Efficient supply chain collaboration method and platform

Abstract

The invention belongs to the technical field of supply chain management, and discloses an efficient supply chain collaboration method and platform, and the method comprises the steps: carrying out the information collection of participating enterprises in a target supply chain, obtaining the corresponding enterprise information, and constructing a corresponding collaboration management center based on the information; the collaborative management center comprises an enterprise terminal and an internet cloud; order information is acquired, and a corresponding pre-collaborative planning scheme and a collaborative supply sub-chain are constructed based on the order information; executing a corresponding pre-collaborative planning scheme in the collaborative supply subchain, performing dynamic information capture on the execution process of the corresponding pre-collaborative planning scheme, and performing collaborative risk monitoring based on the dynamic information capture; according to the invention, efficient collaboration and risk monitoring of participating enterprises in the supply chain are realized, and powerful support is provided for supply chain optimization.

Description

Technical Field

[0001] The present invention relates to the technical field of supply chain management, and more specifically, to an efficient supply chain collaboration method and platform. Background Art

[0002] In today's highly competitive market environment, supply chain management has become a key factor in improving the competitiveness of enterprises. The traditional supply chain management model has many problems in information flow, task allocation, risk response, etc., and it is difficult to meet the needs of enterprises for efficient and collaborative operations.

[0003] Compared with existing technologies, in the traditional supply chain collaborative management process, the information between participating enterprises is isolated and there is a lack of effective sharing mechanism, which increases the time cost and communication cost of cooperation and seriously restricts the overall collaborative efficiency of the supply chain. In addition, in the order processing process, the task allocation lacks scientific planning, resulting in unreasonable task allocation and serious waste of resources. At the same time, in terms of cost control, multiple cost factors are not comprehensively considered, which makes the overall cost of the supply chain high, making it difficult to achieve the goals of minimizing costs and minimizing delivery time. At the same time, once the existing supply chain collaboration plan is determined, it is difficult to adjust and optimize it according to actual conditions during implementation. For example, factors such as changes in market demand and fluctuations in corporate production capacity will affect the normal operation of the supply chain, but the traditional model cannot capture these changes in time and make corresponding adjustments, resulting in poor adaptability of the supply chain and difficulty in maintaining efficient operation. In addition, most companies lack effective risk monitoring methods and cannot monitor the operating status of the supply chain in real time.

[0004] In view of this, the present invention proposes an efficient supply chain collaboration method and platform to solve the above problems. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solutions: An efficient supply chain collaboration method, including: Step 1: Collect information from participating enterprises in the target supply chain, obtain corresponding enterprise information, and build a corresponding collaborative management center based on it; the collaborative management center includes enterprise terminals and Internet cloud; Step 2: Obtain order information and build corresponding pre-collaborative planning solutions and collaborative supply sub-chains based on the order information; Step three: Execute the corresponding pre-collaborative planning scheme within the collaborative supply sub-chain, capture dynamic information of the execution process of the corresponding pre-collaborative planning scheme, and conduct collaborative risk monitoring based on it.

[0006] Furthermore, the process of collecting information from participating enterprises in the target supply chain, obtaining corresponding enterprise information, and building a corresponding collaborative management center based on the information includes: Setting a data collection node, which is deployed in each participating enterprise in the target supply chain, for collecting relevant enterprise data of the corresponding participating enterprise, obtaining corresponding enterprise information, and storing it in a pre-built enterprise terminal; wherein one participating enterprise corresponds to one enterprise terminal; Obtain the participating roles of each enterprise in the target supply chain, wirelessly connect the corresponding enterprise terminals, and set up the Internet cloud to monitor and manage the connected enterprise terminals to obtain the corresponding collaborative management center.

[0007] Furthermore, the process of obtaining order information and building a corresponding pre-collaborative planning scheme and collaborative supply sub-chain based on the order information includes: Obtain order information and order requirements of orders accepted by corresponding participating enterprises, and build corresponding order processing tasks based on them; The obtained order processing tasks are uploaded to the Internet cloud, and the Internet cloud decomposes and aggregates the corresponding order processing tasks to obtain a corresponding task set, wherein the task set includes an autonomous task set and a cooperative task set; and the task set is composed of a number of related but independent subtasks, and the subtasks are composed of a number of related and inseparable meta-tasks; The autonomous task set is assigned to the corresponding participating enterprises, and the enterprise terminals corresponding to the corresponding participating enterprises are marked as core terminals; and the Internet cloud performs terminal search based on the subtasks in the corresponding cooperative task set and the enterprise information stored in each enterprise terminal to obtain the corresponding matching terminal; Construct hierarchical supply chain sub-chains based on the Internet cloud, core terminals, and matching terminals; Based on the pre-built collaborative planning model, and in combination with the obtained order information, a target optimization function is constructed for the Internet cloud, core terminal, and matching terminal in the corresponding supply chain sub-chain to obtain a corresponding collaborative optimization function, which includes a cloud target optimization function, an enterprise target optimization function, and a cooperation target optimization function; Then, based on the constructed target optimization function, the corresponding cooperative task set is collaboratively optimized to obtain a corresponding pre-collaborative planning scheme; the pre-collaborative planning scheme includes a core planning scheme, a matching planning scheme and a cloud planning scheme; Furthermore, the core planning scheme and the matching planning scheme are fed back to the corresponding core terminal and matching terminal respectively, and the corresponding core terminal and matching terminal make cooperation choices between the corresponding participating enterprises. If cooperation is not chosen, the pre-collaborative planning scheme is obtained again and the corresponding matching terminal is ignored; if cooperation is chosen, the corresponding supply chain sub-chain is updated based on the marked cooperation terminal to obtain the corresponding collaborative supply sub-chain.

