Task processing methods, apparatus, equipment, and media for manufacturing service platforms
By constructing a behavioral evolutionary game model and obtaining stable evolutionary game strategies, the static matching problem caused by dynamic changes in user behavior in the manufacturing service platform was solved. This enabled dynamic task matching and improved the stability of the collaboration process, reducing collaboration costs and increasing user satisfaction.
Patent Information
- Application Number
- CN202611244219.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-08-14
- Publication Date
- 2026-11-17
AI Technical Summary
Existing manufacturing service platforms cannot respond promptly to dynamic changes in user behavior characteristics, resulting in static matching strategies failing to achieve dynamic task matching, thus affecting collaboration efficiency and user satisfaction.
By constructing a behavioral evolutionary game model for the manufacturing service platform, stable evolutionary game strategies are obtained, and dynamically adapted service collaboration strategies are formulated to ensure dynamic matching between user behavior characteristics and service capabilities, thereby improving the stability and efficiency of the collaboration process.
It enables dynamic matching of tasks on the manufacturing service platform, reduces collaboration costs, improves task completion quality and user satisfaction, and ensures the stable and orderly operation of the collaboration process.
Smart Images

Figure CN123117614A_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the field of industrial internet, specifically relating to a task processing method, apparatus, equipment, and medium for a manufacturing service platform. Background Technology
[0002] With the continuous development of the manufacturing service collaboration model, this model has gained increasing popularity among users due to its advantages of high efficiency and collaboration. Through this model, different users can rely on the manufacturing service platform to complete various collaborative tasks in a collaborative manner.
[0003] However, existing collaborative service processing methods use a static matching strategy. This strategy pre-stores the user's own ability information and service resource information in the manufacturing service platform, and then filters out users who meet the task requirements and assigns corresponding tasks based on the received service collaboration task requirements.
[0004] However, this approach, which relies on static matching strategies, cannot respond promptly to dynamic changes in user behavior characteristics, and therefore cannot dynamically match and process tasks pending on the manufacturing service platform. Summary of the Invention
[0005] This application provides a task processing method, apparatus, equipment, and medium for a manufacturing service platform, which addresses the problem that existing static matching strategies cannot respond to dynamic changes in users and are difficult to achieve dynamic task matching.
[0006] Firstly, this application provides a task processing method for a manufacturing service platform, including:
[0007] To acquire the service collaboration behavior characteristics of multiple users on the manufacturing service platform and the user preference utility measurement model;
[0008] Based on the service collaboration behavior characteristics and the user preference utility measurement model, a behavioral evolution game model of the manufacturing service platform is established.
[0009] Based on the behavioral evolution game model, the evolution game stable strategy of the manufacturing service platform is obtained, and the evolution game stable strategy keeps the service collaboration behavior of the manufacturing service platform in a stable state.
[0010] Based on the evolutionary game-theoretic stable strategy, a service collaboration strategy for the manufacturing service platform is constructed.
[0011] Based on the service collaboration strategy, service collaboration tasks on the manufacturing service platform are processed.
[0012] Optionally, the acquisition of multi-user service collaboration behavior characteristics and user preference utility measurement models of the manufacturing service platform includes:
[0013] Analyze the user collaboration characteristics of the manufacturing service platform to obtain the service collaboration behavior characteristics;
[0014] Based on the service collaboration behavior characteristics, the user preference utility measurement model is constructed; the user preference utility measurement model is used for comprehensive utility perception evaluation oriented towards user differentiated behavioral preferences; the user preference utility measurement model includes: long-term and short-term utility preference model and risk preference model.
[0015] Optionally, the behavioral evolutionary game model includes: a dynamic equation set replicating the strategy choices of the game participants; the step of establishing a behavioral evolutionary game model for the manufacturing service platform based on the service collaboration behavior characteristics and the user preference utility measurement model includes:
[0016] Based on the service collaboration behavior characteristics, a manufacturing service collaboration delivery scenario for the manufacturing service platform is constructed.
[0017] Based on the service collaboration relationships between users as represented in the manufacturing service collaborative delivery scenario, the game participants and game strategy selection of the manufacturing service platform are determined.
[0018] Based on the service collaboration behavior and utility relationship between users as represented in the manufacturing service collaborative delivery scenario, and the user preference utility measurement model, the payoff matrix of the game participants is calculated.
[0019] Based on the game participants' strategy choices and payoff matrices, a replicating dynamic equation set for the game participants' strategy choices is established. This replicating dynamic equation set is used to simulate the dynamic evolution of the game participants' strategies.
[0020] Optionally, obtaining the evolutionary game-stable strategy of the manufacturing service platform based on the behavioral evolutionary game model includes:
[0021] Based on the strategy choices of the game participants, the dynamic equation system is replicated to calculate the strategy evolution equilibrium point of the game participants.
[0022] Based on the strategy evolution equilibrium points of the game participants, the evolutionary stable strategy of the game participants is obtained.
[0023] Optionally, obtaining the evolutionary game-stable strategy of the game participants based on their strategy evolution equilibrium points includes:
[0024] Calculate the eigenvalues of the Jacobian matrix at the equilibrium point of the strategy evolution;
[0025] Based on the eigenvalue analysis, the global stability of the game participants at the strategy evolution equilibrium point is obtained, yielding the first analysis result;
[0026] Based on the first analysis results, the evolutionary game-stable strategies of the game participants are obtained.
[0027] Optionally, the step of constructing the service collaboration strategy of the manufacturing service platform based on the evolutionary game stable strategy includes:
[0028] Based on the aforementioned evolutionary game stability strategy, the behavioral evolution trend of game participants under different service collaboration influencing factors is obtained;
[0029] Based on the behavioral evolution trends of the game participants, a second analytical result of the behavioral evolution of the game participants is determined;
[0030] Based on the second analysis results, a service collaboration strategy for the manufacturing service platform is constructed.
[0031] Optionally, the factors influencing service collaboration include at least one of the following:
[0032] The impact of the user's initial fulfillment probability and the manufacturing service platform's initial supervision probability on behavioral evolution;
[0033] The impact of long-term user preferences on behavioral evolution;
[0034] The impact of long-term user utility on behavioral evolution.
[0035] Secondly, this application provides a task processing device for a manufacturing service platform, comprising:
[0036] The acquisition module is used to acquire the service collaboration behavior characteristics of multiple users on the manufacturing service platform and the user preference utility measurement model.
[0037] A module is established to build a behavioral evolution game model of the manufacturing service platform based on the service collaboration behavior characteristics and the user preference utility measurement model.
[0038] The acquisition module is used to acquire the evolutionary game stable strategy of the manufacturing service platform based on the behavioral evolutionary game model. The evolutionary game stable strategy keeps the service collaboration behavior of the manufacturing service platform in a stable state.
[0039] The construction module is also used to construct the service collaboration strategy of the manufacturing service platform based on the evolutionary game stable strategy.
[0040] The processing module is used to process service collaboration tasks on the manufacturing service platform based on the service collaboration strategy.
[0041] Optionally, the acquisition module is further configured to analyze the user collaboration characteristics of the manufacturing service platform and acquire the service collaboration behavior characteristics;
[0042] The construction module is specifically used to construct the user preference utility measurement model based on the service collaboration behavior characteristics; the user preference utility measurement model is used for comprehensive utility perception evaluation oriented towards user differentiated behavioral preferences; the user preference utility measurement model includes: long-term and short-term utility preference model and risk preference model.
[0043] Optionally, the building module is further configured to construct a manufacturing service collaboration delivery scenario for the manufacturing service platform based on the service collaboration behavior characteristics;
[0044] The device further includes: a determining module;
[0045] The determining module is used to determine the game participants and game strategy selection of the manufacturing service platform based on the service collaboration relationship between users represented in the manufacturing service collaborative delivery scenario.
[0046] The device further includes: a computing module;
[0047] The calculation module is used to calculate the payoff matrix of the game participants based on the service collaboration behavior and utility relationship between users represented in the manufacturing service collaborative delivery scenario, and the user preference utility measurement model.
