Method and apparatus for generating target strategy for job procedures, and device and medium

Abstract

A method (900) and apparatus (1000) for generating a target strategy for job procedures, and a device (1100) and a medium. The method (900) comprises: acquiring a plurality of genetic algorithm strategies for a plurality of job procedures (902); comparing the shortest job duration of the plurality of genetic algorithm strategies with the shortest job duration of a plurality of assignment strategies (904); in response to the shortest job duration of the plurality of assignment strategies being shorter than the shortest job duration of the plurality of genetic algorithm strategies, reducing a genetic probability used for crossover and / or mutation (906); and using the reduced genetic probability to perform crossover and / or mutation on procedure sequences and / or job devices in the plurality of genetic algorithm strategies, so as to generate a target strategy for the plurality of job procedures (908). During crossover and mutation, a genetic probability used for crossover and / or mutation can be dynamically adjusted on the basis of job durations of genetic algorithm strategies that have been subjected to crossover and / or mutation, thereby shortening the time it takes to acquire a target strategy for job procedures.

Description

Method, apparatus, device and medium for generating target strategy for operation process Technical Field

[0001] Embodiments of the present disclosure relate to the field of industrial automation technology, and more particularly to a method, apparatus, device, and medium for generating a target strategy for a work process. Background Art

[0002] The workshop is the basic unit of production for a factory or enterprise. Multiple production units are arranged within the workshop, working in coordination to fulfill the factory's or enterprise's production, processing, and logistics plans. When machining workpieces in the workshop, the design of the work processes involved falls under the flexible job-shop scheduling problem (FJSP), a category within the job-shop scheduling problem (JSP). In this scenario, multiple workpieces are processed on multiple machines, and each workpiece processing task consists of a series of work processes. Therefore, the design of work process processes can vary widely.

[0003] To improve machining efficiency, workshop managers currently use computing devices to schedule work processes and generate work process design strategies. Therefore, a method is desired to use computing devices to select an ideal strategy from multiple possible work process design strategies to generate a usable strategy.

[0004] Summary of the Invention

[0005] According to an example embodiment of the present disclosure, a technical solution for generating a target strategy for an operation process is provided, which can optimize the strategy of the operation process based on crossover and mutation, and in the process of crossover and mutation, can dynamically adjust the genetic probability used for crossover and / or mutation based on the operation duration of the genetic algorithm strategy after crossover and mutation, thereby gradually reducing the number of crossover and / or mutation strategies, allowing crossover and mutation to quickly find the desired target strategy in the early stage and quickly converge in the later stage, thereby reducing the time to obtain the target strategy for the operation process.

[0006] In a first aspect of the present disclosure, a method for generating a target strategy for a work process is provided. The method may include obtaining multiple genetic algorithm strategies for multiple work processes. The multiple genetic algorithm strategies are generated based on crossover and mutation of process sequences and / or work equipment corresponding to multiple allocation strategies, and each genetic algorithm strategy in the multiple genetic algorithm strategies includes the process sequence of the multiple work processes and the work equipment for each of the multiple work processes. The method may also include comparing the shortest work durations of the multiple genetic algorithm strategies with the shortest work durations of the multiple allocation strategies. After the comparison, the method may also include reducing the genetic probability used for crossover and / or mutation in response to the shortest work duration of the multiple allocation strategies being less than the shortest work duration of the multiple genetic algorithm strategies. The genetic probability includes a crossover probability and / or a mutation probability. The method may also include generating the target strategies for the multiple work processes by crossover and / or mutation of the process sequences and / or work equipment in the multiple genetic algorithm strategies using the reduced genetic probability.

[0007] In combination with the first aspect, in some embodiments, the method further includes determining a plurality of work processes and a plurality of process sequences of the plurality of work processes, and for each process sequence in the plurality of process sequences, encoding each process sequence into a first set of codes by arranging each work process in sequence with a corresponding single-bit representation. The method further includes selecting work equipment for each of the plurality of work processes from the available equipment for each of the plurality of work processes to obtain a plurality of work equipment sets. For each work equipment set, the method further includes encoding the work equipment of the plurality of work processes into a second set of codes by arranging the single-bit representations corresponding to the work equipment of the plurality of work processes according to the numbering order of the workpieces processed by the work process and the order of the work process corresponding to each workpiece when processing the workpiece, and combining the plurality of first sets of codes corresponding to the plurality of process sequences and the plurality of second sets of codes corresponding to the plurality of work equipment sets into a plurality of allocation strategies.

[0008] In combination with the first aspect, in some embodiments, the method further includes, for each allocation strategy, determining, based on the process sequence of multiple work processes, the work equipment of each work process in the multiple work processes, and the operation duration of the multiple work processes, the equipment release duration that each work equipment needs to wait for before executing each corresponding work process. The method further includes, based on the predetermined sequence constraints between the multiple work processes and the operation duration of the multiple work processes, determining the duration of the immediate predecessor process that each work equipment needs to wait for before executing each corresponding work process. The method further includes determining the completion duration of each workpiece based on the equipment release duration and the immediate predecessor process duration of the operation process for processing each workpiece, as well as the operation duration of the operation process for processing each workpiece. The method further includes determining the operation duration of each allocation strategy from the multiple completion durations of the multiple workpieces corresponding to each allocation strategy.

[0009] In combination with the first aspect, in some embodiments, the method also includes comparing the initial probability adjustment coefficient used to update the genetic probability with a predetermined coefficient threshold, and in response to the probability adjustment coefficient being greater than the predetermined coefficient threshold, comparing the operation durations of multiple genetic algorithm strategies and the operation durations of multiple allocation strategies.

[0010] In combination with the first aspect, in some embodiments, reducing the genetic probability includes reducing the probability adjustment coefficient to update the reduced probability adjustment coefficient to the probability adjustment coefficient, and then reducing the genetic probability based on the probability adjustment coefficient.

[0011] In combination with the first aspect, in some embodiments, the method further includes maintaining the genetic probability from being reduced at the target acceptance probability in response to the shortest job duration of multiple allocation strategies being greater than or equal to the shortest job duration of multiple genetic algorithm strategies.

[0012] In conjunction with the first aspect, in some embodiments, crossover and mutation are limited by predetermined sequence constraints between the plurality of work processes and available equipment for the work processes.

[0013] In combination with the first aspect, in some embodiments, generating a target strategy includes crossing multiple genetic algorithm strategies based on the crossover probability to obtain multiple crossover genetic algorithm strategies, mutating the process sequence and operating equipment corresponding to the multiple crossover genetic algorithm strategies based on the mutation probability to obtain multiple candidate strategies, and then determining the target strategy for the operating process from the multiple candidate strategies.

[0014] In combination with the first aspect, in some embodiments, crossing multiple genetic algorithm strategies includes dividing multiple workpieces corresponding to multiple processes into multiple workpiece subsets. The multiple workpiece subsets include a first part of the workpiece subset and a second part of the workpiece subset other than the first part of the workpiece subset. Crossing also includes crossing the process sequence of the operating processes corresponding to the first part of the workpiece subset in multiple genetic algorithm strategies for crossing, and keeping the process sequence of the operating processes corresponding to the second part of the workpiece subset unchanged, so as to obtain the crossover process sequence corresponding to each crossover genetic algorithm strategy. Crossing also includes determining one or more operating processes from the multiple operating processes, and crossing the operating equipment of one or more operating processes in the multiple genetic algorithm strategies for crossing, so as to obtain the crossover operating equipment corresponding to each crossover genetic algorithm strategy.

[0015] In conjunction with the first aspect, in some embodiments, mutating the process sequences and equipment corresponding to multiple crossover genetic algorithm strategies includes determining multiple first process sequences for mutation in the genetic algorithm strategy for mutation, swapping the process sequences of the multiple first process sequences to obtain process sequences corresponding to multiple candidate strategies. Mutating also includes determining multiple second process sequences for mutation in the genetic algorithm strategy for mutation, and changing the equipment for the multiple second process sequences to equipment other than the equipment for the multiple second process sequences from among the available equipment for the multiple second process sequences, to obtain equipment corresponding to the multiple candidate strategies.

[0016] In combination with the first aspect, in some embodiments, in response to satisfying one of the following items, a candidate strategy among multiple candidate strategies that meets the preset duration requirement will be output as a target strategy: the number of crossovers and mutations performed before obtaining the multiple candidate strategies reaches a predetermined number threshold, there are candidate strategies among the multiple candidate strategies whose operation duration is less than or equal to the predetermined duration threshold, or the rate of change of the operation duration of the multiple candidate strategies and the operation duration between the multiple genetic algorithm strategies meets the predetermined change rate condition.

[0017] In a second aspect of the present disclosure, a device for generating target strategies for a work process is provided. The device includes an acquisition module configured to acquire multiple genetic algorithm strategies for multiple work processes. The multiple genetic algorithm strategies are generated based on crossover and mutation of process sequences and / or work equipment corresponding to multiple allocation strategies, and each of the multiple genetic algorithm strategies includes the process sequence of multiple work processes and the work equipment for each of the multiple work processes. The device also includes a comparison module configured to compare the shortest operation durations of the multiple genetic algorithm strategies with the shortest operation durations of the multiple allocation strategies. The device also includes a reduction module configured to reduce the genetic probabilities used for crossover and / or mutation in response to the shortest operation durations of the multiple allocation strategies being less than the shortest operation durations of the multiple genetic algorithm strategies. The genetic probabilities include crossover probabilities and / or mutation probabilities. The device also includes a generation module configured to generate target strategies for the multiple work processes by crossover and / or mutation of the process sequences and / or work equipment in the multiple genetic algorithm strategies using the reduced genetic probabilities.

