Optimal configuration method of distributed blockchain production logistics resources based on improved teaching and learning algorithm

Abstract

The present application relates to a method for optimizing the configuration of distributed blockchain production logistics resources based on an improved teaching and learning algorithm, including: selecting a candidate BCPLR node set corresponding to each blockchain resource set from the production logistics resource BCPLR nodes corresponding to a plurality of preset blockchain resource sets; performing population individual coding and population initialization based on the plurality of candidate BCPLR node sets and the production logistics task volume to generate a plurality of first individual codes; using the improved teaching and learning algorithm TLBO, performing population search iterations on the plurality of first individual codes to generate a plurality of second individual codes, and based on the fitness of the resource configuration method corresponding to the second individual code and the improved TLBO, performing population update iterations on the plurality of second individual codes, and determining the target individual code from the generated plurality of candidate individual codes to obtain an optimized configuration result, wherein the improved TLBO is a TIBO that uses the teaching strategy of multi-teacher grouping and the cross-learning strategy combining randomness and directionality as the teaching strategy and learning strategy of TLBO respectively.

Description

Technical Field

[0001] The present application relates to the field of smart logistics technology, and in particular to a method for optimizing the configuration of distributed blockchain production logistics resources based on an improved teaching and learning algorithm. Background Art

[0002] Blockchain Production Logistics Resource (BCPLR) refers to the virtual resources defined and managed in the blockchain resource platform. It is processed, packaged and managed by the blockchain encapsulation module of the blockchain-based smart gateway operating system (BSGOS). The blockchain encapsulation module records the key feature information and attributes of smart production logistics resources (such as resource identity, specification parameters, production history and ownership, etc.) in the blockchain, and assigns a unique resource identifier to each smart production logistics object to ensure its uniqueness and traceability in the entire platform. These virtual production logistics resources registered and packaged on the platform are collectively referred to as blockchain production logistics resources. BCPLR integrates the decentralization, transparency, immutability and high security characteristics of blockchain, and provides a new type of resource management and sharing method, making the allocation and management of production logistics resources more efficient, transparent and secure, which helps to optimize the operation of the entire production logistics system, thereby better adapting to the dynamic changes in the market and complex production needs.

[0003] In the relevant technologies, production logistics decisions in the production operation process mainly include the structural configuration of production logistics resources, collaborative scheduling plans and dynamic execution control. Among them, the optimal configuration decision of production logistics resources is particularly critical, covering the selection and allocation of production and manufacturing resources, logistics distribution and warehousing resources. The existing production logistics resource configuration methods are often unable to make accurate and effective configuration decisions due to incomplete acquisition of real-time status information of production logistics resources. At the same time, since most production logistics resource configuration decisions adopt a method based on manual experience to configure resources, when faced with complex resource configuration problems, it takes a lot of time, resulting in delays in the issuance of configuration decision instructions, and it is difficult to meet the needs of real-time decision-making.

[0004] At present, there is no effective solution to the problem that the methods of production logistics resource allocation in related technologies cannot use complex resource allocation and cannot meet the needs of real-time decision-making. Summary of the invention

[0005] The embodiment of the present application provides a method for optimizing the configuration of distributed blockchain production logistics resources based on an improved teaching and learning algorithm, so as to at least solve the problem that the method for configuring production logistics resources in the related art cannot use complex resource configuration and cannot meet the real-time decision-making needs.

[0006] In the first aspect, an embodiment of the present application provides a method for optimizing the configuration of distributed blockchain production logistics resources based on an improved teaching and learning algorithm, including: selecting a candidate BCPLR node set corresponding to each of the preset multiple blockchain resource sets from the production logistics resource BCPLR nodes corresponding to the preset multiple blockchain resource sets, wherein each of the blockchain resource sets includes multiple BCPLR nodes, and each of the candidate BCPLR node sets includes at least one BCPLR node that can meet the preset production efficiency target; based on the multiple candidate BCPLR node sets and the production logistics task volume, performing population individual coding and population initialization to generate multiple first individual codes, wherein the first individual code is used to characterize a resource configuration method, and the resource configuration method is associated with one of the candidate BCPLR nodes. The production logistics task volume undertaken by each of the BCPLR nodes in the LR node set and the candidate BCPLR node set; using the improved teaching and learning algorithm TLBO, performing population search iterations on the multiple first individual codes to generate multiple second individual codes, and based on the fitness of the resource configuration method corresponding to the second individual code and the improved TLBO, performing population update iterations on the multiple second individual codes, and determining the target individual code from the generated multiple candidate individual codes to obtain an optimized configuration result, wherein the improved TLBO is a TIBO that uses the teaching strategy of multi-teacher grouping and the cross-learning strategy combining randomness and directionality as the teaching strategy and learning strategy of TLBO respectively, and the optimized configuration result includes the resource configuration method corresponding to the target individual code.

[0007] Compared with the related art, the method for optimizing the configuration of distributed blockchain production logistics resources based on the improved teaching and learning algorithm provided in the embodiment of the present application adopts the method of selecting a candidate BCPLR node set corresponding to each of the preset multiple blockchain resource sets from the production logistics resource BCPLR nodes corresponding to the preset multiple blockchain resource sets, wherein each of the blockchain resource sets includes multiple BCPLR nodes, and each of the candidate BCPLR node sets includes at least one BCPLR node that can meet the preset production efficiency target; based on the multiple candidate BCPLR node sets and the production logistics task volume, population individual coding and population initialization are performed to generate multiple first individual codes, wherein the first individual code is used to characterize a resource configuration method, and the resource configuration method is associated with a candidate BCPLR node set and the production logistics task volume undertaken by each BCPLR node in the candidate BCPLR node set; using the improved teaching and learning algorithm TLBO, a population search iteration is performed on the multiple first individual codes to generate multiple second individual codes, and based on the corresponding second individual codes The fitness of the resource configuration method and the improved TLBO are used to perform population update iteration on multiple second individual codes, and the target individual code is determined from the generated multiple candidate individual codes to obtain the optimized configuration result, wherein the improved TLBO is a TIBO that uses the teaching strategy of multi-teacher grouping and the cross-learning strategy combining randomness and directionality as the teaching strategy and learning strategy of TLBO respectively, and the optimized configuration result includes the resource configuration method corresponding to the target individual code, and adopts a production logistics resource optimization configuration mechanism with total capacity, total service time and total credibility as the optimization targets to achieve the optimization of production logistics resource configuration, and adopts the teaching strategy of multi-teacher grouping and the cross-learning strategy combining randomness and directionality as the teaching strategy and learning strategy of TLBO respectively. The cross-learning strategy achieves an effective balance between global optimization and local exploration, which significantly improves the efficiency and accuracy of the TLBO algorithm in solving complex optimization problems, and solves the problem that the method of production logistics resource configuration in related technologies cannot use complex resource configuration and cannot meet real-time decision-making needs.

[0008] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0010] Figure 1It is a hardware structure block diagram of a terminal of a method for optimizing configuration of distributed blockchain production logistics resources based on an improved teaching and learning algorithm in an embodiment of the present application;

[0011] Figure 2 It is a flow chart of a method for optimizing configuration of distributed blockchain production logistics resources based on an improved teaching and learning algorithm according to an embodiment of the present application;

[0012] Figure 3 This is a schematic diagram of an optimized configuration scenario for wide-area distributed blockchain production logistics resources according to an embodiment of the present application;

[0013] Figure 4 This is a schematic diagram of the operating mode of the optimized configuration of BCPLR for complex personalized orders.

[0014] Figure 5 It is a structural block diagram of an optimization configuration device for distributed blockchain production logistics resources based on an improved teaching and learning algorithm according to an embodiment of the present application. DETAILED DESCRIPTION

[0015] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application. In addition, it can also be understood that although the efforts made in this development process may be complex and lengthy, for ordinary technicians in the field related to the contents disclosed in the present application, some changes such as design, manufacturing or production based on the technical contents disclosed in the present application are only conventional technical means, and should not be understood as insufficient contents disclosed in the present application.

[0016] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0017] Unless otherwise defined, the technical terms or scientific terms involved in this application should be understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantitative limitation and may represent the singular or plural. The terms "including", "comprising", "having" and any of their variations involved in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include unlisted steps or units, or may also include other steps or units inherent to these processes, methods, products or devices. The "multiple links" involved in this application refer to links greater than or equal to two. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships, for example, "A and / or B" may represent: A exists alone, A and B exist at the same time, and B exists alone. The terms "first", "second", "third" and the like involved in this application are only used to distinguish similar objects and do not represent a specific ordering of objects.

[0018] The method embodiment provided in this embodiment can be executed in a terminal, a computer or a similar computing device. Taking running on a terminal as an example, Figure 1 This is a hardware structure block diagram of a terminal for optimizing the configuration method of distributed blockchain production logistics resources based on an improved teaching and learning algorithm in an embodiment of the present application. Figure 1 As shown, the terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data. Optionally, the terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is for illustration only and does not limit the structure of the above terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0019] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the method for optimizing the configuration of distributed blockchain production logistics resources based on the improved teaching and learning algorithm in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0020] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0021] This embodiment provides a method for optimizing the configuration of distributed blockchain production logistics resources based on an improved teaching and learning algorithm running on the above-mentioned terminal. Figure 2 is a flow chart of a method for optimizing the configuration of distributed blockchain production logistics resources based on an improved teaching and learning algorithm according to an embodiment of the present application, such as Figure 2 As shown, the process includes the following steps:

[0022] Step S201, from the production logistics resource BCPLR nodes corresponding to the preset multiple blockchain resource sets, select the candidate BCPLR node set corresponding to each blockchain resource set, wherein each blockchain resource set includes multiple BCPLR nodes, and each candidate BCPLR node set includes at least one BCPLR node that can meet the preset production efficiency target.