[0048] The establishment module is specifically used to establish a replicating dynamic equation set of the strategy selection of the game participants based on their game strategy selection and payoff matrix. The replicating dynamic equation set of the strategy selection is used to simulate the dynamic evolution process of the game participants' strategies.
[0049] Optionally, the calculation module is further configured to replicate the dynamic equations based on the strategy choices of the game participants and calculate the strategy evolution equilibrium point of the game participants.
[0050] The acquisition module is specifically used to acquire the evolutionary game-stable strategy of the game participants based on their strategy evolution equilibrium points.
[0051] Optionally, the calculation module is further configured to calculate the eigenvalues of the Jacobian matrix at the policy evolution equilibrium point;
[0052] The device further includes: an analysis module;
[0053] The analysis module is used to analyze the global stability of the game participants at the strategy evolution equilibrium point based on the feature values, and obtain the first analysis result;
[0054] The acquisition module is specifically used to acquire the evolutionary game-stable strategy of the game participants based on the first analysis result.
[0055] Optionally, the acquisition module is further configured to acquire the behavioral evolution trend of game participants under different service collaboration influencing factors based on the evolutionary game stable strategy;
[0056] The determining module is further configured to determine a second analysis result of the behavioral evolution of the game participants based on the behavioral evolution trend of the game participants;
[0057] The construction module is specifically used to construct the service collaboration strategy of the manufacturing service platform based on the second analysis results.
[0058] Optionally, the factors influencing service collaboration include at least one of the following:
[0059] The impact of the user's initial fulfillment probability and the manufacturing service platform's initial supervision probability on behavioral evolution;
[0060] The impact of long-term user preferences on behavioral evolution;
[0061] The impact of long-term user utility on behavioral evolution.
[0062] Thirdly, this application provides a task processing device for a manufacturing service platform, comprising:
[0063] Memory;
[0064] processor;
[0065] The memory stores computer-executed instructions;
[0066] The processor executes computer execution instructions stored in the memory to implement the task processing method for a manufacturing service platform as described in the first aspect and various possible implementations thereof.
[0067] Fourthly, this application provides a computer storage medium storing computer execution instructions thereon, which are executed by a processor to implement the task processing method for a manufacturing service platform as described in the first aspect and various possible implementations thereof.
[0068] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the task processing method for a manufacturing service platform as described above.
[0069] This application provides a task processing method for manufacturing service platforms. First, it obtains the service collaboration behavior characteristics and user preference utility measurement model of multiple users on the manufacturing service platform. Then, based on these characteristics and model, it establishes a behavioral evolutionary game model for the platform. Next, it obtains a stable evolutionary game strategy that stabilizes the service collaboration behavior. Finally, it constructs a service collaboration strategy for the platform based on this stable strategy, and then processes the service collaboration tasks on the platform according to the strategy. This method, by constructing a behavioral evolutionary game model and obtaining a stable strategy to formulate a service collaboration strategy, solves the problems of existing static matching strategies being unable to respond to dynamic user changes and struggling to achieve dynamic task matching, thus achieving more flexible and efficient service collaboration task processing. Attached Figure Description
[0070] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.
[0071] Figure 1 The flowchart of the task processing method for the manufacturing service platform provided in this application Figure 1 ;
[0072] Figure 2 The flowchart of the task processing method for the manufacturing service platform provided in this application Figure 2 ;
[0073] Figure 3 This is a schematic diagram of the structure of the task processing device for the manufacturing service platform provided in this application;
[0074] Figure 4 This is a schematic diagram of the structure of the task processing equipment for the manufacturing service platform provided in this application.
[0075] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation
[0076] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0077] The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented, for example, in orders other than those illustrated or described herein.
[0078] In this application, the terms "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.
[0079] With continuous technological advancements and growing market demand, collaborative manufacturing services are becoming an increasingly popular choice for users. This allows different users to leverage collaborative services to complete tasks on the manufacturing service platform.
[0080] However, existing collaborative service processing methods employ a static strategy. This strategy pre-stores relevant information about different users, such as service resource information and their own capabilities, in the manufacturing service platform, and then selects the appropriate user based on the received service collaboration task.
[0081] However, this approach, which relies on static matching strategies, cannot respond promptly to dynamic changes in user behavior characteristics, and therefore cannot dynamically match and process tasks pending on the manufacturing service platform.
[0082] To address the aforementioned issues, this application provides a task processing method for manufacturing service platforms. By constructing a behavioral evolutionary game model and obtaining stable strategies to formulate service collaboration strategies, it solves the problems of existing static matching strategies being unable to respond to dynamic changes in users and struggling to achieve dynamic task matching. This method can adapt to the dynamic changes in user behavior characteristics and service capabilities in real time, achieving matching of manufacturing service collaboration tasks with user resources, improving the platform's service collaboration capabilities, ensuring that the service collaboration process is always in a stable and orderly operating state, thereby reducing collaboration costs, improving task completion quality, and increasing user satisfaction.
[0083] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.
[0084] Figure 1 The flowchart of the task processing method for the manufacturing service platform provided in this embodiment Figure 1 .like Figure 1 As shown, the task processing method for a manufacturing service platform provided in this embodiment includes:
[0085] S101: Acquire the service collaboration behavior characteristics of multiple users on the manufacturing service platform and the user preference utility measurement model.
[0086] Among them, the manufacturing service platform is a networked service carrier for the manufacturing industry. It can bring together multiple users, support business docking, task division and collaboration among different users, collect collaborative behavior data generated during the service interaction process of each user, mine the service collaboration behavior characteristics between users, and complete the quantitative evaluation of user preferences by combining the user preference utility measurement model, supporting subsequent analysis and processing related to multi-user service collaboration.
[0087] The manufacturing service platform includes multiple collaborative users, who can act as both service providers and service seekers in the manufacturing service collaboration scenario. The manufacturing service platform can monitor the collaborative behavior of each user during the multi-user service collaboration process.
[0088] Multi-user refers to various entities participating in service collaboration activities on a manufacturing service platform, including but not limited to service providers, service users, and platform operators.
[0089] Service collaboration behavior characteristics are derived from the analysis of historical collaboration behavior data of multiple users on the manufacturing service platform, and can reflect the behavioral patterns of users in the service collaboration process.
[0090] User preference utility measurement models include, but are not limited to, short-term and long-term utility preference models and risk preference models. Short-term and long-term utility preference models measure a user's preference for short-term immediate utility and long-term sustainable utility when participating in collaborative tasks. Risk preference models measure a user's acceptance of potential risks in collaborative tasks and their risk-reward trade-off preferences.
[0091] The purpose of this step is to extract feature information related to user collaborative behavior from the manufacturing service platform and to build a user preference utility measurement model based on this feature information.
[0092] Different acquisition factors have different acquisition methods. When the acquisition factor is a service collaboration behavior feature, the acquisition method may be to first obtain historical collaboration behavior data of multiple users from the manufacturing service platform, such as task participation records and task completion time; and then determine the service collaboration behavior features of multiple users through data cleaning and feature extraction algorithms (such as cluster analysis algorithms).
[0093] When the acquisition factor is a user preference utility measurement model, the acquisition method can be, for example, based on the analysis of data in the service collaboration behavior characteristics, and then obtain the corresponding user preference utility measurement model.
[0094] S102: Based on service collaboration behavior characteristics and user preference utility measurement model, establish a behavioral evolution game model for manufacturing service platforms.
[0095] Among them, the behavioral evolution game model is used to simulate the dynamic changes in user behavior based on their preferences and perceived utility in different collaborative service scenarios. The behavioral evolution game model includes service providers, service demanders, and platform operators. For example, in the automotive manufacturing collaborative service scenario, service providers include parts suppliers who can provide the necessary parts for car manufacturing; service demanders include car manufacturers who need to purchase parts to complete car production; and the platform operator is responsible for supervising the behavioral norms of service providers and service demanders during the collaborative process to ensure the normal operation of the collaborative service.