[0018] In combination with the second aspect, in some embodiments, the apparatus further comprises an encoding module, the encoding module being configured to determine a plurality of work processes and a plurality of process sequences of the plurality of work processes, and for each process sequence in the plurality of process sequences, encoding each process sequence into a first set of codes by arranging each work process in sequence with a corresponding single-bit representation. The encoding module is configured to select the work equipment of each work process in the plurality of work processes from the available equipment of each work process in the plurality of work processes to obtain a plurality of work equipment sets. For each work equipment set, the encoding module is configured to encode the work equipment of the plurality of work processes into a second set of codes by arranging the single-bit representations corresponding to the work equipment of the plurality of work processes in the order of the numbers of the work processes processed by the work processes and the order of the work processes corresponding to each work workpiece, and combining the plurality of first sets of codes corresponding to the plurality of process sequences and the plurality of second sets of codes corresponding to the plurality of work equipment sets into a plurality of allocation strategies.

[0019] In combination with the second aspect, in some embodiments, the device further includes a duration calculation module, which is configured to determine, for each allocation strategy, the equipment release duration that each work equipment needs to wait for before executing each corresponding work process based on the process sequence of multiple work processes, the work equipment of each work process in the multiple work processes, and the work duration of the multiple work processes. The duration calculation module is also configured to determine the predecessor process duration that each work equipment needs to wait for before executing each corresponding work process based on the predetermined sequence constraints between the multiple work processes and the work duration of the multiple work processes. The duration calculation module is also configured to determine the completion duration of each workpiece based on the equipment release duration and the predecessor process duration of the work process for processing each workpiece, as well as the work duration of the work process for processing each workpiece. The duration calculation module is also configured to determine the work duration of each allocation strategy from the multiple completion times of the multiple workpieces corresponding to each allocation strategy.

[0020] In combination with the second aspect, in some embodiments, the comparison module is also configured to compare the initial probability adjustment coefficient used to update the genetic probability with a predetermined coefficient threshold, and in response to the probability adjustment coefficient being greater than the predetermined coefficient threshold, compare the job durations of multiple genetic algorithm strategies and the job durations of multiple allocation strategies.

[0021] In combination with the second aspect, in some embodiments, the reduction module is further configured to reduce the probability adjustment coefficient to update the reduced probability adjustment coefficient to the probability adjustment coefficient, and then reduce the genetic probability based on the probability adjustment coefficient.

[0022] In combination with the second aspect, in some embodiments, the reduction module is further configured to keep the genetic probability from being reduced at the target acceptance probability in response to the shortest job duration of multiple allocation strategies being greater than or equal to the shortest job duration of multiple genetic algorithm strategies.

[0023] In conjunction with the second aspect, in some embodiments, crossover and mutation are limited by predetermined sequence constraints between the plurality of work processes and available equipment for the work processes.

[0024] In combination with the second aspect, in some embodiments, the generation module is further configured to cross multiple genetic algorithm strategies based on the crossover probability to obtain multiple crossover genetic algorithm strategies, and based on the mutation probability, mutate the process sequence and operating equipment corresponding to the multiple crossover genetic algorithm strategies to obtain multiple candidate strategies, and then determine the target strategy for the operating process from the multiple candidate strategies.

[0025] In conjunction with the second aspect, in some embodiments, the generation module is further configured to divide the multiple workpieces corresponding to the multiple processes into multiple workpiece subsets. The multiple workpiece subsets include a first part of the workpiece subset and a second part of the workpiece subset other than the first part of the workpiece subset. The generation module is further configured to cross the process sequence of the operating processes corresponding to the first part of the workpiece subset in multiple genetic algorithm strategies for crossover, and keep the process sequence of the operating processes corresponding to the second part of the workpiece subset unchanged, so as to obtain the crossover process sequence corresponding to each crossover genetic algorithm strategy. The generation module is further configured to determine one or more operating processes from the multiple operating processes, and to cross the operating equipment of one or more operating processes in the multiple genetic algorithm strategies for crossover, so as to obtain the crossover operating equipment corresponding to each crossover genetic algorithm strategy.

[0026] In conjunction with the second aspect, in some embodiments, the generation module is further configured to determine multiple first operating procedures for mutation in the genetic algorithm strategy for mutation, swap the process order of the multiple first operating procedures to obtain process orders corresponding to multiple candidate strategies. The generation module is further configured to determine multiple second operating procedures for mutation in the genetic algorithm strategy for mutation, and change the operating equipment of the multiple second operating procedures to operating equipment other than the operating equipment of the multiple second operating procedures from the multiple available equipment for the second operating procedures to obtain operating equipment corresponding to the multiple candidate strategies.

[0027] In combination with the second aspect, in some embodiments, the generation module is further configured to output a candidate strategy that meets the preset duration requirement among multiple candidate strategies as a target strategy in response to satisfying one of the following items: the number of crossovers and mutations performed before obtaining the multiple candidate strategies reaches a predetermined number threshold, there are candidate strategies among the multiple candidate strategies whose operation duration is less than or equal to the predetermined duration threshold, or the rate of change of the operation durations of the multiple candidate strategies and the multiple genetic algorithm strategies meets the predetermined change rate condition.

[0028] The target strategy generated by the above embodiment can optimize the operation process based on crossover and mutation. During the crossover and mutation process, the genetic probability used for crossover and / or mutation can be dynamically adjusted based on the operation duration of the genetic algorithm strategy after crossover and mutation, gradually reducing the number of crossover and / or mutation strategies. This allows crossover and mutation to quickly find the desired target strategy in the early stages and quickly converge in the later stages. This reduces the time it takes to obtain the target strategy for the operation process.

[0029] In a third aspect of the present disclosure, an electronic device for generating a target policy is provided. The electronic device includes: an electronic device including one or more processors and a memory, the memory being configured to store computer-executable instructions, wherein the computer-executable instructions, when executed by the one or more processors, cause the electronic device to implement any of the methods described in the first aspect above.

[0030] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored. When the computer-executable instructions are executed, at least one processor is caused to perform the method according to any one of the above first aspects.

[0031] In a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein the computer program is executed by a processor to perform the method according to any one of the above first aspects.

[0032] By implementing the above aspects of the present disclosure and combining them with the embodiments, it is possible to optimize the strategies of the operation process based on crossover and mutation, and during the crossover and mutation process, the genetic probability used for crossover and / or mutation can be dynamically adjusted based on the operation duration of the genetic algorithm strategy after crossover and mutation, gradually reducing the number of crossover and / or mutation strategies, so that crossover and mutation can quickly find the desired target strategy in the early stage and quickly converge in the later stage, thereby reducing the time to obtain the target strategy of the operation process.

[0033] This summary is provided to introduce a selection of concepts in a simplified form that are further described in the detailed description below. This summary is not intended to identify key features or essential features of the disclosure, nor is it intended to limit the scope of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0035] FIG1 is a schematic diagram showing a method for generating a target strategy for a job process according to some embodiments of the present disclosure;

[0036] FIG2 shows an example of a job process design strategy obtained by combining coded representations according to some embodiments of the present disclosure;

[0037] FIG3 shows an example of crossover when the job process design strategy includes a vector composed of single-bit representations for representing process sequences according to some embodiments of the present disclosure;

[0038] FIG4 illustrates an example of crossover when a work process design strategy includes a vector composed of single-bit representations for representing work equipment of each work process according to some embodiments of the present disclosure;

[0039] FIG5 shows an example of variation when a job process design strategy includes a vector composed of single-bit representations for representing process sequences according to some embodiments of the present disclosure;

[0040] FIG6 shows an example of variation when a work process design strategy includes a vector composed of single-bit representations for representing work equipment for each work process according to some embodiments of the present disclosure;

[0041] FIG7 shows that when the operation process design strategy is in the form of a code representation, an electronic device decodes it to obtain a Gantt chart of the operation duration according to some embodiments of the present disclosure;

[0042] FIG8 shows an example of simulation results according to some embodiments of the present disclosure;

[0043] FIG9 shows a flowchart of a method for generating a target strategy for a job process according to some embodiments of the present disclosure;

[0044] FIG10 shows a schematic diagram of an apparatus for generating a target strategy for a job process according to some embodiments of the present disclosure; and

[0045] FIG11 shows a schematic structural diagram of a device that can be used to implement an embodiment of the present disclosure.

[0046] List of reference numerals:

[0047] 102: Determine the parameters used to generate the strategy

[0048] 104: Data processing based on the obtained parameters for generating strategies

[0049] 106: Multiple initial operation process design strategies

[0050] 108: Initialize the optimization parameters and combine them with the parameters used for subsequent crossover and mutation

[0051] 110: Determine whether the initial operation process design strategy can be used for workpiece processing

[0052] 112: Optimizing Operation Process Design Strategies

[0053] 1122: Select the operation process design strategy with shorter operation time as the optimization object

[0054] 1124: Cross

[0055] 1126: Mutation

[0056] 114: Reduce crossover probability and / or mutation probability

[0057] 116: Output

[0058] 118: Determine whether the coefficient is too small

[0059] 120: Calculate the operation duration of the updated operation process design strategy

[0060] 122: Calculate or obtain the operation duration of the operation process design strategy before the update

[0061] 124: Calculate the duration difference of the job

[0062] 126: Determine whether the difference is less than zero

[0063] 128: Crossover probability and / or mutation probability decreased

[0064] 130: Decrease according to a certain probability

[0065] 301: A process sequence vector before crossover

[0066] 302: Another process sequence vector before crossover

[0067] 303: A process sequence vector after crossover

[0068] 304: Another process sequence vector after crossover

[0069] 401: A working device vector before crossing

[0070] 402: Another job device vector before crossing

[0071] 403: A working device vector after crossing

[0072] 404: Another job device vector after crossing

[0073] 501: A process sequence vector before mutation

[0074] 502: Another process sequence vector before mutation

[0075] 503: A process sequence vector after mutation

[0076] 504: Another process sequence vector after mutation

[0077] 601: A working device vector before mutation

[0078] 602: Another operating device vector before mutation

[0079] 603: A mutated operating device vector

[0080] 604: Another operating device vector after mutation

[0081] 801: The method disclosed herein obtains the number of iterations of the target strategy.