[0008] Furthermore, define the cloud target optimization function ; In the formula; represents the optimization goal of the cloud planning layer, represents the estimated cost of the cloud planning layer, represents the target cost of the cloud planning layer; and denote the reaction errors of the core terminal and the matching terminal respectively; in, ; In the formula, ; represents the processing cost of the matching terminal corresponding to the participating enterprise in processing the corresponding order subtask; k represents the number of the matching terminal, k=1,2,…,W, W≥3 and W is an integer, and W represents the total number of matching terminals; represents the expected unit cost of processing the corresponding order subtask based on manufacturing resources in the kth matching terminal; and They represent the expected start time and end time of the kth matching terminal processing the kth meta-task within the ith subtask; represents the fixed cost of the parameter enterprise corresponding to the kth matching terminal; i=1,2...,N, N is an integer; N represents the total number of subtasks in the partnership task set, j=1,2...,M, M is an integer, M represents the total number of meta-tasks in the subtask; ; represents the cache cost; the cache cost refers to the cost caused by a subtask not being completed on time but the subsequent subtask arriving at the expected start time; Represents the cache cost per unit time; and Represents the front-end subtask of subtask i The latest start time and the earliest start time of subtask i; D represents the total number of front-end subtasks of subtask i; ; In the formula, Indicates the task processing cost of the core terminal corresponding to the participating enterprises; Indicates the end time of the last meta-task in the last subtask in the autonomous task set; Indicates the start time of the first meta-task in the first subtask in the autonomous task set; Indicates the task processing cost per unit time of the core terminal corresponding to the participating enterprises; It represents the fixed processing costs of the core terminal corresponding to the participating enterprises; ; In the formula, It represents the penalty cost of delayed delivery of core terminals corresponding to participating enterprises; represents the pre-agreed penalty cost per unit time; Indicates the target end time set by the Internet cloud for the corresponding core terminal; It means that the core terminals are delivered on time by the participating enterprises; 1 means that the corresponding participating enterprise of the core terminal failed to deliver on time; Define the enterprise objective optimization function ; Define the cooperative objective optimization function ; It indicates the end time when all subtasks in the corresponding cooperative task set are completed; R1 indicates the expected end time; T indicates transposition.

[0009] Furthermore, the process of obtaining the pre-coordination planning solution includes: Based on the obtained collaborative optimization function, a corresponding fitness function is constructed, and a task combination scheme is randomly generated; the task combination scheme refers to a combination method in which each subtask in the corresponding cooperative task set is assigned to the corresponding matching terminal; The generated combination scheme is encoded with real numbers, and a chromosome is constructed based on it, where the chromosome consists of n×r genes, n is the number of subtasks, and r is the number of matching terminals; Obtain the corresponding chromosome length, and construct an initial population based on the obtained fitness function and the pre-set population size; Based on the fitness function, the fitness of each chromosome in the corresponding initial population is calculated to obtain the fitness value corresponding to each chromosome, and a number of chromosomes with fitness values ​​higher than a preset fitness threshold are selected from the corresponding initial population as parent chromosomes in combination with the roulette method; Then, based on the POX operator, the corresponding parent chromosome is genetically recombined to obtain the corresponding daughter chromosome; the corresponding genetic recombination process is repeated to obtain the corresponding recombinant population, wherein the recombinant population refers to the new initial population obtained after the genetic recombination; Furthermore, gene mutation operations are performed on the genes in the chromosomes in the corresponding recombinant population to obtain corresponding mutant genes, and based on them, the original genes of the original chromosomes are replaced to obtain new mutant chromosomes, which are then decoded to obtain the corresponding optimal combination scheme.

[0010] Furthermore, the process of performing gene mutation operation includes: Obtain the chromosomal genes in the corresponding chromosome, randomly select several chromosomal genes and perform mutation operations on them, and obtain the mutation values ​​corresponding to the corresponding chromosomal genes based on the pre-defined mutation function ; In the formula, Represents the mutation function value of the corresponding chromosome gene mutation operation; and Represent the left and right boundaries of the predefined variance function value respectively; are fixed constants; ; In the formula, and is an integer; t is the current number of iterations, and T represents the maximum number of iterations; Denotes the definition of the variation function, if ,but ;like ,but ; represents the remainder of a randomly generated positive integer λ divided by 2; and if the remainder is not 0, then 1; if the remainder is 0, then ; A mutation threshold is set. If the mutation value is less than the mutation threshold, no other operations are performed. If the mutation value is not less than the mutation threshold, the corresponding mutation value replaces the original mutation function value, and the corresponding chromosome gene is replaced based on it; a new mutation chromosome is obtained, and the acquisition process of the corresponding mutation chromosome is repeated until it meets the iteration stop condition to obtain the corresponding optimal chromosome; and the chromosome is decoded to obtain the corresponding optimal task combination scheme; and based on it, the matching terminals corresponding to each subtask in the corresponding cooperative task set are obtained, and they are marked as cooperative terminals; the iteration stop condition refers to reaching the maximum number of iterations, and obtaining a number of consecutive iterative training processes, and there is no gene replacement process for the corresponding chromosome gene; Furthermore, based on the fitness function value corresponding to the optimal task combination scheme, independent variables are obtained to obtain the task processing cost and task processing time corresponding to each subtask under the corresponding optimal task combination scheme; and the corresponding cloud planning scheme, core planning scheme and cooperative planning scheme are constructed based on them respectively.

[0011] Furthermore, based on executing the corresponding pre-collaborative planning scheme in the collaborative supply sub-chain, dynamically capturing the execution process of the corresponding pre-collaborative planning scheme, and performing collaborative risk monitoring based thereon includes: The core terminal and the cooperative terminal in the collaborative supply subchain respectively process the subtasks based on the received core planning scheme and cooperative planning scheme until the corresponding order is delivered; Setting a capture node, the capture node is used to collect real-time data of the corresponding subtask processing process to obtain corresponding task processing data, the task processing data includes task processing parameters and influencing factors of each subtask; wherein the influencing factors include planning coordination, inventory coordination and other factors; The obtained task processing data is input into a pre-built collaborative risk monitoring model to obtain the corresponding model output results. Based on the model output results, it is determined whether there is a collaborative risk in the processing of the corresponding subtask. If there is no collaborative risk, continuous monitoring is performed based on the corresponding collaborative risk monitoring model until the order delivery is completed. If there is a collaborative risk, the corresponding cooperative terminal or core terminal of the corresponding subtask is marked as a risk terminal, and a risk warning is issued. Then the staff of the corresponding participating enterprise at the corresponding risk terminal processes the corresponding risk warning. After the processing is completed, the Internet cloud constructs a new pre-collaborative planning scheme based on the real-time collected task processing data and combined with the collaborative planning model, and replaces the original pre-collaborative planning scheme with it.

