A method for optimizing the combination of collaborative sensing services for production factors under the Industrial Internet

Abstract

This invention relates to a method for optimizing the collaborative sensing service combination of production factors under the Industrial Internet, comprising: acquiring the production process involved in user needs, and decomposing the production process into multiple sub-tasks; calculating the internal and external collaboration coefficients of the tasks and the current collaboration relationship based on historical and current collaboration relationships, and acquiring the time consumption and cost consumption of the sub-tasks; aggregating the time consumption and cost consumption, and using a teaching optimization model to iteratively analyze and derive the optimal service combination scheme. This invention introduces historical and current collaboration relationships, combining the internal and external collaboration coefficients of production factor services to comprehensively evaluate the collaborative effectiveness of services. Simultaneously, it combines the collaboration effectiveness index with a multi-objective optimization model based on the Teaching Optimization Algorithm (TLBO) to screen the optimal service combination.

Description

Technical Field

[0001] This invention relates to the field of industrial internet technology, and in particular to a method for optimizing the combination of collaborative sensing services for production factors under the industrial internet. Background Technology

[0002] With the development of new-generation information technologies such as cloud computing, big data, and artificial intelligence, the real economy and the virtual economy are increasingly intertwined, gradually changing the development concepts, production tools, and production methods of various industries, leading to another leap in productivity. The Industrial Internet has emerged in response, integrating information technology, communication technology, and operational technology. It aims to connect people, data, and machines through an open, global communication network platform, sharing various production factors and resources throughout the entire industrial production process. This enables the digitalization, networking, automation, and intelligentization of production, thereby improving efficiency and reducing costs in industrial production. The parts, personnel, equipment, and vehicles required in the production process are the industrial production factors and resources that the business process focuses on.

[0003] Simultaneously, numerous industrial internet platforms have emerged, such as GE Predix, ABB Capability, Siemens MindSphere, and PTC ThingWorx. These platforms enable the packaging and distribution of various production factor resources required for production into services, facilitating sharing, collaboration, and combination. In this context, manufacturing enterprises or users may not possess certain industrial production factors and resources, but instead complete more personalized and complex production tasks through service invocation. This allows manufacturing enterprises or users to utilize various industrial manufacturing services as conveniently as water, electricity, and gas. In this scenario, different production factor resources can be considered services, termed production factor services. Similarly, the combination of services is called a production factor service combination.

[0004] In the industrial internet environment, a complex production task may consist of multiple sub-tasks, and completing a single sub-task may require various production factor resource services. Furthermore, production factor resource services have spatiotemporal attributes. Traditional production factor management primarily focuses on the static management of production factors or resources, paying less attention to the dynamic physical environment during the scheduling of production factors and resources, such as the geographical location of resources and the timeliness of production task completion. Therefore, compared to traditional service combinations in the industrial internet environment, service combinations in actual industrial applications are more complex and challenging.

[0005] Currently, there is a lack of research on optimizing the combination of production factor services. Furthermore, most existing studies do not consider collaboration between production factor services, focusing only on service costs and service time, and then employing multi-objective optimization algorithms to obtain the optimal solution for the combination of production factor services. Undoubtedly, collaboration between production factor services affects the overall service quality. Higher levels of collaboration between production factor services lead to smoother business processes, reduced communication costs, and effectively prevent delays.

[0006] With the development of the Industrial Internet and its platforms, optimizing the combination of production factor services has become an urgent problem. Simultaneously, quantifying the degree of collaboration among production factor services and incorporating it into the calculation of the final service quality of the production factor service combination is also a question worth considering. Researching the impact of collaboration on the production process and service quality is of great significance for optimizing the combination of production factor services. Summary of the Invention

[0007] To address the problems existing in the prior art, the purpose of this invention is to provide a method for optimizing the collaborative sensing service combination of production factors under the Industrial Internet, thereby improving the performance of the service combination.

[0008] To achieve the above objectives, the present invention provides the following solution:

[0009] A method for optimizing the collaborative sensing service combination of production factors under the Industrial Internet includes:

[0010] Obtain the production process involved in user requirements, and decompose the production process into multiple sub-tasks;

[0011] Based on historical and current collaboration relationships, calculate the internal and external collaboration coefficients of the task and the current collaboration relationship to obtain the time and cost consumption of the subtask.

[0012] The time consumption and cost consumption are aggregated, and the optimal service combination scheme is determined by iterative analysis using a teaching optimization model.

[0013] Optionally, calculating the internal and external collaboration coefficients of the task includes:

[0014] Obtain the internal collaboration coefficient by utilizing the average collaboration frequency between services within the task:

[0015]

[0016] Among them, IC(t) k ) represents the degree of collaboration within the task, freq(s) i ,s j ) for s i and sj In task t k The frequency of historical calls in the data. For from |S k The number of combinations of choosing two services from a set of services, s i and s j These are two different tasks t k and t j Candidate services, s p For candidate service set One of the candidate services, s q For candidate service set One of the candidate services;

[0017] The average collaboration frequency between services across tasks is used to obtain the external collaboration coefficient.

