Business publishing methods, devices, computer equipment, and storage media

Abstract

This application relates to a business publishing method, apparatus, computer equipment, and storage medium, belonging to the field of financial information technology. A first iterative model adjusts the business selection strategy based on the user's previous iteration's business selection information and outputs the business selection information. A second iterative model outputs new resource values ​​and a new publishing quantity based on the output business selection information. The first and second iterative models are trained iteratively through game theory until both models meet corresponding preset conditions. Based on the target resource value and target publishing quantity when the second iterative model meets its preset conditions, multiple businesses are published to the consortium blockchain. Compared to the traditional approach where the business issuer directly determines the business information before publishing, this solution utilizes two models with different perspectives for game-theoretic training to obtain stable business information before publishing through the consortium blockchain, which is beneficial for achieving an optimal benefit balance between the business issuer and the user.

Description

Technical Field

[0001] This application relates to the field of financial information technology, and in particular to a business publishing method, apparatus, computer equipment, storage medium, and computer program product. Background Technology

[0002] Currently, in the process of handling business, the business publisher needs to determine the conditions for handling the business, such as the amount of resources required to complete the business. Users then need to transfer the corresponding amount of resources to the business publisher to complete the business. The current business publishing and processing process typically involves the business publisher determining the conditions for the business to be published, then announcing the relevant business and its conditions to users. Users then select the business and the business publisher they wish to apply for based on the received business information and conditions.

[0003] However, due to the complexity of user preferences and frequent interactions between users and different service providers, information asymmetry exists between them. Furthermore, the completion of a service transaction depends on the user's trust in the service provider. Therefore, it is impossible for service providers to determine their own transaction conditions when publishing services, as this will not achieve the optimal balance of benefits between them and users. Summary of the Invention

[0004] Therefore, it is necessary to provide a business publishing method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can achieve an optimal balance of benefits to address the aforementioned technical problems.

[0005] Firstly, this application provides a service publishing method. The method includes:

[0006] The system obtains the business information to be published by the publisher object, synchronizes the business information to a pre-built consortium blockchain, and broadcasts it to the nodes of the user group through the consortium blockchain. The business information includes the publisher object information, resource value, and publication quantity of each business. The consortium blockchain includes a publisher group consisting of multiple nodes corresponding to multiple publisher objects, and a user group consisting of multiple nodes corresponding to multiple user objects.

[0007] Based on the business information stored in the consortium blockchain, the business selection information of each user object is simulated through a first iterative model, and the business selection information is saved to the consortium blockchain; the first iterative model is used to adjust the selection strategy of each user object for each business based on the current business information stored in the consortium blockchain, and to simulate the business selection information of each user object under the current business information.

[0008] Based on the business selection information stored in the consortium blockchain, a second iterative model is used to determine the new resource values ​​and new release quantities for each business, and the new resource values ​​and new release quantities are updated to the consortium blockchain and broadcast to the user group through the consortium blockchain; the second iterative model is used to determine the current preferences of the user group and the supply-demand ratio of each business based on the latest business selection information and the release quantity and resource values ​​of each business stored in the consortium blockchain, and to update the resource values ​​and release quantities of each business according to the current preference information and the current supply-demand ratio;

[0009] Returning to the step of simulating the business selection information of each user object through the first iterative model and saving the business selection information to the consortium blockchain, based on the output of the first iterative model and the output of the second iterative model, the first iterative model and the second iterative model are subjected to game-theoretic iterative training in the consortium blockchain until the first iterative model meets the first preset condition and the second iterative model meets the second preset condition;

[0010] Based on the target resource value and target release quantity obtained when the second iterative model meets the second preset condition, the multiple services are released to the consortium blockchain.

[0011] In one embodiment, the step of simulating the business selection information of each user object through a first iterative model based on the business information stored in the consortium blockchain includes:

[0012] The business information stored in the consortium blockchain is input into the first iterative model. The supply-demand ratio of each business is determined through the first iterative model. Based on the historical business selection information of each user object in the previous iteration, the resource values ​​of multiple businesses, and the supply-demand ratio, the values ​​of the first resource transfer parameter and the second resource transfer parameter of the user group for each business are determined. The business selection strategy is adjusted according to the values ​​of the first and second resource transfer parameters. Based on the business selection strategy, the business selection information of each user object under the current business information is simulated in the current iteration.