[0012] Furthermore, the construction process of the collaborative risk monitoring model includes: The backbone network of the collaborative risk monitoring model is an improved BP neural network, and the basic framework of the improved BP neural network is an input layer, a hidden layer and an output layer; The input layer is used to receive an input vector and obtain indicator data related to supply chain collaboration risk in the corresponding input vector; The hidden layer is used to perform nonlinear processing on the indicator data passed in by the input layer to obtain the corresponding output results. The nonlinear processing refers to the feature extraction and transformation of the input data, mining the potential patterns and relationships in the data, and converting the original risk indicator data into more abstract and representative feature information. These feature information are more conducive to the output layer to judge the risk level, and play a key role in improving the prediction ability and adaptability of the model; The output layer is used to receive the output result of the hidden layer and output the collaborative risk assessment result; Defining the loss function of the collaborative risk monitoring model ; In the formula, represents the actual result of the training sample, Represents the prediction result output by the model; h and H represent the training sample index and the total number of training samples respectively; Construct a corresponding training data set based on historical task processing data, and iteratively train the corresponding collaborative risk monitoring model based on the training data set until the loss function area of ​​the model converges, save the model parameters, and the model training is completed; Among them, the training process of the corresponding collaborative risk monitoring model includes: Construct an improved BP neural network, and initialize the neuron thresholds and weights in the improved BP neural network to obtain the desired initial thresholds and initial weights; Then, the training sample is input into the collaborative risk monitoring model, and the forward propagation operation is performed in the order of input layer, hidden layer and output layer to obtain the output result of the corresponding output layer, and the error is calculated between it and the actual result corresponding to the training sample; and it is compared with the expected error. If the error calculation result is less than the expected error, the iterative training ends and the training sample is replaced; if the error calculation result is not less than the expected error; based on the error calculation result, the forward propagation path is followed to return to each hidden layer in turn for back propagation operation, and the error calculation result is apportioned to each neuron according to the initial threshold, and each neuron is threshold-corrected according to the error value, and the forward and reverse propagation operation process is repeated until the error calculation result is less than the expected error; Furthermore, the process of initializing the neuron thresholds and weights in the corresponding BP neural network includes: Constructing an initial bee colony, and performing initial parameter setting for the corresponding initial bee colony based on the number of neurons, wherein the parameters include the number of employed bees, the number of follower bees, and the number of initial solutions; Among them, the initial solution is a number randomly generated between (-1,1), and each initial solution is a D-dimensional vector; Get the fitness parameters of each initial solution in the corresponding initial bee colony ; In the formula, represents the mean square error of the improved BP neural network corresponding to the a-th initial solution; a=1,2,…,A, A is an integer, representing the total number of initial solutions; Then, the initial solution is updated based on the employed bees and the follower bees to obtain the corresponding new solution ; In the formula, represents the ath initial solution under dimension vector b; represents the g-th initial solution under dimension vector b; b=1,2,…,D; g=1,2,…,A; where g≠a; Obtain the fitness parameters of the corresponding new solution, and obtain the yield of the corresponding new solution based on the adaptive judgment factor ; New interpretation The fitness parameter of =1 or -1; if ;but ;like ;but ; MCN represents the maximum number of iterations; s represents the current number of iterations; If the rate of return and fitness parameter of the new solution are greater than the fitness value and rate of return of the initial solution, the original initial solution will be updated based on the corresponding new solution; Repeat the above process of obtaining new solutions until the preset stopping condition is met and several optimal initial solutions are obtained; and they are mapped to the neuron thresholds and weights in the corresponding improved BP neural network; the stopping condition refers to whether the number of iterations for obtaining the new solution reaches the maximum value.

[0013] An efficient supply chain collaboration platform, including: The data acquisition module is used to collect information from participating enterprises in the target supply chain, obtain corresponding enterprise information, and build a corresponding collaborative management center based on it; the collaborative management center includes enterprise terminals and the Internet cloud; Collaborative planning module: used to obtain order information and build corresponding pre-collaborative planning solutions and collaborative supply sub-chains based on the order information; A collaborative feedback module; based on executing the corresponding pre-collaborative planning scheme within the collaborative supply sub-chain, and capturing dynamic information of the execution process of the corresponding pre-collaborative planning scheme, and performing collaborative risk monitoring based on it.

[0014] Technical effects and advantages of an efficient supply chain collaboration method and platform of the present invention: 1. When building a collaborative planning solution based on order information, the Internet cloud decomposes and aggregates the order processing tasks, dividing them into autonomous task sets and cooperative task sets; the autonomous task sets are assigned to the corresponding enterprises, and the cooperative task sets find matching terminals by searching the enterprise terminals to build a hierarchical supply chain sub-chain; at the same time, the cloud, enterprise, and cooperative target optimization functions are built based on the collaborative planning model to collaboratively optimize the cooperative task sets to minimize costs and delivery time; 2. In the process of obtaining the pre-collaborative planning plan, the task combination plan is optimized through continuous iteration; when the collaborative supply sub-chain executes the pre-collaborative planning plan and there is a collaborative risk, the Internet cloud can build a new plan based on real-time data and collaborative planning model to replace the original plan, so as to ensure the continuous and efficient operation of the supply chain. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A schematic diagram of an efficient supply chain collaboration method of the present invention; Figure 2 It is a schematic diagram of an efficient supply chain collaboration platform of the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] Example 1 See also Figure 1 As shown, this embodiment provides an efficient supply chain collaboration method, including: Step 1: Collect information from participating enterprises in the target supply chain, obtain relevant enterprise information, and build a corresponding collaborative management center based on it; the collaborative management center includes enterprise terminals and the Internet cloud; Step 2: Obtain order information and build corresponding pre-collaborative planning solutions and collaborative supply sub-chains based on the order information; Step 3: Execute the corresponding pre-collaborative planning scheme based on the collaborative supply sub-chain, capture dynamic information of the execution process of the corresponding pre-collaborative planning scheme, and conduct collaborative risk monitoring based on it.