[0023] In this embodiment, the core manufacturer (or chain leader enterprise) of the blockchain production resource platform uses the blockchain production logistics resource platform to decompose complex orders into several production logistics tasks. Each task can be achieved through a set of candidate blockchain production logistics resources that meet the production and logistics capacity constraints and service time requirements. The core manufacturer selects the corresponding candidate blockchain production logistics resource sets for the production logistics tasks at different stages of the product based on the product BOM decomposition results, and associates these resources according to the business logic process. After that, the core manufacturer needs to evaluate the production logistics capabilities and production capacity of each BCPLR from the candidate blockchain production logistics resource set to select a BCPLR combination that can meet the order requirements, for example: the core The manufacturer selects one or more BCPLR nodes from multiple outsourced production blockchain resource sets to provide outsourced parts and product production services. At the same time, it selects specific distribution and warehousing nodes from the logistics blockchain resource set to provide logistics distribution and warehousing services. By comprehensively coordinating the cooperation and resource sharing between BCPLR nodes in different blockchain resource sets, efficient delivery of personalized orders can be achieved. In this embodiment, the core manufacturer needs to screen out the optimal BCPLR individuals on the premise of ensuring that the total production capacity of the selected blockchain resource set meets the requirements, and allocate appropriate production task volumes, distribution task volumes, and warehousing task volumes to them, so as to achieve the goals of minimizing the total operating cost of the distributed linkage manufacturing system, minimizing the total service time, and maximizing service credibility.

[0024] Step S202, based on multiple candidate BCPLR node sets and production logistics task volumes, perform population individual coding and population initialization to generate multiple first individual codes, wherein the first individual code is used to characterize a resource configuration method, and the resource configuration method is associated with a candidate BCPLR node set and the production logistics task volume undertaken by each BCPLR node in the candidate BCPLR node set.

[0025] In this embodiment, an improved teaching and learning optimization algorithm is used to solve the optimal configuration problem of distributed blockchain production logistics resources. Therefore, it is necessary to encode the selected optimal BCPLR nodes and the allocated production logistics task volumes (including production task volumes, distribution task volumes and warehousing task volumes) accordingly, so as to use the teaching and learning optimization algorithm to solve the problem based on the corresponding initialization code and the first individual code obtained by population initialization.

[0026] Step S203, using the improved teaching and learning algorithm TLBO, perform population search iterations on multiple first individual codes to generate multiple second individual codes, and based on the fitness of the resource configuration method corresponding to the second individual code and the improved TLBO, perform population update iterations on the multiple second individual codes, and determine the target individual code from the generated multiple candidate individual codes to obtain an optimized configuration result, wherein the improved TLBO is a TIBO that uses the teaching strategy of multi-teacher grouping and the cross-learning strategy that combines randomness and directionality as the teaching strategy and learning strategy of TLBO respectively, and the optimized configuration result includes the resource configuration method corresponding to the target individual code.

[0027] In this embodiment, a preset multi-teacher grouping teaching strategy and a cross-learning strategy combining randomness and directionality are adopted to perform population search iteration on the encoded first individual code, that is, to solve the problem of optimal configuration of distributed blockchain production logistics resources, and use all the local optimal solutions obtained by the solution to compare and evaluate, and based on the comparison and evaluation results, the second individual code corresponding to the local optimal solution is updated and iterated to determine the global optimal solution corresponding to the alternative individual code.

[0028] Through the above steps S201 to S203, a candidate BCPLR node set corresponding to each blockchain resource set is selected from the production logistics resource BCPLR nodes corresponding to the preset multiple blockchain resource sets, each blockchain resource set includes multiple BCPLR nodes, and each candidate BCPLR node set includes at least one BCPLR node that can meet the preset production efficiency target; based on the multiple candidate BCPLR node sets and the production logistics task volume, population individual coding and population initialization are performed to generate multiple first individual codes, and the first individual code is used to characterize a resource configuration method, and the resource configuration method is associated with a candidate BCPLR node set and the production logistics task volume undertaken by each BCPLR node in the candidate BCPLR node set; using the improved teaching and learning algorithm TLBO, a population search iteration is performed on the multiple first individual codes to generate multiple second individual codes, and based on the fitness of the resource configuration method corresponding to the second individual code and the improved TLBO, the multiple first individual codes are coded and initialized. The two-individual coding is updated and iterated in the population, and the target individual coding is determined from the multiple candidate individual codings generated to obtain the optimized configuration result. The improved TLBO is TIBO, which uses the teaching strategy of multi-teacher grouping and the cross-learning strategy combining randomness and directionality as the teaching strategy and learning strategy of TLBO respectively. The optimized configuration result includes the resource allocation method corresponding to the target individual coding. The production logistics resource optimization configuration mechanism with total capacity, total service time and total credibility as the optimization goals is constructed to achieve the optimization of production logistics resource configuration. The teaching strategy of multi-teacher grouping and the cross-learning strategy combining randomness and directionality are used as the teaching strategy and learning strategy of TLBO respectively. The cross-learning strategy achieves an effective balance between global optimization and local exploration, which significantly improves the efficiency and accuracy of the TLBO algorithm in solving complex optimization problems, and solves the problem that the production logistics resource configuration methods in related technologies cannot use complex resource configurations and cannot meet real-time decision-making needs.

[0029] In some embodiments, the step S201 of selecting a candidate BCPLR node set corresponding to each blockchain resource set from the production logistics resource BCPLR nodes corresponding to the preset multiple blockchain resource sets is implemented by the following steps:

[0030] Step 21, traverse all blockchain resource sets, and select multiple candidate BCPLR node sets corresponding to each blockchain resource set from all BCPLR nodes of each traversed blockchain resource set.

[0031] In this embodiment, all blockchain resource sets (for example: SC BCR1 , S.C. BCR2 ,…,SC BCRq ), and determine each blockchain resource set SCBCRi The number of BCPLR nodes in B i , B i From 1 to s i , it is understandable that each SC BCRi The number of BCPLR nodes B i are not the same, which means that each SC BCRi According to the SC BCRi Different numbers of BCPLR nodes are set according to specific requirements and resource configuration; in this embodiment, SC BCR1 , S.C. BCR2 ,…,SC BCRq The resource types include component processing resource nodes, assembly resource nodes, distribution resource nodes, and storage resource nodes. Therefore, i The value ranges from 1 to s i Varies.

[0032] In some of the optional implementations, multiple alternative BCPLR node sets corresponding to each blockchain resource set are selected from all BCPLR nodes of each blockchain resource set traversed, which is achieved by the following steps: all BCPLR nodes of each blockchain resource set traversed are determined, and at least one BCPLR node combination is selected from all BCPLR nodes of each blockchain resource set to obtain multiple alternative BCPLR node sets, wherein each BCPLR node group includes a preset number of BCPLR nodes.

[0033] In this embodiment, after traversing each SC BCRi After all BCPLR nodes, from each SC BCRi Select B from all BCPLR nodes j BCPLR nodes, thus obtaining There are several BCPLR node selection schemes, each of which represents a different resource configuration method, for example: SC BCRi All BCPLR nodes include BCPLR1, BCPLR2, BCPLR3, and BCPLR4. Four BCPLR nodes are selected from them. The corresponding selection schemes include: S1: {BCPLR1, BCPLR2, BCPLR3}, S2: {BCPLR1, BCPLR3, BCPLR4}, S3: {BCPLR1, BCPLR2, BCPLR4}, S4: {BCPLR2, BCPLR3, BCPLR4}. Each selection corresponds to an alternative BCPLR node set. It should be understood that each SC BCRi The number of all BCPLR nodes is different, and B j The number of B j Greater than Bi When BCRi All BCPLR nodes.

[0034] Step 22, obtain the real-time production capacity information corresponding to each blockchain resource set from the blockchain production logistics resource platform, and determine the total output efficiency corresponding to each BCPLR node in each candidate BCPLR node set based on the production capacity information, where the total output efficiency is determined based on the total production capacity, total service time and total credibility of the candidate BCPLR node set.

[0035] In this embodiment, the blockchain production logistics resource platform is used to obtain each SC BCRi The total production capacity TP of the BCPLR nodes in each selection scheme (corresponding to a set of alternative BCPLR nodes) is calculated based on the real-time production capacity and other information. jk , total service time TT and total reliability In this embodiment, the total output efficiency is obtained by coupling the total capacity, total service time and total reliability to ensure the total capacity TP of each BCPLR node jk While meeting production and manufacturing needs, the optimal BCPLR node is obtained. At the same time, the total operating cost corresponding to the corresponding BCPLR node is measured through the total capacity, that is, the production cost and logistics cost required to complete the production logistics tasks corresponding to the total capacity.

[0036] Step 23, based on the total output efficiency, determine whether each BCPLR node of each candidate BCPLR node set meets the production efficiency target, and use all BCPLR nodes that meet the production efficiency target as the candidate BCPLR node set corresponding to the corresponding candidate BCPLR node set.

[0037] In this embodiment, it is determined whether the total capacity and total service time TT meet the requirements of the manufacturing order and whether the credibility of the BCPLR node meets the requirements of the BCPLR node. , if the above conditions are met, the scheme is deemed to be a feasible scheme, and then a candidate BCPLR node set in which all BCPLR nodes meet the requirements is obtained. If the above conditions are not met, the BCPLR node is discarded. For example: for the selection scheme: S1:{BCPLR1, BCPLR2, BCPLR3}, S2:{BCPLR1, BCPLR3, BCPLR4}, S3:{BCPLR1, BCPLR2, BCPLR4}, S4:{BCPLR2, BCPLR3, BCPLR4}, if BCPLR2 does not meet the conditions, BCPLR2 in each candidate BCPLR node is deleted, and the corresponding candidate BCPLR node set is: S1:{BCPLR1, BCPLR3}, S2:{BCPLR1, BCPLR3, BCPLR4}, S3:{BCPLR1, BCPLR4}, S4:{BCPLR3, BCPLR4}.