[0082] 802: The number of iterations of the target strategy obtained by the traditional method

[0083] 902: Obtain multiple genetic algorithm strategies for multiple work processes

[0084] 904: Comparing the shortest operation durations of multiple genetic algorithm strategies and the shortest operation durations of multiple allocation strategies

[0085] 906: In response to the shortest operation duration of the multiple allocation strategies being less than the shortest operation duration of the multiple genetic algorithm strategies, reducing the genetic probability for crossover and / or mutation

[0086] 908: Generate target strategies for multiple work processes by crossover and / or mutation of the process sequences and / or work equipment in the multiple genetic algorithm strategies using reduced genetic probabilities

[0087] 1000: Device

[0088] 1002: Get module

[0089] 1004: Comparison module

[0090] 1006: Reduce module

[0091] 1008: Generate module

[0092] 1010: Encoding module

[0093] 1012: Duration calculation module

[0094] 1100: Equipment

[0095] 1101: CPU

[0096] 1102: ROM

[0097] 1103: RAM

[0098] 1104: Bus

[0099] 1105: I / O interface

[0100] 1106: Input unit

[0101] 1107: Output unit

[0102] 1108: Storage unit

[0103] 1109: Communication unit DETAILED DESCRIPTION

[0104] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0105] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to." The term "based on" should be understood as "based at least in part on." The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment." The terms "first," "second," etc. may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0106] When selecting a desired allocation strategy, one criterion for evaluating its performance is its operation duration. Strategies with shorter operation durations are generally considered more ideal, as such strategies can improve workshop productivity. Therefore, to optimize strategies with shorter operation durations, the shortest possible maximum completion time can be used as the optimization metric. However, current methods often require considerable computational effort, resulting in long computation times.

[0107] The present disclosure proposes a method, apparatus, device, and medium for generating a target strategy for a work process. The method for generating a target strategy for a work process includes obtaining multiple genetic algorithm strategies for multiple work processes. The multiple genetic algorithm strategies are generated based on crossover and mutation of the process sequences and / or work equipment corresponding to multiple allocation strategies, and each of the multiple genetic algorithm strategies includes the process sequences of the multiple work processes and the work equipment for each of the multiple work processes. The method may also include comparing the shortest operation durations of the multiple genetic algorithm strategies with the shortest operation durations of the multiple allocation strategies. After the comparison, the method may also include reducing the genetic probability used for crossover and / or mutation in response to the shortest operation duration of the multiple allocation strategies being less than the shortest operation duration of the multiple genetic algorithm strategies. The genetic probability includes the crossover probability and / or mutation probability. According to the embodiments of the present disclosure, the strategies for the work processes can be optimized based on crossover and mutation. During the crossover and mutation process, the genetic probability used for crossover and / or mutation can be dynamically adjusted based on the operation durations of the genetic algorithm strategies after crossover and mutation, gradually reducing the number of crossover and / or mutation strategies, enabling the crossover and mutation process to quickly find the desired target strategy in the early stages and quickly converge in the later stages. This reduces the time required to obtain the target strategy for the operation process.

[0108] The method proposed in the present disclosure is described below with reference to FIG1 . FIG1 shows a schematic diagram of the method. The method in FIG1 can be executed on a variety of electronic devices, devices, and other computing carriers such as desktop computers, laptop computers, smart phones, and computing platforms. For ease of understanding, in some places in this article, the method in FIG1 is described as being executed by an electronic device, but this should not be understood as a limitation of the present disclosure. In some embodiments, the parameters for generating a strategy can be first determined 102 . In an embodiment of optimizing the operating procedures of a workpiece, the parameters determined in 102 may include the workpieces to be processed, the operating procedures required to process these workpieces, the equipment used to perform these operating procedures, and the processing time required for the equipment to perform these operating procedures. For example, a user can input the following Table 1 into an electronic device so that the electronic device determines the parameters of the actual problem 102 . Alternatively, in some embodiments, the electronic device 102 can also actively obtain parameters such as Table 1 from an external source, such as an external database.

[0109] Table 1 Example of parameters used to generate strategies

[0110] The cells corresponding to equipment and work steps show the processing time required for each piece of equipment to perform the work step. A "-" indicates that the equipment cannot perform the corresponding work step. For example, assuming the processing time is measured in hours, a "2" in the cells corresponding to M1 and O11 indicates that it takes equipment M1 two hours to perform work step O11, while a "-" in the cells corresponding to equipment M3 and work step O21 indicates that equipment M3 cannot perform work step O21. In workshop production, this information is needed to optimize work steps and achieve the desired strategy.

[0111] The electronic device can then perform data processing 104 based on the obtained parameters for generating the strategy to generate 106 a plurality of initial operation process design strategies. In some embodiments, the allocation strategy can refer to the initial operation process design strategy. In other embodiments, the allocation strategy can also refer to the previous generation of non-initial operation process design strategies used to generate the current generation of operation process design strategies in an iterative process (e.g., based on crossover, mutation, etc. as described below). In this case, the current generation of operation process design strategies can be referred to as genetic algorithm strategies. It will be understood that the operation process design strategy can include the process sequence of the operation processes required to process the workpiece, as well as the operation equipment that performs each operation process. Taking the required parameters included in Table 1 as an example, the process sequence corresponding to one of the multiple work process design strategies generated can be: O21->O11->O12->O22->O13->O23->O31->O32->O33, and the optional range of work equipment for each work process (that is, the available equipment for each work process) can be expressed in process sequence as: [M1, M2]->[M1, M2, M3]->[M1, M2, M3]->[M1, M2, M3]->[M1, M3]->[M1, M2, M3]->[M1, M3]->[M1, M2, M3]->[M1, M3]->[M1, M2, M3]->[M1, M3]->[M1, M2, M3], that is, the work equipment of the work process O21 can be one of M1 and M2, and the work equipment of the work process O11 can be one of M1, M2 and M3. No further details are given for other work processes. It should be noted that each operation procedure in the operation procedure design strategy mentioned in this disclosure must comply with the predetermined order constraints and available equipment constraints. For example, in the example in Table 1, operation O21 must be executed before O22 and O23, and O22 must be executed before O23. Moreover, the operation equipment for O21, O22, and O23 can only be selected from [M1, M2], [M1, M2, M3], and [M1, M3], respectively. Therefore, in some embodiments, any processing related to the operation procedure design strategy in this disclosure is also subject to the predetermined order constraints and available equipment constraints, such as the crossover, mutation, and operation duration calculation described below.

[0112] There are various methods for processing data 104, as long as the processed work process design strategy includes the required information described above. For example, parameters 104 can be processed into a table, vector, or the like to obtain multiple initial work process design strategies. In some embodiments, the same type of information can be encoded in a single-bit representation as a set of codes, such as vectors, such as a set of codes corresponding to the process sequence and a set of codes corresponding to the work equipment, to reduce storage space and the amount of computation required for processing. For example, after an electronic device obtains parameters and determines multiple process sequences based on the parameters, the process sequence O21->O11->O12->O22->O13->O23->O31->O32->O33 can be encoded as a set of codes (also referred to as a first set of codes) including single-bit representations corresponding to the work processes O21, O11, O12, O22, O13, O23, O31, O32, and O33, respectively. In some embodiments, the work processes used to process the same workpiece can have the same single-bit representation. For example, the process sequence O21->O11->O12->O22->O13->O23->O31->O32->O33 can be encoded as a single-bit vector 2;1;1;2;1;2;3;3;3, according to the order of the work steps. The values ​​1, 2, and 3 in the vector respectively refer to the work steps used to process workpieces J1, J2, and J3. Due to the predetermined order constraint between the work steps, the work steps used to process the same workpiece can be represented in the vector while reducing the number of single-bit representations. For example, the electronic device can understand that the first 1 from left to right refers to work step O11, the second 1 from left to right refers to work step O12, and so on.

[0113] In some embodiments, the operating equipment for an operating process can also be represented by a single bit. For example, the operating equipment selected from the available equipment for performing the operating process can be arranged according to the order of the numbers of the workpieces processed by the operating process and the order of the corresponding operating process when processing each workpiece to obtain a set of coded representations (also referred to as the second set of codes). For example, assuming that the operating equipment used by O21, O11, O12, O22, O13, O23, O31, O32, and O33 are M2, M3, M1, M2, M1, M3, M2, M1, and M2 respectively, then M2, M3, M1, M2, M1, M3, M2, M1, and M2 can be arranged according to the order of the numbers of the workpieces processed by the operating process and the order of the corresponding operating process when processing each workpiece to encode M2, M3, M1, M2, M1, M3, M2, M1, and M2 into a coded representation including a single bit representation (also referred to as the second set of codes). For example, the encoded representation can be the vector 3;1;1;2;2;3;2;1;2, where 1, 2, and 3 in this vector represent devices M1, M2, and M3, respectively. The first three values ​​3, 3, and 1 indicate that the devices used to perform work steps O11, O12, and O13 are M3, M3, and M1, respectively. The middle three values ​​2, 2, and 3 indicate that the devices used to perform work steps O21, O22, and O23 are M2, M2, and M3, respectively. The last three values ​​2, 1, and 2 indicate that the devices used to perform work steps O31, O32, and O33 are M2, M1, and M2, respectively. The resulting encoding group can be expressed in this manner using the order of the vector itself, using a smaller single-bit representation to reflect the correspondence between work devices and work steps in the vector.