[0013] The second resource transfer parameter is the average value of the values ​​of the first resource transfer parameters corresponding to multiple services; the adjustment objective of the service selection strategy is to reduce the difference between the values ​​of the first resource transfer parameter and the second resource transfer parameter.

[0014] In one embodiment, determining the supply-demand ratio of each service using the first iterative model includes:

[0015] Based on the historical service selection information of each user object and the resource values ​​of each service, determine the optimal demand of each user object for each service;

[0016] Based on the historical service selection information and the optimal demand, the user group's demand expectations for each service are determined;

[0017] The supply-demand ratio for each service is determined based on the ratio of the number of services released to the expected demand.

[0018] In one embodiment, determining the optimal demand for each service for each user based on the historical service selection information of each user and the resource values ​​of each service includes:

[0019] Based on the historical service selection information, determine the number of times each user selects each service, and obtain the current maximum and minimum demand for each service for each user.

[0020] Based on the selected quantity and the resource values ​​of each service, determine the value of the individual resource transfer parameter corresponding to each user object;

[0021] Based on the resource values ​​of each service, the maximum demand, and the minimum demand, the demand corresponding to maximizing the value of the individual resource transfer parameter is determined, which serves as the optimal demand for each user object for each service.

[0022] In one embodiment, determining the values ​​of the first resource transfer parameter for each service and the second resource transfer parameter for the user group for multiple services based on the historical service selection information, resource values ​​of multiple services, and the supply-demand ratio includes:

[0023] Based on the optimal demand for each user object, determine the optimal demand for the user group for multiple services;

[0024] Based on the comparison result between the supply and demand ratio and the preset threshold, a first parameter is determined. Based on the optimal demand of the user group and the first parameter, the value of the first resource transfer parameter for each service of the user group is determined.

[0025] Based on the values ​​of the first resource transfer parameters corresponding to multiple services and the historical service selection information, the values ​​of the second resource transfer parameters for the user group for multiple services are determined.

[0026] In one embodiment, determining the first parameter based on the comparison result of the supply-demand ratio and a preset threshold includes:

[0027] If the supply-demand ratio is greater than or equal to the preset threshold, the first parameter is determined to be a preset first value.

[0028] Otherwise, the value of the first parameter is determined based on the supply-demand ratio and the square of the supply-demand ratio.

[0029] In one embodiment, the historical service selection information represents the selection probability of each user object for each service; adjusting the service selection strategy based on the values ​​of the first resource transfer parameter and the second resource transfer parameter, and outputting the service selection information of each user object under the current service information based on the service selection strategy, includes:

[0030] The difference between the value of the first resource transfer parameter and the value of the second resource transfer parameter is obtained through the first iterative model.

[0031] Based on the product of the difference and the historical service selection information, and the sum of the product and the historical service selection information, the output information of the first iterative model is determined, which serves as the service selection information for each user object under the current service information in this iteration.

[0032] In one embodiment, determining the new resource values ​​and new release quantities for each service based on the service selection information stored in the consortium blockchain using a second iterative model includes:

[0033] The business selection information stored in the consortium blockchain is input into the second iterative model. The difference between the supply-demand ratio and the value corresponding to the supply-demand balance is obtained through the second iterative model. Based on the sum of the difference and the resource value, a new resource value is output.

[0034] Based on the number of releases, determine the value of the cost parameter corresponding to the business;

[0035] Based on the resource values ​​and cost parameters, the new release quantity for each service is determined; the supply-demand ratio and service selection information obtained based on the new resource values ​​and new release quantities for each service tend to stabilize.

[0036] In one embodiment,

[0037] The first preset condition is that the difference between the value of the first resource transfer parameter and the value of the second resource transfer parameter is less than a preset threshold.