[0018] It should be further explained that, in the specific implementation process, the process of collecting information from participating enterprises in the target supply chain, obtaining corresponding enterprise information, and building a corresponding collaborative management center based on it includes: Setting up a data collection node, which is deployed in each participating enterprise in the target supply chain, for collecting relevant enterprise data of the corresponding participating enterprise, obtaining the corresponding enterprise information, and storing it in a pre-built enterprise terminal; wherein one participating enterprise corresponds to one enterprise terminal; Obtain the participating roles of each enterprise in the target supply chain, wirelessly connect the corresponding enterprise terminals, and set up the Internet cloud to monitor and manage the connected enterprise terminals to obtain the corresponding collaborative management center; It should be further explained that, during the specific implementation process, the corresponding participating enterprises can display or view the basic enterprise data of other participating enterprises in the corresponding collaborative management center based on the enterprise terminal; the basic enterprise data includes information such as enterprise background and enterprise field, so as to facilitate the corresponding participating enterprises to seek partners.

[0019] It should be further explained that, in the specific implementation process, the process of obtaining order information and building the corresponding pre-collaborative planning scheme and collaborative supply sub-chain based on the order information includes: Taking a participating enterprise as an example, obtain the order information and order requirements of the orders accepted by the corresponding participating enterprise, and build the corresponding order processing tasks based on them; the order processing tasks include product requirements, demand status, production plan, etc.; The obtained order processing tasks are uploaded to the Internet cloud, and the Internet cloud decomposes and aggregates the corresponding order processing tasks to obtain the corresponding task set, which includes an autonomous task set and a cooperative task set; and the task set is composed of a number of related but independent subtasks, and the subtasks are composed of a number of related and inseparable meta-tasks; it should be further explained that in the specific implementation process, the autonomous task set refers to the subtask set that can be completed independently by the corresponding participating enterprises, which is divided by the corresponding Internet cloud based on the enterprise information of the corresponding participating enterprises; the cooperative task set refers to the subtask set that the corresponding participating enterprises need to seek other participating enterprises to complete together; Then, the autonomous task set is allocated to the corresponding participating enterprises, and the enterprise terminals corresponding to the corresponding participating enterprises are marked as core terminals; At the same time, the Internet cloud searches for terminals based on the subtasks in the corresponding cooperative task set and in combination with the enterprise information stored in each enterprise terminal to obtain the corresponding matching terminal. The matching terminal refers to the enterprise terminal in the corresponding collaborative management center that can handle the subtasks in the cooperative task set. Among them, one subtask can correspond to several matching terminals at the same time. The specific number of corresponding matching terminals depends on actual needs. Construct hierarchical supply chain sub-chains based on the Internet cloud, core terminals, and matching terminals; the Internet cloud is the first layer, the core terminal is the second layer, and the matching terminal is the sub-layer; Then, based on the pre-built collaborative planning model and combined with the obtained order information, the target optimization function is constructed for the Internet cloud, core terminal, and matching terminal in the corresponding supply chain sub-chain to obtain the corresponding collaborative optimization function, which includes the cloud target optimization function, the enterprise target optimization function, and the cooperation target optimization function; Among them, the collaborative planning model is equipped with a cloud planning layer, a core planning layer, and a cooperative planning layer; Furthermore, the cloud planning layer is used to take the order information received by the core terminal corresponding to the participating enterprises as the basic unit, so as to minimize the cost of the cloud planning layer and minimize the error between the expected delivery date and the order demand; further, the cloud planning layer constructs the corresponding cloud objective optimization function based on the order information ; In the formula; represents the optimization goal of the cloud planning layer, represents the estimated cost of the cloud planning layer, represents the target cost of the cloud planning layer; and denote the reaction errors of the core terminal and the matching terminal respectively; in, ; In the formula, ; represents the processing cost of the matching terminal corresponding to the participating enterprise in processing the corresponding order subtask; k represents the number of the matching terminal, k=1,2,…,W, W≥3 and W is an integer, and W represents the total number of matching terminals that can meet the subtask processing requirements; represents the expected unit cost of processing the corresponding order subtask based on manufacturing resources in the kth matching terminal; and They represent the expected start time and end time of the kth matching terminal processing the kth meta-task within the ith subtask; represents the fixed cost of the parameter enterprise corresponding to the kth matching terminal; i=1,2...,N, N is an integer; N represents the total number of subtasks in the partnership task set, j=1,2...,M, M is an integer, M represents the total number of meta-tasks in the subtask; ; Represents the cache cost; the cache cost refers to the cost caused by a subtask not being completed on time but the subsequent subtasks reaching the expected start time; Represents the cache cost per unit time; and Represents the front-end subtask of subtask i The latest start time and the earliest start time of subtask i; D represents the total number of front-end subtasks of subtask i; ; In the formula, Indicates the task processing cost of the core terminal corresponding to the participating enterprises; Indicates the end time of the last meta-task in the last subtask in the autonomous task set; Indicates the start time of the first meta-task in the first subtask in the autonomous task set; Indicates the task processing cost per unit time of the core terminal corresponding to the participating enterprises; It represents the fixed processing costs of the core terminal corresponding to the participating enterprises; ; In the formula, It represents the penalty cost of delayed delivery of core terminals corresponding to participating enterprises; represents the pre-agreed penalty cost per unit time; It means that the core terminals are delivered on time by the participating enterprises; 1 means that the corresponding participating enterprise of the core terminal failed to deliver on time; Indicates the target end time set by the Internet cloud for the corresponding core terminal; The core planning layer is used to minimize the cost of participating enterprises and order delivery time of corresponding core terminals based on autonomous task sets; based on the core planning layer, the enterprise target optimization function corresponding to the corresponding core terminal is constructed. ; The cooperation planning layer is used to arrange tasks for subtasks in the corresponding partnership task set based on the searched matching terminals, and ensure timely delivery to the core terminal. The goal of this layer is to minimize the task processing cost and delivery time; then, based on the cooperation planning layer, the cooperation target optimization function corresponding to the corresponding matching terminal is constructed. ; It indicates the end time when all subtasks in the corresponding cooperative task set are completed; R1 indicates the expected end time; T indicates transposition; Then, based on the constructed target optimization function, the corresponding cooperative task set is collaboratively optimized to obtain the corresponding pre-collaborative planning scheme; the pre-collaborative planning scheme includes a core planning scheme, a matching planning scheme and a cloud planning scheme; The process of obtaining the pre-collaborative planning solution includes: Based on the obtained collaborative optimization function, a corresponding fitness function is constructed, and a task combination scheme is randomly generated; the task combination scheme refers to the combination method in which each subtask in the corresponding cooperative task set is assigned to the corresponding matching terminal; The generated combination scheme is encoded with real numbers, and a chromosome is constructed based on it, where the chromosome consists of n×r genes, n is the number of subtasks, and r is the number of matching terminals; Obtain the corresponding chromosome length, and construct an initial population based on the obtained fitness function and the pre-set population size; Based on the fitness function, the fitness of each chromosome in the corresponding initial population is calculated to obtain the fitness value corresponding to each chromosome, and a number of chromosomes with fitness values ​​higher than a preset fitness threshold are selected from the corresponding initial population as parent chromosomes in combination with the roulette method; Then, based on the POX operator, the corresponding parent chromosomes are genetically recombined to obtain the corresponding daughter chromosomes; the corresponding genetic recombination process is repeated to obtain the corresponding recombinant population, and the recombinant population refers to the new initial population obtained after genetic recombination; Then, the gene mutation operation is performed on the genes in the chromosomes in the corresponding recombinant population to obtain the corresponding mutant genes, and the original genes of the original chromosomes are replaced based on the mutant genes to obtain new mutant chromosomes, which are then subjected to chromosome decoding to obtain the corresponding optimal combination scheme; The process of performing gene mutation operation includes: Obtain the chromosomal genes in the corresponding chromosome, randomly select several chromosomal genes and perform mutation operations on them, and obtain the mutation values ​​corresponding to the corresponding chromosomal genes based on the pre-defined mutation function ; In the formula, Represents the mutation function value of the corresponding chromosome gene mutation operation; and Represent the left and right boundaries of the predefined variance function value respectively; are fixed constants; ; In the formula, and is an integer; t is the current number of iterations, and T represents the maximum number of iterations; Denotes the definition of the variation function, if ,but ;like ,but ; represents the remainder of a randomly generated positive integer λ divided by 2; and if the remainder is not 0, then 1; if the remainder is 0, then ; A mutation threshold is set. If the mutation value is less than the mutation threshold, no other operations are performed. If the mutation value is not less than the mutation threshold, the corresponding mutation value replaces the original mutation function value, and the corresponding chromosome gene is replaced based on it; a new mutant chromosome is obtained, and the acquisition process of the corresponding mutant chromosome is repeated until it meets the iteration stop condition to obtain the corresponding optimal chromosome; the chromosome is decoded to obtain the corresponding optimal task combination scheme; and the matching terminals corresponding to each subtask in the corresponding cooperative task set are obtained based on it, and they are marked as cooperative terminals; the iteration stop condition refers to reaching the maximum number of iterations, and the corresponding chromosome gene does not have a gene replacement process during the acquisition of several consecutive iterative training processes; Then, based on the fitness function value corresponding to the best task combination scheme, the independent variable is obtained to obtain the task processing cost and task processing time corresponding to each subtask under the corresponding best task combination scheme; and the corresponding cloud planning scheme, core planning scheme and cooperative planning scheme are constructed based on them respectively; Furthermore, the core planning scheme and the matching planning scheme are fed back to the corresponding core terminal and matching terminal respectively, and the corresponding core terminal and matching terminal make cooperation choices between the corresponding participating enterprises. If cooperation is not chosen, the pre-collaborative planning scheme is obtained again and the corresponding matching terminal is ignored; if cooperation is chosen, the corresponding supply chain sub-chain is updated based on the marked cooperation terminal to obtain the corresponding collaborative supply sub-chain.