[0096] The purpose of this step is to build a model that can simulate the dynamic changes in user behavior on a manufacturing service platform.
[0097] Understandably, firstly, service collaboration behavior characteristics can reflect users' actual behavioral patterns and rules in the service collaboration process, such as the frequency of user participation in collaboration, the type of collaboration adopted, and the interaction with partners; secondly, user preference utility measurement models can reflect the degree of user preference for different collaborative services and the magnitude of utility they can perceive.
[0098] Therefore, by comprehensively considering the characteristics of service collaboration behavior and the user preference utility measurement model, we can fully take into account the differences in users' actual behavior and preferences. This allows the constructed model to simulate the user's decision-making process when faced with different choices, and how these decisions affect each other, thus obtaining a model that can simulate the dynamic changes in user behavior on the manufacturing service platform.
[0099] S103: Based on the behavioral evolutionary game model, obtain the evolutionary game stable strategy of the manufacturing service platform. The evolutionary game stable strategy keeps the service collaboration behavior of the manufacturing service platform in a stable state.
[0100] Among them, the evolutionary game stable strategy is the optimal strategy set derived from the evolutionary game model of the behavior of the manufacturing service platform. This strategy set can make the collaborative behavior of the service providers, service demanders and platform operators within the manufacturing service platform tend to be stable and will not deviate due to minor adjustments of individual strategies.
[0101] The purpose of this step is to derive the optimal set of strategies that can maintain the long-term stability of multi-user collaborative behavior on the collaborative service platform from the constructed behavioral evolution game model.
[0102] Understandably, since the behavioral evolution game model is built based on the characteristics of service collaboration behavior and the user preference utility measurement model, the model can simulate the dynamic changes in user behavior on the manufacturing service platform.
[0103] Therefore, this behavioral evolution game model can measure the dynamic changes in user behavior, avoid the limitations of traditional static strategies, and ensure that the service collaboration process of the manufacturing service platform remains stable and orderly even when user behavior is dynamically adjusted.
[0104] S104: Based on the evolutionary game-theoretic stable strategy, construct a service collaboration strategy for the manufacturing service platform.
[0105] Among them, the service collaboration strategy refers to a task matching and collaboration management scheme formulated based on the evolutionary game stable strategy and combined with the business scenarios and collaboration needs of the manufacturing service platform.
[0106] The purpose of this step is to construct a specific service collaboration strategy for a manufacturing service platform based on the established evolutionary game-theoretic stable strategy.
[0107] Understandably, evolutionary game theory's stable strategy is derived from users' actual behavioral characteristics and preference utility, possessing dynamic adaptability. Therefore, service collaboration strategies built based on this strategy can avoid the drawbacks of traditional static strategies failing to respond to changes in user behavior, ensuring the accuracy of task matching and the orderliness of the collaboration process on the manufacturing service platform, thereby improving the overall operational efficiency of the manufacturing service platform.
[0108] S105: Based on the service collaboration strategy, process the service collaboration tasks on the manufacturing service platform.
[0109] Understandably, service collaboration strategies are derived from evolutionary game-theoretic stable strategies. They fully integrate users' service collaboration behavior characteristics and preference utility, and have the ability to dynamically adapt to changes in user behavior, thus overcoming the limitations of traditional static matching strategies.
[0110] Therefore, by using strategies to handle tasks, we can achieve accurate matching between service collaboration tasks and user resources, ensure the orderliness and stability of the collaboration process, and avoid problems such as inefficient task matching and collaboration conflicts caused by rigid strategies.
[0111] The task processing method for manufacturing service platforms provided in this embodiment first obtains the service collaboration behavior characteristics and user preference utility measurement model of multiple users on the manufacturing service platform, then establishes a behavioral evolution game model and obtains the stable evolution game strategy, and then constructs a service collaboration strategy and processes the platform service collaboration tasks accordingly.
[0112] This method formulates service collaboration strategies by constructing a behavioral evolution game model and obtaining stable strategies. It solves the problems that existing static matching strategies cannot respond to dynamic changes in users and are difficult to achieve dynamic task matching. It can adapt to the dynamic changes in user behavior characteristics and service capabilities in real time, realize the matching of manufacturing service collaboration tasks and user resources, improve the reliability of platform service collaboration, ensure that the service collaboration process is always in a stable and orderly operating state, thereby reducing collaboration costs, improving task completion quality and user satisfaction.
[0113] Figure 2 The flowchart of the task processing method for the manufacturing service platform provided in this embodiment Figure 2 .like Figure 2 As shown. This embodiment is in Figure 1 Based on the embodiments, the implementation process of task processing is described in detail. The task processing method for manufacturing service platforms provided in this embodiment includes:
[0114] S201: Analyze the user collaboration characteristics of the manufacturing service platform to obtain service collaboration behavior features.
[0115] Among these, user collaboration characteristics include, but are not limited to: the diversity of user participation, the uncertainty of user service collaboration decisions, the similarity of manufacturing resources, and the coupling of collaboration relationships among multiple users.
[0116] The diversity of user participation refers to the roles played by users within a manufacturing service platform. For example, in an automotive manufacturing service platform, user A is a parts supplier, providing various parts such as engines and tires for the automotive manufacturing process; user B is a technical service provider, offering technical support and solutions for the automotive manufacturing process.
[0117] The uncertainty of user service collaboration decisions refers to the dynamic nature of a user's strategy choices and behavioral decisions during the manufacturing service collaboration process, which are influenced by their own preferences, the external environment, and other user behaviors. For example, in an electronics manufacturing service platform, user A maintains a long-term cooperative relationship with user B, procuring necessary components from user B. However, as the platform environment changes, user A, after comprehensive evaluation, discovers that a newly joined user C has a greater advantage in component supply than user B. Based on these factors, user A decides to change partners and cooperate with user C instead. User A's originally stable cooperation decision changes due to changes in the platform environment and the emergence of user C. This characteristic of decision-making being not fixed but dynamically adjusted according to various factors can be termed the uncertainty of user service collaboration decisions.
[0118] The similarity of manufacturing resources refers to the degree of similarity of the resources owned by different users on a manufacturing service platform.
[0119] The coupling of collaborative relationships among multiple users refers to the degree to which collaborative activities among different users influence and depend on each other. It can reflect the impact that a single user's decisions and behaviors may have on other users. For example, in a clothing manufacturing collaboration platform, user A is a fabric supplier, user B is a clothing processor, and user C is a clothing retailer. When user A makes decisions and takes actions, it will affect users B and C.
[0120] The characteristics of service collaboration behavior include, but are not limited to: the group-based, dynamic, and bounded rationality characteristics of service collaboration.
[0121] The collective nature of service collaboration means that the collaborative service behavior of the manufacturing service platform is not completed by a single user, but by multiple users participating and cooperating together.
[0122] The dynamism of service collaboration refers to the fact that the collaborative behavior of users in a manufacturing service platform will continuously adapt to changes in user preferences, adjustments in collaboration scenarios, and changes in the behavior of other participants.
[0123] The bounded rationality characteristic of service collaboration refers to the fact that when collaborative users of a manufacturing service platform make collaborative decisions, they cannot obtain comprehensive and complete collaborative information and can only make relatively reasonable choices based on their own cognition and limited information.
[0124] Understandably, user collaboration characteristics can reflect user behavior from multiple dimensions. For example, the diversity of user participation reflects the different roles different users play in the manufacturing service platform; the uncertainty of user service collaboration decisions reflects that user decisions are dynamically affected by various factors. Therefore, by analyzing the user collaboration characteristics of the manufacturing service platform, we can determine the behaviors exhibited by users in the collaboration process within each platform.
