and b represent the aging coefficient. ku t represents the accuracy of the k-th production line when processing the u-th standard process. ku γ represents the processing time of the k-th production line when handling the u-th standard operation. b Represents the precision coefficient, γ t This represents the processing time coefficient.

[0051] The aging coefficient is related to the number of years the production line has been in use.

[0052] Standard processes refer to the standardized work steps and procedures set for each specific operation or task during production or manufacturing. Standard processes are standardized operating methods developed to ensure consistent product quality, improved production efficiency, and operational safety. The production capacity of a production line can be determined based on its performance in handling standard processes.

[0053] In this invention, production capacity is evaluated based on the performance of the production line (accuracy, processing time, etc.), and an aging factor is introduced to consider the long-term performance of the production line. This method can more accurately and dynamically reflect the true capacity of each production line.

[0054] S5: Match the difficulty of the task with the production capacity of the production line to determine the production efficiency of each production line when producing each task to be processed.

[0055] In one possible implementation, S5 specifically includes sub-steps S501 to S503:

[0056] S501: Divide the difficulty into multiple levels and determine the difficulty level of each task.

[0057] Optionally, the difficulty level can be divided into five levels: very easy, easy, medium, difficult, and very difficult.

[0058] S502: Divide production capacity values ​​into multiple levels to determine the production capacity level of each production line.

[0059] Optionally, the production capacity value can be divided into five levels, namely, very low production capacity, low production capacity, medium production capacity, high production capacity and very high production capacity.

[0060] S503: According to the difficulty level of each task and the production capacity level of each production line, the production efficiency of each production line when producing each task is determined:

[0061]

[0062] wherein, E ki represents the production efficiency of the kth production line to complete the ith task, l d represents the difficulty level of the task, l f represents the production capacity level of the production line, and γ represents the production efficiency decay rate.

[0063] In the present application, the difficulty of the task is matched with the production capacity of the production line, which can more accurately allocate tasks, improve production efficiency, reduce production bottlenecks and resource waste, and through the introduction of the production efficiency decay factor, it can dynamically adapt to the changes of production line capacity and task complexity. This method not only optimizes the load distribution of the production line, but also improves the flexibility and intelligence level of production scheduling, which can provide more efficient, stable and flexible production management solutions for enterprises.

[0064] S6: According to the production efficiency of each production line when producing each to-be-processed task, the estimated completion time of each production line when producing each to-be-processed task is determined.

[0065] In one possible implementation, the estimated completion time of the task is specifically:

[0066]

[0067] wherein, F i represents the estimated completion time of the ith task, C ij represents the estimated completion time of the jth process of the ith task, X ijk represents the allocation of the jth process of the ith task to the kth production line for execution, when the jth process of the ith task is allocated to the kth production line for execution, X ijk = 1, when the jth process of the ith task is not allocated to the kth production line for execution, X ijk = 0, Tr k represents the time for the kth production line to transport the product to the transfer station, and K represents the total number of production lines.

[0068] C ij = B ij + Tij

[0069] wherein C ij represents the estimated completion time of the jth process of the ith task, B ij represents the start time of the jth process of the ith task, T ij represents the processing time of the jth process of the ith task.

[0070]

[0071] wherein W ij represents the workload of the jth process of the ith task, PC kj represents the daily productivity of the kth production line in completing the jth process, E ki represents the production efficiency of the kth production line in completing the ith task.

[0072] In the present application, by calculating the estimated completion time of the task, taking into account various factors such as process processing time, production line production capacity, workload, and transportation time, a more accurate production scheduling and task allocation scheme can be provided. Such a method can optimize production efficiency, reduce bottlenecks, improve resource utilization, and enhance the predictability and reliability of production planning. Through real-time monitoring and dynamic adjustment, enterprises can flexibly respond to various changes that may occur in the production process, thereby improving overall production efficiency and customer satisfaction.

[0073] S7: Determine the timeliness of task completion according to the estimated completion time of each task.

[0074] In one possible implementation, the timeliness of task completion is specifically:

[0075]

[0076] wherein G represents the timeliness of task completion, D i represents the agreed delivery deadline of the ith task, F i represents the estimated completion time of the ith task, a i represents the urgency of the ith task, and I represents the total number of tasks.

[0077] It should be noted that if D i >F i , it means that the task is completed on time or ahead of schedule, and contributes a positive value to the timeliness G of the task. Conversely, if D i <F i , it means that the task is not completed on time, and contributes a negative value to the timeliness G of the task.

[0078] In the present application, the timeliness of task completion can be used to measure the on-time completion of tasks and the effectiveness of production scheduling, providing strong data support for optimizing production efficiency and customer satisfaction.