[0038] In this embodiment, when determining each SC BCRi After the corresponding candidate BCPLR node set, all SC BCRi The corresponding candidate BCPLR node sets are sorted to form a feasible combination solution set { }, the set contains all possible resource configuration solutions that meet the conditions.

[0039] Through the above steps 21 to 23, it is achieved that while ensuring that the aggregate capacity of blockchain resources meets the requirements, the optimal BCPLR node is screened out and appropriate production task volumes, distribution task volumes and warehousing task volumes are allocated to it.

[0040] In some embodiments, judging whether each BCPLR node of each candidate BCPLR node set meets the production efficiency target according to the total output efficiency is achieved by the following steps:

[0041] Step 31, from the total output efficiency, obtain the total capacity value, service time and total informability corresponding to each BCPLR node, and determine the output demand value and service time expectation value corresponding to the production efficiency target, where the output demand value is used to represent the required output capacity value of the manufacturing order corresponding to the corresponding blockchain resource set, and the service time expectation value is used to represent the production time required for the corresponding manufacturing order.

[0042] Step 32, respectively judging whether the total capacity value of each BCPLR node is greater than the output demand value, whether the service time is longer than the expected service time value, and judging whether the total credibility of each BCPLR node is greater than a preset credibility threshold.

[0043] In this embodiment, it is determined whether the total capacity and total service time TT meet the requirements of the manufacturing order (whether the corresponding total capacity value is greater than the output demand value and whether the service time is longer than the expected service time value), and whether the credibility of the BCPLR node meets the requirements. The standard (whether the total credibility of each BCPLR node is greater than the preset credibility threshold).

[0044] Step 33, when it is determined that the total capacity value is greater than the output demand value, the service time is longer than the expected service time value, and the total credibility is greater than the preset credibility threshold, it is determined that the BCPLR node meets the production efficiency target.

[0045] In this embodiment, when it is determined that a BCPLR node meets the production efficiency target, it indicates that the corresponding BCPLR node meets the corresponding target, and the BCPLR node serves as a BCPLR node in the candidate BCPLR node set.

[0046] Step 34, when it is determined that the total capacity value is not greater than the output demand value or the service time is not longer than the expected service time value or the total credibility is not greater than the preset credibility threshold, it is determined that the BCPLR node does not meet the production efficiency target.

[0047] In this embodiment, when it is determined that a BCPLR node does not meet the production efficiency target, the BCPLR node is deleted.

[0048] Through the above steps 31 to 34, it is possible to determine whether the BCPLR node meets the target requirements, thereby screening out the optimal BCPLR node.

[0049] In some of the embodiments, the improved teaching and learning algorithm TLBO is used to perform population search iterations on multiple first individual codes to generate multiple second individual codes, which is achieved by the following steps:

[0050] Step 41, according to the total output efficiency corresponding to each BCPLR node, determine the comprehensive total output efficiency corresponding to the candidate BCPLR node set corresponding to each first body code, and calculate the Euclidean distance between each first body code and the reference code according to the comprehensive total output efficiency, so as to group multiple first body codes into multiple first student code body groups according to the Euclidean distance, wherein the reference code is the first body code with the smallest comprehensive total output efficiency, and the comprehensive total output efficiency is obtained by weighted calculation of the total output efficiencies corresponding to all BCPLR nodes of the corresponding candidate node set.

[0051] In this embodiment, the set of production logistics task amounts undertaken by all BCPLR nodes corresponding to a first individual code represents a student, the production logistics task amount undertaken by each BCPLR node represents a subject, and the subject score represents a comprehensive evaluation value of the total output efficiency corresponding to the BCPLR node. In some optional implementations, the negative value of the corresponding comprehensive evaluation value is used as the subject score corresponding to the total output efficiency; and the comprehensive total output efficiency corresponding to a student represents the fitness of the student corresponding to a first individual code, and the comprehensive total output efficiency is obtained by weighted calculation of the total output efficiency corresponding to all BCPLR nodes corresponding to a student; in this embodiment, the comprehensive total output efficiency of the students corresponding to all first individual codes is calculated (corresponding to the fitness corresponding to a student), and then the first individual codes are arranged in ascending order, and then the first individual code with the smallest comprehensive total output efficiency (corresponding to the reference code) is selected, and its Euclidean distance with other first individual codes is calculated, and the first individual codes are arranged in order from small to large in Euclidean distance; in this embodiment, the Euclidean distance is calculated according to the following formula:

[0052]

[0053] in, represents the Euclidean distance between the two first individual codes, It represents the comprehensive evaluation value of the total output efficiency corresponding to the kth BCPLR node of the first body code corresponding to the i-th student, It represents the comprehensive evaluation value of the total output efficiency corresponding to the kth BCPLR node of the first body code corresponding to the jth student.

[0054] In this embodiment, after calculating the Euclidean distance of the students corresponding to the two first body codes, the first body codes with the closest Euclidean distances are selected according to the Euclidean distance to form a group, that is, to form a first student code body group; it can be understood that after forming a first student code body group, all the first body codes corresponding to the first student code body group are removed from the first body code queue arranged in order, and then the first body codes with the closest Euclidean distances are selected according to the Euclidean distance to form another group, that is, to obtain another first student code body group, so as to realize grouping of multiple first body codes into multiple first student code body groups.

[0055] Step 42, after determining the average total output efficiency corresponding to each first student coding body group, select the first teacher coding body corresponding to each first student coding body group from the first student coding body group, and based on the first teacher coding body and the corresponding average total output efficiency, conduct individual teaching for all the first body codes of the first student coding body group to generate the corresponding second student coding body group, wherein the first teacher coding body is the first coding body with the largest comprehensive total output efficiency in the first student coding body group, and the second student coding body group includes multiple second student coding bodies.

[0056] In this embodiment, according to the comprehensive total output efficiency corresponding to each first student coding body, the first teacher coding body in each first student coding body group is selected, that is, the teacher in each first student coding body group is selected, and then the average total output efficiency corresponding to each first student coding body group is calculated, and then teaching and learning are carried out. In the teaching stage, in each round of iteration, the first student coding body corresponding to a student learns according to the difference between the comprehensive total output efficiency corresponding to the first teacher coding body and the average total output efficiency, and gradually approaches the comprehensive total output efficiency corresponding to the first teacher coding body.

[0057] In some optional implementations, the step 42 of performing individual teaching on all first body codes of the first student code body group based on the first teacher code body and the corresponding average total output effectiveness to generate the corresponding second student code body group is implemented by the following steps:

[0058] Step 421, obtain the preset teaching factor and the first learning factor, determine the comprehensive total output efficiency corresponding to the first teacher coding body, and obtain the teacher output efficiency.

[0059] Step 422, based on the teaching factor and the average total output effectiveness, determine the optimization effectiveness gradient corresponding to the first body code in the first student code body group, and calculate the first difference between the teacher output effectiveness and the optimization effectiveness gradient;

[0060] Step 423, using the first learning factor and the first difference, determine the output efficiency correction variable corresponding to the first individual code in the first student coding body group, and according to the output efficiency correction variable, perform teaching correction on the comprehensive total output efficiency of the first individual code in the first student coding body group, and use the comprehensive total output efficiency obtained by the teaching correction as the comprehensive total output efficiency corresponding to the corresponding second student coding body, to obtain the corresponding second student coding body group.

[0061] In this embodiment, the comprehensive total output efficiency corresponding to the second student code body is calculated according to the following formula: :

[0062] Among them, xGroupTeacher represents the comprehensive total output efficiency corresponding to the first teacher coding body, x GroupMean represents the average total output efficiency corresponding to the first student coding group, and , x i represents the comprehensive total output efficiency corresponding to the i-th first student encoding body, m represents the number of first student encoding bodies in each first student encoding body group, r represents the first learning factor and represents the learning step length, r=rand(0,1), which is a random number between 0 and 1, T f represents the teaching factor, T f =round(1+rand(0,1), the value is 1 or 2.

[0063] In this embodiment, after teaching and learning and generating a new second student code body, the comprehensive total output efficiency corresponding to the new second student code body is also determined. Is the total output efficiency of the first body code in the first student code body group before teaching and learning? (or the corresponding fitness), if it is greater than, then accept the new second student encoding body, otherwise, the corresponding first body encoding before teaching and learning is used as the corresponding second student encoding body.

[0064] Step 43, using a cross-learning strategy, performs individual information learning and updating on all second student encoding bodies of each second student encoding body group to generate a plurality of second individual encodings.

[0065] In some optional implementations, in step 43, a cross-learning strategy is used to perform individual information learning and updating on all second student encoding bodies of each second student encoding body group to generate multiple second individual encodings, which is achieved by the following steps:

[0066] Step 431, in a preset random learning period, two second student code bodies are randomly obtained in each second student code body group, and the two second student code bodies obtained each time are individually learned and updated according to a preset communication learning strategy to generate a third student code body group corresponding to each second student code body group, wherein the communication strategy is used to guide the second student code body with the lowest overall output efficiency among the corresponding two second student code bodies to approach the second student code body with the highest overall output efficiency, and the third student code body group includes multiple first candidate student code bodies corresponding to the second student code bodies.