[0038] The second preset condition is that both the supply-demand ratio and the business selection information reach a preset convergence target.

[0039] Secondly, this application also provides a business publishing device, the device comprising:

[0040] The acquisition module is used to acquire the business information to be published by the publisher object, synchronize the business information to the pre-built consortium blockchain, and broadcast it to the nodes of the user group through the consortium blockchain; the business information includes the publisher object information, resource value and publication quantity of each business; the consortium blockchain includes a publisher group consisting of multiple nodes corresponding to multiple publisher objects, and a user group consisting of multiple nodes corresponding to multiple user objects.

[0041] The first iteration module is used to simulate the business selection information of each user object based on the business information stored in the consortium blockchain through a first iteration model, and save the business selection information to the consortium blockchain; the first iteration model is used to adjust the selection strategy of each user object for each business based on the current business information stored in the consortium blockchain, and simulate the business selection information of each user object under the current business information.

[0042] The second iteration module is used to determine the new resource values ​​and new release quantities for each service based on the service selection information stored in the consortium blockchain, and update the new resource values ​​and new release quantities to the consortium blockchain, and broadcast them to the user group through the consortium blockchain; the second iteration model is used to determine the current preferences of the user group and the supply-demand ratio of each service based on the latest service selection information and the release quantity and resource values ​​of each service stored in the consortium blockchain, and update the resource values ​​and release quantities of each service according to the current preference information and the current supply-demand ratio;

[0043] The training module is used to return the business selection information of each user object simulated by the first iterative model and save the business selection information to the consortium blockchain. Based on the output of the first iterative model and the output of the second iterative model, the first iterative model and the second iterative model are trained in a game-theoretic manner in the consortium blockchain until the first iterative model meets the first preset condition and the second iterative model meets the second preset condition.

[0044] The publishing module is used to publish the multiple services to the consortium blockchain based on the target resource value and target publishing quantity obtained when the second iterative model meets the second preset condition.

[0045] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method described above.

[0046] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the above-described method.

[0047] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the above-described method.

[0048] The aforementioned service publishing method, apparatus, computer equipment, storage medium, and computer program product broadcast service information in a consortium blockchain. A first iterative model adjusts the service selection strategy based on the user's previous iteration's service selection information and outputs the service selection information. A second iterative model outputs new resource values ​​and a new publishing quantity based on the output service selection information. The first and second iterative models are trained iteratively through game theory until both models meet their respective preset conditions. Based on the target resource values ​​and target publishing quantity when the second iterative model meets its preset conditions, multiple services are published to the consortium blockchain. Compared to the traditional approach where the service issuer directly determines the service information before publishing, this scheme utilizes two models with different perspectives for iterative training to obtain stable service information before publishing through the consortium blockchain. This facilitates an optimal balance of benefits between the service issuer and the user. Attached Figure Description

[0049] Figure 1 This is an application environment diagram of a service publishing method in one embodiment;

[0050] Figure 2 This is a flowchart illustrating a service publishing method in one embodiment;

[0051] Figure 3 This is a schematic diagram of the information iteration steps for service selection in one embodiment;

[0052] Figure 4 A schematic diagram illustrating the information iteration step for service selection in another embodiment;

[0053] Figure 5 This is a schematic diagram of the information entropy convergence step in one embodiment;

[0054] Figure 6 This is a schematic diagram of the business information convergence steps in one embodiment;

[0055] Figure 7 This is a structural block diagram of a service publishing device in one embodiment;

[0056] Figure 8 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0058] The service publishing method provided in this application embodiment can be applied to, for example, Figure 1 In the application environment shown, the server nodes in the blockchain can communicate with each other. The server of the business publisher can simulate user business selection information for each business based on the business information of the business publisher using a first iterative model, and adjust and output new business information based on the output business selection information using a second iterative model. Through game-theoretic iterative training of the first and second iterative models, the business information that meets the optimal benefit balance is finally obtained and published to the blockchain. Here, j represents the business of the j-th business publisher, and Γ represents the number of business publishers, specifically Γ = {1, 2, ..., n}. j}; i represents the i-th user object, and φ represents the set of user groups, specifically φ = {1, 2, ..., m}. i}; then S(S={S Г S φ}) represents the group type, S Г Indicates the type of business publisher group, S φ This indicates the type of user group; it can also include a time series T = {1, 2, ..., t}, representing the number of game rounds or the number of cycles of interaction between the business publisher and the user. In a blockchain, each server can be implemented using an independent server or a server cluster composed of multiple servers.