[0114] FIG2 illustrates an example of an initial operation process design strategy obtained by combining the first and second sets of codes in an embodiment of obtaining a first set of codes and a second set of codes to generate an initial operation process design strategy. The operation process design strategy in FIG2 includes two vectors, wherein the upper vector is the first set of codes, which is used to represent the process sequence of multiple operation processes, and the lower vector is the second set of codes, which is used to represent the operation equipment of multiple operation processes. In the embodiment of FIG2 , each first set of codes can be combined with each second set of codes to obtain multiple initial operation process design strategies of the same form as the operation process design strategy shown in FIG2 . It should be noted that the multiple initial operation process design strategies can only be a number of possible operation process design strategies, rather than exhausting all possible operation process design strategies. The electronic device can process these multiple possible operation process design strategies through subsequent optimization to obtain a target strategy, thereby reducing the computational complexity and time consumption of initially generating the operation process design strategy.

[0115] Returning to Figure 1 , when generating the initial operation process design strategy, the electronic device may also initialize optimization parameters for subsequent optimization and combine the optimization parameters with parameters for subsequent crossover and mutation processes 108 to implement the method of the present disclosure. In an embodiment of the present disclosure, the electronic device may initialize optimization parameters for adjusting parameters for subsequent crossover and mutation processes and combine these optimization parameters with parameters for subsequent crossover and mutation processes. Exemplarily, the optimization parameters may include coefficients for reducing the crossover probability and / or mutation probability. For example, during the first iteration, the coefficient for reducing the crossover probability and / or mutation probability may be initialized to 1, and a target value for adjusting the coefficient may be initialized. During subsequent iterations, the coefficient for reducing the crossover probability and / or mutation probability may be dynamically adjusted by changing the target value. The reduced crossover probability and / or mutation probability is determined based on the adjusted coefficient and the current crossover probability and / or mutation probability. Since the first iteration process is used as an example in the description of Figure 1 , the specific process for reducing the crossover probability and / or mutation probability is not discussed here. For the exemplary reduction process, please refer to the description of 114 and 118-130 in Figure 1 below.

[0116] After generating the initial operation process design strategy, the electronic device can determine 110 whether the initial operation process design strategy can be used for workpiece processing (for example, whether a predetermined stop condition is met), that is, whether the initial operation process design strategy can be directly output 116 as a target strategy. In some embodiments, the operation duration of each initial operation process design strategy can be calculated, and the operation process design strategy with a shorter operation duration can be selected from them (for example, the N operation process design strategies with the shortest operation duration, where N is greater than zero). Then, it is determined whether the operation duration of the selected operation process design strategy is short enough. For example, the operation duration can be compared with a predetermined duration threshold. If the operation duration is less than or equal to the predetermined duration threshold, the selected operation process design strategy can be directly output as the target strategy. On the contrary, if the operation duration is greater than the predetermined duration threshold, it means that the operation duration of this batch of initial operation process design strategies is still long and needs to be optimized 112. The specific method for calculating the operation duration is described below. It can be understood that in the present disclosure, any processing related to the operation duration can be performed by selecting an operation process design strategy with a shorter operation duration from multiple operation process design strategies and using its operation duration to represent the operation duration of these multiple operation process design strategies. For example, the comparison between the operation durations mentioned below can be performed by this method, which will not be repeated below.

[0117] After determining that optimization 112 is necessary, the electronic device selects 1122 a process design strategy with a shorter operation duration from the currently generated process design strategies as the optimization target. It should be noted that the principle selected here may or may not be consistent with the previously selected principle. After selecting the process design strategy to be optimized, the electronic device may perform crossover 1124 and mutation 1126 on it to obtain multiple optimized process design strategies. In some embodiments, if the allocation strategy refers to the initial process design strategy, these multiple optimized process design strategies may be referred to as multiple genetic algorithm strategies. It should be noted that while both crossover 1124 and mutation 1126 are shown in FIG1 , only one of them may be performed during actual execution. For example, only crossover 1124 may be performed without mutation 1126, or only mutation 1126 may be performed without 1124. Regarding process sequence crossover, in some embodiments, crossover may be performed for all process steps required to process all workpieces. Alternatively, the process sequence of only the process steps required to process a portion of the workpieces may be crossovered, while the process sequence of the process steps required to process another portion of the workpieces may remain unchanged to avoid confusion and high computational effort. For example, when the workpieces to be processed include J1, J2, and J3, only the operations required for cross-processing J1 and J3 can be performed.

[0118] Referring to Figure 3, an example of a process sequence for cross-processing only a portion of a workpiece is shown when the process design strategy includes a vector composed of single-bit representations representing the process sequence. Vector 301 corresponds to the process sequence O21->O11->O12->O22->O13->O23->O31->O32->O33, and vector 302 corresponds to the process sequence O11->O21->O31->O12->O22->O32->O13->O23->O33. The meaning of each value can be found in the above description and will not be repeated here. Assuming that only the process sequence of the operating procedures required for processing workpieces J1 and J3 is crossed, and the process sequence of the operating procedures required for processing workpiece J2 remains unchanged, the operating procedures for processing workpieces J1 and J3 in 301 and the operating procedures for processing workpieces J1 and J3 in 302 can be crossed to 303 and 304 respectively, and then the operating procedures for processing workpiece J2 are kept unchanged in 303 and 304 to complete the crossing and obtain the crossed process sequences 303 and 304 corresponding to the crossed operating procedure design strategy. For the operating equipment, in some embodiments, the operating equipment of all operating procedures can be crossed. Alternatively, only the operating equipment of some operating procedures can be crossed. In some examples, if the operating equipment of the operating procedure is represented as a coded representation (such as a vector), the operating procedure that needs to cross the operating equipment can be performed based on the position selected in the coded representation.

[0119] Referring to FIG. 4 , an example of performing crossover based on selected positions in the coded representation is shown when the work process design strategy includes a vector composed of single-bit representations representing the work equipment for each work process. Where 401 is the vector when the work equipment used by O11, O12, O13, O21, O22, O23, O31, O32, and O33, respectively, is M2, M3, M1, M2, M1, M3, M2, M1, and M2; and 402 is the vector when the work equipment used by O11, O12, O13, O21, O22, O23, O31, O32, and O33, respectively, is M1, M2, M3, M1, M2, M3, M1, M3, and M1. For example, the electronic device can randomly determine the second to fourth positions in the vector from left to right for crossover. The crossover work equipment corresponding to the crossover work process design strategy can be represented as 403 and 404. It should be noted that the above crossover can be performed only on a portion of the operation process design strategies to be optimized. For example, the electronic device can determine the operation process design strategy to be crossovered among the operation process design strategies to be optimized based on the crossover probability at that time. It should be understood that crossover can be performed on both the process sequence and the operation equipment, or only one of them can be performed.

[0120] After the crossover is completed, the crossover operation process design strategy can be mutated. Similarly, the mutation can also be performed on only a part of the crossover operation process design strategy. For example, the electronic device can determine the operation process design strategy for mutation in the crossover operation process design strategy based on the mutation probability at this time. The mutation process includes the mutation of the process sequence and the mutation of the operation equipment. It can be understood that the electronic device can execute both or one of them. With respect to the process sequence, in some embodiments, the electronic device can select (for example, randomly select) multiple operation processes for mutation from the operation processes in the operation process design strategy for mutation, and then exchange the process sequence between these operation processes to obtain the process sequence corresponding to the mutated operation process design strategy (that is, multiple optimized operation process design strategies, which can also be called genetic algorithm strategies).

[0121] To facilitate understanding of the mutation method, refer to the examples of Figures 5 and 6, where Figure 5 shows an example of mutation based on exchange when the operation process design strategy includes a vector composed of single-bit representations for representing the process sequence. If the third and sixth bits in 501 and 502 are determined as the operation processes for mutation, the process sequences of operation processes O31 and O23 (for 501), and O12 and O31 (for 502) can be exchanged to obtain 503 and 504 to achieve mutation, so as to obtain the process sequence corresponding to the mutated operation process design strategy. In some embodiments, the electronic device can select multiple operation processes for mutation from the operation processes in the operation process design strategy for mutation, and then change the operation equipment of these operation processes to other feasible equipment. Referring to Figure 6, Figure 6 shows an example of mutation when the operation process design strategy includes a vector composed of single-bit representations for representing the operation equipment of each operation process. If the third digit in 601 and 602 is determined as the operation process for variation, the operation equipment of O13 can be changed from M3 to M2 (for 601), and the operation equipment of O13 can be changed from M1 to M2 (for 602) to obtain 603 and 604.

[0122] Returning to FIG1 , after mutation, the electronic device can obtain the mutated operation process design strategy, achieving a round of optimization, and update the initial operation process design strategy in 106 with the mutated operation process design strategy. This process can also be referred to as obtaining multiple genetic algorithm strategies. Since the operation process design strategy with a shorter operation duration is selected for crossover and mutation, the updated operation process design strategy in 106 is better than the initial operation process design strategy. In some embodiments, to ensure that the number of operation process design strategies in 106 is sufficient, the operation process design strategies that have not been crossover and mutation can be supplemented to 106 from the above-mentioned operation process design strategies to be optimized until the number of updated operation process design strategies in 106 reaches a predetermined threshold. This method does not reduce the quality of the updated operation process design strategies in 106.

[0123] Subsequently, the electronic device performs the next round of optimization based on the updated operation process design strategy in 106 and continuously iterates. However, in order to ensure that a large number of operation process design strategies undergo crossover and mutation in the initial rounds of optimization to quickly find the target strategy, and a small number of operation process design strategies undergo crossover and mutation in the later rounds of optimization to quickly converge, the electronic device may reduce 114 at least one of the crossover probability and the mutation probability (also known as the hereditary probability) after updating the operation process design strategy in 106. That is, the electronic device may reduce both the number of operation process design strategies undergoing crossover and mutation, or only one of them. The parameter used to reduce the hereditary probability may be the optimization parameter combined with the parameter used for crossover and mutation in 108.

