Cooperative processing method, apparatus, device, and readable storage medium

Abstract

The application provides a cooperation processing method, device and equipment and a readable storage medium. The method comprises the following steps: obtaining a first cooperation ratio of a cooperation group in a tth time unit, the cooperation group comprising a first participant and a second participant cooperating with the first participant; obtaining contract parameter information of a smart contract relative to the first participant in the tth time unit; determining first income information and second income information in the tth time unit based on the first cooperation ratio and the contract parameter information; and determining a cooperation trend of the cooperation group in the tth time unit based on the first income information and the second income information, the cooperation trend being used to determine the contract parameter information of the smart contract relative to the first participant in a t+1th time unit. The application can automatically regulate the contract parameter information of the smart contract through the cooperation trend, thereby realizing automatic cooperation regulation.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a cooperative processing method, apparatus, device, and readable storage medium. Background Technology

[0002] Currently, SMEs typically employ traditional contractual models for cooperation management in supply chain collaboration, industry alliances, and platform-based transactions. The establishment of cooperative intentions relies on rules based on offline negotiations, platform settings, or historical transaction records. Transaction execution is managed through a centralized system. In terms of behavioral analysis, some studies use static game theory models to establish a framework for predicting inter-firm cooperation intentions. Participants are usually modeled as perfectly rational actors, and the Nash equilibrium point is derived by analyzing the static payoff matrix as the basis for cooperation decisions. This approach utilizes automated cooperation control to ensure stable and orderly cooperation among enterprises. Summary of the Invention

[0003] This application provides a cooperative processing method, apparatus, device, and readable storage medium, which can solve the technical problem of low intelligence in cooperative regulation in related technologies.

[0004] In a first aspect, embodiments of this application provide a cooperative processing method, the method comprising:

[0005] Obtain the first cooperation ratio among the cooperative groups that cooperate with the first participating entity within the t-th time unit, where the cooperative group includes the first participating entity and the second participating entity that cooperates with the first participating entity, and t is a positive integer;

[0006] Obtain the contract parameter information of the smart contract relative to the first participating entity within the t-th time unit. The smart contract is used to execute the cooperation between the first participating entity and the second participating entity. The contract parameter information is used to reflect the behavior of the cooperative group cooperating with the first participating entity.

[0007] Based on the first cooperation ratio and the contract parameter information, the first revenue information and the second revenue information within the t-th time unit are determined. The first revenue information indicates the expected revenue of the cooperative group relative to the first participating entity's choice of cooperation strategy, and the second revenue information indicates the average revenue of the cooperative group.

[0008] Based on the first and second revenue information, the cooperation trend of the cooperative group relative to the first participating entity in choosing a cooperation strategy is determined within the t-th time unit. The cooperation trend is used to determine the contract parameter information relative to the first participating entity within the (t+1)-th time unit.

[0009] Secondly, embodiments of this application provide a cooperative processing apparatus, the apparatus comprising:

[0010] The first acquisition module is used to acquire the first cooperation ratio selected from the cooperative group to cooperate with the first participating entity within the t-th time unit. The cooperative group includes the first participating entity and the second participating entity cooperating with the first participating entity, where t is a positive integer.

[0011] The second acquisition module is used to acquire contract parameter information of the smart contract relative to the first participating entity within the t-th time unit. The smart contract is used to execute the cooperation between the first participating entity and the second participating entity. The contract parameter information is used to reflect the behavior of the cooperative group cooperating with the first participating entity.

[0012] The first determining module is used to determine the first revenue information and the second revenue information within the t-th time unit based on the first cooperation ratio and the contract parameter information. The first revenue information indicates the expected revenue of the cooperative group relative to the cooperation strategy chosen by the first participating entity, and the second revenue information indicates the average revenue of the cooperative group.

[0013] The second determining module is used to determine the cooperation trend of the cooperative group relative to the first participating entity in choosing a cooperation strategy within the t-th time unit based on the first revenue information and the second revenue information. The cooperation trend is used to determine the contract parameter information relative to the first participating entity within the (t+1)-th time unit.

[0014] Thirdly, embodiments of this application provide an electronic device, including: a processor, a memory, and a program stored in the memory and executable on the processor, wherein when the program is executed by the processor, it implements the steps of the cooperative processing method as described in the first aspect.

[0015] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the cooperative processing method as described in the first aspect.

[0016] Fifthly, embodiments of this application provide a computer program product including computer instructions that, when executed by a processor, implement the steps of the cooperative processing method as described in the first aspect.

[0017] In this embodiment, the following steps are taken: First, a cooperation ratio is obtained within the t-th time unit from which a cooperative group selects a first participating entity to cooperate with. The cooperative group includes the first participating entity and a second participating entity cooperating with the first participating entity. Contract parameter information of the smart contract relative to the first participating entity is obtained within the t-th time unit. The smart contract executes the cooperation between the first and second participating entities, and the contract parameter information reflects the cooperative group's behavior in cooperating with the first participating entity. Based on the first cooperation ratio and the contract parameter information, first and second revenue information are determined within the t-th time unit. The first revenue information indicates the expected revenue of the cooperative group relative to the first participating entity's chosen cooperation strategy, and the second revenue information indicates the average revenue of the cooperative group. Based on the first and second revenue information, a cooperation trend is determined within the cooperative group relative to the first participating entity's chosen cooperation strategy within the t-th time unit. This cooperation trend is used to determine the contract parameter information relative to the first participating entity within the (t+1)-th time unit. In this way, by modeling the expected returns in a cooperative group and determining the cooperation trend based on the expected returns, the participants in the cooperative group can adjust their behavioral tendencies according to the current strategic benefit advantage under bounded rationality. For example, if the expected returns brought by the cooperative strategy are greater than those of the non-cooperative strategy, the proportion of the cooperative group choosing the cooperative strategy will gradually increase; if the expected returns brought by the cooperative strategy are less than those of the non-cooperative strategy, the proportion of the cooperative group choosing the cooperative strategy will gradually decrease until an evolutionary stability may be reached. Accordingly, this cooperation trend can be used to characterize the behavioral evolution path of the participants and provide a quantitative basis for setting the incentive mechanism of smart contracts, so as to automatically regulate the contract parameter information of smart contracts and ensure that enterprise cooperation proceeds in a stable and orderly manner. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart of a cooperative processing method provided in an embodiment of this application;

[0020] Figure 2 This is a schematic diagram illustrating the behavioral evolution path of strategy selection within a simulated cooperative group;

[0021] Figure 3 It is a flowchart illustrating the evolution of cooperation trends;

[0022] Figure 4 This is a schematic diagram of the execution flow of a smart contract instance;

[0023] Figure 5 This is a diagram illustrating the core states of a smart contract during its lifecycle and the transition paths between those states.

[0024] Figure 6 This is a weight distribution diagram of the influencing factors;

[0025] Figure 7 This is a graph showing the evolution trend of trust factors under different weighting mechanisms;

[0026] Figure 8 This is a schematic diagram illustrating the dynamic changes in the weights of key factors under an adaptive mechanism;

[0027] Figure 9 This is a schematic diagram of the system's operating logic;

[0028] Figure 10 This is a flowchart of a specific example of a cooperative processing method in an embodiment of this application;

[0029] Figure 11 This is a schematic diagram of the structure of a cooperative processing device provided in an embodiment of this application;

[0030] Figure 12 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0031] The technical solutions of the embodiments 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.

[0032] First, let's introduce the technical background of the embodiments of this application.

[0033] Currently, SMEs typically employ traditional contractual models for cooperation and management in supply chain collaboration, industry alliances, and platform-based transactions. The establishment of cooperation intentions relies on rules based on offline negotiations, platform settings, or historical transaction records, while transaction execution is managed through a centralized system.

[0034] In terms of behavioral analysis, some studies use static game models to establish a framework for predicting the willingness of firms to cooperate. The participants are usually modeled as perfectly rational participants, and the Nash equilibrium point is obtained by analyzing the static payoff matrix as the basis for determining cooperation.

[0035] Smart contracts, as an automated execution tool, have been applied in scenarios such as logistics tracking, financial leasing, and accounts receivable confirmation. Contract terms are primarily set through pre-designed rules, including penalties for breach of contract and incentives for performance, and rely on blockchain technology to ensure contract immutability and information traceability.

[0036] Some systems incorporate reputation assessment models or mechanisms to dynamically score partners, creating a chain of incentives and constraints. In data-driven management systems, behavioral trajectories are used to train classifiers to determine whether a partner should be added to a whitelist.

[0037] In terms of strategy evolution modeling, some studies have attempted to apply strategy optimization tools to the inter-firm interaction modeling process, employing simulation-based multi-round interaction simulations to evaluate cooperation stability. The feedback mechanism for contract performance behavior primarily uses static data updates for state adjustments, with the participants' decision-making strategies being revised or iterated in subsequent cycles.

[0038] In existing research, behavioral decision-making modeling is typically based on regression modeling or supervised learning training using data within a fixed time window, with the model structure remaining unchanged during execution. Contract incentive mechanisms are set before contract signing, and strategy adjustments and changes in game behavior during contract execution are not dynamically incorporated.

[0039] It can be seen that the relevant technologies have the following technical drawbacks.

[0040] (1) There is a lack of modeling mechanism for the dynamic changes in the behavior strategies of small and medium-sized enterprises.

[0041] Existing models mostly employ static game analysis or one-time rule setting, which cannot reflect the strategy evolution process of SMEs in different cooperation cycles and are difficult to capture the changes in cooperation status caused by their bounded rationality and learning behavior.