[0125] In this step, for example, we can first obtain historical collaboration records of multiple users on the manufacturing service platform. These records include task completion time, the degree of cooperation between users, and the users' own abilities and resources. Next, the information in the historical collaboration records is cleaned to remove invalid and erroneous data; then, it is categorized and organized according to different dimensions; then, correlation analysis is conducted to uncover the inherent relationships between the data and obtain user collaboration characteristics. Finally, based on the summarized user collaboration characteristics, service collaboration behavior features are further obtained.
[0126] S202: Based on the characteristics of service collaboration behavior, construct a user preference utility measurement model; the user preference utility measurement model is used for comprehensive utility perception evaluation oriented towards users' differentiated behavioral preferences; the user preference utility measurement model includes: long-term and short-term utility preference model and risk preference model.
[0127] Understandably, service collaboration behavior characteristics are a true reflection of users' actual collaborative behavior on the manufacturing service platform. They include the diversity of user participation, the uncertainty of users' service collaboration decisions, the similarity of manufacturing resources, and the coupling of collaborative relationships among multiple users. This information can reflect users' preferences and needs.
[0128] Therefore, by analyzing the characteristics of service collaboration behavior, we can ensure that the model has high accuracy and relevance, and truly reflects the user's perception of utility in actual collaboration scenarios.
[0129] Optionally, the long-term and short-term utility preference model provided in this application can be represented by the following expression;
[0130] -----Formula 1
[0131] in, Indicates the service provider, Indicates the service demander, Indicates the platform operator; Indicates the degree of long-term preference of service providers; This indicates the degree of long-term preference among service users; This indicates the long-term preference of the platform operator; It indicates the short-term, immediate utility of the service provider; This indicates the short-term, immediate utility of the service demander; This indicates the platform operator's short-term immediate utility; This indicates the long-term potential utility of the service provider; This indicates the long-term potential utility of service users; This indicates the long-term potential utility of the platform operator.
[0132] Optionally, the risk preference model provided in this application can be represented by the following expression.
[0133] -----Formula 2
[0134] in, This represents a risk preference model that reflects a user's overall risk attitude; i represents a possible choice the user might make (e.g., "fulfill" or "default"); n represents the total number of all possible choices the user could make (e.g., if there are 2 choices in total, then n is 2). This represents the objective probability of action i occurring; As a weighting function, it can reflect the user's subjective distortion of probability, such as overestimating low probability and underestimating high probability; This represents the subjective perceived utility of the collaborative user's chosen behavior i, which can reflect the user's subjective feelings about gains or losses.
[0135] Optionally, subjective perceived utility can be represented by the following expression:
[0136] -----Formula 3
[0137] in, This represents the subjective perceived utility derived by the collaborating user from choosing behavior i, and is used to measure the subjective perceived utility that the collaborating user gains from choosing this behavior. It indicates the actual objective utility brought about by a collaborative user's choice of a certain action, such as actual gain or loss; η represents the risk sensitivity coefficient, where η<1 indicates risk aversion, η=1 indicates risk neutrality, and η>1 indicates risk aversion. λ represents the loss aversion coefficient, where λ>1 indicates that users react more strongly to losses than to the same amount of gain.
[0138] S203: Based on the characteristics of service collaboration behavior, construct a manufacturing service collaboration delivery scenario for the manufacturing service platform.
[0139] Among them, the collaborative delivery scenarios for manufacturing services include: when the platform operator chooses to supervise, both the service provider and the service requester choose to perform; when the platform operator chooses to supervise, either the service provider or the service requester chooses to breach the contract; when the platform operator does not choose to supervise, both the service provider and the service requester choose to perform; and when the platform operator does not choose to supervise, either the service provider or the service requester chooses to breach the contract.
[0140] Understandably, service collaboration behavior characteristics can reflect users' actual behavioral patterns, preferences, and decision-making logic during platform collaboration. Therefore, by considering service collaboration behavior characteristics, the constructed manufacturing service collaboration delivery scenario can be made closer to reality, providing a reliable basis for the construction of subsequent behavioral evolution game models.
[0141] S204: Based on the service collaboration relationships between users as represented in the manufacturing service collaborative delivery scenario, determine the game participants and game strategy selection of the manufacturing service platform.
[0142] In this context, service collaboration refers to the relationship formed by service providers, service demanders, and platform operators in a manufacturing service collaboration delivery scenario, all centered around a collaborative task. For example, in a component processing manufacturing service collaboration delivery scenario, the component processing enterprise (service provider), the complete machine manufacturer (service demander), and the industrial internet platform (platform operator) jointly form a service collaboration relationship where "the service provider delivers according to the agreement, the service demander pays on time, and the industrial internet platform is responsible for supervising the performance of the agreement."
[0143] The participants in the game include: service providers, service users, and platform operators.
[0144] The choice of game strategy includes, for the service provider, performance behavior and breach of contract behavior. Performance behavior refers to the service provider's choice to complete the service delivery in accordance with the agreement for the collaborative task, while breach of contract behavior refers to the service provider's choice to fail to perform the agreement, terminate or interrupt the service delivery for the collaborative task.
[0145] For service requesters, this includes performance and breach of contract. Performance refers to the service requester's choice to pay the agreed fees and cooperate in completing the collaborative process for the collaborative task, while breach of contract refers to the service requester's choice not to fulfill the agreement, refuse to pay fees, or terminate the collaboration for the collaborative task.
[0146] For platform operators, this includes both regulated and non-regulated behaviors. Regulated behaviors refer to platform operators actively monitoring the service collaboration and delivery process between service providers and service users, while non-regulated behaviors refer to platform operators not monitoring the service collaboration and delivery process between service providers and service users.
[0147] Understandably, the collaborative delivery scenario of manufacturing services can realistically reproduce the collaborative interaction mode of users within the manufacturing service platform. The service collaboration relationship it represents can reflect the role positioning, behavioral logic, and utility relationship between different users in the collaboration process.
[0148] Therefore, by considering this service collaboration relationship, we can avoid the subsequent construction of behavioral evolution game models from deviating from actual business scenarios, and ensure that the division of game participants and the setting of game strategies are consistent with real collaborative behavior.
[0149] S205: Based on the service collaboration behavior and utility relationship between users in the manufacturing service collaborative delivery scenario, and the user preference utility measurement model, calculate the payoff matrix of the game participants.
[0150] In this context, utility relationship refers to the correspondence between the changes in utility of a game participant due to the strategy choices of the game participants in the context of collaborative delivery of manufacturing services, and the mutual influence and correlation formed between these changes and the strategy choices and utility changes of other participants.
[0151] User preference utility measurement models include, but are not limited to: collaborative user behavior, behavioral interactions between users, and interest relationships. Collaborative user behavior refers to the specific actions and decisions made by participating entities such as service providers, service requesters, and platform operators within a manufacturing service platform, regarding fulfillment, breach of contract, supervision, and cooperation related to collaborative tasks. Behavioral interactions between users refer to the interconnected patterns of interaction and mutual influence among the collaborative behaviors of different users within the manufacturing service platform; for example, one party's strategy choice may directly or indirectly trigger behavioral adjustments in another party. Interest relationships between users refer to the corresponding relationships of profit distribution, benefit sharing, and risk sharing formed among different collaborative users during the collaboration process within the manufacturing service platform.
[0152] The purpose of this step is to combine the actual behavioral interaction rules of the manufacturing service collaborative delivery scenario, the utility correlation logic between users, and the quantitative standards of the user preference utility measurement model to calculate the payoff values of game participants under different strategy combinations and construct a complete payoff matrix.
[0153] Optionally, this application may represent utility relationships in the following ways:
[0154] ----Formula 4
[0155] -------Formula 5
[0156] For Formula 4, i represents the user type, which can be a service provider P, a service requester C, or a platform operator O. j represents the source type of utility, corresponding to different utility scenarios. When j=1, it can represent the additional perceived utility brought about by the collaborative relationship between the service provider and the service requester; when j=2, it can represent the additional perceived utility brought about by the user reputation of the transaction object; when j=3, it can represent the additional utility brought about by the service requester's enjoyment of the product / service; when j=4, it can represent the additional utility brought about by positive performance / positive supervision. This represents the probability that the user will choose the corresponding action, with a value of 100%. The probability that a user will not choose the corresponding action is 0%. This represents the user's subjective feeling when they do not choose this action; the value is 0, meaning the user has no additional feelings.