[0059] In one embodiment, such as Figure 2 As shown, a business deployment method is provided, which can be applied to... Figure 1 Taking the server node in the example, the following steps are included:

[0060] Step S202: Obtain the business information to be published by the publisher object, synchronize the business information to the pre-built consortium blockchain, and broadcast it to the nodes of the user group through the consortium blockchain; the business information includes the publisher object information, resource value and publication quantity of each business; the consortium blockchain includes a publisher group consisting of multiple nodes corresponding to multiple publisher objects, and a user group consisting of multiple nodes corresponding to multiple user objects.

[0061] In this system, the publisher object can be a business publisher object, and there can be multiple publisher objects. Each publisher object can publish one business and its business information, resulting in multiple business information items. The publisher object's server can synchronize the business information to be published to a pre-built consortium blockchain after obtaining it. The consortium blockchain can include a publisher group consisting of multiple nodes corresponding to multiple publisher objects, and a user group consisting of multiple nodes corresponding to multiple user objects. Publisher objects can publish business information in the consortium blockchain, and user objects can select the corresponding business information to process within the blockchain. Nodes in the user group can obtain the corresponding business information from the consortium blockchain. The business information includes publisher object information, the resource values ​​required to process the business, and the number of business items to be published.

[0062] The aforementioned publisher and user objects can engage in iterative game theory based on business information and user choices regarding the business. That is, publishers adjust their business information based on user choices, and users adjust their choices based on the business information. This game theory can be implemented using a two-layer model within a blockchain. For example, the aforementioned consortium blockchain can be a type of blockchain, comprising a user group and a publisher group. The user group layer contains node user objects connected by a blockchain system network topology, and each user object gradually changes its business needs over time. The publisher's server can respond to changes in user business choice strategies by adjusting its resource value strategy accordingly. Specifically, the publisher's server models the user's business choice strategy as an evolutionary game to represent the evolution of the user's business choice strategy. Within the publisher group, each publisher determines and supplies resources based on user needs, and the interaction among multiple publishers in setting resource values ​​through the system platform is modeled as a non-cooperative game. The server of the publisher object can construct a two-layer game model based on the evolutionary model of the user group and the non-cooperative game model of the publisher object. This two-layer game model has information entropy. The server of the publisher object can formally model the two-layer game model with information entropy and then carry out game iteration.

[0063] Step S204: Based on the business information stored in the consortium blockchain, the business selection information of each user object is simulated through the first iterative model, and the business selection information is saved to the consortium blockchain; the first iterative model is used to adjust the selection strategy of each user object for each business based on the current business information stored in the consortium blockchain, and to simulate the business selection information of each user object under the current business information.

[0064] The aforementioned publisher object can store the determined business information in the consortium blockchain. The publisher object's server can pre-build a first iterative model, input the aforementioned business information into the first iterative model, and adjust the selection strategies of each user object for each business based on the current business information. After simulating the business selection information of each user object under the current business information, the simulated business selection information is output and stored in the consortium blockchain. This business selection information can be new business selection information. The publisher object's server can store this business selection information in the consortium blockchain. The first iterative model can be constructed based on the user's previous iteration's business selection information, the values ​​of the first resource transfer parameter, and the values ​​of the second resource transfer parameter. The first resource transfer parameter can represent the parameters corresponding to resource transfers for each business by the user group, and the second resource transfer parameter can represent the parameters corresponding to resource transfers for multiple businesses by the user group. Furthermore, the value of the second resource transfer parameter can be the average value of multiple first resource transfer parameters.