[0042] (2) The smart contract mechanism is not deeply integrated with enterprise behavior feedback.

[0043] In most applications, smart contract terms are set in a fixed format and lack the ability to be dynamically adjusted based on the company's historical performance or interaction data. The contract incentive and penalty mechanisms cannot adapt to the risk changes brought about by the evolution of strategies.

[0044] (3) The factors for modeling the willingness to cooperate are too simple, and the trust mechanism lacks evolutionary expression.

[0045] In related studies, the decision to cooperate or not is often based on simplified reputation or rating mechanisms, neglecting the formation process of trust between firms and its impact on the stability of long-term cooperation. This makes it difficult to support the simulation of paths to cooperation breakdown or repair. Some models use information gain or variance screening methods to select variables, which fails to reflect the nonlinear dependencies between variables and may miss feature combinations that significantly affect the prediction results.

[0046] Based on this, the embodiments of this application provide a new cooperative processing method, which aims to solve the following technical problems.

[0047] (1) Construct an analytical model that can simulate the dynamic evolution of corporate behavior strategies, and support the modeling and prediction of the changes in the cooperation ratio in multiple rounds of interaction under the assumption of bounded rationality.

[0048] (2) Design a smart contract structure that integrates behavioral feedback and trust parameters, i.e., trust factor adjustment mechanism, so that the contract terms can be dynamically modified according to the game results during the execution process, thereby improving the contract adaptability and performance efficiency.

[0049] (3) Establish a trust evolution mechanism driven by multi-dimensional cooperation factors, namely influencing factors, and integrate variables such as economic benefits, performance history, and interaction frequency to achieve a comprehensive assessment and evolution simulation of the long-term cooperation stability of SMEs.

[0050] See Figure 1 , Figure 1 This is a flowchart of a cooperative processing method provided in an embodiment of this application, such as... Figure 1 As shown, the method includes the following steps:

[0051] Step 101: Obtain the first cooperation ratio selected from the cooperative groups within the t-th time unit to cooperate with the first participating entity. The cooperative group includes the first participating entity and the second participating entity cooperating with the first participating entity, where t is a positive integer.

[0052] Step 102: Obtain the contract parameter information of the smart contract relative to the first participating entity within the t-th time unit. The smart contract is used to execute the cooperation between the first participating entity and the second participating entity. The contract parameter information is used to reflect the behavior of the cooperative group cooperating with the first participating entity.

[0053] Step 103: Based on the first cooperation ratio and the contract parameter information, determine the first revenue information and the second revenue information within the t-th time unit. The first revenue information indicates the expected revenue of the cooperative group relative to the first participating entity in choosing a cooperation strategy, and the second revenue information indicates the average revenue of the cooperative group.

[0054] Step 104: Based on the first revenue information and the second revenue information, determine the cooperation trend of the cooperative group relative to the first participating entity in choosing a cooperation strategy within the t-th time unit. The cooperation trend is used to determine the contract parameter information relative to the first participating entity within the (t+1)-th time unit.

[0055] It should be noted that the embodiments of this application involve technologies such as artificial intelligence and security, and are applied to a collaborative processing device. This device may include multiple functional modules to interactively implement the collaborative processing method of the embodiments of this application.

[0056] In step 101, the cooperative group refers to the group under the supply chain, which may include at least two participating entities. These participating entities may be enterprises or individuals, without specific limitations.

[0057] The cooperative group can include a first participating entity and a second participating entity. The first participating entity can act as the purchaser in the supply chain, while the second participating entity can act as the supplier in the supply chain.

[0058] In some embodiments, the number of second participating entities may include at least one; the second participating entities will be described as a whole in the following description.

[0059] Specifically, a game theory model can be constructed, where participating entities act as players, choosing between a cooperative or defective strategy in each round of interaction based on historical records and expectations of each other's behavior. A smart contract automatically executes the cooperation agreement signed by both parties, including defined reward or penalty mechanisms, thereby determining the expected payoff for the cooperative group. The contract parameters of the smart contract are updated based on the cooperation trend determined by the expected payoff, and this information is fed back to the game theory model. By evolving the cooperation trend of the cooperative group in choosing a cooperative strategy, the model influences the evolutionary path of the next round's strategy.

[0060] In some embodiments, the game model may include two players. and Let represent the first participant and the second participant, respectively. In each round of the game, each party can choose one of two strategies: a cooperative strategy or a non-cooperative strategy, denoted by (Cooperate, C) and (Defect, D), respectively. Cooperation means fulfilling the terms of the smart contract and performing cooperative actions according to the agreement; non-cooperation means refusing to fulfill the contract, delaying delivery, or breaching the contract.

[0061] In the initial stage of the game, let... This indicates the selection of game participants within a cooperative group. The first cooperation ratio, This indicates the selection of game participants within a cooperative group. The proportion of non-cooperation to cooperation; This indicates the selection of game participants within a cooperative group. Choose the second cooperation ratio. This indicates the selection of game participants within a cooperative group. Choose the proportion of cooperation that does not involve cooperation. The strategy space for the game participants is: .

[0062] It should be noted that if the second participating entity is considered as a whole, the relationship between the first and second cooperation ratios can be expressed as the second cooperation ratio equal to 1 minus the first cooperation ratio. The first cooperation ratio can also be represented as the ratio of the number of participants selected within the cooperative group to the number of game participants. The probability of cooperation, or the second cooperation ratio, can also represent the choice of participants in the game within the cooperative group. The probability of cooperation.

[0063] The execution cycle of a smart contract can include a time unit, which can be the execution unit of the smart contract, for example, executing the smart contract in months.

[0064] Within the t-th time unit, the first cooperation ratio among participating entities in the cooperative group that have signed smart contracts with the first participating entity can be determined based on the number of participating entities in the cooperative group that have signed smart contracts with the first participating entity. For example, if the cooperative group includes 5 companies (including the first participating entity), and in the 1st time unit, one of them signs a smart contract with the first participating entity, the first cooperation ratio can be determined to be 25%. Or, for example, in the 4th time unit, one company withdraws from the cooperation with the first participating entity, but the first participating entity signs contracts with two new companies, then the first cooperation ratio can be determined to be 50%.

[0065] After the first and second participating entities sign the smart contract, the execution phase of the smart contract can begin. In step 102, based on the strategy combination and the smart contract mechanism, the following contract parameters can be set:

[0066] This indicates the basic economic benefits brought about by cooperation;

[0067] Indicates the cost of cooperative behavior;

[0068] This indicates the cost of being penalized for breach of contract;

[0069] This indicates a loss of trust caused by the other party's breach of contract;

[0070] The trust gain or additional reward resulting from the accumulation of a history of cooperation can be called the trust factor.

[0071] To regulate cooperative behavior, smart contracts can also set two types of incentive mechanisms: performance rewards and breach penalties. Both can be set by the cooperative processing device or through negotiation between the parties and can be dynamically adjusted during evolution. The following key parameters can be defined:

[0072] This refers to the basic performance bonus, which is the economic benefit obtained by the partner after fulfilling the contract on time.

[0073] This indicates the severity of the penalty for breach of contract, that is, the cost of breach that a party must pay when it fails to perform its obligations under the agreement;

[0074] This represents the reward multiplier, which can change based on performance history, forming a credit-increasing incentive.

[0075] This represents the penalty growth coefficient; the more frequent the breach, the higher the penalty, thus forming a behavioral suppression mechanism.

[0076] The contract parameter information of the above contract parameters can be obtained. Since the contract parameter information of the smart contract is dynamically updated according to the behavioral feedback of the participating entities, the contract parameter information can reflect the behavior of the cooperative group and the first participating entity. Therefore, the contract parameter information will be different when the execution unit of the smart contract, i.e. the t-th time unit, is different.

[0077] In some embodiments, the contract parameter information can indirectly reflect the cooperative behavior between the cooperative group and the first participating entity, such as the basic economic benefits brought about by the cooperation. and the cost of penalties for breach of contract The tendency of a cooperative group to choose to cooperate with the primary participant indirectly reflects the selection behavior within the cooperative group.

[0078] In some embodiments, the contract parameter information can also directly reflect the cooperative behavior between the collaborating group and the first participating entity. For example, the trust factor of the participating entity. The smaller the value, the more frequent the historical default behavior of the participating entity, directly reflecting the entity's performance behavior.

[0079] In step 103, at the initial stage of the game, i.e., t equals 0, the following payoff matrix can be constructed based on the above contract parameter information, where rows represent game participants. The choice strategy, represented by the columns, indicates the game participants. The selection strategy.

[0080] .

[0081] Based on the probability of strategy selection, game participants The expected return can be expressed as:

[0082] .

[0083] During the execution phase of a smart contract, in some embodiments, the expected returns of its collaborating group are affected by rewards and penalties during contract fulfillment.

[0084] The actual incentives and penalties in smart contracts can be modeled as follows:

[0085] .

[0086] Where Reward(t) represents the reward for the t-th time unit, which the second participating entity can obtain if it performs the contract normally in the t-th time unit. Penalty(t) represents the penalty for the t-th time unit, which the second participating entity must bear if it defaults in the t-th time unit.

[0087] In the initial stage of the game, the smart contract was not executed, causing This represents the expected return of the cooperative group relative to the first participating entity in choosing a cooperation strategy, i.e., the first return information. This represents the average return of the entire group, i.e., the second return information.