[0157] against This indicates the additional perceived utility that the collaborative relationship between service providers can bring to the service providers.
[0158] against This refers to the additional perceived utility that the user reputation of the trading partner brings to the service provider.
[0159] against This indicates the additional perceived utility that the platform operator's proactive regulatory actions bring to the service provider.
[0160] against This indicates that the collaborative relationship between service providers can bring additional perceived utility to service users.
[0161] against This refers to the additional perceived utility that the user reputation of the trading partner brings to the service requester.
[0162] against This indicates the additional utility that the enjoyment of a product or service brings to the service user.
[0163] against This indicates the additional utility that the platform operator's proactive regulatory actions bring to service users.
[0164] against This indicates the additional utility that collaborative users bring to the platform operator through their active fulfillment of obligations in transactions.
[0165] For Formula 5, i represents the user type, which can be a service provider P, a service requester C, or a platform operator O.
[0166] against This indicates the long-term utility that the service provider's current behavioral choices will bring to it in subsequent manufacturing service collaborations.
[0167] against This indicates the long-term utility that the current behavioral choices of service demanders bring to them in subsequent manufacturing service collaborations.
[0168] against This indicates the long-term utility that the platform operator's current behavioral choices will bring to it in subsequent manufacturing service collaborations.
[0169] Optionally, the game payoff matrix provided in this application includes the following cases:
[0170] In the first scenario, where the platform operator chooses regulation and both service providers and service demanders choose to fulfill their obligations, the game payoff matrix can be:
[0171] ---Formula 6
[0172] In the second scenario, where the platform operator chooses regulation, the service provider chooses fulfillment, and the service demander chooses default, the game payoff matrix can be:
[0173] -----Formula 7
[0174] The third scenario, where the platform operator chooses regulation, the service provider chooses default, and the service demander chooses fulfillment, results in a game payoff matrix that can be:
[0175] ---Formula 8
[0176] Fourthly, in the case where the platform operator chooses regulation, and both the service provider and the service demander choose to default, the game payoff matrix can be:
[0177] -Formula 9
[0178] Fifthly, in the scenario where the platform operator chooses not to regulate, and both service providers and service demanders choose to fulfill their obligations, the game payoff matrix can be:
[0179] ---Formula 10
[0180] The sixth scenario, where the platform operator chooses not to regulate, the service provider chooses to fulfill its obligations, and the service requester chooses to default, results in the following payoff matrix:
[0181] ---Formula 11
[0182] The seventh scenario, where the platform operator chooses not to regulate, the service provider chooses to default, and the service demander chooses to fulfill the obligation, results in the following game payoff matrix:
[0183] ---Formula 12
[0184] The eighth scenario, where the platform operator chooses not to regulate, and the service provider and service demander choose to default, results in a game payoff matrix that can be:
[0185] ---Formula 13
[0186] in, , , These represent the combined subjective perceived utility of service providers, service demanders, and platform operators under different behavioral strategy choices made by collaborative users. , , The long-term preferences of users among service providers, service demanders, and platform operators; This refers to the total service price that the service requester needs to pay to the platform operator and service provider when both the service provider and the service requester actively fulfill their obligations. This indicates the proportion of service prices allocated between the service provider and the platform operator. Between 0 and 1. A portion of the collaborative transaction revenue received by the service provider; This refers to the price at which a service provider sells products or services through offline channels when the service provider intentionally defaults. This refers to the transaction switching costs incurred by a service provider when it initiates a default. The price at which a service requester purchases an alternative product or service through offline channels when the service provider defaults. The transaction switching costs that service requesters must pay when switching transaction channels in the event of a service provider's breach of contract; This refers to the price at which a service requester can purchase similar products or services offline when the service requester defaults on the service. The transaction switching cost that a service requester must pay when switching transaction channels in the event of a service requester's voluntary default. This refers to the price at which a service provider temporarily sells products or services through offline channels when a service consumer defaults on their service request. The transaction switching costs that a service provider must pay to switch transaction channels when a service requester defaults. and The time and communication costs incurred by service providers and service seekers in the early stages of transactions on the platform. Regulatory fees that service providers and service users need to pay to platform operators when platform operators implement regulations. For the regulatory costs incurred by platform operators when implementing regulations, \ Bonuses earned by service providers and service demanders for actively fulfilling their obligations. \ Fines payable by service providers and service users for temporary breach of contract. These refer to the additional perceived utility that the collaborative relationship between service providers can bring to both service providers and service demanders. These refer to the additional perceived utility that the user reputation of the transaction counterpart brings to the service provider and the service demander. The additional utility that the enjoyment of a product or service brings to the service user. The additional utility that collaborative users bring to platform operators through their active fulfillment of obligations in transactions. The additional utility that proactive regulatory actions by platform operators bring to service providers and service seekers. The study examines the long-term utility of the current behavioral choices of three types of collaborative users—service providers, service demanders, and platform operators—in subsequent collaborative manufacturing services.
[0187] S206: Based on the game participants' strategy choices and payoff matrices, establish a replicating dynamic equation set for the game participants' strategy choices. This replicating dynamic equation set is used to simulate the dynamic evolution of the game participants' strategies. The behavioral evolution game model includes: the replicating dynamic equation set for the game participants' strategy choices.
[0188] Understandably, firstly, the strategic choices made by participants in a game can reflect differences in their behavioral decisions in collaborative delivery scenarios, such as service providers choosing to fulfill or breach contracts, service demanders choosing to fulfill or breach contracts, and platform operators choosing to regulate or not regulate.
[0189] Secondly, the payoff matrix can reflect the gains and costs of game participants under different combinations of behavioral choices, clarifying their gains and losses in various strategy combinations.
[0190] Therefore, by comprehensively considering the game participants' strategy choices and payoff matrices, a dynamic equation set replicating the strategy choices of game participants can be constructed. This can realistically simulate the dynamic adjustment process of user strategies in the manufacturing service platform, avoiding evolutionary analysis from deviating from actual payoff-driven behavioral patterns.
[0191] Optionally, the strategy provided in this application selects to replicate the dynamic equations, which can be represented by the following expression:
[0192] ---Formula 14
[0193] in, , , The average payoff for game participants (service providers, service consumers, and platform operators) when implementing performance or regulatory strategies. , , This represents the average payoff for each participant in the game.
[0194] against It can be represented by the following expression:
[0195] ---Formula 15
[0196] in, This represents the average revenue that a service provider receives from choosing to fulfill its obligations. This indicates the probability that a service requester will choose to fulfill the service request. This indicates the probability that a platform operator will choose a regulatory strategy. 1-v represents the overall subjective perceived utility of the service provider's choice to perform the service; 1-v represents the probability that the service requester will choose to default. This represents the overall subjective perceived utility of the service provider's choice of performance behavior; This represents the overall subjective perceived utility of the service provider's choice of performance behavior; This represents the overall subjective perceived utility of a service provider's choice of performance behavior.
[0197] against It can be represented by the following expression:
[0198] ---Formula 16
[0199] in, This represents the average payoff of the service provider during the game; This indicates the probability that the service provider will choose to fulfill the contract. This represents the average revenue that a service provider receives for choosing to fulfill its obligations. This indicates the probability that the service provider will choose to default. This represents the average benefit a service provider receives for choosing to default.
[0200] against It can be represented by the following expression:
[0201] ---Formula 17
[0202] in, This represents the average benefit a service provider receives from choosing to default. This indicates the probability that a service requester will choose to fulfill the service request. This indicates the probability that a platform operator will choose a regulatory strategy. This represents the overall subjective perceived utility of the service provider's choice to engage in breach of contract. This indicates the probability that a service requester will choose to default on their service request. This represents the overall subjective perceived utility of the service provider's choice to engage in breach of contract. This represents the overall subjective perceived utility of the service provider's choice to engage in breach of contract. This represents the overall subjective perceived utility of a service provider's choice to engage in breach of contract.