[0079] S8: Determine the fluctuation index of the flow line according to the workloads of each production line.

[0080] In one possible implementation, the fluctuation index of the flow line is specifically:

[0081]

[0082] Where S represents the fluctuation index of the flow line, L k represents the workload of the kth production line, max represents the maximum value, X ijk represents the allocation of the jth process of the ith task to the kth production line for execution, when the jth process of the ith task is allocated to the kth production line for execution, X ijk = 1, when the jth process of the ith task is not allocated to the kth production line for execution, X ijk = 0, T ij represents the processing time of the jth process of the ith task, I represents the total number of tasks, and J represents the total number of processes.

[0083] Where the fluctuation index of the flow line measures the difference in workload between production lines, and the goal is to make the workload of the production lines more balanced.

[0084] In the present application, by calculating and optimizing the fluctuation index of the flow line, the difference in load between production lines can be comprehensively measured, so as to realize reasonable allocation of tasks and optimized use of resources.

[0085] S9: Determine the flow line operation scheme by an intelligent flow line operation model based on artificial intelligence AI, aiming to improve the timeliness of task completion and reduce the fluctuation index of the flow line.

[0086] In one possible implementation, S9 specifically includes sub-steps S901 and S902:

[0087] S901: Build a target function aiming to improve the timeliness of task completion and the fluctuation index of the flow line.

[0088] Optionally, the target function is specifically:

[0089] maxf(X) = λ1G - λ2S

[0090] Where max represents the maximum value, f represents the target function, X represents the flow line operation scheme, X = {X ijk}, Xijk Xij k represents the assignment situation of the jth process of the ith task to the kth production line, Xij k = 1 when the jth process of the ith task is assigned to the kth production line, Xij k = 0 when the jth process of the ith task is not assigned to the kth production line, G represents the task completion timeliness, S represents the pipeline fluctuation index, λ1 represents the weight coefficient of the task completion timeliness, and λ2 represents the weight coefficient of the pipeline fluctuation index. ijk ijk

[0091] The weight coefficient λ1 of the task completion timeliness and the weight coefficient λ2 of the pipeline fluctuation index can be set by a person skilled in the art according to actual conditions, and the present application is not limited.

[0092] S902: According to the objective function, the optimal pipeline operation scheme is determined by combining flower pollination and genetic optimization algorithm.

[0093] The flower pollination and genetic optimization algorithm combines the flower pollination algorithm (FPA) and the genetic algorithm (GA). The flower pollination algorithm is a natural heuristic optimization algorithm, which is inspired by the “pollen transmission” behavior in the process of plant pollination, especially the natural process of pollen transmission by bees and other insects. Through a mathematical model, the global and local optimization of the problem is realized. The genetic algorithm is a global optimization method based on natural selection and genetic mechanism, which simulates the process of biological evolution. Through genetic operations (selection, crossover, mutation), the population is continuously optimized to find the approximate optimal solution of the problem. Genetic algorithm is good at global search, but lacks local search ability. After introducing the flower pollination algorithm, the algorithm can flexibly adjust the search strategy according to the complexity of the problem and the optimization stage.

[0094] Specifically, the objective function is used as the fitness function of the flower pollination and genetic optimization algorithm.

[0095] Initialize the population, which contains multiple individuals, each individual representing a feasible pipeline operation scheme.

[0096] An elite selection strategy is adopted to remove 25% of the individuals with the lowest fitness values to form the first population.

[0097] In the present application, the elite selection strategy can improve the efficiency and effectiveness of the genetic algorithm or other optimization algorithms by retaining the individuals with the highest fitness values and removing the individuals with the lowest fitness values.

[0098] The individuals in the first population are subjected to a crossover operation to form a second population:

[0099] ​​Y1 = rand * X1 + (1 - rand) * X2

[0100] Y2 = rand * X2 + (1 - rand) * X1

[0101] where Y1, Y2 represent new individuals, X1 represents the first parent, X2 represents the second parent, and rand represents a random number between 0 and 1.

[0102] In the present application, the crossover operation generates new individuals (offspring) by combining parts of the genes of two parents. This approach helps to increase diversity in the population, as the new individuals can contain combined features not present in the parents. This diversity avoids the situation where individuals in the population are too similar, reducing the risk of the algorithm getting stuck in a local optimal solution.

[0103] The individuals in the second population are subjected to a mutation operation to form a third population:

[0104]

[0105] where Y3 represents a new individual, X3 represents a parent, X max represents the individual with the highest fitness value, X min represents the individual with the lowest fitness value, and rand represents a random number between 0 and 1.