[0088] The first benefit information can be obtained by superimposing the expected benefits of each participating entity (including the first participating entity) in the cooperative group that chose the cooperative strategy relative to the first participating entity.

[0089] With two participating entities (respectively, the game participants) and game participants For example, based on the first cooperation ratio and contract parameter information, the first and second revenue information can be determined, and the revenue information can be expanded into the following formula:

[0090] ;

[0091] ;

[0092] .

[0093] in, This represents the average return for the firm when choosing not to cooperate, relative to the expected return of the first participating entity choosing a non-cooperation strategy; the specific return depends on the other party's choice. Participant in the game The probability of choosing a cooperation strategy. These are the fundamental economic benefits brought about by cooperation. Specifically:

[0094] If the game participants The game participants choose the non-cooperative strategy (D), and the game participants... If the players choose the cooperative strategy (C), then the game participants... You will get The benefits (i.e., the benefits that the non-cooperating party receives from the cooperating party).

[0095] If the game participants The game participants choose the non-cooperative strategy (D), and the game participants... Choosing the non-cooperation strategy (D) then The return is 0.

[0096] therefore, This indicates when choosing a game participant The probability of non-cooperation is And choose to be a participant in the game. The probability of cooperation is In this situation, the game participants Will receive The benefits.

[0097] In some embodiments, during the execution phase of a smart contract, each participating entity also needs to combine corresponding reward and penalty benefits to obtain first benefit information and second benefit information.

[0098] In step 104, in evolutionary game theory, the replication dynamics equation is used to characterize the changing trend of the proportion of a certain strategy in a cooperative group. The replication dynamics equation is expressed as:

[0099] .

[0100] equation Indicates the first cooperation ratio Over time The rate of change. Specifically, This represents the proportion of individuals in the cooperative group who choose a cooperative strategy relative to the first participant; that is, the percentage of individuals in the cooperative group who choose a cooperative strategy relative to the first participant. This equation describes how cooperative strategies change over time within the cooperative group.

[0101] if The proportion of cooperative strategies is increasing.

[0102] if The proportion of cooperative strategies is decreasing.

[0103] if Then the proportion of cooperative strategies reaches a stable state.

[0104] The replication dynamic equation can be further expressed as:

[0105] .

[0106] This equation describes how firms, under conditions of bounded rationality, adjust their behavioral tendencies based on the current strategic advantage. If the expected benefits of cooperation outweigh those of non-cooperation, the proportion of the group choosing cooperation will gradually increase, potentially reaching an evolutionary stability. This model can be used to simulate long-term cooperation trends and behavioral evolution paths, and provides a quantitative basis for setting incentive mechanisms for smart contracts.

[0107] In some embodiments, if the proportion of cooperation strategies indicated by the cooperation trend is increasing, it is determined that the number of cooperating parties is increasing from an overall perspective. In this case, the contract parameter information may not be modified, or the penalty growth coefficient may be increased to constrain the default behavior of the cooperating parties.

[0108] In some embodiments, if the proportion of cooperation strategies indicated by the cooperation trend is decreasing, it is determined that the number of cooperating parties is decreasing from an overall perspective. Contract parameter information can be modified, for example, by increasing the basic performance reward and reward multiplier coefficient, to incentivize the cooperation group to choose to cooperate with the first participating entity.

[0109] The following can simulate the behavioral evolution path of strategy selection in a cooperative group, such as... Figure 2 The figure illustrates the trend over time of the proportion of participants choosing a cooperation strategy in a smart contract environment under different initial conditions. This model employs one-sided replicator dynamics modeling, setting contract parameters including: cooperation benefits... Cooperation costs Loss of trust and trust gain .

[0110] like Figure 2 As shown, the horizontal axis represents evolution time, such as using one month as the evolution time unit, and the vertical axis represents the proportion of the cooperative group that chooses the cooperative strategy. The multiple curves in the graph correspond to different combinations of initial strategies. The curve corresponding to the initial strategy combination (0.1, 0.9) is 201, the curve corresponding to the initial strategy combination (0.3, 0.7) is 202, the curve corresponding to the initial strategy combination (0.5, 0.5) is 203, the curve corresponding to the initial strategy combination (0.7, 0.3) is 204, and the curve corresponding to the initial strategy combination (0.9, 0.1) is 205.

[0111] in, This represents the probability that the cooperating group will choose to initially cooperate with its own party, i.e., the first participating entity. This represents the probability of choosing to cooperate with the other party, i.e., the second participating entity, within a cooperative group.

[0112] from Figure 2 The following trends can be observed:

[0113] As can be seen from curve 205, when the probability of choosing to cooperate with the other party is relatively high in the cooperative group (e.g., Even if one's initial willingness to cooperate is weak (e.g.) The proportion of cooperative partners choosing to cooperate with each other within a cooperative group will gradually increase, showing a positive evolutionary tendency, and eventually evolving into... =0, =1 (Increased cooperation ratio).

[0114] As can be seen from curve 201, when the probability of choosing to cooperate with the other party is low in the cooperative group (e.g., Even if one is initially very inclined to cooperate (e.g.) It will also quickly evolve into a non-cooperative state between the two sides, and eventually evolve into =0, =1;

[0115] The evolution curves under different initial conditions exhibit convergence, decay, or oscillation behaviors, reflecting the characteristics of bounded rational participants in the game adjusting their strategies based on differences in payoffs.

[0116] Eventually, it will evolve to a stable state, where the cooperation ratio no longer changes. The stable point of the evolution curve reflects the final behavioral state of the system: when... When convergence reaches 0, it indicates that the strategy of choosing cooperation with the first participating agent gradually disappears in the group, evolving into a stable state dominated by non-cooperation strategies; when When convergence to 1, it indicates that the cooperation strategy with the first participating entity is dominant; when... When the convergence is to a value between 0 and 1, it indicates that a stable state of the mixed strategy has been reached, that is, some participants choose to cooperate with the first participant, while others choose not to cooperate with the first participant.

[0117] Figure 2 This study intuitively reveals the significant impact of contract parameters, such as smart contract incentive mechanisms and trust environment, on the cooperative evolution path, providing a quantitative basis for subsequent mechanism design.

[0118] In other words, this cooperative trend can be used to determine the contract parameter information relative to the first participating entity within the (t+1)th time unit, so as to realize the cooperative regulation between the first and second participating entities.

[0119] Figure 3 It shows a flowchart illustrating the evolution of cooperation trends, such as... Figure 3As shown, taking a cooperative group including companies A and B as an example, we can proceed to the behavioral evolution modeling stage. This stage mainly reflects the behavioral evolution of the cooperative group in choosing a cooperation strategy relative to company A. This stage constructs the expected returns of the cooperative group (i.e., first return information and second return information), and based on the first and second return information, constructs a replication dynamic equation to simulate the cooperation trend of the cooperative group in choosing a cooperation strategy relative to the first participating entity. Finally, the evolution results are output, including the evolution curve of the first cooperation ratio and the stable cooperation level. * and the type of behavioral evolution trend (e.g., increase, decrease, or stability).

[0120] In some embodiments, the contract parameter information includes a trust factor of a second participating entity cooperating with the first participating entity, and the method further includes:

[0121] Obtain the score information of the influence factor within the t-th time unit, as well as the weight information of the influence factor, which is used to influence the cooperation between the first participating entity and the second participating entity;

[0122] The scoring information and the weighting information are weighted to obtain the trust factor of the second participating entity in the t-th time unit. The trust factor of the second participating entity in the t-th time unit is used to determine the first benefit information and the second benefit information.

[0123] In some embodiments, the contract parameter information further includes the reward and penalty growth factor of the second participating entity, and the method further includes:

[0124] Obtain the contract performance status of the second participating entity within the t-th time unit;

[0125] Based on the contract performance and the trust factor of the second participating entity in the t-th time unit, determine the reward and punishment growth factor of the second participating entity in the t-th time unit;

[0126] Based on the reward and punishment growth factor, determine the reward and punishment benefits of the second participating entity within the t-th time unit;

[0127] Step 103 specifically includes:

[0128] Based on the first cooperation ratio, the contract parameter information, and the reward and punishment benefits, the first benefit information and the second benefit information within the t-th time unit are determined.

[0129] In cooperative game theory among collaborative groups, smart contracts not only serve as automated execution tools but also as crucial regulatory factors in the game mechanism. By setting incentive and penalty rules, they guide participants to evolve stable cooperative strategies. The design of smart contract mechanisms can be elaborated from three aspects: parameterization of contract terms, dynamic adjustment mechanisms, and contract state modeling.

[0130] The above has explained that the actual incentives and penalties in smart contracts can be modeled as follows:

[0131] .

[0132] in, and It can be dynamically updated based on trust factors and contract performance, such as the number of performances and the status of contract performance. It is the reward and punishment growth factor for the second participating entity in the t-th time unit. If the second participating entity performs its obligations in the t-th time unit, the reward multiplier coefficient is updated to form a credit-increasing incentive; if the second participating entity defaults in the t-th time unit, the punishment growth coefficient is updated to form a default suppression.

[0133] In other words, during the execution phase of a smart contract, the expected returns of the collaborating group are affected by the rewards and penalties in the contract performance process, requiring a combination of rewards and penalties.

[0134] In some embodiments, and It can be represented as:

[0135] .

[0136] in, As a trust factor, These are adjustable weighting coefficients.

[0137] To ensure that the smart contract mechanism is responsive to participating behaviors, a trust factor is introduced. It represents the other party's performance history and reputation level during the interaction process.