[0203] against It can be represented by the following expression;
[0204] ---Formula 18
[0205] in, This represents the average benefit received by service requesters when choosing to fulfill their service requests. This indicates the probability that the service provider will choose to fulfill the contract. This indicates the probability that a platform operator will choose regulatory action; This represents the comprehensive subjective perceived utility of the service requester when choosing to fulfill the service request. This indicates the probability that the service provider will choose to default. This represents the overall subjective perceived utility of service demanders when choosing to fulfill their obligations. This represents the overall subjective perceived utility of service demanders when choosing to fulfill their obligations. This indicates the probability that a platform operator will choose not to regulate the behavior. This indicates the perceived utility of platform operators choosing not to regulate certain behaviors.
[0206] against It can be represented by the following expression:
[0207] ---Formula 19
[0208] in, This represents the average payoff of service demanders during the game process; This indicates the probability that a service requester will choose to fulfill the service request. This represents the average benefit received by service requesters when choosing to fulfill their service requests. This indicates the probability that a service requester will choose to default on their service request. This represents the average benefit received by service demanders who choose to default.
[0209] against It can be represented by the following expression:
[0210] ---Formula 20
[0211] in, This represents the average benefit received by service demanders who choose to default. This indicates the probability that the service provider will choose to fulfill the contract. This indicates the probability that a platform operator will choose regulatory action; This represents the overall subjective perceived utility of a service requester choosing to breach a contract. This indicates the probability that the service provider will choose to default. This represents the overall subjective perceived utility of a service requester choosing to breach a contract. This indicates the probability that a platform operator will choose not to regulate the behavior. This represents the overall subjective perceived utility of a service requester choosing to breach a contract. This represents the overall perceived utility of service demanders when choosing to breach contracts.
[0212] against It can be represented by the following expression:
[0213] ---Formula 21
[0214] in, This represents the average benefit that platform operators receive when choosing regulatory actions; This indicates the probability that the service provider will choose to fulfill the contract. This indicates the probability that a service requester will choose to fulfill the service request. Platform operators' perception of the overall effectiveness of choosing regulatory oversight; This indicates the probability that the service provider will choose to default. This represents the overall perceived utility of platform operators in choosing regulatory actions; This indicates the probability that a service requester will choose to default on their service request. This represents the overall perceived utility of platform operators in choosing regulatory actions; This indicates the overall perceived utility of platform operators' choices regarding regulatory actions.
[0215] against It can be represented by the following expression:
[0216] ---Formula 22
[0217] in, This represents the average payoff for the platform operator during the game. This indicates the probability that a platform operator will choose regulatory action; This represents the average benefit that platform operators receive when choosing regulatory actions; This indicates the probability that a platform operator will choose not to regulate the behavior. This represents the average revenue that platform operators receive when choosing not to regulate.
[0218] against It can be represented by the following expression:
[0219] ---Formula 23
[0220] in, This represents the average revenue that platform operators receive when choosing not to regulate their operations. This indicates the probability that the service provider will choose to fulfill the contract. This indicates the probability that a service requester will choose to fulfill the service request. This indicates the perceived utility of platform operators choosing to remain unregulated; This indicates the probability that the service provider will choose to default. This represents the overall perceived utility of platform operators choosing not to regulate certain behaviors; This refers to the regulatory fees that service providers and service users need to pay to platform operators when platform operators implement regulations; This indicates the probability that a service requester will choose to default on their service request. This represents the overall perceived utility of platform operators choosing not to regulate certain behaviors; This indicates the perceived utility of platform operators choosing not to regulate certain behaviors.
[0221] S207: Based on the strategy choices of game participants, replicate the dynamic equations to calculate the strategy evolution equilibrium point of game participants.
[0222] In this context, the strategy evolution equilibrium point refers to the stable state reached during the evolutionary game process when the probability of game participants choosing each strategy no longer changes over time. At this point, the strategy adjustment speed of all participants is zero, and the distribution of group strategies enters dynamic equilibrium, no longer spontaneously changing. Each strategy evolution equilibrium point is represented by a triple (u,v,w), corresponding to the probability of the service provider, service demander, and platform operator choosing the "performance / regulation" strategy, respectively. The set {(0,0,0),(1,0,0),(0,1,0),(0,0,1),(1,1,0),(1,0,1),(0,1,1),(1,1,1)} represents the equilibrium state under all extreme strategy combinations.
[0223] The purpose of this step is to find the equilibrium point of all strategies in the game process by solving the dynamic equations of the strategy selection replication, thereby determining the stable evolution trend of multi-user collaborative strategies in the manufacturing service platform.
[0224] S208: Based on the evolutionary equilibrium point of the game participants' strategies, obtain the stable evolutionary game strategies of the game participants.
[0225] Among them, the stable strategy in evolutionary game refers to a stable state that is eventually reached in the process of strategy evolution of game participants through repeated games and adaptations. In this state, the participants cannot obtain higher returns by unilaterally changing their strategies, thus forming an equilibrium cooperative or competitive relationship.
[0226] The purpose of this step is to extract the evolutionary stable strategies of the game participants based on their strategy evolution equilibrium points.
[0227] Understandably, a strategy evolution equilibrium point only represents a static state where the rate of change of strategy is zero during the game, but not all equilibrium points are resistant to disturbances. Some equilibrium points will cause participants to deviate from their state when faced with small policy changes.
[0228] Therefore, by analyzing the evolutionary equilibrium points of the game participants' strategies, we can identify stable strategies in the evolutionary game and eliminate those unstable equilibrium points, thereby deriving a strategy combination that can maintain stability.
[0229] Optionally, this application provides a possible implementation, including:
[0230] The first step is to calculate the eigenvalues of the Jacobian matrix at the policy evolution equilibrium point.
[0231] Understandably, in evolutionary game theory, the strategy evolution equilibrium point only describes the relatively stable state of the players' strategies at a certain moment. However, real-world games are influenced by various factors, causing minor changes in the players' strategies. The Jacobian matrix can be used to analyze the impact of these minor changes on the game process.
[0232] Therefore, by calculating the Jacobian matrix at the policy evolution equilibrium point, the eigenvalues of that equilibrium point can be obtained, thus providing a basis for subsequently judging the stability of the policy evolution equilibrium point.
[0233] Optionally, the Jacobian matrix provided in this application can be represented in the following way:
[0234] ---Formula 24
[0235] in, Represents the Jacobian matrix. Represents the replication dynamic equations of the service provider; The replication dynamic equation representing the service demander; Represents the replication dynamic equation of the platform operator; Indicates the rate of change in the service provider's strategy. According to its own strategy probability Sensitivity to change; Indicates the rate of change in the service provider's strategy. Service demander strategy probability Sensitivity to change; Indicates the rate of change in the service provider's strategy. Probability of platform operator strategy Sensitivity to change; Indicates the rate of change in service demanders' strategies Probability of service provider strategy Sensitivity to change; Indicates the rate of change in service demanders' strategies According to its own strategy probability Sensitivity to change; Indicates the rate of change in service demanders' strategies Probability of platform operator strategy Sensitivity to change; Indicates the platform operator's strategy change rate Probability of service provider strategy Sensitivity to change; Indicates the rate of change in the platform operator's strategy. Service demander strategy probability Sensitivity to change; Indicates the rate of change in the platform operator's strategy. According to its own strategy probability Sensitivity to change.
[0236] The second step involves analyzing the global stability of game participants at the strategy evolution equilibrium point based on eigenvalue analysis, yielding the first analysis result.