[0018]

[0019] Among them, EC(t) k ) represents the degree of external collaboration for the task, t j and t k For the mission, To directly follow in task t k The number of tasks after |S k |To complete the task t k The required number of services, |S j |To complete the task t j The required number of services, freq(s) i ,s j ) for s i and s j The number of historical calls, For service s i The corresponding set of candidate services For service s j The corresponding set of candidate services.

[0020] Optionally, calculating the current collaboration relationship includes:

[0021] The current collaboration coefficient is determined based on the number of services from the same service provider in the current service portfolio:

[0022]

[0023] Among them, P i For service providers, PC(P) i ) for service provider P i The corresponding current collaboration parameter, d max And α are adjustment parameters, 1-d max Num(P) represents the minimum allowed discount.i ) is the service provider P in the current service portfolio i The number of services selected.

[0024] Optionally, the cost of acquiring the subtask includes:

[0025]

[0026] Among them, Cost(t) k To complete task t after considering the collaborative effectiveness of the current service. k The required cost, cost(s) i (This refers to the initial services that do not consider current collaboration.) i Cost consumption, S k To complete the task t k The required number of candidate services For service s i The provider For service providers The corresponding current collaboration parameters.

[0027] Optionally, aggregating the time consumption and the cost consumption includes:

[0028] Based on the execution structure of the subtask, perform QoS aggregation on the time consumption and cost consumption to obtain the comprehensive QoS value of the combined service:

[0029]

[0030] Where F(sc) is the overall QoS value of the combined services, and sc is a service combination scheme. and These represent the maximum and minimum times required for all service combination options. and These represent the highest and lowest costs required among all service combination schemes, respectively, and γ is the weight parameter in F(sc) used to determine the weights of different QoS attributes.

[0031] Optionally, the execution structure includes: sequential time and cost, parallel time and cost, selected time and cost, and loop time and cost.

[0032] Optionally, the optimal service combination scheme can be determined through iterative analysis using a teaching optimization algorithm, including:

[0033] Based on the aggregation results, an objective function for service composition optimization is established, and the optimal service composition scheme is obtained through iterative analysis using a teaching optimization model.

[0034] Optionally, the objective function for optimizing the service composition includes:

[0035] F = min(Time(sc), Cost(sc))

[0036]

[0037] Where Cost(sc) is the cost of service composition based on collaboration awareness, Time(sc) is the time consumption of service composition, t0 is the maximum time limit of the task, c0 is the maximum cost limit of the task, and F is the objective function used to quantify the merits of service composition schemes.

[0038] Optionally, the optimal service combination scheme can be determined through iterative analysis using a teaching optimization model, including:

[0039] Step 1: Generate an initial service composition scheme for each subtask and calculate the initial objective function value;

[0040] Step 2: Treat the service composition scheme as a student, and use the teacher module based on the teaching optimization model to iteratively update each student and calculate the objective function value of the updated service composition scheme.

[0041] The expression for iteratively updating each student using the teacher module is as follows:

[0042]

[0043] difference = r i *(X teacer -TF i *Mean)

[0044] in, and Let r represent the pre-learning value and post-learning value of the i-th student under the teacher's guidance, respectively. i Let TF be the learning step size of the i-th student. i X is the learning factor, Mean is the average of all students, and X is the learning factor. teacer The individual with the best fitness value in the current population;

[0045] Step 3: If the objective function value of the updated service composition scheme is better, then accept the update; otherwise, retain the original value.

[0046] Step 4: Based on the teaching optimization model, the student module randomly selects students to communicate and updates the model, and calculates the updated objective function value for each student.

[0047] The expression for randomly selecting students for interaction using the student module and then updating the data is as follows:

[0048]

[0049] in, and Let r be the pre-learning value and post-learning value of the i-th student under the teacher's guidance. i Let X be the learning step size of the i-th student. i and X j F(X) represents the i-th and j-th students respectively. i ) and F(X j ) represent the fitness values ​​of the i-th and j-th students, respectively;

[0050] Step 5: If the updated student's objective function value is better, then accept the update; otherwise, retain the original value.

[0051] Step 6: Repeat steps 2-5 according to the set number of iterations or convergence conditions. In each iteration, record the current optimal service combination scheme and its objective function value. When the number of iterations is reached or the convergence condition is met, output the optimal service combination scheme.

[0052] The beneficial effects of this invention are as follows:

[0053] This invention comprehensively evaluates the collaborative effectiveness of production factor services by incorporating historical and current collaborative relationships and combining internal and external collaborative coefficients. Simultaneously, it integrates collaborative effectiveness indicators with a multi-objective optimization model based on the Teaching-Based Optimization (TLBO) algorithm to select the optimal service combination.

[0054] This invention offers significant improvements in time and cost optimization compared to traditional metaheuristic algorithms (such as genetic algorithms and particle swarm optimization), and its overall QoS metrics perform better in the optimized service portfolio plan. Attached Figure Description

[0055] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0056] Figure 1 This is a flowchart of a method for optimizing the collaborative sensing service combination of production factors under the Industrial Internet, according to an embodiment of the present invention.