[0106] In the present application, the mutation operation introduces randomness to change certain parts of the current solution, effectively preventing the algorithm from getting stuck in a local optimal solution during the search process. In particular, in genetic algorithms, after multiple generations of evolution, the population tends to converge to certain optimal solution regions. Without the mutation operation, the algorithm may stagnate near some local optimal solutions. The mutation operation introduces new solutions, increasing the diversity of the solution space, which helps to avoid this local convergence.

[0107] The individuals in the third population are subjected to position updates according to the flower pollination optimization algorithm to form a fourth population. A random number is randomly generated to determine whether the conversion probability is greater than the random number. If so, cross-pollination is performed. Otherwise, self-pollination is performed.

[0108] When cross-pollination is performed, the position of the individual is updated according to the Levy flight mechanism:

[0109]

[0110] where, represents the position of the i-th individual at the t+1 iteration, represents the position of the i-th individual at the t iteration, and θ represents the step size influence factor, L represents the step size, represents the global optimal solution at the t iteration.

[0111]

[0112] where Γ denotes the standard Gamma function, λ denotes the exponential parameter, and s denotes the scale parameter.

[0113] In the present application, the Levy flight mechanism enables the search process to cover a wider solution space by simulating the behavior of long jumps in nature. Compared to the conventional gradient descent algorithm, Levy flight generates step lengths with a heavy-tailed distribution, allowing individuals to make large random jumps and increase the coverage of the solution space. In this way, the algorithm can avoid being trapped in local optimal solutions and explore regions of the solution space far from the current solution.

[0114]

[0115] where θ t denotes the step size influence factor at the tth iteration, q denotes the scaling coefficient, and T denotes the maximum number of iterations.

[0116] In the present application, in the early stage of optimization, the step size is large, enabling the algorithm to extensively explore the solution space and avoid being trapped in local optimal solutions. A larger step size helps to search further regions, thereby improving the global search ability. As the number of iterations increases, the step size gradually decreases, which helps the optimization algorithm to perform fine local search when approaching the optimal solution. A smaller step size can help the algorithm to fine-tune near the global optimal solution, improving the accuracy of the solution.

[0117] When self-pollination is performed, the individual position is updated according to the golden sine mechanism:

[0118]

[0119] x1=-π+2π(1-τ)

[0120] x2=-π+2πτ

[0121] where xj(t) denotes the position of the jth individual at the tth iteration, denotes the position of the kth individual at the tth iteration, r1 and r2 denote random numbers between 0 and 2π, x1 and x2 denote the self-pollination coefficient, and τ denotes the golden section number.

[0122] ​In the present application, by controlling the self-pollination coefficient and the golden sine mechanism, the algorithm can make more flexible adjustments in the local search process, prevent the over-concentration and similarity of individuals, and increase the diversity of the solution space. This can effectively reduce the problem of early convergence, so that the algorithm can continuously explore new solution space regions. At the same time, the golden section number controls the balance of the search range, which can both conduct extensive global search and conduct local optimization when approaching the optimal solution.

[0123] The third population and the fourth population are merged to form a fifth population.

[0124] It is judged whether the current iteration number reaches the maximum iteration number; if yes, the pipeline operation scheme represented by the individual with the highest fitness in the fifth population is output; otherwise, the iteration is continued.

[0125] In the present application, by using the AI-based intelligent pipeline operation model, combining flower pollination and genetic optimization algorithm to optimize the timeliness of task completion and the volatility index of the pipeline, multi-objective optimization can be achieved, the resource utilization efficiency of the production line is improved, the production delay is reduced, and the stability of the production line is improved. The intelligent scheduling system can dynamically adjust task allocation according to real-time production data, optimize production efficiency, reduce production bottlenecks, and enhance the flexibility and adaptability of the production process. This method provides a powerful optimization tool for modern intelligent manufacturing, and promotes the intelligentization and automation of the production system.

[0126] S10: Execute the pipeline operation scheme through the Robotic Process Automation (RPA) technology.

[0127] Among them, the Robotic Process Automation uses automated robots (software robots) to simulate manual operations and complete various tasks on the pipeline according to predetermined production processes, task allocation and scheduling. RPA can automatically perform tasks, monitor production progress, collect data and make decisions during the production process, thereby improving production efficiency, reducing human errors and optimizing production resource utilization.