[0124] In an embodiment of the present disclosure, the operation duration of the updated operation process design strategy (which may refer to a genetic algorithm strategy in some cases described above) and the operation duration of the operation process design strategy before the update (which may refer to an allocation strategy in some cases described above) can be compared to determine whether it is necessary to reduce the crossover probability and / or the mutation probability. For example, an example implementation 118-130 of 114 can be used to reduce at least one of the crossover probability and the mutation probability. In some embodiments, 118-130 can be implemented by computer code. As shown in Figure 1, the difference between the shortest operation duration of the updated operation process design strategy and the shortest operation duration of the operation process design strategy before the update can be calculated 124, and it is determined 126 whether the difference is less than zero. If the difference is less than zero, it means that the crossover and mutation based on the current crossover probability and mutation probability are valid, so the crossover probability and / or mutation probability can be left unchanged, but crossover and mutation can continue with a higher probability to quickly find the target strategy. On the contrary, if the difference is greater than or equal to zero, it means that the crossover and mutation effects based on the current crossover probability and mutation probability are not good, and the optimization has reached a certain bottleneck. Therefore, the crossover probability and / or mutation probability can be reduced to converge quickly.

[0125] In some embodiments, the electronic device may reduce the crossover probability and / or mutation probability based on a coefficient for reducing the crossover probability and / or mutation probability (also referred to as a probability adjustment coefficient). For example, the electronic device may predetermine an initial coefficient equal to 1 and a target value for reducing the coefficient that is less than 1 and greater than 0 at 108. When the calculated difference is greater than or equal to zero, the electronic device calculates the product between the target value and the initial coefficient, updates the initial coefficient with the product, and makes the updated coefficient less than 1. The electronic device then calculates the product of the updated coefficient and the current crossover probability and / or mutation probability, and updates 114 the current crossover probability and / or mutation probability with the calculated product, thereby reducing 128 the crossover probability and / or mutation probability. Conversely, if the calculated difference is less than zero, the coefficient and the crossover probability and / or mutation probability may not be updated. In some embodiments, if the calculated difference is less than zero, the coefficient and the crossover probability and / or mutation probability may also be updated 130 according to a certain probability, thereby preventing the probability update process from falling into a local optimum. For example, the probability may be the difference between 1 and the target acceptance probability. The target acceptance probability can be obtained based on the coefficient, the shortest operation time of the updated operation process design strategy, and the shortest operation time of the operation process design strategy before the update using formula (1):

[0126] Among them, P is the acceptance probability, E t The shortest operation time of the strategy designed for the updated operation process, E t+1 The minimum operation duration of the operation process design strategy before the update, T is the coefficient, and k is a predetermined value. It can be understood that the target acceptance probability is the probability of maintaining the crossover probability and / or mutation probability without decreasing.

[0127] In some embodiments, the operation duration of the operation process design strategy can be determined based on the equipment release time that each workpiece needs to wait on the operation equipment, the time of the previous process, and the operation time of the operation process corresponding to each workpiece. Taking the operation duration calculation of an operation process design strategy as an example, it can be understood that this calculation process is applicable to all operation process design strategies in this disclosure, such as the above-mentioned allocation strategy, genetic algorithm strategy, etc. For example, this calculation process can be used to calculate the operation duration in steps 110, 120, and 122. Alternatively, the operation duration can be calculated by this calculation method in steps 110 and 120, and the calculated operation duration (such as the operation duration calculated in 110) is obtained in step 122. During the calculation, since the operation equipment may be occupied by other operation processes, it is necessary to determine the time required to wait for the equipment to be idle. First, based on the process sequence of multiple operation processes, the operation equipment of each operation process in the multiple operation processes, and the operation time of the multiple operation processes, the time (also known as the equipment release time) that each operation equipment needs to wait for the equipment to be idle before executing each corresponding operation process can be determined. For example, if after the operation process O12 is completed, the operation process O13 needs to be executed on M2, but M2 is executing other operation processes when the operation process O12 is completed, it is necessary to wait for the operation equipment M2 to complete the other operation process O12 before starting to execute the operation process O13, that is, it is necessary to wait for the equipment to be released before executing the subsequent operation process. Subsequently, since there are predetermined sequence constraints between the multiple operation processes as mentioned above, it is necessary to determine the time required to wait for the completion of the predecessor process. Based on the predetermined sequence constraints between the multiple operation processes and the operation durations of the multiple operation processes, it is possible to determine the time required for each operation equipment to wait for the completion of the predecessor process before executing each corresponding operation process (also referred to as the predecessor process duration). In some embodiments, the size of the predecessor process duration and the equipment release duration can be compared to determine which waiting time for the workpiece is longer, and then the actual completion time of the workpiece is determined based on the longer waiting time and the operation duration of the operation process that processes the workpiece. Finally, the operation duration of the operation process design strategy is determined from the completion time of each workpiece. In some embodiments, the longest completion time may be selected as the operation duration of the operation process design strategy.

[0128] For easier understanding, refer to Figure 7, which shows a Gantt chart of the duration of an operation when the operation process design strategy is in the form of a code group. Taking the operation process design strategy of O21(M2)->O11(M3)->O12(M1)->O22(M2)->O13(M1)->O23(M3)->O31(M2)->O32(M1)->O33(M2) as an example, Figure 7 shows that the steps for calculating the completion time of workpieces J1, J2, and J3 are as follows:

[0129] M2 takes 3 hours to process O21, the current processing time of workpiece J2 is 3 hours, and the current equipment release time of M2 is 3 hours later. M3 takes 1 hour to process O11, the current processing time of workpiece J1 is 1 hour, and the current equipment release time of M3 is 1 hour later. M1 takes 3 hours to process O12, the current processing time of workpiece J1 is 4 hours, and the current equipment release time of M1 is 4 hours later. M2 takes 3 hours to process O22. It has to wait for M2 to be released and for workpiece J2's immediately preceding O21 to start processing O22. Since the equipment release time and the immediately preceding process time are both 3 hours, the current processing time of workpiece J2 is the sum of the maximum of the equipment release time and the immediately preceding process time and 3 hours, that is, 6 hours (the calculation process will not be repeated below). The current equipment release time of M2 is 6 hours later. M1 takes 2 hours to process O13. It must wait for M1 to be released and for workpiece J1's immediate predecessor, O12, to begin processing O13. Since the equipment release time is 3 hours and the immediate predecessor process time is 4 hours, the current processing time for workpiece J1 is 6 hours. At this point, all three operations for workpiece J1 have been completed, so the completion time for workpiece J1 is 6 hours, and M1's current equipment release time is in the future. M3 takes 6 hours to process O23. It must wait for M3 to be released and for workpiece J2 to complete processing O22 before it can begin processing O23. Since the equipment release time is 1 hour and the immediate predecessor process time is 6 hours, the current processing time for workpiece J2 is 12 hours. At this point, all three operations for workpiece J2 have been completed, so the completion time for workpiece J1 is 12 hours. M3's current equipment release time is in the future, and M3's current equipment release time is in the future. M2 takes 5 hours to process O31 and must wait for M2 to be released. Since the equipment release time is 6 hours and the predecessor process time is 0 hours, the current processing time for workpiece J3 is 11 hours. M2's current equipment release time is after 11 hours. M1 takes 1 hour to process O32 and must wait for M1 to be released. It must also wait for workpiece J3 to complete processing O31 before it can begin processing O32. Since the equipment release time is 12 hours and the predecessor process time is 5 hours, the current processing time for workpiece J3 is 12 hours. M1's current equipment release time is after 12 hours. M2 takes 3 hours to process O33 and must wait for M2 to be released. It must also wait for workpiece J3 to complete processing O32 before it can begin processing O33. Since the equipment release time is 12 hours and the predecessor process time is 6 hours, the current processing time for workpiece J3 is 15 hours. At this point, all three operations for workpiece J3 have been completed, so the completion time for workpiece J3 is 15 hours. Subsequently, the electronic device may determine the maximum 15 hours as the operation duration of the operation process design strategy.

[0130] Returning to the above-mentioned examples 118-130 in FIG. 1 for reducing the crossover probability and / or mutation probability 114, which can be implemented by computer code, in some embodiments, in order to avoid the coefficient being too low, resulting in the updated crossover probability and / or mutation probability being inapplicable, it is possible to determine whether the coefficient 118 is too small before comparing the shortest operation duration of the updated operation process design strategy with the shortest operation duration of the operation process design strategy before the update. If it is too small, the coefficient is no longer reduced. For example, the coefficient can be compared with a predetermined coefficient threshold. If the coefficient is greater than the predetermined coefficient threshold, it means that the coefficient can still be reduced. At this time, the electronic device can execute 120 to calculate the shortest operation duration of the updated operation process design strategy, and then execute step 122 to calculate or obtain the shortest operation duration of the operation process design strategy before the update. The following shows an example judgment process for implementing some steps in 118-130, and the method of reducing the crossover probability and mutation probability is described in the example judgment process:

[0131] Where dE is the difference in operation duration, Y(i+1) is the updated operation process design strategy, and Y(i) is the operation process design strategy before the update.

[0132] Subsequently, the electronic device can re-execute steps 110 and 112 on the updated operation process design strategy in 106 based on the reduced genetic probability, continuously iteratively optimizing in the form of crossover and mutation until the operation process design strategy generated by the latest iteration (also referred to as a candidate strategy) satisfies a predetermined stopping condition. For example, when both the crossover probability and the mutation probability are reduced, the next round of optimization can be performed based on the reduced crossover probability and the reduced mutation probability. When only the crossover probability is reduced, the next round of optimization can be performed based on the reduced crossover probability and the unchanged mutation probability. When only the mutation probability is reduced, the next round of optimization can be performed based on the reduced mutation probability and the unchanged crossover probability. The specific crossover and mutation processing can refer to the above description. For example, when performing process sequence crossover, the operation process design strategy used for crossover (also referred to as the genetic algorithm strategy used for crossover) in the updated operation process design strategy can be determined based on the reduced crossover probability, and crossover can be performed based on the workpiece subsets obtained after the workpiece is divided (the crossover and unchanged workpiece subsets can be referred to as the first part of the workpiece subset and the second part of the workpiece subset, respectively) to obtain the crossover operation process design strategy (also referred to as the genetic algorithm strategy after crossover). When performing mutation, the electronic device can determine the operation process design strategy for mutation in the operation process design strategy after the crossover at this time based on the reduced mutation probability (also known as the genetic algorithm strategy for mutation), and then determine the operation process for exchanging the process sequence (also known as the first operation process) and the operation process for changing the operation equipment (also known as the second operation process), and perform mutation based on the determined operation process to obtain the mutated operation process design strategy at this time (also known as the candidate strategy). As described above, in the iterative process, the previous generation of operation process design strategy used to generate the current generation of operation process design strategy in the iterative process can also be called an allocation strategy, and the generated current generation of operation process design strategy can be called a genetic algorithm strategy, that is, the method provided by the present disclosure is also applicable to processing in the iterative process.