[0057] Figure 2 This is a sample diagram of the ship production process according to an embodiment of the present invention;

[0058] Figure 3This is a comparison chart of the evolution curves of different methods in embodiments of the present invention. Detailed Implementation

[0059] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0060] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0061] like Figure 1 As shown in the figure, this embodiment discloses a method for optimizing the collaborative perception service combination of production factors under the Industrial Internet, including: obtaining the production process involved in user needs and decomposing the production process into multiple sub-tasks; calculating the internal and external collaboration coefficients of the task and the current collaboration relationship based on historical collaboration relationships and current collaboration relationships, and obtaining the time consumption and cost consumption of the sub-tasks; aggregating the time consumption and cost consumption, and using a teaching optimization model to iteratively analyze the optimal service combination scheme.

[0062] Specifically, this embodiment discloses a method for optimizing the collaborative sensing service combination of production factors under the Industrial Internet, including the following steps:

[0063] (1) Task decomposition: Decompose the production process involved in user needs into multiple sub-tasks, each of which requires one or more types of production factor services; (2) QoS attribute definition: Define the QoS attributes of production factor services, including time consumption and cost consumption; (3) Time consumption calculation: Considering historical collaboration relationships, calculate the internal and external collaboration coefficients of the task, and calculate the time consumption of the task; (4) Cost consumption calculation: Considering the current collaboration relationships, calculate the current collaboration coefficient, and calculate the cost consumption of the task; (5) QoS aggregation: Consider the QoS aggregation module, aggregate the time consumption and cost consumption of the task to obtain the comprehensive QoS value of the task; (6) Service composition optimization: Use the Teaching Optimization Algorithm (TLBO) to derive the optimal service composition scheme. Use the Teaching Optimization Algorithm (TLBO) to achieve global optimization of the service composition scheme.

[0064] Furthermore, in step (1), the tasks published by enterprises or users on the industrial internet platform are decomposed. The production process can be decomposed into a three-dimensional P, including a set of tasks, a set of execution relationships between tasks, and a set of production factor services that tasks can use.

[0065] Furthermore, in step (2), the QoS attributes of production factor services are defined, including time consumption and cost consumption. This invention considers three service types: human resources, material resources, and machine resources. Time and cost are considered as QoS attributes in this invention. It should be noted that different types of services have different QoS attributes. The QoS attribute of human resources only considers usage cost; the QoS attribute of material resources considers usage cost, delivery cost, and delivery time; the QoS attribute of machine resources includes usage cost, delivery cost, delivery time, and execution time.

[0066] Furthermore, the internal and external collaboration coefficients of the calculation task include:

[0067] Obtain the internal collaboration coefficient by utilizing the average collaboration frequency between services within the task:

[0068]

[0069] Among them, IC(t) k ) represents the degree of collaboration within the task, freq(s) i ,s j ) for s i and s j In task t k The frequency of historical calls in the data. For from |S k The number of combinations of choosing two services from a set of services, s i and s j These are two different tasks t k and t j Candidate services, s p For candidate service set One of the candidate services, s q For candidate service set One of the candidate services;

[0070] The average collaboration frequency between services across tasks is used to obtain the external collaboration coefficient.

[0071]

[0072] Among them, EC(t) k ) represents the degree of external collaboration for the task, t j and t k For the mission, To directly follow in task t k The number of tasks after |S k |To complete the task t k The required number of services, |S j |To complete the task t j The required number of services, freq(s)i ,s j ) for s i and s j The number of historical calls, For service s i The corresponding set of candidate services For service s j The corresponding set of candidate services.

[0073] Specifically, historical collaboration relationships include internal task collaboration and external task collaboration. The internal collaboration coefficient is obtained by calculating the average collaboration frequency between services within a task, and the external collaboration coefficient is obtained by calculating the average collaboration frequency between services between tasks.

[0074] The formula for calculating the degree of collaboration within a task includes:

[0075]

[0076] Among them, t k It is a subtask, freq(s) i ,s j ) is s i and s j In task t k The frequency of historical calls in the data is only s i and s j s is only called when they are called simultaneously. i and s j There is historical cooperation. From |S k The number of combinations of choosing two services from a given set of services.

[0077] The formula for calculating the degree of external collaboration for a task includes:

[0078]

[0079] Among them, task t j In task t k Execute upon completion, i.e., task t j The beginning depends on task t k The completion of. To directly follow in task t k The number of tasks after that, s i and s j These are two different tasks t k and t j Candidate services, |S k |To complete the task t k The required number of services, |S j |To complete the task t j The required number of services, freq(s)i ,s j ) for s i and s j The number of historical calls. For service s i The corresponding set of candidate services For service s j The corresponding set of candidate services.

[0080] Furthermore, calculating the current collaboration relationship includes:

[0081] The current collaboration coefficient is determined based on the number of services from the same service provider in the current service portfolio:

[0082]

[0083] Among them, P i For service providers, PC(P) i ) for service provider P i The corresponding current collaboration parameter, d max And α are adjustment parameters, 1-d max Num(P) represents the minimum allowed discount. i ) is the service provider P in the current service portfolio i The number of services selected.