[0067] In the random learning method of this embodiment, the learning method of the second student encoding body corresponding to a student is the same as the learning stage of the existing TLBO algorithm, and the following formula is used for learning to obtain the comprehensive total output efficiency corresponding to the first candidate student encoding body:

[0068]

[0069] Among them, x i and x j They represent the comprehensive total output efficiency of the students corresponding to the two randomly selected second student encoding bodies, r represents the second learning factor, f(x i ) and f(x j ) represents the comprehensive evaluation value (fitness) of the total output efficiency corresponding to two randomly selected students.

[0070] Step 432, after the random learning period ends, determine the second student code body with the highest comprehensive total output efficiency in each second student code body group, obtain the second teacher code body, and according to the preset directional learning strategy, perform directional learning update on all second student code bodies except the second teacher code body in each second student code body group, and generate a fourth student code body group corresponding to each second student code body group, wherein the directional learning strategy is used to guide the second student code bodies except the second teacher code body in each second student code body to learn from the second teacher code body, and the fourth student code body group includes the second candidate student code body, and the second candidate student code body includes the second teacher code body and the second student code body after the directional learning update.

[0071] In the directed learning method of this embodiment, student x i No longer randomly giving x to other students j Instead, the second teacher coding body of the group is targeted to learn, so as to ensure that the direction of algorithm iteration is always moving towards a better solution. In some optional implementations, the following formula is used to perform directional learning to calculate the comprehensive total output efficiency corresponding to the second candidate student coding body: :

[0072]

[0073] Among them, x i represents the comprehensive total output efficiency corresponding to the second student coding body, r i represents the learning factor of the second student code body learning from the second teacher code body, x GroupTeacher Represents the comprehensive total output effectiveness corresponding to the second teacher coding body.

[0074] Step 433, according to the preset cross coefficient and the current corresponding random learning weight, determine the first cross learning weight corresponding to the first candidate student encoding body, and determine the second cross learning weight corresponding to the second candidate student encoding body.

[0075] Step 434, after respectively obtaining the comprehensive total output efficiency of the first candidate student coding body and the second candidate student coding body corresponding to the corresponding second student coding body, and obtaining the first comprehensive total output efficiency and the second comprehensive total output efficiency, cross-learning update is performed on the comprehensive total output efficiency corresponding to the second student coding body according to the first cross-learning weight, the second cross-learning weight, the first total output efficiency and the second total output efficiency, and the comprehensive total output efficiency obtained by the cross-learning update is used as the comprehensive total output efficiency corresponding to the corresponding second individual coding, to obtain the corresponding second individual coding.

[0076] In this embodiment, the first candidate student coding body and the second candidate student coding body are cross-learned to obtain the corresponding second individual coding. In this embodiment, the comprehensive total output efficiency corresponding to the second individual coding is calculated according to the following formula: :

[0077]

[0078] Among them, x i represents the comprehensive total output efficiency of the student corresponding to the corresponding second student encoding body, t i Indicates the number of current iterations, t max represents the maximum number of iterations, represents the cross coefficient, represents the comprehensive total output efficiency corresponding to the first candidate student coding body, Represents the comprehensive total output efficiency corresponding to the second alternative student coding body.

[0079] It should be understood that the weights of random learning and directed learning are dynamically adjusted as the algorithm iterations proceed. In the early stages of the algorithm, the weight of the random learning method is relatively large to ensure the diversity of the population, prevent the algorithm from falling into the local optimal solution too early, and conduct extensive searches. As the algorithm approaches the end of the iteration, the weight of the directed learning method increases, accelerating the convergence to the optimal solution and allowing the algorithm to approach the optimal solution more efficiently. Through this dynamic weight adjustment, the cross-learning strategy achieves an effective balance between global optimization and local exploration, significantly improving the efficiency and accuracy of the TLBO algorithm in solving complex optimization problems, making it more suitable for various complex application scenarios.

[0080] Through the above steps 41 to 43, the optimized iteration of teaching and learning based on the improved TIBO is realized, so as to iterate the first individual encoding of the initial encoding into the second individual encoding, which significantly improves the efficiency and accuracy of the TLBO algorithm in solving complex optimization problems.

[0081] In some of the embodiments, based on the fitness of the resource configuration mode corresponding to the second individual code and the improved TLBO, a population update iteration is performed on multiple second individual codes, which is achieved by the following steps:

[0082] Step 51, determining the fitness corresponding to the corresponding individual code according to the comprehensive total output efficiency of the candidate BCPLR node set associated with the corresponding individual code, wherein the corresponding individual code includes one of the first individual code and the second individual code.

[0083] In this embodiment, the corresponding individual code is represented as the individual code to be processed currently, which can be the first individual code or the second individual code that has completed at least one iteration; in this embodiment, the fitness of the individual code is determined according to the comprehensive total output efficiency corresponding to the corresponding individual code, and preferably the negative value of the comprehensive evaluation value of the comprehensive total output efficiency is used as the fitness of the corresponding individual code.

[0084] Step 52, determine all second individual codes to be updated and optimized for the Nth population, obtain the individual codes to be selected, and determine the first difference in fitness between each individual code to be selected and the corresponding historical individual code, where N=1, the historical individual code includes the first individual code, N>1, the historical individual code includes the first individual code after N-1 population update optimizations, and N is a positive integer.

[0085] Step 53, determine whether the first difference is greater than a preset threshold value, and when it is determined that the first difference is not greater than the preset threshold value, calculate the Euclidean distance between the individual code to be selected and the second reference code according to the fitness corresponding to the individual code to be selected, so as to group the multiple individual codes to be selected into multiple fifth student code body groups according to the corresponding Euclidean distances, wherein the second reference code is the individual code to be selected with the smallest fitness.

[0086] Step 54, based on the average total output efficiency of the third teacher encoding body and the corresponding fifth student encoding body group, individual teaching is performed on the candidate individual encodings of the fifth student encoding body group to generate the corresponding sixth student encoding body group, and the cross-learning strategy is used to perform individual information learning and update on the student encoding bodies corresponding to each sixth student encoding body group, and the new student encoding bodies generated by the update are used as the candidate individual encodings corresponding to the Nth population update optimization, wherein the third teacher encoding body is the candidate individual encoding with the greatest fitness in the fifth student encoding body group.

[0087] Step 55, when it is determined that the first difference is not greater than the preset threshold, the first individual code after the N-1th population update optimization is completed is obtained, and the obtained first individual code is used as the corresponding candidate individual code.

[0088] In some embodiments, determining a target individual code from among a plurality of generated candidate individual codes to obtain an optimized configuration result comprises the following steps:

[0089] Step 61, determining the fitness corresponding to each candidate individual code.

[0090] Step 62, select the candidate individual code with the highest fitness from multiple candidate individual codes to obtain the target individual code, and determine the candidate BCPLR node set corresponding to the target individual code and the production logistics task volume undertaken by each BCPLR node in the corresponding candidate BCPLR node set.

[0091] The preferred embodiments of the present application are described below:

[0092] The method for optimizing the configuration of distributed blockchain production logistics resources based on the improved teaching and learning algorithm of this embodiment is an optimization configuration model for distributed blockchain production logistics resources based on the improved teaching and learning algorithm applied to a wide area. This configuration model comprehensively considers the credibility of blockchain resources and the total operating cost and service time of the production logistics system, and aims to build a more comprehensive and reasonable model to enhance the cost-effectiveness and reliability of the system.

[0093] In the process of production logistics operations, the core manufacturer (i.e., the chain leader enterprise) will use the blockchain production logistics resource platform to decompose complex orders into several production logistics tasks. Each task can be achieved through a set of candidate blockchain production logistics resources that meet the production and logistics capacity constraints and service time requirements. That is, the core manufacturer will select the corresponding candidate blockchain production logistics resource set for the production logistics tasks at different stages of the product based on the product BOM decomposition results, and associate these resources according to the business logic process; next, the core manufacturer needs to evaluate the production logistics capabilities and production capacity of each BCPLR from the candidate blockchain production logistics resource set to select a BCPLR combination that can meet the order requirements. For example, the core manufacturer may select one or more BCPLRs from multiple outsourced production blockchain resource sets to provide outsourced parts and product production services; at the same time, select specific distribution and warehousing nodes from the logistics blockchain resource set to provide logistics distribution and warehousing services, and achieve efficient delivery of personalized orders by comprehensively coordinating the cooperation and resource sharing between BCPLR nodes in different blockchain resource sets.

[0094] In this embodiment, in the optimization configuration scenario for wide-area distributed blockchain production logistics resources, reference Figure 3, the core manufacturers need to screen out the optimal BCPLR nodes and allocate appropriate production tasks, distribution tasks and warehousing tasks to them, while ensuring that the total production capacity of the selected blockchain resources meets the requirements, so as to achieve the goal of minimizing the total operating cost of the distributed linkage manufacturing system (sDSMS), minimizing the total service time and maximizing the service credibility.