[0138] In some embodiments, trust factor The impact factor can be obtained by weighting the score information and weight information of the impact factor within the t-th time unit. In some embodiments, without changing the score information and weight information, the trust factor... The trust factor of the previous time unit can be obtained by updating it based on the contract performance status.

[0139] In some embodiments, the method further includes:

[0140] Based on the contract performance status of the second participating entity in the t-th time unit, update the trust factor of the second participating entity in the t-th time unit to obtain the trust factor of the second participating entity in the (t+1)-th time unit.

[0141] The trust factor can be dynamically updated according to the following function:

[0142] .

[0143] in, For memory factors, This indicates the contract fulfillment status, signifying the [missing information]. Whether the contract is fulfilled within each time unit. If fulfilled, then... Otherwise, it is 0.

[0144] In this embodiment, based on the trust factor adjustment mechanism, the contract incentive intensity will be automatically amplified when trust increases and the penalty will be increased simultaneously when default occurs, so as to realize the real-time response of the contract mechanism to behavioral feedback.

[0145] In some embodiments, a smart contract includes several states during its execution cycle, i.e., its lifecycle. Based on the game theory process, the following three core states are defined:

[0146] Pending: The contract has been generated and is awaiting confirmation and activation by both parties.

[0147] Active: The contract has entered the execution phase, and the cooperative behavior is monitored in real time;

[0148] Terminated: The termination mechanism is triggered when the contract is fulfilled or a default event occurs.

[0149] In some embodiments, the method further includes:

[0150] If, during the execution of the smart contract, the number of defaults by the second participating entity is greater than or equal to a first preset threshold, or if the first cooperation ratio is less than or equal to a second preset threshold within the t-th time unit, the smart contract is terminated and target information is output; wherein,

[0151] The target information includes the cooperation trend, strategy suggestions, and contract results of the cooperative group relative to the first participating entity in the t-th time unit. The strategy suggestions are used to indicate the cooperation suggestions with the second participating entity after the t-th time unit, and the contract results are used to indicate the execution status of the smart contract.

[0152] In some embodiments, the contract state transition function can be defined as follows:

[0153]

[0154] in, Indicates the contract fulfillment status. Indicates the remaining execution cycles. If in Under the condition that the cumulative number of defaults exceeds the first preset threshold, i.e., the threshold The smart contract will terminate prematurely.

[0155] In some embodiments, if the first cooperation ratio in the cooperative group evolves stably to be less than or equal to a second preset threshold, such as close to 0, it indicates that all members of the cooperative group have chosen not to cooperate with the first participating entity, and the smart contract is forced to terminate.

[0156] In addition, contract trigger condition functions can be defined. Used to determine whether a reward / penalty has been activated:

[0157]

[0158] This mechanism ensures that contract logic can achieve behavior-driven adaptive management under the premise of being programmable and verifiable, thereby enhancing the stability of strategic games and the sustainability of cooperation.

[0159] Figure 4 The diagram illustrates the execution flow of a smart contract instance, as follows: Figure 4 As shown, the reward multiplier coefficient during smart contract execution. As the number of fulfillments increases, the performance reward increases with each round, while the penalty growth coefficient... As the number of defaults increases, the cost of defaulting also increases significantly, ultimately leading to more stable cooperation in the future.

[0160] In related technologies, traditional cooperative processing methods mostly rely on one-way incentive mechanisms or static punishment strategies, which cannot be dynamically adjusted according to behavioral evolution, resulting in discontinuous strategy effects, unstable results, and difficulty in adapting to complex behavioral environments. This embodiment proposes a dynamic regulation strategy system integrating incentives and punishments. By constructing a response function between cooperative trends and incentive / punishment parameters, the incentive multiplier and punishment intensity are adjusted based on experimental data. An evolutionary path for the regulation strategy is defined to achieve multi-stage strategy switching, and a regulation strategy recommendation mechanism based on cooperative trends is established to generate optimal intervention strategies under different initial conditions. Thus, by optimizing the cooperative regulation strategy by integrating incentive and punishment mechanisms, and adjusting the regulation intensity according to real-time behavioral feedback and trust fluctuations, the guidance, constraint, and continuous optimization of cooperative behavior can be achieved, improving the regulation efficiency and behavioral guidance effect of the cooperative system.

[0161] Figure 5This diagram illustrates the core states of a smart contract throughout its lifecycle and the transition paths between states in a collaborative scenario involving a group of partners. The state machine diagram defines five basic states: Pending Execution, Executing, Fulfillment Completed, Default Termination, and Termination, corresponding to the logical positions of the smart contract at different stages. The logical description of its state transitions is as follows:

[0162] After a smart contract is created, it is in a pending execution state. It will enter the execution state after both parties confirm and activate it.

[0163] During the execution process, if both parties continue to fulfill their contractual obligations until the expiration date, the contract is considered fulfilled.

[0164] If either party breaches the contract during its performance, a default termination status will be triggered.

[0165] Whether the contract is fulfilled through performance or terminated due to breach of contract, it will eventually be transferred to a terminated state, indicating the end of the contract's life cycle.

[0166] Figure 5 Each directed edge in the code is labeled with a corresponding transition condition, such as "activate contract," "continue performance until end," and "default triggers termination," demonstrating the smart contract mechanism's responsiveness to behavioral feedback. Through this state modeling approach, smart contracts not only possess automatic execution capabilities but can also dynamically control the validity and incentive triggering of contracts based on behavioral performance, thereby enhancing the stability and contractual binding force of the cooperation process for SMEs.

[0167] In the event of termination of a smart contract, target information can be output, such as the cooperation trend, strategy suggestions, and contract results among the cooperating groups relative to the first participating entity in choosing a cooperation strategy.

[0168] Among these, when the cooperation trend stabilizes, a stable output level can also be achieved. *(like (*=1); the strategy suggestion can indicate cooperation recommendations with the second participant after the t-th time unit. For example, it can indicate suggestions on the contract parameters for the next smart contract signed with the second participant. The contract outcome can include the contract execution status. For example, the contract outcome could be termination due to multiple defaults by the second participant. If the contract outcome is termination due to multiple defaults by the second participant, the strategy suggestion can indicate increasing the penalty intensity and penalty growth coefficient for the second participant's default.

[0169] In some embodiments, to improve the decision-making accuracy and adaptability of behavioral game models and smart contract mechanisms, it is necessary to identify, quantify, and standardize the key factors, i.e., influencing factors, that affect the evolution of enterprise strategies. This process transforms subjective judgments and environmental factors into computable parameters, providing dynamic and updatable inputs for behavioral evolution models that select cooperative strategies and for smart contract incentive mechanisms.

[0170] By identifying influencing factors, constructing and applying the Analytic Hierarchy Process (AHP), and performing variable mapping and parameter normalization, subjective judgments can be transformed into parameter inputs that can be used for game evolution and contract incentive modeling.

[0171] In cooperative game theory, strategy selection is influenced by the interaction of multiple factors, which can be summarized as follows:

[0172] 1. Economic Return ): The direct benefits and cost savings brought about by cooperation;

[0173] 2. Cooperation History ): Past performance record and level of trust accumulation;

[0174] 3. Market Condition ): Level of competition, transaction frequency, external uncertainties;

[0175] 4. Policy Incentive Tax breaks and incentive subsidies provided by the government or platform;

[0176] 5. Risk Preference ): A company's tolerance for the consequences of failure and its strategic conservatism.

[0177] The above-mentioned influencing factors are information on external and internal factors that affect strategy selection.

[0178] In some embodiments, obtaining the weight information of the influence factors within the t-th time unit includes:

[0179] Based on the scoring information within the t-th time unit, the relative importance of different influencing factors within the t-th time unit is determined, and a judgment matrix is ​​obtained;

[0180] Consistency verification is performed based on the judgment matrix to obtain the weight information of the influencing factors in the t-th time unit.

[0181] In other words, the weight information of the impact factors can be constructed using the analytic hierarchy process (AHP) based on the scoring information of the aforementioned impact factors.

[0182] The input of impact factors can be obtained and can be uniformly represented as a set of impact factors. It is the quantified and normalized rating information.

[0183] When applying AHP, a pairwise comparison matrix needs to be constructed to compare the score information of the influencing factors pairwise, thereby obtaining their relative importance. Based on the relative importance, the weight information of the influencing factors is determined. Then, based on the calculated weight information, it is mapped to the contract parameters.

[0184] The specific mapping process is as follows:

[0185] Trust factor The normalized score information of the influence factor can be mapped to the trust factor using a weighting function. The formula is as follows: .

[0186] in, The weight information is obtained through AHP. It is the first The impact factor in the first Normalized scoring information within a time unit. For example, cooperation history ( The rating information will affect the adjustment of the trust factor, thereby affecting the incentive and punishment strategies of the contract.

[0187] Economic interests ( ) and market environment ( The rating information will directly adjust the cooperation rewards. and penalties for breach of contract The value. For example, when the market environment is more competitive, the penalty for breach of contract... This could increase the cost of default, thereby affecting the attractiveness of non-cooperative strategies in the game.

[0188] Risk tolerance ( The scoring information influences the trade-offs of firms between cooperation and non-cooperation, thereby affecting strategy choices in the game model. Firms with lower risk tolerance may be more inclined to cooperate, thus adjusting the proportion of cooperation in the evolutionary game.

[0189] The above five types of influencing factors together constitute the input basis for the behavioral evolution model of strategy selection and contract parameters.