[0020] It should be further explained that, in the specific implementation process, the corresponding pre-collaborative planning scheme is executed within the collaborative supply sub-chain, and the dynamic information of the execution process of the corresponding pre-collaborative planning scheme is captured, and the process of collaborative risk monitoring based on it includes: The core terminal and the cooperative terminal in the collaborative supply subchain process the subtasks based on the received core planning scheme and cooperative planning scheme respectively until the corresponding order is delivered; Set up a capture node, which is used to collect real-time data of the corresponding subtask processing process and obtain the corresponding task processing data. The task processing data includes the task processing parameters and influencing factors of each subtask; the influencing factors include planning coordination, inventory coordination and other factors; The obtained task processing data is input into the pre-built collaborative risk monitoring model to obtain the corresponding model output results. Based on the model output results, it is determined whether there is a collaborative risk in the corresponding subtask processing process. If there is no collaborative risk, continuous monitoring is performed based on the corresponding collaborative risk monitoring model until the order delivery is completed; if there is a collaborative risk, the corresponding cooperative terminal or core terminal of the corresponding subtask is marked as a risk terminal, and a risk warning is issued; then the staff of the corresponding participating enterprise of the corresponding risk terminal processes the corresponding risk warning. After the processing is completed, the Internet cloud builds a new pre-collaborative planning plan based on the real-time collected task processing data and combined with the collaborative planning model, and replaces the original pre-collaborative planning plan with it; It should be further explained that, in the specific implementation process, the construction process of the collaborative risk monitoring model includes: The backbone network of the collaborative risk monitoring model is an improved BP neural network, and the basic framework of the improved BP neural network is an input layer, a hidden layer and an output layer; The input layer is used to receive input vectors and obtain indicator data related to supply chain collaboration risks in the corresponding input vectors; The hidden layer is used to perform nonlinear processing on the indicator data passed in by the input layer to obtain the corresponding output results. Nonlinear processing refers to the feature extraction and transformation of the input data, mining the potential patterns and relationships in the data, and converting the original risk indicator data into more abstract and representative feature information. These feature information is more conducive to the output layer to judge the risk level, and plays a key role in improving the prediction ability and adaptability of the model. The output layer is used to receive the output results of the hidden layer and to coordinate risk assessment results based on the output; Defining the loss function of the collaborative risk monitoring model ; In the formula, represents the actual result of the training sample, Represents the prediction result output by the model; h and H represent the training sample index and the total number of training samples respectively; Construct a corresponding training data set based on historical task processing data, and iteratively train the corresponding collaborative risk monitoring model based on the training data set until the loss function area of ​​the model converges and the model parameters are saved, that is, the model training is completed; Among them, the training process of the corresponding collaborative risk monitoring model includes: Construct an improved BP neural network, and initialize the neuron thresholds and weights in the improved BP neural network to obtain the desired initial thresholds and initial weights; Then, the training sample is input into the collaborative risk monitoring model, and the forward propagation operation is performed in the order of input layer, hidden layer and output layer to obtain the output result of the corresponding output layer, and the error is calculated between it and the actual result corresponding to the training sample; and it is compared with the expected error. If the error calculation result is less than the expected error, the iterative training ends and the training sample is replaced; if the error calculation result is not less than the expected error; based on the error calculation result, the forward propagation path is followed to return to each hidden layer in turn for back propagation operation, and the error calculation result is apportioned to each neuron according to the initial threshold, and each neuron is threshold-corrected according to the error value, and the forward and reverse propagation operation process is repeated until the error calculation result is less than the expected error; It should be further explained that, in the specific implementation process, the process of initializing the neuron threshold and weight in the corresponding BP neural network includes: Construct an initial bee colony and set the parameters of the corresponding initial bee colony based on the number of neurons. The parameters include the number of employed bees, the number of follower bees and the number of initial solutions. Among them, the initial solution is a number randomly generated between (-1,1), and each initial solution is a D-dimensional vector; Get the fitness parameters of each initial solution in the corresponding initial bee colony ; In the formula, represents the mean square error of the improved BP neural network corresponding to the a-th initial solution; a=1,2,…,A, A is an integer, representing the total number of initial solutions; Then, the initial solution is updated based on the employed bees and the follower bees to obtain the corresponding new solution ; In the formula, represents the ath initial solution under dimension vector b; represents the g-th initial solution under dimension vector b; b=1,2,…,D; g=1,2,…,A; where g≠a; Obtain the fitness parameters of the corresponding new solution, and obtain the yield of the corresponding new solution based on the adaptive judgment factor ; New interpretation The fitness parameter of =1 or -1; if ;but ;like ;but ; MCN represents the maximum number of iterations; s represents the current number of iterations; If the rate of return and fitness parameter of the new solution are greater than the fitness value and rate of return of the initial solution, the original initial solution will be updated based on the corresponding new solution; Repeat the above process of obtaining new solutions until the preset stopping conditions are met and several optimal initial solutions are obtained; and they are mapped to the neuron thresholds and weights in the corresponding improved BP neural network; the stopping condition refers to whether the number of iterations for obtaining the new solution reaches the maximum value.