[0095] In this embodiment, the specific definition of the parameter symbols of the optimization configuration problem model for wide-area distributed blockchain production logistics resources is as follows: I represents the total number of tasks decomposed from complex orders on the blockchain logistics resource platform, i=1, 2, ..., I, T i Indicates Production logistics tasks, Indicates The first production logistics task A collection of blockchain resources, represents the kth blockchain production logistics resource of the jth blockchain production logistics resource set, represents the kth blockchain production logistics resource of the jth blockchain production logistics resource set, q represents the total number of candidate blockchain production logistics resource sets bcplr in the sDSMS system, s j represents the number of BCPLR nodes in the j-th candidate blockchain production logistics resource set in the sDSMS system, PC represents the production cost required to complete the required production logistics order task volume, LC represents the distribution cost required to complete the required production logistics order task volume, WC represents the warehousing cost required to complete the required production logistics order task volume, C fix represents the jth candidate The fixed cost required for the kth BLPCR node in the set to produce a unit of parts / products, C var represents the variable cost required to produce a unit of parts / products at the kth BLPCR node of the jth candidate BCPLR set, including the original material, labor, and energy costs that are proportional to the production volume, C fix +C var represents the jth candidate The kth set The node calculates the corresponding quotation based on its actual production situation and submits this quotation to the core manufacturer. C1 represents the unit distribution cost required for the unit distance of unit parts / product transportation, and C wrepresents the unit storage cost required for a unit part / product, pt represents the unit production time required for the kth BCPLR node of the jth candidate BCPLR set to produce a unit part / product, lt represents the unit transportation time required for the kth BCPLR node of the jth candidate BCPLR set to transport a unit part / product, wt represents the unit storage time required for the kth BCPLR node of the jth candidate BCPLR node set to store a unit part / product, ST represents the start production time of the production logistics order task, represents the cost weight coefficient, represents the time weight coefficient, represents the credibility weight coefficient, represents the credibility value of the kth BCPLR node in the jth candidate BCPLR node set, is a 0-1 variable, 1 means the i-th order task selects the k-th BCPLR node of the j-th candidate BCPLR node set, 0 means others, represents the production task quantity of the kth BCPLR node assigned to the jth candidate BCPLR node set by the i-th order task, represents the transportation task volume of the i-th order task from the k-th BCPLR node to the v-th BCPLR node, represents the storage task volume of the i-th order task assigned to the k-th BCPLR node of the j-th candidate BCPLR node set, represents the logistics transportation distance of the i-th order task from the k-th BCPLR node to the v-th BCPLR node, represents the real-time maximum capacity limit of the kth BCPLR node for the i-th order task, Represents the total amount of order tasks assigned to the jth candidate BCPLR node.

[0096] This embodiment first calculates the three objectives of the optimal configuration model of the wide-area distributed blockchain production logistics resources, which are the total credibility Re, the total operation cost TC and the total service time TT, and then constructs the optimal configuration model of the wide-area distributed BCPLR.

[0097] Total credibility calculation

[0098] In the process of optimizing the configuration of the sDSMS system for blockchain production logistics resources, the reputation level of resource nodes is an important measurement indicator, which has a significant impact on the quality of service (QoS) of resource nodes. Therefore, the concept of resource "credibility" is proposed as an important indicator for evaluating the comprehensive reputation level of BCPLR.

[0099] Reliability, also known as reliability or credibility, refers to the comprehensive credibility level of a blockchain production logistics resource, which is obtained from the multi-source and multi-dimensional information recorded in the blockchain resource platform. This information includes service ratings, integrity levels, the number of visits to blockchain resources and the number of reservations, etc. Based on the above information, the credibility of resources can be quantitatively expressed through four key indicators: service, integrity, access, and reservation.

[0100] Service degree. In the blockchain production logistics resource platform, users have the right to evaluate the corresponding blockchain resources after using them. This evaluation process is a direct feedback on the experience of using blockchain production logistics resources. The user's rating is expressed in the form of Degree of Service (DoS), which ranges from 0 to 5 points. The platform will collect all users' ratings of specific blockchain production logistics resources and calculate the comprehensive rating of the resource based on this. This comprehensive rating is a key indicator for measuring the overall performance of blockchain production logistics resources and user satisfaction, reflecting the quality, reliability and user acceptance of the resources. The service degree is calculated according to the following formula: :

[0101]

[0102] in, To calculate the user's The standardized score (i.e., service level) of a blockchain resource is calculated by considering the evaluation scores of all customer groups on the resource. Indicates Customers to The rating of blockchain resources, Indicates the total number of customers who rated this blockchain resource.

[0103] Honesty. In the blockchain production logistics resource platform, users can objectively evaluate the integrity of resource providers after using blockchain resources. User evaluation can be divided into two types: one is to mark the resource node as untrustworthy in the breach record, and the other is to indicate the recommendation of the resource node in the performance record. The blockchain production logistics resource platform uses these two records to quantify and reflect the integrity of the resource provider (Degree of Honesty, referred to as DoH):

[0104]

[0105] in, Indicates The integrity value of a blockchain resource, Indicates The number of fulfillment records of production logistics resources on a blockchain, Indicates the number of breach of contract records and integrity By calculating the The number of blockchain resources fulfilled Total number of transactions (number of fulfillments) Add the number of breaches ) is determined by the ratio of the resource node to the resource node. This formula effectively quantifies the integrity of the resource node and reflects the probability of its performance in future transactions.

[0106] Accessibility, the degree of trust users have in blockchain production logistics resources significantly affects the popularity of these resources. Specifically, the higher the credibility of a resource, the stronger its ability to attract users. This attractiveness is reflected in two aspects: first, users are more likely to pay repeatedly to use the resource; second, users are more willing to recommend these resources to others. Therefore, under normal circumstances, blockchain production logistics resources with higher credibility will have more visits. Based on this, this embodiment uses the degree of accessibility (DoA) as an important indicator to measure the credibility of blockchain production logistics resources. The access degree quantifies the frequency of resource access and calculates the access degree according to the following formula: :

[0107]

[0108] in, Indicates The accessibility of blockchain production logistics resources, express The number of visits to blockchain production logistics resources, and Represents the number of visits to the blockchain production logistics resource with the highest visit rate in the same category; through this formula, the access degree of each blockchain production logistics resource can be quantified, which is helpful to evaluate the market performance and user acceptance of blockchain resources, and provide key data support for resource optimization and strategy formulation.

[0109] The reservation degree can effectively evaluate the user's demand and planned use intention for these resources by obtaining the future reservation data of blockchain node resources in real time. The number of users' reservations for specific blockchain resources not only reveals their specific needs, but also reflects their specific interests and reservation plans for the resources. In this embodiment, the reservation degree (DoB) is used as an important indicator to measure the credibility of blockchain production logistics resources. By quantifying the reservation degree, the popularity and trust level of each resource can be accurately understood, which provides a key decision-making basis for the efficient management and optimal allocation of resources, thereby improving the overall value and benefits of resources. Specifically, the reservation degree is calculated according to the following formula: :

[0110]

[0111] in, Indicates The reservation degree of production logistics resources of each blockchain, It indicates the number of reservations for production logistics resources of the i-th blockchain in the future. It represents the number of reservations for the blockchain production logistics resources with the highest reservation rate in the i-th category. By comparing the number of reservations for each resource with the highest number of reservations in the same category, this formula effectively measures the reservation degree of blockchain production logistics resources.

[0112] By normalizing the above-mentioned service degree, integrity degree, access degree and reservation degree, a "QoS utility" is formed, that is, the credibility of the corresponding BCPLR node. In this embodiment, the corresponding credibility is measured according to the following evaluation model:

[0113] (1)

[0114] (2)

[0115] (3)

[0116] (4)

[0117] (5)

[0118] Among them, formula (1) describes the credibility evaluation model of resource nodes. Indicates that the i-th blockchain resource is executing the order task The normalized credibility evaluation value at the time of the test is a combination of service, integrity, access and reservation. The importance of each dimension is determined by the weight Decide, ,

[0119] , and Respectively represent the i-th blockchain resource in The maximum and actual ratings on the dimension, and and It means that all blockchain resources are The maximum and minimum scores on the dimension; Formula (2) represents the maximum score of the i-th blockchain production logistics resource in terms of service level; Formula (3) represents the maximum score of the integrity of the i-th blockchain production logistics resource; formula (4) represents the highest score of the i-th blockchain production logistics resource in terms of accessibility; Formula (5) Represents the maximum score of the i-th blockchain production logistics resource in terms of reservation degree.

[0120] Total operating cost calculation

[0121] In the process of optimizing the configuration of the sDSMS system for blockchain production logistics resources, its total operating cost is also a core performance indicator. The total operating cost is mainly composed of the production cost and logistics cost required to complete the production logistics tasks. Specifically, the production cost ( ) refers to the production cost required by each production node to complete the corresponding production task; logistics cost ( ) refers to the logistics and distribution costs of transporting products from one manufacturing node to another; warehousing costs ( ) refers to the storage cost of finished products at the warehouse node. The total operating cost model of the constructed sDSMS system is:

[0122] (6)

[0123] (7)

[0124] (8)

[0125] (9)

[0126] Among them, formula (6) represents the total operating cost of the production logistics system when completing the order task volume, including the production cost, logistics transportation cost and storage cost of each manufacturing node; formula (7) represents the production cost of each production node, including the fixed cost C fix and variable cost C var ; Formula (8) represents the distribution cost of each distribution node; Formula (9) represents the storage cost of each warehouse node.

[0127] Total service time calculation

[0128] In the process of optimizing the configuration of the sDSMS system for blockchain production logistics resources, the total service time is an important performance indicator. It measures the entire time span from the customer submitting a personalized order task on the blockchain production logistics platform to the order product being loaded and shipped from the shipping warehouse. This time span mainly includes two parts: production time and logistics time. Specifically: Production time (PT) refers to the time from order confirmation to the completion of product manufacturing. Logistics time: divided into logistics distribution time and warehousing time. Logistics distribution time (LT) refers to the time required for the distribution of products (or semi-finished products) between different manufacturing nodes. The warehousing time (WT) refers to the storage time of the finished product in the warehouse until it is loaded and shipped to the customer. The constructed sDSMS system service time model is:

[0129] TT=ST+PT+LT+WT (10)

[0130] (11)

[0131] (12)

[0132] (13)

[0133] Among them, formula (10) represents the total service time of the sDSMS system, including the production logistics task start time ST, production time, delivery time and warehousing time; formula (11) represents the production time required to complete all order tasks; formula (12) represents the delivery time required to complete all order tasks; formula (13) represents the warehousing time required to complete all order tasks.