[0237] The first analytical result refers to the conclusion regarding whether each equilibrium point possesses global stability, obtained by analyzing the eigenvalues of the Jacobian matrix at each strategy evolution equilibrium point. The first analytical result includes, but is not limited to, the stability type of each equilibrium point (e.g., stable, unstable, saddle point, etc.) and the corresponding eigenvalue sign distribution.
[0238] Understandably, the eigenvalues of the Jacobian matrix can reflect the dynamic trend of policy evolution near the equilibrium point: when the eigenvalue is negative, it corresponds to the policy's tendency to converge toward the equilibrium point; when the eigenvalue is positive, it corresponds to the policy's tendency to diverge from the equilibrium point.
[0239] Therefore, by analyzing the eigenvalues at each equilibrium point, it is possible to determine whether each equilibrium point possesses global stability, avoiding errors caused by subjective judgment and ensuring that the selected stable strategies can truly reflect the collaborative evolution of the manufacturing service platform.
[0240] The third step is to obtain the evolutionary game-stable strategies of the game participants based on the results of the first analysis.
[0241] Understandably, the first analysis clearly defined the stability attributes of each policy evolution equilibrium point, identifying which equilibrium points are resistant to disturbances and which are susceptible to policy mutations. Therefore, by considering these analysis results, unstable equilibrium points can be removed, while stable ones can be retained, resulting in a policy combination that maintains stability.
[0242] S209: Based on evolutionary game-theoretic stable strategies, construct service collaboration strategies for manufacturing service platforms.
[0243] Optionally, this application provides a possible implementation, including:
[0244] The first step is to obtain the behavioral evolution trends of game participants under different service collaboration influencing factors based on the stable strategy of evolutionary game.
[0245] Understandably, firstly, evolutionary game-based stable strategies can reflect the optimal behavioral choices that participants can achieve in long-term interactions. Secondly, factors influencing service collaboration can include a variety of factors, such as users' long-term preferences, which directly affect participants' decisions and strategy choices.
[0246] Therefore, by selecting stable evolutionary game strategies and combining them with various service collaboration influencing factors in the manufacturing service scenario, we can obtain the behavioral evolution trends of game participants under the influence of different influencing factors.
[0247] The second step is to determine the second analytical result of the behavioral evolution of the game participants based on the behavioral evolution trend of the game participants.
[0248] The second analysis result is used to indicate the final behavior of game participants under the influence of different service collaboration factors. For example, service providers tend to choose performance strategies, service demanders will prioritize trustworthy strategies, and platform operators will dynamically adjust the intensity of supervision based on the behavior of both supply and demand sides.
[0249] Understandably, the behavioral evolution trend of game participants can reflect the dynamic process of their choices changing over time or under different service collaboration influencing factors. This trend can demonstrate how participants adjust their strategies in long-term interactions to adapt to changes in the external environment and the reactions of other participants.
[0250] Therefore, by considering the behavioral evolution trends of game participants, we can better understand their final behavioral performance under the influence of different service collaboration factors.
[0251] The third step is to construct a service collaboration strategy for the manufacturing service platform based on the results of the second analysis.
[0252] The purpose of this step is to develop a service collaboration strategy suitable for the manufacturing service platform.
[0253] Understandably, the second analysis results can clearly define the final behavioral performance of the game participants under different service collaboration influencing factors. Therefore, constructing a service collaboration strategy for the manufacturing service platform based on the second analysis results can ensure that the generated strategy matches the behavioral characteristics of the game participants, thereby formulating a targeted collaboration strategy and effectively guiding all participants to converge toward the optimal collaboration state.
[0254] Optionally, the service collaboration factors provided in this application include at least one of the following:
[0255] The impact of the user's initial fulfillment probability and the manufacturing service platform's initial regulatory probability on behavioral evolution.
[0256] The initial probability of fulfillment refers to the likelihood that a user will fulfill their commitment when joining the manufacturing service platform. A higher initial probability of fulfillment indicates a greater likelihood of fulfillment; conversely, a lower initial probability of fulfillment indicates a lower likelihood of fulfillment.
[0257] The initial regulatory probability of a manufacturing service platform refers to the likelihood that the platform will monitor the behavior of participants. A higher initial regulatory probability indicates a greater likelihood of the platform monitoring participant behavior, and vice versa.
[0258] Understandably, a higher initial probability of user fulfillment indicates that users are more likely to keep their promises, thereby promoting the establishment of cooperative relationships; a higher initial probability of regulatory oversight by the manufacturing service platform indicates that the manufacturing service platform is more likely to regulate the behavior of users within the platform.
[0259] Therefore, by comprehensively considering the user's initial fulfillment probability and the manufacturing service platform's initial regulatory probability, the risk of default can be effectively reduced, the efficiency of cooperation can be improved, and this will help to build a more stable cooperative environment in service collaboration and delivery scenarios.
[0260] The impact of long-term user preferences on behavioral evolution.
[0261] Among them, the degree of long-term user preference can reflect the user's consistent preference and choice tendency for a specific service or product over a certain period of time.
[0262] Understandably, long-term user preferences are stable behavioral tendencies formed based on factors such as users' collaborative experiences and service experiences. When a user has a high long-term preference for a certain service model, it indicates that the user is more inclined to continuously choose the corresponding collaborative strategy or partner. Therefore, the degree of a user's long-term preference can influence the evolution of their own and related participants' game behavior.
[0263] The impact of long-term user utility on behavioral evolution.
[0264] Among them, long-term user utility refers to the utility that users obtain during the process of using the service.
[0265] Understandably, long-term user utility is the comprehensive value that a user gains from continuous service collaboration, including economic benefits, reputation enhancement, and long-term cooperation opportunities. When a user's long-term utility is high, it indicates that the user obtains more utility during the service collaboration process. Therefore, a user's long-term utility can influence the evolution of their own and related participants' game behavior.
[0266] S210: Based on the service collaboration strategy, process the service collaboration tasks on the manufacturing service platform.
[0267] The explanation of step S210 can be found in the explanation of the above embodiments, and will not be repeated here.
[0268] The task processing method for manufacturing service platforms provided in this embodiment first analyzes the user collaboration characteristics of the manufacturing service platform to obtain service collaboration behavior features. Then, based on these features, it constructs a user preference utility measurement model and a manufacturing service collaboration delivery scenario to determine the game participants and strategies. Combining the user preference utility measurement model, it calculates the payoff matrix, establishes a strategy selection replication dynamic equation system, solves the strategy evolution equilibrium point to obtain the evolutionary game stable strategy, and then constructs a service collaboration strategy to process platform service collaboration tasks.
[0269] This method formulates service collaboration strategies by constructing a behavioral evolution game model and obtaining stable strategies. It can capture the dynamic changes of user behavior in complex and ever-changing environments in real time and flexibly adjust the service collaboration strategies according to the changes, ensuring that the strategies continuously match the actual needs of users. This solves the problem that existing static matching strategies cannot respond to dynamic changes of users and are difficult to achieve dynamic task matching, effectively enhancing the overall service capabilities of the manufacturing service platform.
[0270] Figure 3 A schematic diagram of the task processing device for a manufacturing service platform provided in this application. Figure 3 As shown, this application provides a task processing apparatus for a manufacturing service platform. The task processing apparatus 300 for a manufacturing service platform includes:
[0271] Module 301 is used to acquire the service collaboration behavior characteristics of multiple users on the manufacturing service platform and the user preference utility measurement model.
[0272] Module 302 is established to build a behavioral evolution game model for the manufacturing service platform based on service collaboration behavior characteristics and user preference utility measurement model.
[0273] The acquisition module 301 is used to acquire the evolutionary game stable strategy of the manufacturing service platform based on the behavioral evolutionary game model. The evolutionary game stable strategy keeps the service collaboration behavior of the manufacturing service platform in a stable state.
[0274] Module 303 is also used to construct service collaboration strategies for the manufacturing service platform based on evolutionary game-based stable strategies.
[0275] The processing module 304 is used to process service collaboration tasks on the manufacturing service platform based on the service collaboration strategy.