[0128] Specifically, first, the production tasks and processes need to be standardized, and the RPA tool is used to design the automation process. After the intelligent pipeline operation model based on artificial intelligence AI determines the pipeline operation scheme, the RPA robot simulates manual operation to automatically complete task allocation, data input, material handling, production monitoring and other repetitive work. At the same time, through integration with existing production line systems (such as MES, ERP, etc.), resources are scheduled in real time, production progress is monitored, and data is collected during task execution for feedback and optimization. In this way, RPA can improve production efficiency, reduce human errors, optimize resource allocation, and ensure that production tasks are completed on time, thereby realizing intelligent management of the pipeline.

[0129] The technical scheme provided by the embodiment of the present application has at least the following beneficial effects:

[0130] In the present application, by using an intelligent pipeline operation model based on artificial intelligence AI, the timely degree of task completion is improved and the fluctuation index of the pipeline is reduced, the pipeline operation scheme is dynamically determined in real time, and when the production environment changes, rapid adjustment can be made in real time, the production efficiency is improved, the load imbalance of the production line is reduced, the fluctuation of the production line is reduced, and the stability of the production line is improved.

[0131] Referring to the accompanying drawings Figure 2 , a structure diagram of an intelligent pipeline operation system integrating RPA and AI is shown.

[0132] The present application also provides an intelligent pipeline operation system 20 integrating RPA and AI, which is applied to the intelligent pipeline operation method integrating RPA and AI described above, and comprises:

[0133] a processor 201;

[0134] a memory 202, the memory 202 stores computer readable instructions, and when the computer readable instructions are executed by the processor 201, the intelligent pipeline operation method integrating RPA and AI as described in the method embodiment is realized.

[0135] The intelligent pipeline operation system 20 integrating RPA and AI provided by the present application can execute the intelligent pipeline operation method integrating RPA and AI described above and realize the same or similar technical effects. To avoid repetition, the present application will not be described again.

[0136] The technical scheme provided by the embodiment of the present application has at least the following beneficial effects:

[0137] In the present application, by using an intelligent pipeline operation model based on artificial intelligence AI, the timely degree of task completion is improved and the fluctuation index of the pipeline is reduced, the pipeline operation scheme is dynamically determined in real time, and when the production environment changes, rapid adjustment can be made in real time, the production efficiency is improved, the load imbalance of the production line is reduced, the fluctuation of the production line is reduced, and the stability of the production line is improved.

[0138] It should be appreciated that a processor in the embodiments of the present application can be a central processing unit (CPU). The processor can 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 gates or transistor logic components, discrete hardware components, etc. The general purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0139] It should also be appreciated that the memory in the embodiments of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memory. The non-volatile memory can be a read-only memory (ROM), a programmable ROM (PROM), an erasable PROM (EPROM), an electrically EPROM (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM) used as an external cache. By way of example, and not limitation, many forms of random access memory (RAM) are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0140] The above-described embodiments can be implemented in whole or in part by software, hardware (e.g., circuitry), firmware, or any combination thereof. When implemented in software, the above-described embodiments can be implemented 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 and executed on a computer, the processes or functions described in the embodiments of the present application are wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center through wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server, data center, etc. containing one or more available medium collections. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium can be a solid state disk.

[0141] It should be understood that the term "and / or" herein merely describes an association relationship of associated objects, which means that there can be three relationships, for example, A and / or B can represent the following three cases: A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. In addition, the character " / " herein generally represents an "or" relationship between the associated objects before and after it, but it can also represent an "and / or" relationship, which can be understood according to the context before and after it.

[0142] In the present application, "at least one" means one or more, and "multiple" means two or more. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple.

[0143] It should be understood that in various embodiments of the present application, the size of the sequence number of each process described above does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0144] Those skilled in the art can clearly understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0145] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the devices, apparatuses and units described above can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0146] In several embodiments provided by the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0147] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0148] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically independently, or two or more units can be integrated into one unit.

[0149] If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0150] The embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to realize the intelligent pipeline operation method of fusing RPA and AI.

[0151] The computer readable storage medium provided by the present application can realize the steps and effects of the intelligent pipeline operation method of fusing RPA and AI in the above method embodiment, and the present application will not be repeated here.

[0152] The technical solutions provided by the embodiments of the present application have at least the following beneficial effects:

[0153] In the present application, the intelligent pipeline operation model based on artificial intelligence AI is used to improve the timeliness of task completion and reduce the fluctuation index of the pipeline, dynamically determine the pipeline operation scheme in real time, make rapid adjustment in real time when the production environment changes, improve the production efficiency, reduce the imbalance of the production line load, reduce the fluctuation of the production line, and improve the stability of the production line.

[0154] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0155] The following points need to be explained:

[0156] (1) The drawings of the embodiments of the present application only involve the structures related to the embodiments of the present application, and other structures can refer to the usual design.