[0133] In some embodiments, the predetermined stopping condition may refer to the current number of iterations having reached a predetermined threshold. For example, a workshop worker may set the predetermined threshold to 200. If the number of iterations (e.g., the total number of crossovers and mutations) reaches 200, the strategy with the shortest operation duration among the multiple strategies generated most recently will be output as the target strategy. In other embodiments, the predetermined stopping condition may refer to the fact that a strategy with an operation duration less than or equal to the predetermined threshold already exists among the strategies generated by the most recent iteration. In this case, the iteration can be considered successful, and the strategy with the shortest operation duration among the strategies generated most recently will be output as the target strategy. In yet other embodiments, the predetermined stopping condition may refer to the fact that the rate of change in operation duration between multiple batches of operation process design strategies generated during the iteration (e.g., when another iteration is performed based solely on the current generation of genetic algorithm strategies, the rate of change between the batch of the most recently generated candidate strategies and the batch of the current generation of genetic algorithm strategies) meets a predetermined rate of change condition. For example, the predetermined rate of change condition may refer to a rate of change that is approximately zero, or greater than zero, indicating that the operation duration cannot be significantly reduced after the iteration. If the predetermined change rate condition is met, it means that further iterations cannot optimize the strategy. In this case, the strategy with the shortest operation duration among the latest strategies can be output as the target strategy.

[0134] Referring to Figure 8, Figure 8 shows the simulation results of the method disclosed in the present invention, where the X-axis is the number of iterations, and the direction of the arrow on the Y-axis indicates that the operation duration is gradually reduced. The predetermined number threshold is 200, the initial crossover probability is 0.6, and the initial mutation probability is 0.01. The solid line portion corresponds to the method disclosed in the present invention, and the dotted line portion corresponds to the traditional method. 801 and 802 correspond to the number of iterations of the target strategy obtained by the method disclosed in the present invention and the traditional method, respectively. It can be seen that the method disclosed in the present invention can optimize the strategy of the operation process based on crossover and mutation, and in the process of crossover and mutation, the genetic probability for crossover and / or mutation can be dynamically adjusted based on the operation duration of the genetic algorithm strategy after crossover and mutation, gradually reducing the number of crossover and / or mutation strategies, so that crossover and mutation can quickly find the desired target strategy in the early stage and converge quickly in the later stage. Thereby reducing the time to obtain the target strategy of the operation process.

[0135] To better understand the present disclosure, FIG9 illustrates a flow chart of a method 900 for generating target strategies for work processes according to some embodiments of the present disclosure. At block 902, multiple genetic algorithm strategies for multiple work processes are obtained. In some embodiments, an allocation strategy can be derived by encoding the parameters used to generate the strategies. Crossover and mutation of the process sequence and / or work equipment corresponding to the allocation strategy can then be generated. To reduce storage space and computing resources during encoding, the process sequence and work equipment information can be encoded as a single-bit representation into a single group of codes. Furthermore, to further reduce space usage, work processes belonging to the same workpiece can be encoded using the same single-bit representation to reduce the number of single-bit representations. For example, if workpieces include J1, J2, and J3, the work processes corresponding to J1, J2, and J3 can be encoded using the same single-bit representation. For example, the work processes O11, O12, and O13 corresponding to J1 can all be encoded using a single-bit representation of "1," while the work processes corresponding to J2 and J3 can be encoded using single-bit representations of "2" and "3," respectively, to produce the vector shown above in FIG2 .

[0136] In some embodiments, the parameters used to generate the strategy can be obtained from an external database or input by workshop personnel. For example, when the method of FIG. 9 is executed by an electronic device, the electronic device can receive the parameters used to generate the strategy input by the workshop personnel, or can automatically obtain the parameters used to generate the strategy from an external database. These parameters can be presented in the form of, for example, Table 1. These parameters may include parameters such as the workpieces to be processed, the operating procedures required to process these workpieces, the equipment used to perform these operating procedures, and the processing time required for the equipment to perform these operating procedures. Thus, each genetic algorithm strategy includes the process sequence of multiple operating procedures and the operating equipment for each of the multiple operating procedures.

[0137] At block 904, the shortest operation durations of multiple genetic algorithm strategies are compared with the shortest operation durations of multiple allocation strategies. The operation duration of each strategy varies depending on the corresponding process sequence and the operating equipment. By comparing the shortest operation duration before crossover and mutation with the shortest operation duration after crossover and mutation, it can be determined whether the crossover and mutation are still effective, thereby determining whether the crossover and / or mutation parameters need to be adjusted later. In some embodiments, the completion time of each workpiece can be first determined, and then the operation duration of the strategy can be determined from this. For example, the completion time of each workpiece can be determined based on the equipment release time, the duration of the immediate predecessor process, and the operation duration of each operation process. The longest completion time can then be selected as the operation duration of the strategy. For example, the equipment release time and the duration of the immediate predecessor process can be calculated sequentially using the Gantt chart shown in FIG7 . The current processing time of the corresponding workpiece can then be determined based on the operation time, equipment release time, and the duration of the immediate predecessor process. This is done until all operation processes of the workpiece are calculated. The completion time of the workpiece can then be obtained to determine the operation duration of the strategy.

[0138] At frame 906 places, in response to the shortest operation duration of a plurality of allocation strategies being less than the shortest operation duration of a plurality of genetic algorithm strategies, reduce the genetic probability that is used for crossover and / or mutation.If the shortest operation duration of a plurality of allocation strategies is less than the shortest operation duration of a plurality of genetic algorithm strategies, then illustrate that the shortest operation duration before crossover and mutation is less than the shortest operation duration after crossover and mutation, crossover and mutation are no longer in effect, therefore need to adjust the genetic probability that is used for crossover and / or mutation, with fast convergence.For example when the shortest operation duration of allocation strategy is 10 hours, and the shortest operation duration of the genetic algorithm strategy that obtains after crossover and mutation is 11 hours, then illustrate that crossover and mutation have improved operation duration on the contrary, so crossover and mutation are no longer in effect.By reducing the genetic probability that is used for crossover and / or mutation, can reduce the number of the strategy of crossover and / or mutation, to reach the purpose of fast convergence.In certain embodiments, the reducing of genetic probability can be realized by reducing the probability adjustment coefficient. For example, you can refer to the example judgment process in the above article to reduce the genetic probability. In the first round of iteration, you can initialize the adjustment coefficient to 1. When you need to reduce the genetic probability, you can first reduce the probability adjustment coefficient, and then calculate the product between the probability adjustment coefficient and the genetic probability to obtain an updated genetic probability.

[0139] At block 908, target strategies for the plurality of work processes are generated by performing crossover and / or mutation on the process sequences and / or work equipment in the plurality of genetic algorithm strategies using the reduced genetic probabilities. It will be appreciated that when both the crossover probability and the mutation probability are reduced, the next round of optimization may be performed based on the reduced crossover probability and the reduced mutation probability; when only the crossover probability is reduced, the next round of optimization may be performed based on the reduced crossover probability and the unchanged mutation probability; and when only the mutation probability is reduced, the next round of optimization may be performed based on the reduced mutation probability and the unchanged crossover probability.

[0140] When crossing the sequence of processes, only the sequence of the process steps of some workpieces can be crossed. For example, when the workpieces to be processed include J1, J2 and J3, only the process steps of J1 and J3 can be crossed, while the process step of J2 remains unchanged to avoid confusion. For example, referring to FIG3 , only the single-bit representations "1" and "3" corresponding to the workpieces J1 and J3 can be crossed, while the single-bit representation "2" of J2 remains unchanged. When crossing the operating equipment, the position to be crossed can be selected for crossing. For example, for the vector used to represent the operating equipment in FIG4 , the second to fourth positions from left to right can be selected as the selected positions for crossing, and the crossing of the operating equipment is achieved by crossing the vector value of the selected position (i.e., the single-bit representation of the operating equipment). In FIG4 , the operating equipment of the operating processes O12, O13 and O21 are crossed.

[0141] When mutating the process sequence, the mutation can be performed by swapping. For example, for the vector used to represent the process sequence in Figure 5, the third and sixth bits can be selected for swapping, and the process sequence can be mutated by swapping the vector values ​​of the third and sixth bits. When mutating the operating equipment, the current operating equipment of the operating process can be changed to other equipment among the available equipment. For example, for vector 601 in Figure 6, since the available equipment of O13 includes M1, M2, and M3, the vector value representing the operating equipment of O13 can be changed from the single-bit representation "3" corresponding to M3 to the single-bit representation corresponding to other equipment among the available equipment to obtain the mutated vector 603 (changed to the single-bit representation "2" corresponding to M2 in Figure 6). In some embodiments, if the latest strategy generated during the iteration process meets the preset stop condition, the strategy with the shortest operation duration among the latest strategies can be output as the target strategy. The preset stop condition can be associated with one of the number of iterations, the operation duration, and the rate of change of the operation duration. For details, please refer to the description of the preset stop condition above.