[0190] To determine the relative importance of each influencing factor, the Analytic Hierarchy Process (AHP) was used to calculate factor weights. The AHP method constructs pairwise comparison matrices to... Influencing factors By comparing each pair of items, a judgment matrix is ​​obtained, which is... ,in, Indicating the impact factor Compared to The importance of.

[0191] Then, normalization and consistency checks are performed, and weight information is calculated. ,satisfy:

[0192] .

[0193] The consistency index is:

[0194] .

[0195] in, The largest eigenvalue of the matrix. This is a random consistency indicator. If If so, then the matrix is ​​acceptable.

[0196] 1. Judgment Matrix middle Indicating the impact factor Relative to impact factor The relative importance of factors is usually determined by the relative weights between the two factors, and is expressed using a scale of 1 to 9. For example, 1 means that the two factors are equally important, 3 means that the first factor is slightly more important than the second factor, and so on.

[0197] 2. Normalization and weight information calculation.

[0198] : Represents the elements in the normalized judgment matrix. The elements in each column are normalized so that the sum of each column is 1.

[0199] : indicates the first The weights of each influencing factor reflect their relative importance in the overall decision-making process. They are calculated by taking the average of each row of the normalized matrix.

[0200] 3. Consistency check.

[0201] The eigenvalue represents the largest eigenvalue of a matrix and is an important indicator of matrix consistency. Ideally, if a matrix has good consistency, the largest eigenvalue should be close to the order of the matrix. .

[0202] Consistency index: This measure is used to assess the consistency of a judgment matrix. A higher consistency index indicates a larger discrepancy in the judgments within the matrix.

[0203] The consistency ratio is used to assess whether the consistency metric is within an acceptable range. If... If the value is less than 0.1, the consistency of the matrix is ​​considered acceptable.

[0204] The random consistency index is based on the order of the matrix. The calculated constant is usually obtained by looking up a table. It is used to calculate the consistency ratio. .

[0205] Figure 6 This is a weighted distribution chart of the influence factors. Figure 6 The weights of the five main influencing factors, calculated using the Analytic Hierarchy Process (AHP), are shown.

[0206] Economic benefits (weight 0.35): This is the most important factor influencing corporate strategy, indicating that companies are more inclined to make decisions based on direct benefits.

[0207] Cooperation history (weight 0.25): Performance record and trust accumulation also significantly influence behavioral evolution;

[0208] Market environment and risk tolerance (0.15 each): This indicates that companies will consider the external environment and their own risk appetite;

[0209] Policy support (weight 0.10): Although important, its impact is relatively low and may be related to actual subsidies or implementation availability.

[0210] The calculated influence factor weights Mapped to contract parameters in the model, such as the trust parameters that influence the evolutionary equation. Contract incentive coefficient wait.

[0211] set up Let the function representing the mapping from the influence factors to the model parameters be:

[0212] .

[0213] For example, the trust factor can be expressed as a weighted function:

[0214] .

[0215] in, For the first The impact factor in the first Normalized scoring information within each time unit, with score values ​​categorized by interval. Normalization is performed to ensure that all factors have a uniform dimension in the model.

[0216] In related technologies, current cooperative game models mostly adopt fixed strategy settings, lacking dynamic modeling of individual trust changes, making it difficult to capture the evolution of cooperative willingness in real-world interactions. Simultaneously, incentive and punishment mechanisms are often treated in isolation, failing to form a closed-loop control system, thus limiting the model's applicability and adjustment accuracy. This embodiment, however, uses a cooperative behavior modeling method based on trust evolution and strategy game theory. It sets trust as a variable state variable, updating it in real-time based on interaction results; introduces multi-dimensional state factors, including historical cooperative behavior, the probability of the other party's behavior, and internal trust levels; and uses cooperative willingness as the output indicator, mapping it to specific behaviors through evolutionary rules. This transforms subjective judgments of enterprises into quantifiable parameters, enhancing the model's real-world adaptability and behavioral interpretability. It also establishes a modeling framework integrating trust evolution, cooperation rate (i.e., cooperation ratio) feedback, and strategy adjustment. By quantifying the two-way influence of trust and behavior, it promotes the natural formation and stable evolution of cooperative behavior, possessing strong adaptability and behavioral interpretability, and capable of simulating cooperative trends under various social interaction models.

[0217] To improve the responsiveness and evolutionary adaptability of the influence factor weighting mechanism in actual system operation, an adaptive analytic hierarchy process (A-AHP) is proposed based on the traditional analytic hierarchy process (AHP) to achieve dynamic updating of influence factor weights and behavior feedback-driven strategy regulation.

[0218] In traditional AHP methods, the weights of influencing factors are fixed once set, making it difficult to effectively reflect the actual impact of each factor on the outcome when faced with evolving collaborative behaviors or adjustments in corporate strategies. To address this issue, the following two improvement strategies can be proposed.

[0219] In some embodiments, after determining the weight information of the influencing factors within the t-th time unit based on the relative importance, the method further includes:

[0220] Based on the contract performance status of the second participating entity in the (t-1)th time unit, update the trust factor of the second participating entity in the (t-1)th time unit;

[0221] With the goal of minimizing the trust factor in the t-th time unit obtained by weighting the scoring information and weight information, and the trust factor based on the contract performance status update of the second participating entity in the (t-1)-th time unit, the weight information of the influencing factor in the t-th time unit is optimized.

[0222] A weighted regression optimization mechanism based on behavioral outcomes can be used to optimize the weight information of influencing factors, ensuring that the weight information corresponds to corporate behavior. This mechanism uses the final performance of cooperative behavior (such as the convergence value of the cooperation rate) as the objective function, constructs a mapping model between factor scores and behavioral outcomes, and optimizes the weights of influencing factors by minimizing the fitting error.

[0223] The optimization goals are as follows:

[0224] .

[0225] in:

[0226] Let be the actual trust factor within the t-th time unit;

[0227] For the first Scores of each impact factor;

[0228] Weights to be optimized.

[0229] This method minimizes the trust prediction error and dynamically optimizes the weight information of AHP, making subjective expert ratings more closely aligned with behavioral outcomes, thereby improving the system's prediction accuracy and the effectiveness of policy intervention.

[0230] In some embodiments, after performing consistency verification based on the judgment matrix to obtain the weight information of the influencing factors in the t-th time unit, the method further includes:

[0231] Based on the rating information of the trust factor and the influence factor of the second participating subject in the t-th time unit, the sensitivity of the influence factor to the change of the trust factor is determined.

[0232] Based on the sensitivity and the weight information of the influencing factors in the t-th time unit, the weight information of the influencing factors in the (t+1)-th time unit is determined.

[0233] A dynamic weight adjustment mechanism based on trust feedback can be used, which incorporates trust factors during behavioral evolution. As a dynamic feedback signal, the corresponding factor weights are adjusted in real time by measuring the sensitivity of each influencing factor to changes in the trust value.

[0234] The specific correction function is shown below:

[0235] .

[0236] in:

[0237] Indicates the first The impact factor in the first Weights within each time unit;

[0238] For the first Normalized score information of each impact factor;

[0239] This represents the partial derivative of the trust factor with respect to that factor's score;

[0240] Adjust the step size coefficient for the weights to control the rate of change.

[0241] This mechanism ensures that when a factor significantly impacts the evolution of cooperation willingness, its weight automatically increases; conversely, if it has no significant effect over a long period, its weight is dynamically reduced. Feedback control enables real-time reconstruction of factor influence, enhancing the adaptability of strategy evolution modeling.

[0242] The two mechanisms mentioned above can be combined to form a factor weight self-regulation mechanism driven by behavioral feedback, providing dynamic parameter support for evolutionary game models and significantly enhancing the system's ability to model changes in cooperative strategies and its responsiveness to reality.

[0243] In related technologies, traditional AHP methods rely on manually setting fixed weights, making it difficult to respond to changes in factor importance during strategy evolution, lacking a real-time feedback mechanism, and limiting adaptability and predictive ability. This embodiment proposes an adaptive AHP method combining trust feedback and behavioral outcome optimization. It constructs the sensitivity derivative of the trust factor to factor scoring and adjusts the weights according to the gradient; and utilizes behavioral data for objective function regression optimization of the weight structure. This upgrades the traditional static scoring structure to a dynamic feedback self-adjusting structure. Based on the adaptive hierarchical analysis mechanism of behavioral feedback, it enables dynamic adjustment of factor weights. By introducing a derivative-driven weight adjustment mechanism and a cooperative behavioral outcome-based optimization mechanism, the system's weight configuration responds in real-time to behavioral evolution trends.

[0244] Figure 7 This is a graph showing the evolution trend of the trust factor under different weighting mechanisms. It illustrates the impact of the adaptive weight adjustment mechanism on the evolution of the model's trust factor and the weight changes of influencing factors. Specifically, it demonstrates the impact of the feedback mechanisms of the three influencing factors on the trust factor. The impact of this is evident. It can be observed that when the Adaptive AHP mechanism is adopted and the influence factor is given a higher weight, the trust factor grows significantly faster, indicating that the system responds more effectively to behavioral data.

[0245] Under traditional static weight settings, It rises slowly, as shown by curve 702;

[0246] For high impact factors, an adaptive AHP is adopted, whose weights dynamically respond to high impact factors and trust grows faster, as shown in curve 701.

[0247] For low-impact factors, an adaptive AHP is used, but its weight adjustment lags and its growth is slow, as shown in curve 703.