[0065] Step S206: Based on the business selection information stored in the consortium blockchain, the new resource values ​​and new release quantities for each business are determined through the second iteration model, and the new resource values ​​and new release quantities are updated to the consortium blockchain and broadcast to the user group through the consortium blockchain; the second iteration model is used to determine the current preferences of the user group and the supply-demand ratio of each business based on the latest business selection information and the release quantity and resource values ​​of each business stored in the consortium blockchain, and to update the resource values ​​and release quantities of each business according to the current preference information and the current supply-demand ratio.

[0066] In this model, the user's business selection information output by the first iterative model can be stored in the consortium blockchain. The server of the publishing party can input the current business selection information into the second iterative model. Based on the latest stored business selection information and the release quantity and resource value of each business, the second iterative model determines the current preferences of the user group and the supply-demand ratio of each business. After updating the resource value and release quantity of each business according to the current preference information and the current supply-demand ratio, it outputs the new resource value and new release quantity for each business. The server of the publishing party can update the new resource value and new release quantity to the consortium blockchain, which can then be broadcast to the user group. Thus, the server of the publishing party can use the first iterative model to simulate the adjustment of the user group's selection strategy for each business after receiving the new resource value and new release quantity of each business, realizing iterative game theory.

[0067] The release quantity can be the release quantity for each of the aforementioned services, and the resource value can be the resource value that needs to be transferred to the release object when a user selects each service. Specifically, there can be corresponding release quantities and resource values ​​at each point in time. The release quantity can be expressed as... It represents the business j (j∈Г) at time t. k (t k The number of resources published (∈T); resource values ​​are represented as It represents the business j (j∈Г) at time t. k (t k The resource value corresponding to ∈T).

[0068] Step S208: Return to the step of simulating the business selection information of each user object through the first iterative model and saving the business selection information to the consortium blockchain. Based on the output of the first iterative model and the output of the second iterative model, perform game-theoretic iterative training on the first iterative model and the second iterative model in the consortium blockchain until the first iterative model meets the first preset condition and the second iterative model meets the second preset condition.

[0069] In this process, after the server of the publishing object determines the new resource values ​​and new publishing quantities for each service through the second iteration model, it can return to the steps described above, which simulated the service selection information of each user object through the first iteration model and saved the service selection information to the consortium blockchain. Then, based on the outputs of the first and second iteration models, the server of the publishing object performs game-theoretic iterative training on the first and second iteration models within the consortium blockchain until the first iteration model meets the first preset condition and the second iteration model meets the second preset condition, at which point the iteration ends. That is, the first iteration model needs to consider the resource values ​​and publishing quantities output by the second iteration model to adjust the user object's service selection strategy, so that the user object has higher efficiency after selecting the service. The second iteration model needs to consider the service selection information output by the first iteration model to adjust the resource values ​​and publishing quantities of each service, so that the publishing object has higher efficiency after publishing the service. The aforementioned first and second preset conditions respectively indicate that the outputs of the first and second iteration models have reached a stable state.

[0070] Step S210: Based on the target resource value and target release quantity obtained when the second iterative model meets the second preset condition, release multiple services to the consortium blockchain.

[0071] When the first iterative model meets the first preset condition, its output is the target selection information of user objects for each service, reaching a stable state. When the server of the publishing object meets the second preset condition based on the second iterative model and the aforementioned target selection information, its output is the target resource value and target publication quantity, reaching a stable state. Thus, the server of the publishing object can use the aforementioned target resource value and target publication quantity as the target service information for the aforementioned multiple services. The server of the publishing object publishes the multiple services and their target service information to the aforementioned consortium blockchain. Each user object can select and process services based on the target service information. In this case, an optimal balance of benefits can be achieved between the publishing object and the user objects.