[0021] By building a collaborative management center, generating collaborative planning plans, executing pre-collaborative planning plans and monitoring risks, efficient collaboration among supply chain enterprises can be achieved; and there will be significant improvements in beneficial effects such as information sharing and cooperation convenience, optimization of task allocation and cost control, and risk monitoring and timely response.

[0022] Example 2 See also Figure 2 As shown, the part not described in detail in this embodiment is described in Example 1, which provides an efficient supply chain collaboration platform, including: The data acquisition module is used to collect information from participating enterprises in the target supply chain, obtain corresponding enterprise information, and build a corresponding collaborative management center based on it; the collaborative management center includes enterprise terminals and the Internet cloud; Collaborative planning module: used to obtain order information and build corresponding pre-collaborative planning solutions and collaborative supply sub-chains based on the order information; Collaborative feedback module: executes the corresponding pre-collaborative planning scheme within the collaborative supply sub-chain, captures dynamic information of the execution process of the corresponding pre-collaborative planning scheme, and monitors collaborative risks based on it; The modules are connected to each other via wired and / or wireless means to achieve data transmission between modules.

[0023] Example 3 This embodiment discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the operation mode of an efficient supply chain collaboration method and platform provided above is implemented.

[0024] Since the electronic device introduced in this embodiment is an electronic device used to implement an efficient supply chain collaboration method and platform in the embodiment of this application, based on the efficient supply chain collaboration method and platform introduced in the embodiment of this application, the technical personnel of this field can understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of this application is not described in detail here. As long as the technical personnel of this field implement the electronic device used in the efficient supply chain collaboration method and platform in the embodiment of this application, it belongs to the scope of protection of this application.

[0025] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0026] The above are only preferred embodiments of the present invention. The protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technical users in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. An efficient supply chain collaboration method, characterized in that: include: Step 1: Collect information from participating companies in the target supply chain, obtain relevant company information, and build a corresponding collaborative management center based on it; The collaborative management center includes enterprise terminals and the Internet cloud; Step 2: Obtain order information and build corresponding pre-collaborative planning solutions and collaborative supply sub-chains based on the order information; Step three: Execute the corresponding pre-collaborative planning scheme within the collaborative supply sub-chain, capture dynamic information of the execution process of the corresponding pre-collaborative planning scheme, and conduct collaborative risk monitoring based on it.

2. The efficient supply chain collaboration method according to claim 1, characterized in that: The process of collecting information from participating enterprises in the target supply chain, obtaining corresponding enterprise information, and building a corresponding collaborative management center based on it includes: Setting a data collection node, which is deployed in each participating enterprise in the target supply chain, for collecting relevant enterprise data of the corresponding participating enterprise, obtaining corresponding enterprise information, and storing it in a pre-built enterprise terminal; Obtain the participating roles of each enterprise in the target supply chain, wirelessly connect the corresponding enterprise terminals, and set up the Internet cloud to monitor and manage the connected enterprise terminals to obtain the corresponding collaborative management center.