[0142] Referring to FIG10 , an embodiment of the present disclosure further provides an apparatus 1000 for generating a target strategy for a work process. The apparatus 1000 includes an acquisition module 1002 configured to acquire multiple genetic algorithm strategies for multiple work processes. The multiple genetic algorithm strategies are generated based on crossover and mutation of the process sequences and / or work equipment corresponding to the multiple allocation strategies, and each of the multiple genetic algorithm strategies includes the process sequences of the multiple work processes and the work equipment for each of the multiple work processes. The apparatus also includes a comparison module 1004 configured to compare the shortest work durations of the multiple genetic algorithm strategies with the shortest work durations of the multiple allocation strategies. The apparatus also includes a reduction module 1006 configured to reduce the genetic probability used for crossover and / or mutation in response to the shortest work duration of the multiple allocation strategies being less than the shortest work duration of the multiple genetic algorithm strategies. The genetic probability includes a crossover probability and / or a mutation probability. The apparatus further includes a generation module 1008 configured to generate target strategies for a plurality of work processes by crossover and / or mutation of process sequences and / or work equipment in a plurality of genetic algorithm strategies using reduced genetic probabilities.

[0143] In some embodiments, the apparatus may further include an encoding module 1010 configured to determine a plurality of work processes and a plurality of process sequences of the plurality of work processes, and for each process sequence in the plurality of process sequences, encode each process sequence into a first set of codes by arranging each work process in sequence using a corresponding single-bit representation. The encoding module 1010 is configured to select work equipment for each of the plurality of work processes from the available equipment for each of the plurality of work processes to obtain a plurality of work equipment sets. For each work equipment set, the encoding module 1010 is configured to encode the work equipment of the plurality of work processes into a second set of codes by arranging the single-bit representations corresponding to the work equipment of the plurality of work processes according to the order of the numbers of the work processes processed by the work processes and the order of the work processes corresponding to each work work. The plurality of first sets of codes corresponding to the plurality of process sequences and the plurality of second sets of codes corresponding to the plurality of work equipment sets are combined into a plurality of allocation strategies.

[0144] In some embodiments, the apparatus may further include a duration calculation module 1012, which is configured to determine, for each allocation strategy, the equipment release duration that each work equipment needs to wait for before executing each corresponding work process based on the process sequence of multiple work processes, the work equipment of each work process in the multiple work processes, and the work duration of the multiple work processes. The duration calculation module 1012 is also configured to determine the predecessor process duration that each work equipment needs to wait for before executing each corresponding work process based on the predetermined sequence constraints between the multiple work processes and the work duration of the multiple work processes. The duration calculation module 1012 is also configured to determine the completion duration of each work piece based on the equipment release duration and the predecessor process duration of the work process for processing each work piece, as well as the work duration of the work process for processing each work piece. The duration calculation module 1012 is also configured to determine the work duration of each allocation strategy from the multiple completion times of the multiple work pieces corresponding to each allocation strategy.

[0145] In some embodiments, the comparison module 1004 is also configured to compare the initial probability adjustment coefficient used to update the genetic probability with a predetermined coefficient threshold, and in response to the probability adjustment coefficient being greater than the predetermined coefficient threshold, compare the job durations of multiple genetic algorithm strategies and the job durations of multiple allocation strategies.

[0146] In some embodiments, the reduction module 1006 is further configured to reduce the probability adjustment coefficient to update the reduced probability adjustment coefficient to the probability adjustment coefficient, and then reduce the genetic probability based on the probability adjustment coefficient.

[0147] In some embodiments, the reduction module 1006 is further configured to maintain the genetic probability without reducing at the target acceptance probability in response to the shortest job duration of the multiple allocation strategies being greater than or equal to the shortest job duration of the multiple genetic algorithm strategies.

[0148] In some embodiments, crossover and mutation are subject to predetermined sequence constraints between the multiple work steps and the available equipment for the work steps.

[0149] In some embodiments, the generation module 1008 is further configured to cross multiple genetic algorithm strategies based on the crossover probability to obtain multiple crossover genetic algorithm strategies, mutate the process sequences and operating equipment corresponding to the multiple crossover genetic algorithm strategies based on the mutation probability to obtain multiple candidate strategies, and then determine the target strategy for the operating process from the multiple candidate strategies.

[0150] In some embodiments, the generation module 1008 is further configured to divide the multiple workpieces corresponding to the multiple processes into multiple workpiece subsets. The multiple workpiece subsets include a first part of the workpiece subset and a second part of the workpiece subset other than the first part of the workpiece subset. The generation module 1008 is further configured to cross the process sequence of the work processes corresponding to the first part of the workpiece subset in multiple genetic algorithm strategies for crossover, and keep the process sequence of the work processes corresponding to the second part of the workpiece subset unchanged, so as to obtain the crossover process sequence corresponding to each crossover genetic algorithm strategy. The generation module 1008 is further configured to determine one or more work processes from the multiple work processes, and to cross the work equipment of one or more work processes in the multiple genetic algorithm strategies for crossover, so as to obtain the crossover work equipment corresponding to each crossover genetic algorithm strategy.

[0151] In some embodiments, the generation module 1008 is further configured to determine a plurality of first operating procedures for mutation in the genetic algorithm strategy for mutation, swap the sequence of the plurality of first operating procedures to obtain the sequence of procedures corresponding to the plurality of candidate strategies. The generation module 1008 is further configured to determine a plurality of second operating procedures for mutation in the genetic algorithm strategy for mutation, and change the operating equipment of the plurality of second operating procedures to operating equipment other than the operating equipment of the plurality of second operating procedures from the plurality of available equipment for the second operating procedures to obtain the operating equipment corresponding to the plurality of candidate strategies.

[0152] In some embodiments, the generation module 1008 is also configured to output a candidate strategy that meets the preset duration requirement among multiple candidate strategies as a target strategy in response to satisfying one of the following items: the number of crossovers and mutations performed before obtaining the multiple candidate strategies reaches a predetermined number threshold, there is a candidate strategy among the multiple candidate strategies whose operation duration is less than or equal to the predetermined duration threshold, or the rate of change of the operation duration between the multiple candidate strategies and the multiple genetic algorithm strategies meets a predetermined change rate condition.

[0153] The target strategy generated by the above embodiment can optimize the operation process based on crossover and mutation. In the process of crossover and mutation, the genetic probability used for crossover and / or mutation can be dynamically adjusted based on the operation time of the genetic algorithm strategy after crossover and mutation, gradually reducing the number of crossover and / or mutation strategies, so that crossover and mutation can quickly find the desired target strategy in the early stage and converge quickly in the later stage. This reduces the time to obtain the target strategy of the operation process.

[0154] According to the various embodiments of the present disclosure described above and their combined embodiments, the efficiency of configuring functional states can be improved. It should be understood that the implementation methods illustrated in Figures 1 to 10 above are only schematic. Depending on the actual application, the architecture or process illustrated in Figures 1 to 10 may have other different forms and may also include more or fewer one or more functional modules and / or units. These modules and / or units may be partially or fully implemented as hardware modules, software modules, firmware modules, or any combination thereof, and the embodiments of the present disclosure are not limited thereto.

[0155] It is understood that the specific names and / or protocols of the various components in the system described herein are merely intended to help those skilled in the art better understand the concepts of the present disclosure and are not intended to limit the scope of the present disclosure in any way. Moreover, in other embodiments, more or better components may be included, and alternative components having the same or similar functions may also be included.

[0156] Figure 11 shows a schematic block diagram of an example device 1100 that can be used to implement some embodiments of the present disclosure. Device 1100 can be implemented as a server or PC, etc., and the embodiments of the present disclosure do not limit the specific implementation type of device 1100. As shown in Figure 11, device 1100 includes a central processing unit (CPU) 1101, which can perform various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) 1102 or computer program instructions loaded from a storage unit 1108 into a random access memory (RAM) 1103. In RAM 1103, various programs and data required for the operation of device 1000 can also be stored. CPU 1101, ROM 1102 and RAM 1103 are connected to each other via a bus 1104. Input / output (I / O) interface 1105 is also connected to bus 1104.

[0157] Various components in device 1100 are connected to I / O interface 1105, including an input unit 1106, such as a keyboard and mouse; an output unit 1107, such as various types of displays and speakers; a storage unit 1108, such as a magnetic disk and optical disk; and a communication unit 1109, such as a network card, an update modem, a wireless communication transceiver, etc. Communication unit 1109 allows device 1100 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0158] The processing unit 1101 can perform the various methods and / or processes described above, such as the method shown in Figure 11. For example, in some embodiments, the method can be implemented as a computer software program, which is tangibly contained in a device-readable medium, such as the storage unit 1108. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 1100 via the ROM 1102 and / or the communication unit 1109. When the computer program is loaded into the RAM 1103 and executed by the CPU 1101, one or more steps of the method described above can be performed. Alternatively, in other embodiments, the CPU 1101 can be configured to perform the method by any other appropriate means (e.g., by means of firmware, etc.).

[0159] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), and the like.

[0160] In some embodiments, the methods and processes described above may be implemented as a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for executing various aspects of the present disclosure.

[0161] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the device, partially on the device, as a stand-alone software package, partially on the device and partially on a remote device, or entirely on a remote device or server.

[0162] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions to be stored in the computer-readable storage medium in each computing / processing device.

[0163] The computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, device instructions, device-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, and conventional procedural programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server.

[0164] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a device such that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device is generated that implements the functions / actions specified in one or more blocks in the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner, so that the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks in the flowchart and / or block diagram. The computer-readable program instructions can also be loaded onto a computer, other programmable data processing device, or other device, so that a series of operational steps are performed on the computer, other programmable data processing device, or other device to produce a computer-implemented process, so that the instructions executed on the computer, other programmable data processing device, or other device implement the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0165] In the information disclosed herein, a device-readable medium may be a tangible medium that may contain or store a program for use by an instruction execution system, device, or apparatus or used in conjunction with an instruction execution system, device, or apparatus. A device-readable medium may be a device-readable signal medium or a device-readable storage medium. A device-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or apparatus, or any suitable combination of the foregoing. More specific examples of device-readable storage media may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0166] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and the part of the module, program segment or instruction contains one or more executable instructions for realizing the prescribed logical function. In some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart, can be implemented by a special hardware-based system that performs the prescribed function or action, or can be implemented by a combination of special hardware and computer instructions.