[0248] Among these, high-impact factors refer to those factors that, from a business perspective, directly determine trust. These influencing factors are directly derived from actual collaborative behavior and are most sensitive to changes in trust. Once these influencing factors are assigned high weights, They react quickly to changes in behavior. For example, the history of cooperation can directly reflect actual cooperative behavior, making it a high-impact factor. Low-impact factors (such as environmental or indirect factors) are more of a background constraint, changing slowly and lagging behind. For example, market fluctuations may not reflect individual behavior in the short term, policy support may be stable but have limited impact on a single cooperation, and risk tolerance tends to be structural and non-immediate in behavior; therefore, they are low-impact factors.

[0249] From a model perspective, the essential difference lies in the weighting of factors; those with larger weights are high-impact factors, while those with smaller weights are low-impact factors.

[0250] The following explanation uses two scenarios as examples: a high-impact factor-dominated scenario and a low-impact factor-dominated scenario. Table 1 below shows examples of the weighting information for the high-impact factor-dominated and low-impact factor-dominated scenarios.

[0251] Table 1 Examples of Two Dominant Scenarios

[0252]

[0253] Table 2 shows a comparison of the model response features under different weight configurations.

[0254] Table 2 Comparison of Model Response Features under Different Weight Configurations

[0255]

[0256] Figure 8 This is a schematic diagram illustrating the dynamic changes in the weights of key factors under an adaptive mechanism. Figure 8 This is reflected in the dynamic changes in the weights of the three key factors (economic benefits, cooperation history, and market environment) with each round of system interaction. It can be seen that:

[0257] The weight of the economic benefit factor remained at a relatively high level in the early stage of evolution, and then showed slight fluctuations and tended to stabilize in the process of multiple rounds of interaction, as shown by curve 801.

[0258] The weight of the cooperation history factor remained relatively stable during the period when the trust factor increased, as shown by curve 802.

[0259] The market environment factor increases in proportion in the early stage and then slightly decreases in the later stage, reflecting the system's ability to adapt to environmental stability, as shown by curve 803.

[0260] Through the above-mentioned improved methods, the proposed Adaptive-AHP mechanism demonstrates good responsiveness and dynamic adjustment capabilities, providing higher-precision support for the modeling and regulation of corporate cooperative behavior.

[0261] The following is a detailed explanation of the cooperative processing method provided in the embodiments of this application using a specific example.

[0262] This application's embodiments construct a behavioral evolution modeling system for smart contract collaboration environments of SMEs. It integrates evolutionary game theory, smart contract incentive mechanisms, trust feedback mechanisms, and factor weight evaluation methods to form a closed-loop behavioral decision analysis and dynamic incentive control platform. The system consists of five core modules: game modeling and strategy evolution module, smart contract execution and adjustment module, trust and performance feedback module, influencing factor weight evaluation module, and simulation and visualization analysis module.

[0263] As participants in the game, SMEs choose between a cooperative or non-cooperative strategy in each round of interaction based on historical records and expectations of the other party's behavior. Smart contracts automatically execute the cooperation agreement signed by both parties, including the established reward or penalty mechanisms. The system updates the participants' trust factors based on actual performance, feeding this information back to the game model and influencing the strategy evolution path in the next round. Simultaneously, the Analytic Hierarchy Process (AHP) is used to identify and quantify the weights of key behavioral drivers such as cost, incentive intensity, and trust level, further optimizing the model parameters.

[0264] Figure 9 This is a schematic diagram of the system's operating logic, such as... Figure 9 As shown, the entire system operates in a loop of "strategy evolution—contract execution—behavioral feedback—parameter update," forming a dynamic and responsive cooperative game analysis process. In the initial stage, the game strategy ratios and smart contract parameters are set. In each round, the direction of strategy evolution is calculated, triggering the smart contract to determine the performance status and execute incentive terms. Subsequently, the system records the interaction results, updates the trust value and key factor status, and dynamically adjusts the contract terms accordingly, thereby continuously converging the strategy and contract mechanism to an evolutionary stable state. It should be noted that all information involved in the embodiments of this application has been anonymized to ensure data privacy.

[0265] The following describes how a dynamic simulation model is constructed to simulate the evolution path of cooperation strategies among SMEs under different initial conditions and incentive parameters. The main objective is to evaluate the model's response characteristics to key input variables and output the final cooperation level and strategy convergence characteristics. The dynamic simulation and strategy output results are shown in Table 3 below. The output results may include the strategy trend type, final cooperation rate, and number of rounds required for convergence for each experimental group.

[0266] Table 3. Dynamic Simulation and Strategy Output Results

[0267]

[0268] Figure 10 This is a flowchart illustrating a specific example of a collaborative processing method in an embodiment of this application. Figure 10 As shown, the simulation process is as follows: In the dynamic simulation, the system first obtains initial parameters such as the initial cooperation rate of participating enterprises, the other party's willingness to cooperate, the initial trust value, and the penalty intensity and incentive multiplier set in the smart contract, which constitute the initial input conditions for the simulation experiment. In each round of interaction, the system constructs a payoff function based on the current cooperation strategy ratio and contract parameters, calculates the expected payoff corresponding to cooperation and non-cooperation strategies, and uses a replication dynamic equation to iteratively update the cooperation strategy ratio to characterize the evolution process of the strategy in the group. At the same time, the system updates the trust factor according to the enterprise's performance or breach of contract behavior in this round. The trust factor not only reflects the historical behavior results, but also dynamically adjusts the results of weighted evaluation of key influencing factors such as economic interests, cooperation history, and market environment. The updated trust factor further acts on the incentive and penalty parameters in the smart contract and feeds back to the next round of strategy evolution, forming a closed-loop simulation mechanism of strategy decision-making—behavioral feedback—trust update—contract adjustment, until the strategy evolution curve reaches a stable state.

[0269] Simulations show that a high cooperation rate or a high initial trust value usually leads to a rapid evolution towards a high cooperation rate (e.g., Exp-1, Exp-2, Exp-4); insufficient trust or a low cooperation rate in the external environment will lead to a rapid decline in the cooperation rate (e.g., Exp-3); increasing the incentive multiplier (e.g., Exp-5) can cause the originally volatile cooperation tendency to converge to a higher level; increasing the intensity of punishment (e.g., Exp-6) can delay betrayal behavior, but it will also cause policy fluctuations in the early stages.

[0270] The simulation results above show that the embodiments of this application can accurately simulate the behavioral evolution process of SMEs under the influence of bounded rationality and incentive system, and provide quantitative support for the design of contract incentive parameters and trust management mechanisms.

[0271] Compared with existing cooperative trend recognition technologies based on static statistical analysis or fixed behavioral rules, the embodiments of this application have the following technical advantages in terms of trend discrimination accuracy, strategy adaptability, system feedback response, and prediction capability:

[0272] 1. Introduce an automatic behavioral trend recognition mechanism to achieve intelligent analysis of cooperation dynamics.

[0273] This application's embodiments construct an automatic behavioral trend identification module by modeling and processing time-series data on cooperation ratios. This module can distinguish various evolutionary paths, including typical trend types such as monotonous rise and fluctuating decline. Compared to trend judgment methods that rely on manual interpretation or static statistics, this mechanism possesses algorithm-driven discrimination capabilities, enabling rapid identification of trend directions in the early stages of behavior. This provides a preliminary basis for strategic intervention, significantly improving the efficiency and accuracy of trend judgment.

[0274] 2. Construct a multi-dimensional evaluation index system to support the systematic evaluation of strategy effectiveness.

[0275] This application's embodiments further introduce multi-dimensional quantitative indicators, including the final cooperation ratio, convergence time, and volatility, on the basis of trend recognition, to comprehensively evaluate the dynamic performance of the cooperation strategy. Unlike related technologies that only focus on the final cooperation result, this mechanism focuses on the evolutionary trajectory and dynamic feedback throughout the entire strategy process, which can more realistically reflect the advantages and disadvantages of the strategy, guide strategy iteration and parameter optimization, and enhance the system's strategy adaptability and reliability.

[0276] 3. Integrate data-driven prediction models to improve the system's foresight and the efficiency of strategic decision-making.

[0277] This application's embodiments train a cooperation trend prediction model based on experimental data, enabling outcome prediction under different initial conditions and control parameters. It allows for trend forecasting before strategy implementation, assisting in the development of more targeted intervention plans. Compared to traditional post-hoc outcome analysis methods, this method achieves a forward closed-loop process from identification to prediction, making cooperation strategies forward-looking and controllable, providing data support and a decision-making basis for behavioral intervention, and significantly improving the efficiency and scientific rigor of strategy adjustments.

[0278] The trust-driven collaborative evolution mechanism and behavioral trend recognition technology in this application respond to the needs of digital platforms and intelligent decision-making systems in modern enterprises. As the demand for stable platform operation and efficient collaboration continues to increase, behavioral modeling and game theory systems are increasingly being used in areas such as user incentives, recommendation system optimization, community interaction analysis, and multi-agent systems. According to the latest market research report, the global intelligent behavioral modeling market is projected to exceed $30 billion by 2025, with an average annual growth rate of approximately 17.2%. Furthermore, the application of behavioral modeling technology in digital platforms, especially personalized recommendations and collaborative optimization for platform users, is becoming a key tool for improving user retention and optimizing operational efficiency.

[0279] In the context of supply chain finance for SMEs, this proposal can effectively address the challenges of credit deficiency, inefficiency, and risk control inherent in traditional financing models. During smart contract execution, collaborative prediction and control mechanisms reduce human intervention and default risks. Furthermore, in the process of smart contract credit splitting and transfer, analysis and control of trust mechanisms among multi-level suppliers improve the efficiency of cooperation among different SMEs in the supply chain.