[0072] In the aforementioned business deployment method, business information is broadcast in the consortium blockchain. A first iterative model adjusts the business selection strategy based on the user's previous iteration's business selection information and outputs the new business selection information. A second iterative model outputs new resource values ​​and a new deployment quantity based on the output business selection information. The first and second iterative models are trained iteratively in a game-theoretic manner until both models meet their respective preset conditions. Based on the target resource values ​​and target deployment quantity when the second iterative model meets its preset conditions, multiple businesses are deployed to the consortium blockchain. Compared to the traditional method where the business issuer directly determines the business information before deployment, this scheme utilizes two models with different perspectives for game-theoretic iterative training to obtain stable business information before deployment through the consortium blockchain. This approach helps achieve an optimal balance of benefits between the business issuer and the user.

[0073] In one embodiment, based on the business information stored in the consortium blockchain, the business selection information of each user object is simulated through a first iterative model, including: inputting the business information stored in the consortium blockchain into the first iterative model; determining the supply-demand ratio of each business through the first iterative model; determining the values ​​of the first resource transfer parameters for each business and the values ​​of the second resource transfer parameters for multiple businesses based on the historical business selection information of each user object in the previous iteration, the resource values ​​of multiple businesses, and the supply-demand ratio; adjusting the business selection strategy based on the values ​​of the first and second resource transfer parameters; and simulating the business selection information of each user object under the current business information in the current iteration based on the business selection strategy; wherein, the value of the second resource transfer parameter is the average value of the values ​​of multiple first resource transfer parameters corresponding to multiple businesses; and the adjustment objective of the business selection strategy is to reduce the difference between the values ​​of the first and second resource transfer parameters.

[0074] In this embodiment, the consortium blockchain can store business information determined by the second iteration model of the publishing object. This business information may include publishing object information, resource values, and publishing quantity. The server of the publishing object inputs the above-mentioned business information into the first iteration model, which can determine the supply-demand ratio of each business based on the business information. The supply-demand ratio represents the ratio of the number of businesses published by the publishing object to the number of businesses selected by the user object. The first iteration model can be constructed based on business selection information, the values ​​of the first resource transfer parameter, and the values ​​of the second resource transfer parameter. Furthermore, the iteration can be repeated multiple times. The server of the publishing object can determine the values ​​of the first resource transfer parameter for each user group for each business and the values ​​of the second resource transfer parameter for each user group for multiple businesses based on the historical business selection information of each user object in the previous iteration, the resource values ​​of multiple businesses, and the supply-demand ratio. In the first iteration, the historical service selection information of each user object in the previous iteration can be pre-set, for example, by randomly selecting the service selection information of each user object. The value of the first resource transfer parameter can represent the value of the resources transferred by each user object in the user group for each selected service. The value of the second resource transfer parameter can be determined based on the value of the resources transferred by each user object in the user group when selecting multiple services. The value of the second resource transfer parameter can be the average value of multiple first resource transfer parameters corresponding to multiple services. The first resource transfer parameter can also be called the net payoff function of the user group, and the second resource transfer parameter can also be called the average net payoff function of the user group.

[0075] After the server of the publishing object obtains the values ​​of the first resource transfer parameter and the second resource transfer parameter, it can adjust the business selection strategy based on these values. This allows the first iterative model to simulate the business selection information of each user object under the current business information in this iteration. The adjustment objective of the business selection strategy is to reduce the difference between the values ​​of the first and second resource transfer parameters.

[0076] The aforementioned historical service selection information can represent the selection probability of each user object for each service. The publisher's server can then iterate through the service selection information multiple times based on these probabilities. For example, in one embodiment, when adjusting the service strategy using a first iterative model, the publisher's server can obtain the difference between the values ​​of the first and second resource transfer parameters using the first iterative model. Based on the product of this difference and the historical service selection information, and the sum of this product and the historical service selection information, the output information of the first iterative model is determined, serving as the service selection information for each user object under the current service information in this iteration.

[0077] Specifically, the first iterative model described above is stable, and its iteration can be a game optimization mechanism with the concept of information entropy. The server of the publisher object can obtain the average dynamic differential equation of the evolutionary game model of the user object based on the first resource transfer parameters as follows:

[0078] in, Indicates the partial derivative sign. Indicates the user group in t k The probability of time selecting each service j can also be called service selection information. Indicates t k The value of the time-first resource transfer parameter. Indicates t k时间 The value of the second resource transfer parameter.