[0084] Specifically, the current collaboration relationship is determined by calculating the number of services from the same service provider in the current service portfolio to determine the current collaboration coefficient.

[0085] The specific formula for calculating the cooperation coefficient includes:

[0086]

[0087] Among them, P i For service providers, PC(P) i ) for service provider P i The corresponding current collaboration parameter, its range is PC(P) i )∈(d max -0.5,d max ], and d max α and are adjustment parameters, with ranges of d and d respectively. max ∈[0.5,1], α∈(0,1], so 1-d max This represents the lowest allowed discount. Num(P) i ) is the service provider P in the current service portfolio i The number of services selected.

[0088] Furthermore, the cost of acquiring subtasks includes:

[0089]

[0090] Among them, Cost(t) k To complete task t after considering the collaborative effectiveness of the current service. k The required cost, cost(s) i (This refers to the initial services that do not consider current collaboration.) i Cost consumption, S k To complete the task t k The required number of candidate services For service s i The provider For service providers The corresponding current collaboration parameters.

[0091] Specifically, current collaboration further reduces service costs by optimizing resource allocation and scheduling, thereby decreasing the overall cost of the task. The specific formula for calculating cost consumption includes:

[0092]

[0093] Among them, Cost(t) k The task t is completed after considering the collaborative effectiveness of the current service. k The required cost, cost(s) i () is the initial service that does not consider the current collaboration. i Cost consumption, S k To complete the task t k The required number of candidate services For service s i The provider For service providers The corresponding current collaboration parameters. Therefore, considering the current collaboration between services can further reduce cost consumption in the production process.

[0094] Furthermore, the aggregation of time consumption and cost consumption includes:

[0095] Based on the execution structure of the subtasks, perform QoS aggregation on time and cost consumption to obtain the comprehensive QoS value of the combined service:

[0096]

[0097] Where F(sc) is the overall QoS value of the combined services, and sc is a service combination scheme. and These represent the maximum and minimum times required for all service combination options. and These represent the highest and lowest costs required among all service combination schemes, respectively, and γ is the weight parameter in F(sc) used to determine the weights of different QoS attributes.

[0098] Furthermore, the execution structure includes: sequential time and cost, parallel time and cost, selected time and cost, and loop time and cost. Sequential means that tasks are executed in a predetermined order, and the next task only begins after the previous task is completed. Parallel means that multiple tasks are executed simultaneously and independently of each other without waiting for other tasks to complete. Conditional means that a task is executed based on a specific condition. Loop means that a task is executed repeatedly as long as the condition is met, until the condition is no longer met.

[0099] Specifically, the QoS aggregation module is also used to perform QoS aggregation operations based on the execution structure of the tasks (sequential, parallel, conditional, or cyclic) to obtain a comprehensive QoS value for the combined services. Here, sequential means that tasks are executed in a predetermined order, with the next task starting only after the previous one is completed; parallel means that multiple tasks are executed simultaneously and independently of each other, without waiting for other tasks to complete; conditional means that a task is executed based on a specific condition; and cyclic means that a task is repeatedly executed as long as the condition is met, until the condition is no longer met.

[0100] As shown in Table 1, the specific formulas or rules for aggregation methods include:

[0101] Table 1

[0102]

[0103] Among them, t i It is the i-th task in the production process, Cost(t) i ) is the call to t i The cost of the required services, while Time(t) i ) is the call to t i The time consumption of the required service, N s N refers to the number of tasks in a sequential structure. p N is the number of branches in a parallel structure. c p is the number of branches in the selection structure. i That is the probability of triggering a branch and has loop(t i ) represents the number of iterations in the loop structure.

[0104] Furthermore, the optimal service combination scheme is derived through iterative analysis using a teaching optimization algorithm, including:

[0105] Based on the aggregation results, an objective function for service composition optimization is established, and the optimal service composition scheme is obtained through iterative analysis using a teaching optimization model.

[0106] Furthermore, the objective function for optimizing the service composition includes:

[0107] F = min(Time(sc), Cost(sc))

[0108]

[0109] Where Cost(sc) is the cost of the service composition based on collaboration awareness, Time(sc) is the time consumption of the service composition, t0 is the maximum time limit of the task, and c0 is the maximum cost limit of the task.

[0110] Specifically, the Teaching Optimization Algorithm (TLBO) in the optimization algorithm module is used to maximize the overall QoS of service composition by considering the effectiveness of cooperation. The attributes of overall QoS include time consumption and cost consumption. The service composition optimization model includes:

[0111] F = min(Time(sc), Cost(sc))

[0112]

[0113] Where Cost(sc) is the cost of service composition based on collaboration awareness, Time(sc) is the time consumption of service composition, t0 is the maximum time limit of the task, c0 is the maximum cost limit of the task, and F is the objective function used to quantify the merits of service composition schemes.