[0280] In enterprise-level collaboration platforms, the collaboration prediction and control mechanism proposed in this proposal can significantly improve the platform's operational efficiency. Taking a medium-sized online collaborative office platform as an example, the platform has an average of 100,000 daily active users and millions of registered users. By introducing collaboration behavior prediction and control technology, preliminary test results show that in project-based tasks, the success rate of collaboration has increased by an average of about 5%, which directly leads to improved platform efficiency and reduces the additional time and resource waste caused by task collaboration failures. At the same time, the platform's user retention rate has also improved, especially in long-term collaborative tasks, where the retention rate is 7% higher than the traditional model.

[0281] External company application scenarios and market opportunities.

[0282] Virtual Community Management: As social platforms and virtual communities continue to expand, they face the challenge of massive user behavior data. Industry data shows that global social platforms have hundreds of millions of daily active users, making it crucial to improve the quality and efficiency of community interactions. By introducing trust-driven behavior prediction technology, social platforms can automatically optimize community interactions based on user behavior, improving interaction quality. Preliminary data shows that this mechanism can increase the frequency of community member interactions by 18% and user activity by 10%, enhancing user stickiness and platform value.

[0283] Blockchain Social Governance and Smart Contracts: With the maturity of blockchain technology, the application scenarios of smart contracts are gradually expanding. Especially in decentralized social platforms and smart contract applications, trust-driven cooperation mechanisms can help platforms accurately identify and optimize participant behavior, reducing default risks. Market research reports indicate that the blockchain smart contract market is projected to reach $26 billion by 2024, with an annual growth rate of nearly 22%. The behavioral modeling technology in this application can provide intelligent decision support for blockchain platforms, optimize contract execution efficiency, reduce losses caused by smart contract defaults, and simultaneously improve platform participation and trust.

[0284] Future scalability and technology portability.

[0285] The technical framework of this application possesses strong portability and scalability, enabling rapid adaptation to the needs of different platforms. Through a trust-driven collaborative evolution mechanism, the platform can flexibly respond to changes in user behavior in a dynamic market environment, continuously improving operational efficiency and user engagement. This technology provides robust support for online education platforms, sharing economy platforms, and enterprise collaboration platforms. Market research indicates that as enterprises increasingly demand intelligent decision support and behavioral prediction technologies, approximately 40% of digital platforms will adopt similar intelligent behavioral modeling technologies in the coming years to optimize platform operations and reduce costs associated with failed collaborations or user churn.

[0286] See Figure 11 , Figure 11 This is a schematic diagram of the structure of a cooperative processing device provided in an embodiment of this application, as shown below. Figure 11 As shown, the cooperative processing device 1100 includes:

[0287] The first acquisition module 1101 is used to acquire the first cooperation ratio selected from the cooperative group to cooperate with the first participating entity within the t-th time unit, wherein the cooperative group includes the first participating entity and the second participating entity cooperating with the first participating entity, and t is a positive integer;

[0288] The second acquisition module 1102 is used to acquire contract parameter information of the smart contract relative to the first participating entity within the t-th time unit. The smart contract is used to execute the cooperation between the first participating entity and the second participating entity. The contract parameter information is used to reflect the behavior of the cooperative group cooperating with the first participating entity.

[0289] The first determining module 1103 is used to determine the first revenue information and the second revenue information within the t-th time unit based on the first cooperation ratio and the contract parameter information. The first revenue information indicates the expected revenue of the cooperative group relative to the cooperation strategy chosen by the first participating entity, and the second revenue information indicates the average revenue of the cooperative group.

[0290] The second determining module 1104 is used to determine the cooperation trend of the cooperative group relative to the first participating entity in the t-th time unit based on the first revenue information and the second revenue information. The cooperation trend is used to determine the contract parameter information relative to the first participating entity in the (t+1)-th time unit.

[0291] Optionally, the contract parameter information includes a trust factor for a second participating entity cooperating with the first participating entity, and the device further includes:

[0292] The third acquisition module is used to acquire the score information of the influence factor in the t-th time unit, as well as the weight information of the influence factor, which is used to influence the cooperation between the first participating entity and the second participating entity.

[0293] The weighted processing module is used to weight the scoring information and the weight information to obtain the trust factor of the second participating entity in the t-th time unit. The trust factor of the second participating entity in the t-th time unit is used to determine the first benefit information and the second benefit information.

[0294] Optionally, the device further includes:

[0295] The first update module is used to update the trust factor of the second participating entity in the t-th time unit based on the contract performance status of the second participating entity in the t-th time unit, so as to obtain the trust factor of the second participating entity in the (t+1)-th time unit.

[0296] Optionally, the contract parameter information further includes the reward and penalty growth factor of the second participating entity, and the device further includes:

[0297] The fourth acquisition module is used to acquire the contract performance status of the second participating entity within the t-th time unit;

[0298] The third determining module is used to determine the reward and punishment growth factor of the second participating entity in the t-th time unit based on the contract performance and the trust factor of the second participating entity in the t-th time unit.

[0299] The fourth determining module is used to determine the reward or punishment benefits of the second participating entity within the t-th time unit based on the reward or punishment growth factor.

[0300] The first determining module 1103 is specifically used to determine the first income information and the second income information within the t-th time unit based on the first cooperation ratio, the contract parameter information, and the reward and punishment income.

[0301] Optionally, the device further includes:

[0302] The output module is configured to terminate the smart contract and output target information when the contract performance indicator shows that the number of defaults by the second participating entity during the execution of the smart contract is greater than or equal to a first preset threshold, or that the first cooperation ratio is less than or equal to a second preset threshold within the t-th time unit; wherein,

[0303] The target information includes the cooperation trend, strategy suggestions, and contract results of the cooperative group relative to the first participating entity in the t-th time unit. The strategy suggestions are used to indicate the cooperation suggestions with the second participating entity after the t-th time unit, and the contract results are used to indicate the execution status of the smart contract.

[0304] Optionally, the third acquisition module is specifically used for:

[0305] Based on the scoring information within the t-th time unit, the relative importance of different influencing factors within the t-th time unit is determined, and a judgment matrix is ​​obtained;

[0306] Consistency verification is performed based on the judgment matrix to obtain the weight information of the influencing factors in the t-th time unit.

[0307] Optionally, the device further includes:

[0308] The second update module is used to update the trust factor of the second participating entity within the (t-1)th time unit based on the contract performance status of the second participating entity within the (t-1)th time unit.

[0309] The optimization module is used to optimize the weight information of the influencing factors in the t-th time unit with the goal of minimizing the trust factor obtained by weighting the scoring information and weight information in the t-th time unit, and the trust factor based on the contract performance status update of the second participating entity in the (t-1)-th time unit.

[0310] Optionally, the device further includes:

[0311] The fifth determining module is used to determine the sensitivity of the influence factor to changes in the trust factor based on the rating information of the trust factor and the influence factor of the second participating subject within the t-th time unit.

[0312] The sixth determining module is used to determine the weight information of the influence factor in the (t+1)th time unit based on the sensitivity and the weight information of the influence factor in the tth time unit.

[0313] The cooperative processing device 1100 can implement the various processes implemented in the above-described cooperative processing method embodiments and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0314] See Figure 12 The figure shows a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Figure 12 As shown, the electronic device 1200 includes: a processor 1201, a memory 1202, a user interface 1203, and a bus interface 1204.

[0315] Processor 1201 is used to read the program from memory 1202 and execute the following procedures:

[0316] Obtain the first cooperation ratio among the cooperative groups that cooperate with the first participating entity within the t-th time unit, where the cooperative group includes the first participating entity and the second participating entity that cooperates with the first participating entity, and t is a positive integer;

[0317] Obtain the contract parameter information of the smart contract relative to the first participating entity within the t-th time unit. The smart contract is used to execute the cooperation between the first participating entity and the second participating entity. The contract parameter information is used to reflect the behavior of the cooperative group cooperating with the first participating entity.

[0318] Based on the first cooperation ratio and the contract parameter information, the first revenue information and the second revenue information within the t-th time unit are determined. The first revenue information indicates the expected revenue of the cooperative group relative to the first participating entity's choice of cooperation strategy, and the second revenue information indicates the average revenue of the cooperative group.

[0319] Based on the first and second revenue information, the cooperation trend of the cooperative group relative to the first participating entity in choosing a cooperation strategy is determined within the t-th time unit. The cooperation trend is used to determine the contract parameter information relative to the first participating entity within the (t+1)-th time unit.

[0320] exist Figure 12In this context, the bus architecture can include any number of interconnected buses and bridges, specifically linking various circuits of one or more processors represented by processor 1201 and memory represented by memory 1202 together. The bus architecture can also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. Bus interface 1204 provides an interface. For different user devices, user interface 1203 can also be an interface capable of connecting external or internal devices, including but not limited to keypads, displays, speakers, microphones, joysticks, etc.

[0321] The processor 1201 is responsible for managing the bus architecture and general processing, while the memory 1202 can store the data used by the processor 1201 when performing operations.

[0322] In some embodiments, the contract parameter information includes a trust factor of a second participating entity cooperating with the first participating entity, and the processor 1201 is further configured to:

[0323] Obtain the score information of the influence factor within the t-th time unit, as well as the weight information of the influence factor, which is used to influence the cooperation between the first participating entity and the second participating entity;

[0324] The scoring information and the weighting information are weighted to obtain the trust factor of the second participating entity in the t-th time unit. The trust factor of the second participating entity in the t-th time unit is used to determine the first benefit information and the second benefit information.