3. The efficient supply chain collaboration method according to claim 2, characterized in that: The process of obtaining order information and building corresponding pre-collaborative planning solutions and collaborative supply sub-chains based on the order information includes: Obtain order information and order requirements of orders accepted by corresponding participating enterprises, and build corresponding order processing tasks based on them; The obtained order processing tasks are uploaded to the Internet cloud, and the Internet cloud decomposes and aggregates the corresponding order processing tasks to obtain a corresponding task set, wherein the task set includes an autonomous task set and a cooperative task set; and the task set is composed of a number of related but independent subtasks, and the subtasks are composed of a number of related and inseparable meta-tasks; The autonomous task set is assigned to the corresponding participating enterprises, and the enterprise terminals corresponding to the corresponding participating enterprises are marked as core terminals; and the Internet cloud performs terminal search based on the subtasks in the corresponding cooperative task set and the enterprise information stored in each enterprise terminal to obtain the corresponding matching terminal; Construct hierarchical supply chain sub-chains based on the Internet cloud, core terminals, and matching terminals; Based on the pre-built collaborative planning model, and in combination with the obtained order information, a target optimization function is constructed for the Internet cloud, core terminal, and matching terminal in the corresponding supply chain sub-chain to obtain a corresponding collaborative optimization function, which includes a cloud target optimization function, an enterprise target optimization function, and a cooperation target optimization function; Based on the constructed collaborative optimization function, the corresponding cooperative task set is collaboratively optimized to obtain a corresponding pre-collaborative planning scheme; the pre-collaborative planning scheme includes a core planning scheme, a matching planning scheme and a cloud planning scheme; The core planning scheme and matching planning scheme are fed back to the corresponding core terminal and matching terminal respectively, and the corresponding core terminal and matching terminal make cooperation choices between the corresponding participating enterprises. If cooperation is not chosen, the pre-collaborative planning scheme is obtained again and the corresponding matching terminal is ignored; if cooperation is chosen, the corresponding supply chain sub-chain is updated based on the marked cooperation terminal to obtain the corresponding collaborative supply sub-chain.

4. The efficient supply chain collaboration method according to claim 3, characterized in that: Define the cloud-based target optimization function ; In the formula; represents the optimization goal of the cloud planning layer, represents the estimated cost of the cloud planning layer, represents the target cost of the cloud planning layer; and denote the reaction errors of the core terminal and the matching terminal respectively; in, ; In the formula, ; It indicates the processing cost of the matching terminal corresponding to the participating enterprise in processing the corresponding order subtask; Indicates the number of the matching terminal. and is an integer, Indicates the total number of matching terminals; Indicates The expected unit cost of processing the corresponding order subtask based on manufacturing resources in a matching terminal; and Respectively represent A matching terminal handles Within each subtask The expected start and end times of each meta-task; represents the fixed cost of the parameter enterprise corresponding to the kth matching terminal; is an integer; Represents the total number of subtasks in the partner task set, , is an integer, Represents the total number of meta-tasks within a subtask; ; represents the cache cost; Represents the cache cost per unit time; and Represents a subtask Front-end subtasks The latest start time and the earliest start time of subtask i; D represents the total number of front-end subtasks of subtask i; ; In the formula, Indicates the task processing cost of the core terminal corresponding to the participating enterprises; Indicates the end time of the last meta-task in the last subtask in the autonomous task set; Indicates the start time of the first meta-task in the first subtask in the autonomous task set; Indicates the task processing cost per unit time of the core terminal corresponding to the participating enterprises; It represents the fixed processing costs of the core terminal corresponding to the participating enterprises; ; In the formula, It represents the penalty cost of delayed delivery of core terminals corresponding to participating enterprises; represents the pre-agreed penalty cost per unit time; Indicates the target end time set by the Internet cloud for the corresponding core terminal; It means that the core terminals are delivered on time by the participating enterprises; 1 means that the corresponding participating enterprise of the core terminal failed to deliver on time; Define the enterprise objective optimization function ; Define the cooperative objective optimization function ; Indicates the end time when all subtasks in the corresponding cooperative task set are completed; Indicates the expected end time; Indicates transpose.

5. The efficient supply chain collaboration method according to claim 3, characterized in that: The process of obtaining a pre-collaborative planning solution includes: Based on the obtained collaborative optimization function, a corresponding fitness function is constructed, and a task combination scheme is randomly generated; The generated combination scheme is encoded with real numbers and a chromosome is constructed based on it, where the chromosome is composed of Gene composition, is the number of subtasks, is the number of matching terminals; Obtain the corresponding chromosome length, and construct an initial population based on the obtained fitness function and the pre-set population size; Based on the fitness function, the fitness of each chromosome in the corresponding initial population is calculated to obtain the fitness value corresponding to each chromosome, and a number of chromosomes with fitness values ​​higher than a preset fitness threshold are selected from the corresponding initial population as parent chromosomes in combination with the roulette method; Then, based on the POX operator, the corresponding parent chromosome is genetically recombined to obtain the corresponding daughter chromosome; the corresponding genetic recombination process is repeated to obtain the corresponding recombinant population, wherein the recombinant population refers to the new initial population obtained after genetic recombination; Furthermore, gene mutation operations are performed on the genes in the chromosomes in the corresponding recombinant population to obtain corresponding mutant genes, and based on them, the original genes of the original chromosomes are replaced to obtain new mutant chromosomes, which are then decoded to obtain the corresponding optimal combination scheme.

6. The efficient supply chain collaboration method according to claim 5, characterized in that: The process of performing gene mutation manipulation includes: Obtain the chromosomal genes in the corresponding chromosome, randomly select several chromosomal genes and perform mutation operations on them, and obtain the mutation values ​​corresponding to the corresponding chromosomal genes based on the pre-defined mutation function ; In the formula, Represents the mutation function value of the corresponding chromosome gene mutation operation; and Represent the left and right boundaries of the predefined variance function value respectively; are fixed constants; ; In the formula, and is an integer; t is the current number of iterations, and T represents the maximum number of iterations; Denotes the definition of the variation function, if ,but ;like ,but ; represents the remainder of a randomly generated positive integer λ divided by 2; and if the remainder is not 0, then 1; if the remainder is 0, then ; Set a mutation threshold, continue to compare the mutation value with the corresponding mutation threshold, and perform gene replacement based on the comparison result; obtain a new mutant chromosome, repeat the process of obtaining the corresponding mutant chromosome until it meets the iteration stop condition, and obtain the corresponding optimal chromosome; and decode the chromosome to obtain the corresponding optimal task combination solution; and based on it, obtain the matching terminals corresponding to each subtask in the corresponding cooperative task set, and mark them as cooperative terminals; Based on the fitness function value corresponding to the optimal task combination scheme, independent variables are obtained to obtain the task processing cost and task processing time corresponding to each subtask under the corresponding optimal task combination scheme; and corresponding cloud planning schemes, core planning schemes and cooperative planning schemes are constructed based thereon respectively.