[0114] Furthermore, the optimal service combination scheme is derived through iterative analysis using the teaching optimization model, including:

[0115] Step 1: Generate an initial service composition scheme for each subtask and calculate the initial objective function value;

[0116] Step 2: Treat the service composition scheme as a student, and use the teacher module based on the teaching optimization model to iteratively update each student and calculate the objective function value of the updated service composition scheme.

[0117] The expression for iteratively updating each student using the teacher module is as follows:

[0118]

[0119] difference = r i *(X teacer -TF i *Mean)

[0120] Wherein, the time before and after the i-th student learns under the teacher's guidance are represented as follows: and r i Let TF be the learning step size for the i-th student, ranging from [0,1]. i For learning factors, TF i =round[1+rand(0,1)], its value is between [1,2], Mean is the average of all students, X teacer This refers to the individual with the best fitness value in the current population.

[0121] Step 3: If the objective function value of the updated service composition scheme is better, then accept the update; otherwise, retain the original value.

[0122] Step 4: Based on the teaching optimization model, the student module randomly selects students to communicate and updates the model, and calculates the updated objective function value for each student.

[0123] The expression for randomly selecting students to interact with using the student module and then updating the selection is:

[0124]

[0125] Wherein, the time before and after the i-th student learns under the teacher's guidance are represented as follows: and r i Let X be the learning step size of the i-th student. i and X j F(X) represents the i-th and j-th students respectively. i ) and F(X j ) represent the fitness values ​​of the i-th and j-th students, respectively.

[0126] Step 5: If the updated student's objective function value is better, then accept the update; otherwise, retain the original value.

[0127] Step 6: Repeat steps 2-5 according to the set number of iterations or convergence conditions. In each iteration, record the current optimal service combination scheme and its objective function value. When the number of iterations is reached or the convergence condition is met, output the optimal service combination scheme.

[0128] Currently, research on service composition of production factors in the Industrial Internet environment is relatively limited. Existing studies largely draw on the ideas of traditional service computing, mainly focusing on selecting one service for each task or optimizing service composition through combinatorial optimization models and heuristic algorithms. However, these methods neglect the collaborative relationships between services, potentially leading to poor overall performance of the service composition. Therefore, this embodiment proposes a novel collaboratively perceived service composition optimization method for production factors in the Industrial Internet, named CaSCO. First, this embodiment analyzes historical collaboration data to calculate the collaboration frequency between services, including service collaboration within tasks (internal collaboration) and service collaboration between tasks (external collaboration). Then, based on the number of service providers in the current service composition, the effectiveness index of the current collaboration is quantified. Second, the collaboratively perceived service composition optimization model is combined with the Teaching-to-Optimize Algorithm (TLBO), i.e., the CaSCO method, to optimize the overall QoS of the service composition. Finally, the optimized service composition solution is delivered to the user, achieving dual optimization of time and cost.

[0129] The overall framework of the collaborative sensing service combination optimization method for production factors under the Industrial Internet proposed in this embodiment is as follows: Figure 2 As shown, it mainly includes the following four core parts:

[0130] (1) Task decomposition: Decompose the user's production process into multiple tasks, each of which requires one or more types of production factor services; (2) QoS attribute definition: Define the QoS attributes of production factor services, including time consumption and cost consumption; (3) Time consumption calculation: Considering historical collaboration relationships, calculate the internal and external collaboration coefficients of the task, and calculate the time consumption of the task; (4) Cost consumption calculation: Considering the current collaboration relationships, calculate the current collaboration coefficient, and calculate the cost consumption of the task; (5) QoS aggregation: Consider the QoS aggregation module, aggregate the time consumption and cost consumption of the task to obtain the comprehensive QoS value of the task; (6) Service composition optimization: Use the Teaching Optimization Algorithm (TLBO) to achieve global optimization of the service composition scheme.

[0131] The research motivation, model construction, and experimental verification of this embodiment will be explained in detail below.

[0132] To describe the problem of combining production factor services in the industrial manufacturing process under the Industrial Internet environment, this invention uses a coarse-grained shipbuilding process in a real-world scenario as an example to illustrate its production process. The shipbuilding process is as follows: Figure 2As shown, the shipbuilding process includes five different tasks: steel processing, section production, equipment processing, berth closure, and ship testing. Each task requires at least one type of production factor resource, namely material resources or machine resources, and each type of production factor resource may require one or more. Task T1 requires two types of production factor resources, and each type of production factor resource requires two types. Task T3 requires two types of machine resources, while task T5 requires only one type of machine resource. The sequence of tasks can be sequential, parallel, conditional, or cyclical. The subtasks in this shipbuilding process only have two execution relationships: sequential and parallel. In this process, T1, T2, T3, and T4 all need to be completed by composite services, that is, the collaboration of two or more manufacturing services, while T5 only requires one manufacturing service. Based on each task (single service) or composite service, a complete service combination chain can be formed.

[0133] First, the tasks posted by enterprises or users on the industrial internet platform are decomposed. The production process can be decomposed into a three-dimensional P, including a set of tasks, a set of execution relationships between tasks, and a set of production factor services that the tasks can use.