[0134] Taking into account the three key goals of sDSMS system optimization configuration, this embodiment formalizes the multi-objective optimization configuration problem of blockchain production logistics resources for wide-area distribution as follows:

[0135] (14)

[0136] (15)

[0137] (16)

[0138] (17)

[0139] (18)

[0140] (19)

[0141] (20)

[0142] (twenty one)

[0143] % (twenty two)

[0144] Among them, formula (14) represents the multi-objective function of the optimization configuration problem, whose goal is to minimize the weighted total system operation cost TC and total service time TT, and maximize the weighted total system node credibility Re; formula (15) represents the assignment of the i-th order task to the k-th The maximum production task volume of a node cannot exceed its maximum real-time capacity limit; Formula (16) indicates that the production task volume of all BCPLR nodes in the jth candidate BCPLR node set assigned to the i-th order task must meet the total task volume of the order production; Formula (17) indicates that the logistics distribution volume allocated from BCPLR node k to BCPLR node v cannot exceed their respective production task volumes; Formula (18) indicates that the transportation to node The sum of all logistics distribution volumes is equal to its production task volume; Formula (19) indicates that the sum of logistics distribution volumes distributed from BCPLR node k is equal to its warehousing task volume; Formulas (20) to (21) indicate that production logistics tasks can only be executed when the immediate predecessor task has been completed, and must be performed when the corresponding BCPLR node is available; Formula (22) represents the credibility qualification constraint of the candidate blockchain production logistics resources.

[0145] This embodiment assigns corresponding weights to the three objectives of operating cost, service time and node credibility according to the user's demand preferences. The multi-objective optimization configuration problem for wide-area distributed blockchain production logistics resources is transformed into a single-objective optimization problem by using the classic weighted summation method and normalization processing. This method allows users to adjust the importance of each objective according to their specific needs, so as to find the most suitable configuration solution. The specific conversion formula is:

[0146]

[0147] Among them, F goal Represents a comprehensive evaluation value, which is used to measure the overall effect of different configuration schemes. They represent the weight coefficients of blockchain production logistics resource demanders on operating costs, service time and credibility, which indicate the relative importance of these factors in the decision-making process. The sum of these weight coefficients is 1, that is, , ensuring that all factors are considered in a balanced manner, They represent the operation cost, service time and credibility of the i-th solution respectively; They represent the maximum values ​​of optimal solution centralized operation cost, service time and reliability respectively. They represent the minimum values ​​of optimal solution centralized operation cost, service time and reliability respectively.

[0148] The optimization configuration method for wide-area distributed blockchain production logistics resources proposed in this embodiment aims to minimize system operating costs, minimize service time, and maximize reliability by establishing a multi-objective optimization function. This method not only takes into account the cost and time dimension indicators of the system resource structure configuration, but also further incorporates the reliability dimension indicators of the system, providing evolutionary structural strategy support for optimizing the resource configuration structure in the sDSMS system. The optimization configuration method of integrated blockchain technology proposed in this embodiment not only improves the accuracy and efficiency of resource configuration, but also enhances the transparency and traceability of the entire manufacturing system, enabling manufacturing companies to more effectively respond to the complexity and variability of market demand, optimize resource allocation, and thus improve the efficiency and responsiveness of the entire manufacturing system.

[0149] This embodiment improves the teaching strategy and learning strategy of the traditional teaching and learning optimization algorithm, proposes an improved teaching and learning algorithm (iTLBO) with multi-teacher grouping teaching strategy and cross-learning learning strategy, and gives a solution process of the improved teaching and learning optimization algorithm for optimization configuration problems.

[0150] Figure 4 Demonstrates the operational logic of configuring distributed blockchain production logistics resources for complex personalized orders, see Figure 4 In the optimization configuration process of BCPLR driven by complex personalized orders, there are generally three main participants: customers, blockchain resource platforms, and production logistics resource providers. As the demander of intelligent resources, customers are mainly responsible for submitting complex personalized order products to the blockchain production logistics resource platform to start the optimization configuration process of intelligent production logistics resources. As the provider of intelligent production logistics resources, the main responsibility of production logistics companies is to provide various production logistics resources sufficient to complete these complex order products. The blockchain production logistics resource platform plays a core role in the entire operation system. It not only formulates the optimization configuration rules and mechanisms of blockchain resources, but also connects resource providers in different geographical locations to the platform through the blockchain network, providing a transparent and secure transaction collaboration service platform for multiple stakeholders, facilitating interaction, cooperation and transactions between demanders and providers.

[0151] First, customers submit detailed information about complex and personalized order tasks on the blockchain production logistics resource platform, such as order demand, product types, delivery deadlines, production capacity requirements, process constraints, acceptable production logistics costs, and credit values. Subsequently, production logistics companies register their resources and publish them on the blockchain resource platform in the form of blockchain production logistics resources (BCPLR) through the platform's blockchain resource encapsulation and virtualization technology. This process realizes the blockchain encapsulation of production logistics resources, thereby building an intelligent BCPLR pool.

[0152] When the platform receives a complex personalized order task submitted by a customer, it will decompose it into multiple tasks (including the manufacturing of various parts of complex order products, product assembly, and finished product distribution and warehousing tasks) according to the product BOM decomposition results, delivery date, production complexity and other requirements. Subsequently, the platform selects candidate blockchain production logistics resource sets that can meet the requirements of each task from the blockchain production logistics resource pool based on the production capacity and production capacity of blockchain resources. Then, the platform calls the corresponding intelligent optimization configuration algorithm according to the set BCPLR optimization configuration strategy to obtain the optimal configuration plan result. After executing the configuration plan, the production logistics enterprise will receive the execution right of the production logistics task and feedback the production logistics process information to the blockchain resource platform. At the same time, customers can remotely obtain information on the blockchain production logistics set that meets the relevant requirements of complex order tasks, and can obtain production logistics execution information of related tasks from the blockchain production logistics resource platform.

[0153] This embodiment also provides an optimized configuration device for distributed blockchain production logistics resources based on an improved teaching and learning algorithm, which is used to implement the above embodiments and preferred implementations, and will not be repeated for what has been described. As used below, the terms "module", "unit", "subunit", etc. can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0154] Figure 5 is a structural block diagram of an optimized configuration device for distributed blockchain production logistics resources based on an improved teaching and learning algorithm according to an embodiment of the present application, such as Figure 5 As shown, the device includes a selection module 51, an encoding module 52 and a processing module 53, wherein:

[0155] A selection module 51 is used to select a candidate BCPLR node set corresponding to each blockchain resource set from the production logistics resource BCPLR nodes corresponding to the preset multiple blockchain resource sets, wherein each blockchain resource set includes multiple BCPLR nodes, and each candidate BCPLR node set includes at least one BCPLR node that can meet the preset production efficiency target;

[0156] The encoding module 52 is coupled to the selection module 51 and is used to perform population individual encoding and population initialization based on multiple candidate BCPLR node sets and production logistics task amounts, and generate multiple first individual codes, wherein the first individual code is used to represent a resource configuration method, and the resource configuration method is associated with a candidate BCPLR node set and the production logistics task amount undertaken by each BCPLR node in the candidate BCPLR node set;

[0157] The processing module 53 is coupled to the encoding module 52, and is used to use the improved teaching and learning algorithm TLBO to perform population search iterations on multiple first individual codes to generate multiple second individual codes, and based on the fitness of the resource configuration method corresponding to the second individual code and the improved TLBO, perform population update iterations on the multiple second individual codes, and determine the target individual code from the generated multiple candidate individual codes to obtain an optimized configuration result, wherein the improved TLBO is a TIBO that uses the teaching strategy of multi-teacher grouping and the cross-learning strategy combining randomness and directionality as the teaching strategy and learning strategy of TLBO respectively, and the optimized configuration result includes the resource configuration method corresponding to the target individual code.

[0158] In some embodiments, the selection module 51 further includes:

[0159] The selection unit is used to traverse all blockchain resource sets and select multiple candidate BCPLR node sets corresponding to each blockchain resource set from all BCPLR nodes of each traversed blockchain resource set.

[0160] The acquisition unit is coupled to the first selection unit and is used to obtain the real-time production capacity information corresponding to each blockchain resource set from the blockchain production logistics resource platform, and determine the total output efficiency corresponding to each BCPLR node in each candidate BCPLR node set based on the production capacity information, wherein the total output efficiency is determined based on the total production capacity, total service time and total credibility of the candidate BCPLR node set.

[0161] The judgment unit is coupled to the first acquisition unit and is used to judge whether each BCPLR node of each alternative BCPLR node set meets the production efficiency target based on the total output efficiency, and take all BCPLR nodes that meet the production efficiency target as the candidate BCPLR node set corresponding to the corresponding alternative BCPLR node set.

[0162] In some of the embodiments, the judgment unit is also used to obtain the total capacity value, service time and total informability corresponding to each BCPLR node from the total output efficiency, and determine the output demand value and service time expected value corresponding to the production efficiency target, wherein the output demand value is used to characterize the required output capacity value of the manufacturing order corresponding to the corresponding blockchain resource set, and the service time expected value is used to characterize the production manufacturing time required by the corresponding manufacturing order; respectively judge whether the total capacity value of each BCPLR node is greater than the output demand value, whether the service time is longer than the expected service time value, and whether the total credibility of each BCPLR node is greater than a preset credibility threshold; when it is judged that the total capacity value is greater than the output demand value, the service time is longer than the expected service time value, and the total credibility is greater than the preset credibility threshold, it is determined that the BCPLR node meets the production efficiency target; when it is judged that the total capacity value is not greater than the output demand value or the service time is not longer than the expected service time value or the total credibility is not greater than the preset credibility threshold, it is determined that the BCPLR node does not meet the production efficiency target.