[0276] Optionally, the acquisition module 301 is also used to analyze the user collaboration characteristics of the manufacturing service platform and acquire service collaboration behavior characteristics.
[0277] Module 303 is specifically used to build a user preference utility measurement model based on service collaboration behavior characteristics. The user preference utility measurement model is used for comprehensive utility perception evaluation of differentiated user behavior preferences. The user preference utility measurement model includes: long-term and short-term utility preference model and risk preference model.
[0278] Optionally, module 303 is also used to construct a manufacturing service collaboration delivery scenario for the manufacturing service platform based on service collaboration behavior characteristics.
[0279] The device also includes: a determining module 304;
[0280] The determination module 304 is used to determine the game participants and game strategy selection of the manufacturing service platform based on the service collaboration relationship between users represented in the manufacturing service collaborative delivery scenario.
[0281] The device also includes: a computing module 305;
[0282] The calculation module 305 is used to calculate the payoff matrix of game participants based on the service collaboration behavior and utility relationship between users in the manufacturing service collaborative delivery scenario, as well as the user preference utility measurement model.
[0283] Module 302 is specifically used to establish a dynamic equation set for the strategy selection of game participants based on their strategy selection and payoff matrix. This dynamic equation set is used to simulate the dynamic evolution of the strategies of game participants.
[0284] Optionally, the calculation module 305 is also used to replicate the dynamic equations based on the strategy choices of the game participants, and to calculate the strategy evolution equilibrium point of the game participants.
[0285] The acquisition module 301 is specifically used to acquire the evolutionary stable strategy of the game participants based on the strategy evolution equilibrium point of the game participants.
[0286] Optionally, the computation module 305 is also used to compute the eigenvalues of the Jacobian matrix at the policy evolution equilibrium point;
[0287] The device also includes: analysis module 306;
[0288] Analysis module 306 is used to analyze the global stability of game participants at the strategy evolution equilibrium point based on eigenvalue analysis to obtain the first analysis result;
[0289] The acquisition module 301 is specifically used to acquire the evolutionary stable strategy of the game participants based on the first analysis result.
[0290] Optionally, the acquisition module 301 is also used to acquire the behavioral evolution trend of game participants under different service collaboration influencing factors based on the evolutionary game stable strategy;
[0291] The determination module 304 is also used to determine the second analysis result of the behavioral evolution of the game participants based on the behavioral evolution trend of the game participants;
[0292] Module 303 is specifically used to construct a service collaboration strategy for the manufacturing service platform based on the second analysis results.
[0293] Optionally, service collaboration influencing factors include at least one of the following:
[0294] The impact of the user's initial fulfillment probability and the manufacturing service platform's initial regulatory probability on behavioral evolution;
[0295] The impact of long-term user preferences on behavioral evolution;
[0296] The impact of long-term user utility on behavioral evolution.
[0297] Figure 4 A schematic diagram of the structure of the task processing equipment for the manufacturing service platform provided in this application. Figure 4 As shown, this application provides a task processing device for a manufacturing service platform. The task processing device 400 for the manufacturing service platform includes: a receiver 401, a transmitter 402, a processor 403, and a memory 404.
[0298] Receiver 401 is used to receive instructions and data;
[0299] Transmitter 402 is used to send commands and data;
[0300] Memory 404 is used to store instructions executed by the computer;
[0301] Processor 403 is used to execute computer execution instructions stored in memory 404 to implement the various steps of the task processing method for a manufacturing service platform in the above embodiments. For details, please refer to the relevant descriptions in the foregoing embodiments of the task processing method for a manufacturing service platform.
[0302] Optionally, the memory 404 can be either standalone or integrated with the processor 403.
[0303] When the memory 404 is set up independently, the electronic device also includes a bus for connecting the memory 404 and the processor 403.
[0304] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the task processing method for a manufacturing service platform as described above, performed by the task processing device for a manufacturing service platform.
[0305] It will be understood by those skilled in the art that all or some of the steps, systems, or apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software may be distributed on a computer-readable medium, which may include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.
[0306] The technical solutions of this application have been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it is readily understood by those skilled in the art that the scope of protection of this application is obviously not limited to these specific embodiments. The above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.
Claims
1. A task processing method for a manufacturing service platform, characterized in that, include: To obtain the service collaboration behavior characteristics of multiple users on the manufacturing service platform and the user preference utility measurement model; Based on the service collaboration behavior characteristics and the user preference utility measurement model, a behavioral evolution game model of the manufacturing service platform is established. Based on the behavioral evolution game model, the evolution game stable strategy of the manufacturing service platform is obtained, and the evolution game stable strategy keeps the service collaboration behavior of the manufacturing service platform in a stable state. Based on the evolutionary game-theoretic stable strategy, a service collaboration strategy for the manufacturing service platform is constructed. Based on the service collaboration strategy, service collaboration tasks on the manufacturing service platform are processed.
2. The method according to claim 1, characterized in that, The multi-user service collaboration behavior characteristics and user preference utility measurement model of the acquisition manufacturing service platform include: Analyze the user collaboration characteristics of the manufacturing service platform to obtain the service collaboration behavior characteristics; Based on the service collaboration behavior characteristics, the user preference utility measurement model is constructed; the user preference utility measurement model is used for comprehensive utility perception evaluation oriented towards user differentiated behavioral preferences; the user preference utility measurement model includes: long-term and short-term utility preference model and risk preference model.
3. The method according to claim 2, characterized in that, The behavioral evolutionary game model includes: a dynamic equation set for replicating the strategy choices of game participants; the behavioral evolutionary game model of the manufacturing service platform, established based on the service collaboration behavior characteristics and the user preference utility measurement model, includes: Based on the service collaboration behavior characteristics, a manufacturing service collaboration delivery scenario for the manufacturing service platform is constructed. Based on the service collaboration relationships between users as represented in the manufacturing service collaborative delivery scenario, the game participants and game strategy selection of the manufacturing service platform are determined. Based on the service collaboration behavior and utility relationship between users as represented in the manufacturing service collaborative delivery scenario, and the user preference utility measurement model, the payoff matrix of the game participants is calculated. Based on the game participants' strategy choices and payoff matrices, a replicating dynamic equation set for the game participants' strategy choices is established. This replicating dynamic equation set is used to simulate the dynamic evolution process of the game participants' strategies.
4. The method according to claim 3, characterized in that, The step of obtaining the evolutionary game-stable strategy of the manufacturing service platform based on the behavioral evolutionary game model includes: Based on the strategy choices of the game participants, the dynamic equation system is replicated to calculate the strategy evolution equilibrium point of the game participants. Based on the strategy evolution equilibrium points of the game participants, the evolutionary stable strategy of the game participants is obtained.
5. The method according to claim 4, characterized in that, The step of obtaining the evolutionary stable strategy of the game participants based on their strategy evolution equilibrium points includes: Calculate the eigenvalues of the Jacobian matrix at the equilibrium point of the strategy evolution; Based on the eigenvalue analysis, the global stability of the game participants at the strategy evolution equilibrium point is obtained, yielding the first analysis result; Based on the first analysis results, the evolutionary game-stable strategies of the game participants are obtained.
6. The method according to claim 5, characterized in that, The service collaboration strategy for the manufacturing service platform, based on the evolutionary game-theoretic stable strategy, includes: Based on the aforementioned evolutionary game stability strategy, the behavioral evolution trend of game participants under different service collaboration influencing factors is obtained; Based on the behavioral evolution trends of the game participants, a second analytical result of the behavioral evolution of the game participants is determined; Based on the second analysis results, a service collaboration strategy for the manufacturing service platform is constructed.
7. The method according to claim 6, characterized in that, The factors influencing service collaboration include at least one of the following: The impact of the user's initial fulfillment probability and the manufacturing service platform's initial supervision probability on behavioral evolution; The impact of long-term user preferences on behavioral evolution; The impact of long-term user utility on behavioral evolution.
8. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-7.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-7.
10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-7.