[0325] In some embodiments, the processor 1201 is further configured to:

[0326] Based on the contract performance status of the second participating entity in the t-th time unit, the trust factor of the second participating entity in the t-th time unit is updated to obtain the trust factor of the second participating entity in the (t+1)-th time unit.

[0327] In some embodiments, the contract parameter information further includes the reward and penalty growth factor of the second participating entity, and the processor 1201 is further used for:

[0328] Obtain the contract performance status of the second participating entity within the t-th time unit;

[0329] Based on the contract performance and the trust factor of the second participating entity in the t-th time unit, determine the reward and punishment growth factor of the second participating entity in the t-th time unit;

[0330] Based on the reward and punishment growth factor, determine the reward and punishment benefits of the second participating entity within the t-th time unit;

[0331] Based on the first cooperation ratio, the contract parameter information, and the reward and punishment benefits, the first benefit information and the second benefit information within the t-th time unit are determined.

[0332] In some embodiments, the processor 1201 is further configured to:

[0333] If, during the execution of the smart contract, the number of defaults by the second participating entity is greater than or equal to a first preset threshold, or if the first cooperation ratio is less than or equal to a second preset threshold within the t-th time unit, the smart contract is terminated and target information is output; wherein,

[0334] The target information includes the cooperation trend, strategy suggestions, and contract results of the cooperative group relative to the first participating entity in the t-th time unit. The strategy suggestions are used to indicate the cooperation suggestions with the second participating entity after the t-th time unit, and the contract results are used to indicate the execution status of the smart contract.

[0335] In some embodiments, the processor 1201 is further configured to:

[0336] Based on the scoring information within the t-th time unit, the relative importance of different influencing factors within the t-th time unit is determined, and a judgment matrix is ​​obtained;

[0337] Consistency verification is performed based on the judgment matrix to obtain the weight information of the influencing factors in the t-th time unit.

[0338] In some embodiments, the processor 1201 is further configured to:

[0339] Based on the contract performance status of the second participating entity in the (t-1)th time unit, update the trust factor of the second participating entity in the (t-1)th time unit;

[0340] With the goal of minimizing the trust factor in the t-th time unit obtained by weighting the scoring information and weight information, and the trust factor based on the contract performance status update of the second participating entity in the (t-1)-th time unit, the weight information of the influencing factor in the t-th time unit is optimized.

[0341] In some embodiments, the processor 1201 is further configured to:

[0342] Based on the rating information of the trust factor and the influence factor of the second participating subject in the t-th time unit, the sensitivity of the influence factor to the change of the trust factor is determined.

[0343] Based on the sensitivity and the weight information of the influencing factors in the t-th time unit, the weight information of the influencing factors in the (t+1)-th time unit is determined.

[0344] Preferably, the present invention also provides an electronic device 1200, including a processor 1201, a memory 1202, and a computer program stored in the memory 1202 and executable on the processor 1201. When the computer program is executed by the processor 1201, it implements the various processes of the above-described cooperative processing method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0345] This invention also provides a readable storage medium storing a computer program. When executed by a processor, this computer program implements the various processes of the above-described cooperative processing method embodiments and achieves the same technical effects. To avoid repetition, it will not be described again here. The readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0346] This application also provides a computer program product, including computer instructions. When executed by a processor, the computer instructions implement the various processes of the above-described cooperative processing method embodiments and achieve the same technical effects. To avoid repetition, they will not be described again here.

[0347] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0348] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0349] In the embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0350] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of the present invention, depending on actual needs.

[0351] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0352] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0353] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A cooperative processing method, characterized in that, The method includes: Obtain the first cooperation ratio among the cooperative groups that cooperate with the first participating entity within the t-th time unit, where the cooperative group includes the first participating entity and the second participating entity that cooperates with the first participating entity, and t is a positive integer; Obtain the contract parameter information of the smart contract relative to the first participating entity within the t-th time unit. The smart contract is used to execute the cooperation between the first participating entity and the second participating entity. The contract parameter information is used to reflect the behavior of the cooperative group cooperating with the first participating entity. Based on the first cooperation ratio and the contract parameter information, the first revenue information and the second revenue information within the t-th time unit are determined. The first revenue information indicates the expected revenue of the cooperative group relative to the first participating entity's choice of cooperation strategy, and the second revenue information indicates the average revenue of the cooperative group. Based on the first and second revenue information, the cooperation trend of the cooperative group relative to the first participating entity in choosing a cooperation strategy is determined within the t-th time unit. The cooperation trend is used to determine the contract parameter information relative to the first participating entity within the (t+1)-th time unit.

2. The method according to claim 1, characterized in that, The contract parameter information includes a trust factor for a second participating entity that cooperates with the first participating entity, and the method further includes: Obtain the score information of the influence factor within the t-th time unit, as well as the weight information of the influence factor, which is used to influence the cooperation between the first participating entity and the second participating entity; The scoring information and the weighting information are weighted to obtain the trust factor of the second participating entity in the t-th time unit. The trust factor of the second participating entity in the t-th time unit is used to determine the first benefit information and the second benefit information.

3. The method according to claim 2, characterized in that, The method further includes: Based on the contract performance status of the second participating entity in the t-th time unit, update the trust factor of the second participating entity in the t-th time unit to obtain the trust factor of the second participating entity in the (t+1)-th time unit.

4. The method according to claim 2, characterized in that, The contract parameter information also includes the reward and penalty growth factor for the second participating entity, and the method further includes: Obtain the contract performance status of the second participating entity within the t-th time unit; Based on the contract performance and the trust factor of the second participating entity in the t-th time unit, determine the reward and punishment growth factor of the second participating entity in the t-th time unit; Based on the reward and punishment growth factor, determine the reward and punishment benefits of the second participating entity within the t-th time unit; The determination of the first revenue information and the second revenue information within the t-th time unit based on the first cooperation ratio and the contract parameter information includes: Based on the first cooperation ratio, the contract parameter information, and the reward and punishment benefits, the first benefit information and the second benefit information within the t-th time unit are determined.

5. The method according to claim 4, characterized in that, The method further includes: If, during the execution of the smart contract, the number of defaults by the second participating entity is greater than or equal to a first preset threshold, or if the first cooperation ratio is less than or equal to a second preset threshold within the t-th time unit, the smart contract is terminated and target information is output; wherein, The target information includes the cooperation trend, strategy suggestions, and contract results of the cooperative group relative to the first participating entity in the t-th time unit. The strategy suggestions are used to indicate the cooperation suggestions with the second participating entity after the t-th time unit, and the contract results are used to indicate the execution status of the smart contract.

6. The method according to claim 2, characterized in that, Obtain the weight information of the influence factors within the t-th time unit, including: Based on the scoring information within the t-th time unit, the relative importance of different influencing factors within the t-th time unit is determined, and a judgment matrix is ​​obtained; Consistency verification is performed based on the judgment matrix to obtain the weight information of the influencing factors in the t-th time unit.

7. The method according to claim 6, characterized in that, After determining the weight information of the influencing factors in the t-th time unit based on the relative importance, the method further includes: Based on the contract performance status of the second participating entity in the (t-1)th time unit, update the trust factor of the second participating entity in the (t-1)th time unit; With the goal of minimizing the trust factor in the t-th time unit obtained by weighting the scoring information and weight information, and the trust factor based on the contract performance status update of the second participating entity in the (t-1)-th time unit, the weight information of the influencing factor in the t-th time unit is optimized.

8. The method according to claim 6, characterized in that, After performing consistency verification based on the judgment matrix to obtain the weight information of the influencing factors in the t-th time unit, the method further includes: Based on the rating information of the trust factor and the influence factor of the second participating subject in the t-th time unit, the sensitivity of the influence factor to the change of the trust factor is determined. Based on the sensitivity and the weight information of the influencing factors in the t-th time unit, the weight information of the influencing factors in the (t+1)-th time unit is determined.

9. A cooperative processing apparatus, characterized in that, The device includes: The first acquisition module is used to acquire the first cooperation ratio selected from the cooperative group to cooperate with the first participating entity within the t-th time unit. The cooperative group includes the first participating entity and the second participating entity cooperating with the first participating entity, where t is a positive integer. The second acquisition module is used to acquire contract parameter information of the smart contract relative to the first participating entity within the t-th time unit. The smart contract is used to execute the cooperation between the first participating entity and the second participating entity. The contract parameter information is used to reflect the behavior of the cooperative group cooperating with the first participating entity. The first determining module is used to determine the first revenue information and the second revenue information within the t-th time unit based on the first cooperation ratio and the contract parameter information. The first revenue information indicates the expected revenue of the cooperative group relative to the cooperation strategy chosen by the first participating entity, and the second revenue information indicates the average revenue of the cooperative group. The second determining module is used to determine the cooperation trend of the cooperative group relative to the first participating entity in choosing a cooperation strategy within the t-th time unit based on the first revenue information and the second revenue information. The cooperation trend is used to determine the contract parameter information relative to the first participating entity within the (t+1)-th time unit.

10. An electronic device, characterized in that, include: A processor, a memory, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the steps of the cooperative processing method as described in any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the cooperative processing method as described in any one of claims 1 to 8.

12. A computer program product, characterized in that, It includes computer instructions that, when executed by a processor, implement the steps of the cooperative processing method as described in any one of claims 1 to 8.

Images