[0163] In some of the embodiments, the selection unit is also used to determine all BCPLR nodes of each traversed blockchain resource set, and select at least one BCPLR node combination from all BCPLR nodes of each blockchain resource set to obtain multiple alternative BCPLR node sets, wherein each BCPLR node group includes a preset number of BCPLR nodes.

[0164] In some embodiments, the processing module 53 further includes:

[0165] A determination unit is used to determine the comprehensive total output efficiency corresponding to the candidate BCPLR node set corresponding to each first body code according to the total output efficiency corresponding to each BCPLR node, and calculate the Euclidean distance between each first body code and the reference code according to the comprehensive total output efficiency, so as to group multiple first body codes into multiple first student code body groups according to the Euclidean distance, wherein the reference code is the first body code with the smallest comprehensive total output efficiency, and the comprehensive total output efficiency is obtained by weighted calculation of the total output efficiencies corresponding to all BCPLR nodes of the corresponding candidate node set.

[0166] The teaching unit is coupled to the determination unit and is used to select the first teacher coding body corresponding to each first student coding body group from the first student coding body group after determining the average total output efficiency corresponding to each first student coding body group, and based on the first teacher coding body and the corresponding average total output efficiency, conduct individual teaching on all the first body codes of the first student coding body group to generate the corresponding second student coding body group, wherein the first teacher coding body is the first coding body with the largest comprehensive total output efficiency in the first student coding body group, and the second student coding body group includes multiple second student coding bodies.

[0167] The learning unit is coupled to the teaching unit and is used to utilize a cross-learning strategy to perform individual information learning and updating on all second student encoding bodies of each second student encoding body group to generate a plurality of second individual encodings.

[0168] In some of the embodiments, the teaching unit is also used to obtain a preset teaching factor and a first learning factor, determine the comprehensive total output efficiency corresponding to the first teacher coding body, and obtain the teacher output efficiency; based on the teaching factor and the average total output efficiency, determine the optimization efficiency gradient corresponding to the first body coding in the first student coding body group, and calculate the first difference between the teacher output efficiency and the optimization efficiency gradient; use the first learning factor and the first difference to determine the output efficiency correction variable corresponding to the first body coding in the first student coding body group, and according to the output efficiency correction variable, perform teaching correction on the comprehensive total output efficiency of the first body coding in the first student coding body group, and use the comprehensive total output efficiency obtained by the teaching correction as the comprehensive total output efficiency corresponding to the corresponding second student coding body to obtain the corresponding second student coding body group.

[0169] In some of the embodiments, the learning unit is further used to randomly obtain two second student code bodies in each second student code body group during a preset random learning period, and perform individual learning updates on the two second student code bodies obtained each time according to a preset communication learning strategy to generate a third student code body group corresponding to each second student code body group, wherein the communication strategy is used to guide the second student code body with the lowest comprehensive total output efficiency in the corresponding two second student code bodies to approach the second student code body with the highest comprehensive total output efficiency, and the third student code body group includes a plurality of first candidate student code bodies corresponding to the second student code bodies; after the random learning period ends, the second student code body with the highest comprehensive total output efficiency in each second student code body group is determined to obtain the second teacher code body, and according to the preset directional learning strategy, all second student code bodies in each second student code body group except the second teacher code body are subjected to directional learning updates to generate a fourth student code body group corresponding to each second student code body group, wherein the directional learning strategy is used to guide the second student code body with the lowest comprehensive total output efficiency in the corresponding two second student code bodies to approach the second student code body with the highest comprehensive total output efficiency, and the third student code body group includes a plurality of first candidate student code bodies corresponding to the second student code bodies. In order to guide the second student encoding bodies other than the second teacher encoding body in each second student encoding body to learn from the second teacher encoding body, the fourth student encoding body group includes the second candidate student encoding body, and the second candidate student encoding body includes the second teacher encoding body and the second student encoding body after completing the directional learning update; according to the preset cross coefficient and the current corresponding random learning weight, the first cross-learning weight corresponding to the first candidate student encoding body is determined, and the second cross-learning weight corresponding to the second candidate student encoding body is determined; after respectively obtaining the comprehensive total output efficiency of the first candidate student encoding body and the second candidate student encoding body corresponding to the corresponding second student encoding body, and obtaining the first comprehensive total output efficiency and the second comprehensive total output efficiency, according to the first cross-learning weight, the second cross-learning weight, the first total output efficiency and the second total output efficiency, the comprehensive total output efficiency corresponding to the second student encoding body is cross-learned and updated, and the comprehensive total output efficiency obtained by the cross-learning update is used as the comprehensive total output efficiency corresponding to the corresponding second individual code, and the corresponding second individual code is obtained.

[0170] In some of the embodiments, the processing module 53 is also used to determine the fitness corresponding to the corresponding individual code according to the comprehensive total output efficiency of the candidate BCPLR node set associated with the corresponding individual code, wherein the corresponding individual code includes one of the first individual code and the second individual code; determine all the second individual codes to be updated and optimized for the Nth population to obtain the selected individual code, and determine the first difference in fitness corresponding to each selected individual code and the corresponding historical individual code, wherein N=1, the historical individual code includes the first individual code, N>1, the historical individual code includes the first individual code after N-1 population update optimizations, and N is a positive integer; determine whether the first difference is greater than a preset threshold, and if it is determined that the first difference is not greater than the preset threshold, calculate the Euclidean distance between the selected individual code and the second reference code according to the fitness corresponding to the selected individual code, so as to obtain the fitness according to the selected individual code. Corresponding Euclidean distance, multiple candidate individual codes are grouped into multiple fifth student code body groups, wherein the second reference code is the candidate individual code with the smallest fitness; based on the average total output efficiency corresponding to the third teacher code body and the corresponding fifth student code body group, the candidate individual codes of the fifth student code body group are individually taught to generate the corresponding sixth student code body group, and the cross-learning strategy is used to perform individual information learning and update on the student code bodies corresponding to each sixth student code body group, and the new student code body generated by the update is used as the candidate individual code corresponding to the Nth population update optimization, wherein the third teacher code body is the candidate individual code with the largest fitness in the fifth student code body group, and when it is judged that the first difference is not greater than the preset threshold, the first individual code after the N-1th population update optimization is completed is obtained, and the obtained first individual code is used as the corresponding candidate individual code.

[0171] In some of the embodiments, the processing module 53 is also used to determine the fitness corresponding to each alternative individual code; among multiple alternative individual codes, the alternative individual code with the highest fitness is selected to obtain the target individual code, and the candidate BCPLR node set corresponding to the target individual code and the corresponding production logistics task volume undertaken by each BCPLR node in the candidate BCPLR node set are determined.

[0172] This embodiment further provides a service platform, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0173] Optionally, the service platform may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0174] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0175] S1. From the BCPLR nodes of production logistics resources corresponding to the preset multiple blockchain resource sets, select the candidate BCPLR node set corresponding to each blockchain resource set. Each blockchain resource set includes multiple BCPLR nodes, and each candidate BCPLR node set includes at least one BCPLR node that can meet the preset production efficiency target.

[0176] S2, based on multiple candidate BCPLR node sets and production logistics task volumes, performs population individual coding and population initialization to generate multiple first individual codes. The first individual code is used to characterize a resource configuration method. The resource configuration method is associated with a candidate BCPLR node set and the production logistics task volume undertaken by each BCPLR node in the candidate BCPLR node set.

[0177] S3, using the improved teaching and learning algorithm TLBO, performs population search iterations on multiple first individual codes to generate multiple second individual codes, and based on the fitness of the resource configuration method corresponding to the second individual code and the improved TLBO, performs population update iterations on the multiple second individual codes, and determines the target individual code from the generated multiple candidate individual codes to obtain the optimized configuration result. The improved TLBO is TIBO, which uses the teaching strategy of multi-teacher grouping and the cross-learning strategy combining randomness and directionality as the teaching strategy and learning strategy of TLBO respectively. The optimized configuration result includes the resource configuration method corresponding to the target individual code.

[0178] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0179] In addition, in combination with the distributed blockchain production logistics resource optimization configuration method based on the improved teaching and learning algorithm in the above embodiment, the embodiment of the present application can provide a storage medium for implementation. The storage medium stores a computer program; when the computer program is executed by the processor, any one of the distributed blockchain production logistics resource optimization configuration methods based on the improved teaching and learning algorithm in the above embodiment is implemented.