[0134] Then, the QoS attributes of production factor services are defined, including time consumption and cost consumption. This invention considers three service types: human resources, material resources, and machine resources. Time and cost are considered as QoS attributes in this invention. It should be noted that different types of services have different QoS attributes. The QoS attribute of human resources only considers usage cost; the QoS attribute of material resources considers usage cost, delivery cost, and delivery time; the QoS attribute of machine resources includes usage cost, delivery cost, delivery time, and execution time.

[0135] Historical collaboration relationships are considered to calculate task time consumption. Historical collaboration relationships include internal task collaboration and external task collaboration. The internal collaboration coefficient is obtained by calculating the historical average collaboration frequency between services within the task, and the external collaboration coefficient is obtained by calculating the historical average collaboration frequency between services between tasks.

[0136] The formula for calculating the degree of collaboration within a task includes:

[0137]

[0138] Among them, t k It is a subtask, freq(s) i ,s j ) is s i and s j In task t k The frequency of historical calls in the data is only s i and s js is only called when they are called simultaneously. i and s j There is historical cooperation. From |S k The number of combinations of choosing two services from a given set of services.

[0139] The formula for calculating the degree of external collaboration for a task includes:

[0140]

[0141] Among them, task t j In task t k Execute upon completion, i.e., task t j The beginning depends on task t k The completion of. To directly follow in task t k The number of tasks after that, s i and s j These are two different tasks t k and t j Candidate services, |S k |To complete the task t k The required number of services, |S j |To complete the task t j The required number of services, freq(s) i ,s j ) for s i and s j The number of historical calls. For service s i The corresponding set of candidate services For service s j The corresponding set of candidate services.

[0142] Next, the current collaboration relationships of the task are considered to calculate the task's cost. The current collaboration relationship is determined by calculating the number of services from the same service provider in the current service mix, which forms the current collaboration coefficient. The specific formula for calculating the collaboration coefficient includes:

[0143]

[0144] Among them, P i For service providers, PC(P) i ) for service provider P i The corresponding current collaboration parameter, its range is PC(P) i )∈(d max -0.5,d max ], and d max α and are adjustment parameters, with ranges of d and d respectively. max∈[0.5,1], α∈(0,1], so 1-d max This represents the lowest allowed discount. Num(P) i ) is the service provider P in the current service portfolio i The number of services selected.

[0145] Furthermore, current collaboration optimizes resource allocation and scheduling, thereby reducing service costs and ultimately decreasing the overall cost of the task. The specific formula for calculating cost consumption includes:

[0146]

[0147] Among them, Cost(t) k The task t is completed after considering the collaborative effectiveness of the current service. k The required cost, cost(s) i () is the initial service that does not consider the current collaboration. i Cost consumption, S k To complete the task t k The required number of candidate services For service s i The provider. Therefore, considering the current collaboration between services can further reduce cost consumption in the production process.

[0148] Then, the QoS aggregation module is used to perform QoS aggregation operations based on the task's execution structure (sequential, parallel, conditional, or cyclic) to obtain a comprehensive QoS value for the combined services.

[0149] Finally, the Teaching Optimization Algorithm (TLBO) from the optimization algorithm module is used to maximize the overall QoS of the service composition by considering the effectiveness of collaboration. The overall QoS attributes include time consumption and cost consumption. The service composition optimization model includes:

[0150] F = min(Time(sc), Cost(sc))

[0151]

[0152] Where Cost(sc) is the cost of the service composition based on collaboration awareness, Time(sc) is the time consumption of the service composition, t0 is the maximum time limit of the task, and c0 is the maximum cost limit of the task.

[0153] The Teaching Optimization Algorithm (TLBO) consists of a teacher phase and a student phase. Through iterative optimization of the teacher and student phases, the optimal service composition scheme is derived.

[0154] The update formula for the teacher stage includes:

[0155]

[0156] difference = r i *(X teacher -Tf i *Mean)

[0157] Wherein, the time before and after the i-th student learns under the teacher's guidance are represented as follows: and r i Let TF be the learning step size for the i-th student, ranging from [0,1]. i For learning factors, TF i =round[1+rand(0,1)], whose value is between [1,2], and Mean is the average of all students.

[0158] The update formulas for the student stage include:

[0159]

[0160] Wherein, the time before and after the i-th student learns under the teacher's guidance are represented as follows: and r i Let X be the learning step size of the i-th student. i and X j F(X) represents the i-th and j-th students respectively. i ) and F(X j ) represent the fitness values ​​of the i-th and j-th students, respectively.

[0161] In this embodiment, the recommended method provided by the present invention was experimentally verified. The dataset and experimental parameter settings, evaluation indicators, comparison methods and experimental results of this embodiment are described in detail below.

[0162] Dataset and Experiment Setup:

[0163] Figure 2 The specific production process of a ship is presented, which can be decomposed into five sub-tasks. These tasks exhibit both sequential and parallel execution modes; therefore, QoS aggregation only considers the sequential and parallel scenarios. Furthermore, based on this dataset, this invention also simulated and generated 400 historical production factor service combination data records. Specific information about this dataset is shown in Table 2.