7. The efficient supply chain collaboration method according to claim 1, characterized in that: The process of executing the corresponding pre-collaborative planning scheme based on the collaborative supply sub-chain, capturing dynamic information of the execution process of the corresponding pre-collaborative planning scheme, and performing collaborative risk monitoring based on the scheme includes: The core terminal and the cooperative terminal in the collaborative supply subchain respectively process the subtasks based on the received core planning scheme and cooperative planning scheme until the corresponding order is delivered; Setting a capture node, the capture node is used to collect real-time data of the corresponding subtask processing process to obtain corresponding task processing data, the task processing data includes task processing parameters and influencing factors of each subtask; The obtained task processing data is input into a pre-built collaborative risk monitoring model to obtain the corresponding model output results. Based on the model output results, it is determined whether there is a collaborative risk in the processing of the corresponding subtask. If there is no collaborative risk, continuous monitoring is performed based on the corresponding collaborative risk monitoring model until the order delivery is completed. If there is a collaborative risk, the corresponding cooperative terminal or core terminal of the corresponding subtask is marked as a risk terminal, and a risk warning is issued. Then the staff of the corresponding participating enterprise at the corresponding risk terminal processes the corresponding risk warning. After the processing is completed, the Internet cloud constructs a new pre-collaborative planning scheme based on the real-time collected task processing data and combined with the collaborative planning model, and replaces the original pre-collaborative planning scheme with it.

8. The efficient supply chain collaboration method according to claim 7, characterized in that: The construction process of the collaborative risk monitoring model includes: The backbone network of the collaborative risk monitoring model is an improved BP neural network, and the basic framework of the improved BP neural network is an input layer, a hidden layer and an output layer; The input layer is used to receive an input vector and obtain indicator data related to supply chain collaboration risk in the corresponding input vector; The hidden layer is used to perform nonlinear processing on the index data transmitted from the input layer to obtain the corresponding output result; The output layer is used to receive the output result of the hidden layer and output the collaborative risk assessment result; Defining the loss function of the collaborative risk monitoring model ; In the formula, represents the actual result of the training sample, Represents the prediction result output by the model; h and H represent the training sample index and the total number of training samples respectively; Construct a corresponding training data set based on historical task processing data, and iteratively train the corresponding collaborative risk monitoring model based on the training data set until the loss function area of ​​the model converges, save the model parameters, and the model training is completed; Among them, the training process of the corresponding collaborative risk monitoring model includes: Construct an improved BP neural network, and initialize the neuron thresholds and weights in the improved BP neural network to obtain the desired initial thresholds and initial weights; Then, the training samples are input into the collaborative risk monitoring model, and the forward propagation operation is performed in the order of input layer, hidden layer and output layer to obtain the output result of the corresponding output layer, and the error is calculated between it and the actual result corresponding to the training sample; and it is compared with the expected error. If the error calculation result is less than the expected error, the iterative training ends and the training sample is replaced; if the error calculation result is not less than the expected error; based on the error calculation result, the forward propagation path is followed to return to each hidden layer for back propagation operation, and the error calculation result is distributed to each neuron according to the initial threshold, and each neuron is threshold-corrected according to the error value, and the forward and reverse propagation operation process is repeated until the error calculation result is less than the expected error.

9. The efficient supply chain collaboration method according to claim 1, characterized in that: The process of initializing the neuron thresholds and weights in the corresponding BP neural network includes: Constructing an initial bee colony, and performing initial parameter setting for the corresponding initial bee colony based on the number of neurons, wherein the parameters include the number of employed bees, the number of follower bees, and the number of initial solutions; Among them, the initial solution is a number randomly generated between (-1,1), and each initial solution is a D-dimensional vector; Get the fitness parameters of each initial solution in the corresponding initial bee colony ; In the formula, represents the mean square error of the improved BP neural network corresponding to the a-th initial solution; a=1,2,…,A, A is an integer, representing the total number of initial solutions; Then, the initial solution is updated based on the employed bees and the follower bees to obtain the corresponding new solution ; In the formula, represents the ath initial solution under dimension vector b; represents the g-th initial solution under dimension vector b; b=1,2,…,D; g=1,2,…,A; where g≠a; Obtain the fitness parameters of the corresponding new solution, and obtain the yield of the corresponding new solution based on the adaptive judgment factor ; New interpretation The fitness parameter of =1 or -1; if ;but ;like ;but ; MCN represents the maximum number of iterations; s represents the current number of iterations; If the rate of return and fitness parameter of the new solution are greater than the fitness value and rate of return of the initial solution, the original initial solution will be updated based on the corresponding new solution; Repeat the above process of obtaining new solutions until the preset stopping condition is met and several optimal initial solutions are obtained; and they are mapped to the neuron thresholds and weights in the corresponding improved BP neural network; the stopping condition refers to whether the number of iterations for obtaining the new solution reaches the maximum value.

10. An efficient supply chain collaboration platform, used to implement the efficient supply chain collaboration method according to any one of claims 1 to 9, characterized in that: include: The data acquisition module is used to collect information from participating enterprises in the target supply chain, obtain corresponding enterprise information, and build a corresponding collaborative management center based on it; the collaborative management center includes enterprise terminals and the Internet cloud; Collaborative planning module: used to obtain order information and build corresponding pre-collaborative planning solutions and collaborative supply sub-chains based on the order information; A collaborative feedback module; based on executing the corresponding pre-collaborative planning scheme within the collaborative supply sub-chain, and capturing dynamic information of the execution process of the corresponding pre-collaborative planning scheme, and performing collaborative risk monitoring based on it.

Images