[0167] In addition, although each operation is described in a specific order, this should be understood as requiring such operation to be performed in the specific order shown or in a sequential order, or requiring that all illustrated operations should be performed to obtain the desired result. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details have been included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the information of the separate embodiment can also be implemented in a single implementation in combination. On the contrary, the various features described in the information of the single implementation can also be implemented in multiple implementations individually or in the mode of any suitable sub-combination.

[0168] Although the subject matter has been described in language specific to structural features and / or methodological logical acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims.

[0169] The various embodiments of the present disclosure have been described above. The above description is exemplary and not exhaustive, and is not limited to the disclosed embodiments. In addition, nouns and pronouns related to people in this patent application are not limited to specific genders. Without departing from the scope and spirit of the various embodiments described, many modifications and changes are obvious to those of ordinary skill in the art. The choice of terms used in this article is intended to best explain the principles of the various embodiments, practical applications or technical improvements to the technology in the market, or to enable other ordinary technicians in this technology to understand the various embodiments disclosed herein.

[0170] Nouns and pronouns referring to persons in this patent application are not limited to a specific gender.

Claims

1. A method (900) for generating a target strategy for a work process, comprising: Acquiring (902) a plurality of genetic algorithm strategies for a plurality of operation processes, wherein the plurality of genetic algorithm strategies are generated based on crossover and mutation of process sequences and / or operation equipment corresponding to the plurality of allocation strategies, and each genetic algorithm strategy in the plurality of genetic algorithm strategies includes the process sequence of the plurality of operation processes and the operation equipment of each operation process in the plurality of operation processes; comparing (904) the shortest operation durations of the plurality of genetic algorithm strategies and the shortest operation durations of the plurality of allocation strategies; In response to the shortest job duration of the plurality of allocation strategies being less than the shortest job duration of the plurality of genetic algorithm strategies, reducing (906) the genetic probability for crossover and / or mutation, wherein the genetic probability comprises a crossover probability and / or a mutation probability; and Target strategies for the plurality of operation processes are generated (908) by crossover and / or mutation of process sequences and / or operation equipment in the plurality of genetic algorithm strategies using the reduced genetic probabilities.

2. The method (900) of claim 1, further comprising: Determining the plurality of operation steps and a plurality of operation sequences of the plurality of operation steps; For each process sequence in the plurality of process sequences, encoding each process sequence into a first set of codes by arranging each operation process in order with a corresponding single-bit representation; Selecting the operation equipment of each operation process in the plurality of operation processes from the available equipment of each operation process in the plurality of operation processes to obtain a plurality of operation equipment sets; For each set of working equipment, the working equipment of the multiple working processes are encoded into a second set of codes by arranging the single-bit representations corresponding to the working equipment of the multiple working processes in the order of the numbers of the workpieces processed by the working processes and the order of the corresponding working processes when processing each workpiece; as well as The plurality of first group codes corresponding to the plurality of process sequences and the plurality of second group codes corresponding to the plurality of work equipment sets are combined into the plurality of allocation strategies.

3. The method (900) according to claim 1, wherein the plurality of operation steps are used to process a plurality of workpieces, and the method (900) further comprises: For each allocation strategy, based on the process sequence of the multiple work processes, the work equipment of each work process in the multiple work processes and the work duration of the multiple work processes, determine the time for each work equipment to perform each work process. The time required to wait for the equipment to be released before the corresponding operation process; Based on the predetermined sequence constraints between the multiple operation procedures and the operation durations of the multiple operation procedures, determining the duration of the preceding operation that each operation equipment needs to wait for before executing each corresponding operation procedure; Determine the completion time of each workpiece based on the equipment release time and the preceding process time of the operation process for processing each workpiece, and the operation time of the operation process for processing each workpiece; as well as The operation duration of each allocation strategy is determined from a plurality of completion durations of a plurality of workpieces corresponding to each allocation strategy.

4. The method (900) of claim 1, wherein comparing (904) the shortest operation durations of the plurality of genetic algorithm strategies and the shortest operation durations of the plurality of allocation strategies comprises: comparing an initial probability adjustment coefficient for updating the genetic probability with a predetermined coefficient threshold; as well as In response to the probability adjustment coefficient being greater than the predetermined coefficient threshold, the job durations of the plurality of genetic algorithm strategies are compared with the job durations of the plurality of allocation strategies.

5. The method of claim 4, wherein reducing (906) the genetic probability comprises: reducing the probability adjustment coefficient to update the reduced probability adjustment coefficient to the probability adjustment coefficient; as well as The genetic probability is reduced (906) based on the probability adjustment factor.

6. The method (900) of claim 4, further comprising: In response to the shortest job durations of the multiple allocation strategies being greater than or equal to the shortest job durations of the multiple genetic algorithm strategies, the genetic probability is maintained at a target acceptance probability without being reduced.

7. The method (900) according to claim 6, wherein the target acceptance probability is obtained based on the initial probability adjustment coefficient, the operation duration of the multiple genetic algorithm strategies and the operation duration of the multiple allocation strategies.

8. The method (900) of claim 1, wherein the crossover and the variation are subject to predetermined sequence constraints between the plurality of work processes and available equipment for the work processes.

9. The method (900) of claim 1, wherein the genetic probability includes a crossover probability and a mutation probability, and generating (908) the target strategy comprises: Based on the crossover probability, the multiple genetic algorithm strategies are crossovered to obtain multiple crossover genetic algorithm strategies; Based on the mutation probability, the process sequence and operation setting corresponding to the plurality of crossover genetic algorithm strategies are Prepare mutations to obtain multiple candidate strategies; as well as The target strategy for the work process is determined from the plurality of candidate strategies.

10. The method (900) according to claim 9, wherein the crossover probability is used to determine a plurality of genetic algorithm strategies for crossover among the plurality of genetic algorithm strategies, wherein crossover of the plurality of genetic algorithm strategies comprises: Dividing the plurality of workpieces corresponding to the plurality of processes into a plurality of workpiece subsets, wherein the plurality of workpiece subsets include a first portion of workpiece subsets and a second portion of workpiece subsets other than the first portion of workpiece subsets; Crossing the process sequence of the operation processes corresponding to the first part of the workpiece subset in the plurality of genetic algorithm strategies for crossover, and keeping the process sequence of the operation processes corresponding to the second part of the workpiece subset unchanged, so as to obtain a crossover process sequence corresponding to each crossover genetic algorithm strategy; determining one or more operation steps from the plurality of operation steps; as well as The operating equipment of the one or more operating procedures in the multiple genetic algorithm strategies for crossover are crossovered to obtain the crossover operating equipment corresponding to each crossover genetic algorithm strategy.

11. The method (900) according to claim 9, wherein the mutation probability is used to determine a genetic algorithm strategy for mutation among the plurality of crossover genetic algorithm strategies, and mutating the process sequence and operation equipment corresponding to the plurality of crossover genetic algorithm strategies comprises: Determining a plurality of first operation steps for mutation in the genetic algorithm strategy for mutation; Exchanging the process sequence of the plurality of first operation processes to obtain the process sequence corresponding to the plurality of candidate strategies; Determining a plurality of second operation steps for mutation in the genetic algorithm strategy for mutation; as well as The operating equipment of the plurality of second operating procedures is changed to operating equipment other than the operating equipment of the plurality of second operating procedures among the available equipment of the plurality of second operating procedures, so as to obtain the operating equipment corresponding to the plurality of candidate strategies.

12. The method (900) according to claim 9, wherein determining the target strategy of the operation process from the plurality of candidate strategies comprises: In response to satisfying any one of the following items, outputting a candidate strategy that meets the preset duration requirement among the multiple candidate strategies as the target strategy: The number of crossovers and mutations performed before obtaining the plurality of candidate strategies reaches a predetermined number threshold; There is a candidate strategy whose operation duration is less than or equal to a predetermined duration threshold among the multiple candidate strategies; or It is obtained that the change rates of the operation durations of the multiple candidate strategies and the operation durations between the multiple genetic algorithm strategies meet a predetermined change rate condition.

13. A device (1000) for generating a target strategy for a work process, comprising: An acquisition module (1002) is configured to acquire a plurality of genetic algorithm strategies for a plurality of operation processes, wherein the plurality of genetic algorithm strategies are generated based on crossover and mutation of the process sequences and / or operation equipment corresponding to the plurality of allocation strategies, and each genetic algorithm strategy in the plurality of genetic algorithm strategies includes the process sequence of the plurality of operation processes and the operation equipment of each operation process in the plurality of operation processes; A comparison module (1004), configured to compare the shortest operation durations of the plurality of genetic algorithm strategies with the shortest operation durations of the plurality of allocation strategies; A reduction module (1006) configured to reduce the genetic probability for crossover and / or mutation in response to the shortest job duration of the plurality of allocation strategies being less than the shortest job duration of the plurality of genetic algorithm strategies, wherein the genetic probability includes a crossover probability and / or a mutation probability; and A generation module (1008) is configured to generate target strategies for the plurality of operation processes by crossover and / or mutation of the process sequences and / or operation equipment in the plurality of genetic algorithm strategies using the reduced genetic probabilities.

14. An electronic device (1100), the electronic device (1100) comprising: One or more processors (1101); as well as A memory for storing computer executable instructions, wherein the computer executable instructions, when executed by the one or more processors (1101), enable the electronic device (1000) to implement the method according to any one of claims 1-12.

15. A computer-readable storage medium (1103) storing computer-executable instructions, wherein the computer-executable instructions, when executed by a processor (1101), implement the method according to any one of claims 1 to 12.

16. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 12.

Images