[0164] Table 2 Parameter settings for the dataset

[0165]

[0166] Table 3 shows that the dataset generates QoS data for candidate services and historical service combination data. In the generated dataset, an abstract service has 10 candidate services, each requiring a certain time and cost. The time cost ranges from 5 to 20, and the cost ranges from 40 to 50. Each service is provided by a corresponding provider; in this invention, a total of 6 service providers participate in providing the services. Therefore, there are 10 to 1000 composite service candidates to complete a task. In the experiment, α = 0.1, d max =0.5, γ=0.5.

[0167] Evaluation indicators:

[0168] To evaluate the performance of the proposed method, this invention selects the following metrics as evaluation standards: time consumption, cost consumption, and overall QoS. Time consumption refers to the total time in the production process, cost consumption is the total cost in the production process, and overall QoS represents the overall quality index. The time consumption and cost consumption of production tasks are calculated through the historical collaboration module and the current collaboration module, respectively. Then, the time and cost of each sub-task are aggregated through the QoS aggregation module to obtain the overall time consumption and cost consumption of the service composition scheme. For the overall QoS (i.e., fitness value) of a service composition scheme, since this invention needs to optimize both time and cost metrics simultaneously, a dimensionless standardization method is adopted to transform the multi-objective optimization problem into a single-objective optimization problem for easier optimization and evaluation. The calculation formula for the overall QoS of service composition is as follows.

[0169]

[0170] Here, sc represents a service composition scheme. and These represent the maximum and minimum times required for all service combination options. and These represent the highest and lowest costs among all service combination options. Through dimensionless standardization, the service combination options can be further filtered to obtain the one offering the highest service quality.

[0171] Baseline comparison method:

[0172] To verify the performance of the CaSCO algorithm, a series of experiments were conducted. The method proposed in this invention will be compared with the following methods: GA, PSO, TLBO, GA-CaSCO, and PSO-CaSCO.

[0173] (1) GA: Genetic Algorithm has powerful global search capabilities and can effectively avoid local optima. It adapts to complex constraints and multi-objective optimization, and can flexibly handle different needs. Through population evolution and adaptive adjustment, the genetic algorithm can dynamically adapt to changes and provide high-quality service combinatorial solutions.

[0174] (2) PSO: Particle Swarm Optimization has strong global search capabilities and fast convergence. By simulating the swarm behavior of particles and local information sharing, it can effectively explore the solution space. PSO is highly adaptable to constraints and is suitable for handling dynamically changing service composition problems.

[0175] (3) TLBO: The Teaching-Learning-Based Optimization algorithm is simple to implement and does not require gradient information of the problem. By simulating the interactive learning process between teachers and students, TLBO can effectively explore the solution space and find the global optimum. It has good handling ability for constraints and can adapt quickly in dynamic environments.

[0176] (4) GA-CaSCO: Genetic Algorithm-Collaboration aware Service Composition Optimization takes into account the collaborative relationship between services into the service composition optimization method. It can adapt to dynamic environmental changes, meet multi-objective needs, and handle complex constraints.

[0177] (5) PSO-CaSCO: Similar to GA-CaSCO, the Particle Swarm Optimization-Collaboration aware Service Composition Optimization method based on the particle swarm optimization algorithm takes into account the collaborative relationship between services into the service composition optimization method, which can effectively handle multi-objective optimization problems and adapt to dynamic environmental changes.

[0178] Table 3 Performance Comparison with Baseline

[0179]

[0180] Experimental Results and Analysis:

[0181] Performance evaluation is presented through comparison with baselines, and the evolution of the collaboratively-aware service composition optimization process is investigated using different metaheuristic algorithms. Table 3 shows the performance comparison with baselines for total time, cost, and overall QoS metrics. It can be seen that among GA, PSO, and TLBO, TLBO is slightly better than GA and PSO. Without considering collaboration, GA is the worst for service composition optimization. Similarly, among GA-CaSCO, PSOCaSCO, and TLBO-CaSCO, TLBO-CaSCO is slightly better than GACaSCO and PSO-CaSCO. GA-CaSCO is the worst for service composition optimization considering collaboration. GA-CaSCO, PSO-CaSCO, and TLBO-CaSCO are better than GA, PSO, and TLBO, respectively. In summary, regardless of the metaheuristic algorithm used to solve the proposed collaboratively-aware service composition optimization model, considering collaboration between services can effectively improve overall QoS.

[0182] To further investigate the effectiveness of this method, the evolution curves of integrated QoS under different methods were studied to address the problem of collaboratively aware service composition optimization. Figure 3 This shows how the overall QoS value changes with the number of iterations. Figure 3 It can be seen that TLBO-CaSCO obtains the optimal solution in the 38th iteration, PSOCaSCO in the 86th iteration, and GA-CaSCO in the 45th iteration. In summary, TLBO-CaSCO obtains the optimal solution with the fewest iterations.