[0180] Those skilled in the art should understand that the technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0181] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A distributed blockchain production logistics resource optimization configuration method based on an improved teaching and learning algorithm, characterized in that: include: From the production logistics resource BCPLR nodes corresponding to the preset multiple blockchain resource sets, select a candidate BCPLR node set corresponding to each of the blockchain resource sets, wherein each of the blockchain resource sets includes multiple BCPLR nodes, and each of the candidate BCPLR node sets includes at least one of the BCPLR nodes that can meet the preset production efficiency target; Based on the multiple candidate BCPLR node sets and the production logistics task volume, population individual coding and population initialization are performed to generate multiple first individual codes, wherein the first individual code is used to characterize a resource configuration method, and the resource configuration method is associated with a candidate BCPLR node set and the production logistics task volume undertaken by each BCPLR node in the candidate BCPLR node set; Using the improved teaching and learning algorithm TLBO, a population search iteration is performed on the multiple first individual codes to generate multiple second individual codes, and based on the fitness of the resource configuration method corresponding to the second individual code and the improved TLBO, a population update iteration is performed on the multiple second individual codes, and a target individual code is determined from the generated multiple candidate individual codes to obtain an optimized configuration result, wherein the improved TLBO is a TIBO that uses a teaching strategy of multi-teacher grouping and a cross-learning strategy combining randomness and directionality as the teaching strategy and learning strategy of TLBO respectively, and the optimized configuration result includes the resource configuration method corresponding to the target individual code, Among them, from the production logistics resource BCPLR nodes corresponding to the preset multiple blockchain resource sets, a candidate BCPLR node set corresponding to each blockchain resource set is selected, including: Traversing all the blockchain resource sets, and selecting a plurality of candidate BCPLR node sets corresponding to each blockchain resource set from all the BCPLR nodes of each blockchain resource set traversed; Obtaining the real-time production capacity information corresponding to each of the blockchain resource sets from the blockchain production logistics resource platform, and determining the total output efficiency corresponding to each of the BCPLR nodes in each of the candidate BCPLR node sets based on the production capacity information, wherein the total output efficiency is determined based on the total capacity, total service time and total credibility of the candidate BCPLR node set; According to the total output efficiency, determine whether each of the BCPLR nodes in each of the candidate BCPLR node sets meets the production efficiency target, and use all the BCPLR nodes that meet the production efficiency target as the candidate BCPLR node set corresponding to the corresponding candidate BCPLR node set; According to the total output efficiency, judging whether each BCPLR node of each candidate BCPLR node set meets the production efficiency target includes: From the total output efficiency, the total capacity value, service time and total information availability corresponding to each BCPLR node are obtained, and the output demand value and service time expectation value corresponding to the production efficiency target are determined, wherein the output demand value is used to represent the required output capacity value of the manufacturing order corresponding to the corresponding blockchain resource set, and the service time expectation value is used to represent the production manufacturing time required by the corresponding manufacturing order; Respectively determine whether the total capacity value of each BCPLR node is greater than the output demand value, whether the service time is longer than the expected service time value, and determine whether the total credibility of each BCPLR node is greater than a preset credibility threshold; When it is determined that the total capacity value is greater than the output demand value, the service time is longer than the expected service time value, and the total credibility is greater than a preset credibility threshold, it is determined that the BCPLR node meets the production efficiency target; When it is determined that the total capacity value is not greater than the output demand value or the service time is not longer than the expected service time value or the total credibility is not greater than a preset credibility threshold, it is determined that the BCPLR node does not meet the production efficiency target; The improved teaching and learning algorithm TLBO is used to perform population search iterations on the plurality of first individual codes to generate a plurality of second individual codes, including: According to the total output efficiency corresponding to each of the BCPLR nodes, determine the comprehensive total output efficiency corresponding to the candidate BCPLR node set corresponding to each of the first individual codes, and calculate the Euclidean distance between each of the first individual codes and a reference code according to the comprehensive total output efficiency, so as to group a plurality of the first individual codes into a plurality of first student code body groups according to the Euclidean distance, wherein the reference code is the first individual code with the minimum comprehensive total output efficiency, and the comprehensive total output efficiency is obtained by weighted calculation of the total output efficiencies corresponding to all the BCPLR nodes of the corresponding candidate BCPLR node set; After determining the average total output efficiency corresponding to each of the first student encoding body groups, a first teacher encoding body corresponding to each of the first student encoding body groups is selected from the first student encoding body groups, and based on the first teacher encoding body and the corresponding average total output efficiency, individual teaching is performed on all the first individual encodings of the first student encoding body group to generate a corresponding second student encoding body group, wherein the first teacher encoding body is the first student encoding body with the largest comprehensive total output efficiency in the first student encoding body group, and the second student encoding body group includes a plurality of second student encoding bodies; By using the cross-learning strategy, individual information learning and updating are performed on all the second student encoding bodies of each second student encoding body group to generate a plurality of the second individual encodings.

2. The method according to claim 1, characterized in that From all the BCPLR nodes of each of the traversed blockchain resource sets, multiple candidate BCPLR node sets corresponding to each of the blockchain resource sets are selected, including: Determine all the BCPLR nodes of each of the traversed blockchain resource sets, and select at least one BCPLR node combination from all the BCPLR nodes of each of the blockchain resource sets to obtain a plurality of candidate BCPLR node sets, wherein each BCPLR node group includes a preset number of BCPLR nodes.

3. The method according to claim 1, characterized in that Based on the first teacher coding body and the corresponding average total output effectiveness, individual teaching is performed on all the first individual codings of the first student coding body group to generate a corresponding second student coding body group, including: Obtaining a preset teaching factor and a first learning factor, determining the comprehensive total output effectiveness corresponding to the first teacher coding body, and obtaining the teacher output effectiveness; Based on the teaching factor and the average total output effectiveness, determining the optimization effectiveness gradient corresponding to the first individual code in the first student code body group, and calculating the first difference between the teacher output effectiveness and the optimization effectiveness gradient; The first learning factor and the first difference are used to determine the output efficiency correction variable corresponding to the first individual code in the first student coding body group, and according to the output efficiency correction variable, the comprehensive total output efficiency of the first individual code in the first student coding body group is subjected to teaching correction, and the comprehensive total output efficiency obtained by the teaching correction is used as the comprehensive total output efficiency corresponding to the corresponding second student coding body to obtain the corresponding second student coding body group.

4. The method according to claim 1, characterized in that: Using the cross-learning strategy, individual information learning and updating are performed on all the second student encoding bodies of each second student encoding body group to generate a plurality of second individual encodings, including: In a preset random learning period, two second student encoding bodies are randomly obtained in each second student encoding body group, and the two second student encoding bodies obtained each time are individually learned and updated according to a preset communication learning strategy to generate a third student encoding body group corresponding to each second student encoding body group, wherein the communication learning strategy is used to guide the second student encoding body with the lowest comprehensive total output efficiency in the corresponding two second student encoding bodies to approach the second student encoding body with the highest comprehensive total output efficiency, and the third student encoding body group includes a plurality of first candidate student encoding bodies corresponding to the second student encoding bodies; After the random learning period is over, the second student code body with the highest comprehensive total output efficiency in each of the second student code body groups is determined to obtain a second teacher code body, and all of the second student code bodies except the second teacher code body in each of the second student code body groups are updated through directional learning according to a preset directional learning strategy to generate a fourth student code body group corresponding to each of the second student code body groups, wherein the directional learning strategy is used to guide the second student code bodies except the second teacher code body in each of the second student code bodies to learn from the second teacher code body, and the fourth student code body group includes a second candidate student code body, and the second candidate student code body includes the second teacher code body and the second student code body after the directional learning update is completed; Determine a first cross-learning weight corresponding to the first candidate student encoding body and determine a second cross-learning weight corresponding to the second candidate student encoding body according to a preset cross-coefficient and a currently corresponding random learning weight; After respectively acquiring the comprehensive total output efficiency of the first candidate student coding body and the second candidate student coding body corresponding to the corresponding second student coding body to obtain the first comprehensive total output efficiency and the second comprehensive total output efficiency, the comprehensive total output efficiency corresponding to the second student coding body is cross-learned and updated according to the first cross-learning weight, the second cross-learning weight, the first comprehensive total output efficiency and the second comprehensive total output efficiency, and the comprehensive total output efficiency obtained by the cross-learning update is used as the comprehensive total output efficiency corresponding to the corresponding second individual coding to obtain the corresponding second individual coding.

5. The method according to claim 4, characterized in that Based on the fitness of the resource configuration mode corresponding to the second individual code and the improved TLBO, a plurality of the second individual codes are updated and iterated, including: Determine the fitness corresponding to the corresponding individual code according to the comprehensive total output efficiency of the candidate BCPLR node set associated with the corresponding individual code, wherein the corresponding individual code includes one of the first individual code and the second individual code; Determine all the second individual codes to be subjected to the Nth population update optimization, obtain the candidate individual codes, and determine the first difference of the fitness corresponding to each candidate individual code and the corresponding historical individual code, wherein N=1, the historical individual code includes the first individual code, N>1, the historical individual code includes the first individual code after the N-1th population update optimization, and N is a positive integer; Determine whether the first difference is greater than a preset threshold value, and if it is determined that the first difference is not greater than the preset threshold value, calculate the Euclidean distance between the candidate individual code and the second reference code according to the fitness corresponding to the candidate individual code, so as to group the plurality of candidate individual codes into a plurality of fifth student code body groups according to the corresponding Euclidean distances, wherein the second reference code is the candidate individual code with the smallest fitness; Based on the average total output efficiency of the third teacher coding body and the corresponding fifth student coding body group, individual teaching is performed on the candidate individual codings of the fifth student coding body group to generate the corresponding sixth student coding body group, and the cross-learning strategy is used to perform individual information learning and update on the student coding bodies corresponding to each of the sixth student coding body groups, and the new student coding bodies generated by the update are used as the candidate individual coding corresponding to the Nth population update optimization, wherein the third teacher coding body is the candidate individual coding with the largest fitness in the fifth student coding body group.

6. The method according to claim 5, characterized in that When it is determined that the first difference is not greater than a preset threshold, the method further includes: acquiring the first individual code after the N-1th population update optimization is completed, and using the acquired first individual code as the corresponding candidate individual code.

7. The method according to claim 5, characterized in that From the generated multiple candidate individual codes, determine the target individual code and obtain the optimized configuration result, including: Determining the fitness corresponding to each candidate individual code; Among the multiple candidate individual codes, the candidate individual code with the highest fitness is selected to obtain the target individual code, and the candidate BCPLR node set corresponding to the target individual code and the production logistics task volume undertaken by each BCPLR node in the corresponding candidate BCPLR node set are determined.

Images