[0157] (2) For clarity, in the drawings used to describe the embodiments of the present application, the thickness of layers or regions are exaggerated or reduced, that is, the drawings are not drawn on scale. It will be understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, it can be "directly" on or under the other element or an intervening element can also be present.

[0158] (3) The embodiments of the present application and the features in the embodiments can be combined with each other to obtain new embodiments, without conflict.

[0159] The above merely describes the specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for intelligent pipeline operation by fusing RPA and AI, characterized in that, The method comprises the following steps: S1: constructing an intelligent pipeline operation model based on artificial intelligence AI; S2: obtaining tasks to be processed; S3: determining the difficulty of each task to be processed; S4: determining the production capacity value of each production line; S5: matching the difficulty of the task with the production capacity value of the production line to determine the production efficiency of each production line when producing each task to be processed: ； wherein, E ki represents the production efficiency of the kth production line to complete the ith task, l d represents the difficulty level of the task, l f represents the production capacity level of the production line, and γ represents the production efficiency decay rate; S6: determining the estimated completion time of each production line when producing each task to be processed according to the production efficiency of each production line when producing each task to be processed: ； wherein, F i represents the estimated completion time of the i-th task, C ij represents the estimated completion time of the j-th process of the i-th task, X ijk represents the allocation of the j-th process of the i-th task to the k-th production line for execution, when the j-th process of the i-th task is allocated to the k-th production line for execution, , when the j-th process of the i-th task is not allocated to the k-th production line for execution, , Tr k represents the time for the k-th production line to transport the product to the transit station, and K represents the total number of production lines; ； wherein C ij represents the estimated completion time of the jth process of the ith task, B ij represents the start time of the jth process of the ith task, T ij represents the processing time of the jth process of the ith task; ； wherein, W ij represents the work load of the jth process of the ith task, PC kj represents the daily productivity of the kth production line to complete the jth process, E ki represents the production efficiency of the kth production line to complete the ith task; S7: determining the timeliness of task completion according to the estimated completion time of each task; S8: determining the fluctuation index of the pipeline according to the workload of each production line: ； ； wherein S denotes a fluctuation index of the pipeline, L k denotes a workload of the kth production line, max denotes a maximum value, X ijk denotes an assignment of the jth process of the ith task to the kth production line for execution, when the jth process of the ith task is assigned to the kth production line for execution, , when the jth process of the ith task is not assigned to the kth production line for execution, , T ij denotes a processing time of the jth process of the ith task, I denotes a total number of tasks, and J denotes a total number of processes. S9: determining a pipeline operation scheme through an intelligent pipeline operation model based on artificial intelligence AI, aiming to improve the timeliness of task completion and reduce the fluctuation index of the pipeline; S10: executing the pipeline operation scheme through robot process automation RPA technology; The S9 specifically comprises: S901: constructing an objective function aiming to improve the timeliness of task completion and the fluctuation index of the pipeline; S902: determining the best pipeline operation scheme through flower pollination combined with genetic optimization algorithm according to the objective function; The objective function is specifically: ； wherein max denotes a maximum value, f denotes an objective function, X denotes a pipeline operation plan, , X ijk denotes an assignment of the jth process of the ith task to the kth production line, when the jth process of the ith task is assigned to the kth production line, , when the jth process of the ith task is not assigned to the kth production line, , G denotes a task completion timeliness, S denotes a pipeline fluctuation index, λ1 denotes a weight coefficient of the task completion timeliness, and λ2 denotes a weight coefficient of the pipeline fluctuation index. 2.The intelligent pipeline job method of fusing RPA with AI according to claim 1, wherein, The S3 is specifically: determining the difficulty of the task to be processed according to the process required by the task to be processed. 3.The intelligent pipeline job method of fusing RPA with AI according to claim 1, wherein, The S4 is specifically: determining the production capacity value of the production line according to the performance of the production line when processing standard processes. 4.The intelligent pipeline job method of fusing RPA with AI according to claim 1, wherein, The S5 specifically comprises: S501: dividing the difficulty into multiple levels to determine the difficulty level of each task; S502: dividing the production capacity value into multiple levels to determine the production capacity level of each production line; S503: determining the production efficiency of each production line when producing each task according to the difficulty level of each task and the production capacity level of each production line.

5. An intelligent pipeline operation system fusing RPA and AI, characterized in that, The method comprises the following steps: a processor; a memory, the memory having computer readable instructions stored thereon, the computer readable instructions being executed by the processor to implement the intelligent pipeline operation method of fusion RPA and AI according to any one of claims 1 to 4.

Images