[0183] This invention proposes an optimization model for collaborative sensing service composition under the Industrial Internet, which is solved using an advanced teaching optimization algorithm. The proposed method considers both historical collaboration relationships (including internal and external collaboration) and current collaboration relationships. Historical collaboration optimizes the time of the target service composition, while current collaboration optimizes the cost. Therefore, considering collaboration relationships can improve overall QoS. Experimental results on simulated datasets show that regardless of the metaheuristic algorithm used to solve the proposed collaborative sensing service composition optimization model, considering inter-service collaboration effectively improves overall QoS.

[0184] The embodiments described above are merely preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Various modifications and improvements made to the technical solutions of the present invention by those skilled in the art without departing from the spirit of the present invention should fall within the protection scope defined by the claims of the present invention.

Claims

1. A method for optimizing the combination of collaborative sensing services for production factors under the Industrial Internet, characterized in that, include: Obtain the production process involved in user requirements, and decompose the production process into multiple sub-tasks; Based on historical and current collaboration relationships, calculate the internal and external collaboration coefficients of the task and the current collaboration relationship to obtain the time and cost consumption of the subtask. Calculating the internal and external collaboration coefficients of the task includes: Obtain the internal collaboration coefficient by utilizing the average collaboration frequency between services within the task: ； in, For the degree of internal collaboration within the task, for and In the mission The frequency of historical calls in the data. From The number of combinations of choosing two services from a given service. and Two different tasks and Candidate services, For candidate service set One of the candidate services, For candidate service set One of the candidate services; The average collaboration frequency between services across tasks is used to obtain the external collaboration coefficient. ； in, The degree of external collaboration for the task. and For the mission, To follow directly in the mission The number of tasks after that, To complete the task The required number of services To complete the task The required number of services for and The number of historical calls, For service The corresponding set of candidate services For service The corresponding set of candidate services; Calculating the current collaboration relationship includes: The current collaboration coefficient is determined based on the number of services from the same service provider in the current service portfolio: ； in, For service providers, For service providers The corresponding current collaboration parameters, and To adjust the parameters, This represents the lowest allowed discount. For the current service portfolio from service providers The number of services selected; The cost of acquiring the subtask includes: ； in, To complete the task after considering the collaborative effectiveness of the current service. The required cost For the initial service that did not take into account the current collaboration Cost consumption, To complete the task The required number of candidate services For service The provider ( ) for service providers The corresponding current collaboration parameters; The time consumption and cost consumption are aggregated, and the optimal service combination scheme is determined through iterative analysis using a teaching optimization model. The optimal service composition scheme is derived through iterative analysis using teaching optimization algorithms, including: Based on the aggregation results, an objective function for service composition optimization is established, and the optimal service composition scheme is obtained through iterative analysis using a teaching optimization model. The objective function for optimizing the service composition includes: ； in, It is the cost consumption of service combinations based on collaboration awareness. It is the time consumption of the service combination. This is the maximum time limit for the task. It is the maximum cost constraint of the task. The objective function is used to quantify the merits of different service combination schemes. The optimal service combination scheme is derived through iterative analysis using a teaching optimization model, including: Step 1: Generate an initial service composition scheme for each subtask and calculate the initial objective function value; Step 2: Treat the service composition scheme as a student, and use the teacher module based on the teaching optimization model to iteratively update each student and calculate the objective function value of the updated service composition scheme. The expression for iteratively updating each student using the teacher module is as follows: ； ； in, and They represent the first Each student's pre- and post-learning values ​​are determined under the teacher's guidance. For the first The learning pace of each student As a learning factor, The average of all students, The individual with the best fitness value in the current population; Step 3: If the objective function value of the updated service composition scheme is better, then accept the update; otherwise, retain the original value. Step 4: Based on the teaching optimization model, the student module randomly selects students to communicate and updates the model, and calculates the updated objective function value for each student. The expression for randomly selecting students for interaction using the student module and then updating the data is as follows: ； in, and The first Each student's pre- and post-learning values ​​are determined under the teacher's guidance. For the first The learning pace of each student and Representing the first and the One student, and Representing the first and the The fitness value of each student; Step 5: If the updated student's objective function value is better, then accept the update; otherwise, retain the original value. Step 6: Repeat steps 2-5 according to the set number of iterations or convergence conditions. In each iteration, record the current optimal service combination scheme and its objective function value. When the number of iterations is reached or the convergence condition is met, output the optimal service combination scheme.

2. The method for optimizing the combination of collaborative sensing services for production factors under the Industrial Internet according to claim 1, characterized in that, Aggregating the time consumption and the cost consumption includes: Based on the execution structure of the subtask, perform QoS aggregation on the time consumption and cost consumption to obtain the comprehensive QoS value of the combined service: ； in, The overall QoS value for combined services, As a service portfolio solution, and These represent the maximum and minimum times required for all service combination options. and These represent the highest and lowest costs required for all service combination options. for The weight parameters in the code are used to determine the weights of different QoS attributes.

3. The method for optimizing the combination of collaborative sensing services for production factors under the Industrial Internet according to claim 2, characterized in that, The execution structure includes: sequential time and cost, parallel time and cost, selected time and cost, and loop time and cost.

Images