[0079] Then, the terminal can perform approximate iteration using the following discrete replication dynamic formula under continuous time action: This formula can then be used as the first iterative model; where T represents the number of iterations, and k1 represents the iteration step size. For any small difference constant ε1>0, the following is performed... Then this formula can be used as the first preset condition, that is, the first preset condition is that the difference between the value of the first resource transfer parameter and the value of the second resource transfer parameter is less than the preset threshold ε1.

[0080] The publisher's server can iteratively optimize the user selection strategy based on an evolutionary stabilization approach. For example, at T=1, the publisher's server initializes the distribution of the user object's business selection strategy. User object i∈φ randomly selects a service j∈Г for processing. Through interaction, the server of the publishing object determines the value of the first resource transfer parameter based on the above parameters. Then, based on the blockchain network backup data, it integrates all S(S={S Г S φThe selection process within the `})` parameter, i.e., the user group's choice of various services, involves calculating the value of the second resource transfer parameter. The publisher's server then adjusts the user's service selection strategy for each service `j` based on the aforementioned parameters and their values ​​using the first iterative model. The server of the publishing object sets T = T + 1, and repeats the above steps until the first preset condition is met, i.e.

[0081] The first iterative model described above has an asymptotically stable solution, specifically: It possesses asymptotically stable solutions. This can be proven, for example, using the Lyapunov function employed in replication dynamics. Specifically, the server of the publisher object can be configured to have an evolutionarily stable solution vector. Then we have the Lyapunov function:

[0082] Because the vector components of the evolutionary stable solution satisfy If this holds for any j∈Г, then It is always true, that is It always possesses positive definiteness. The server command function of the publisher object. Taking the partial derivative with respect to time t, we get:

[0083] When the evolutionary game used for the group is asymptotically stable, for the business publisher object that receives the largest value of the first resource transfer parameter, the following always holds: This explains the Lyapunov function. At θ=θ * Since the time possesses negative definiteness, according to the strategy stability theorem for negative definiteness, the stable solution θ = θ of the proven evolutionary game model of the user group is... * It exhibits asymptotic stability. At this point, the user's selection strategy in the evolutionary game model converges to an asymptotically stable state over time, that is, it reaches Pareto optimality, meaning the selection strategy will converge to the evolutionary equilibrium of the game model.

[0084] Through the above embodiments, the server of the publishing object can use the first iterative model to iteratively simulate the user's business selection information based on the supply-demand ratio, the value of the first resource transfer parameter, and the value of the second resource transfer parameter, so that the end user's business selection information tends to be stable. Business can be published based on stable business selection information to achieve the optimal balance of benefits.

[0085] In one embodiment, determining the supply-demand ratio of each service through a first iterative model includes: determining the optimal demand for each service for each user based on the historical service selection information of each user and the resource values ​​of each service; determining the user group's demand expectation for each service based on the historical service selection information and the optimal demand; and determining the supply-demand ratio corresponding to each service based on the ratio of the number of services released to the demand expectation.

[0086] In this embodiment, the publisher's server can determine the supply-demand ratio for each service in each iteration. The publisher's server can first obtain the historical service selection information of each user object and the resource values ​​for each service. The resource values ​​represent the amount of resources that need to be transferred to the publisher object corresponding to that service when a user selects it. The publisher's server can then determine the optimal demand for each user object for each service based on the historical service selection information and resource values ​​of each service through the first iteration model. The optimal demand represents the user object's demand at time t. k The timeframe represents the business demand that maximizes the benefits for the user group. The publisher's server can also, based on the first iterative model and the aforementioned historical business selection information and optimal demand, determine the user group's expected demand for each business. Here, expected demand represents the user group's anticipated demand for each business in the future. The publisher's server can, based on the first iterative model, determine the supply-demand ratio for each business based on the ratio of the published quantity of each business to the expected demand.

[0087] The server of the publishing object can determine the optimal demand for each user object for each service using a specific formula. For example, in one embodiment, the server of the publishing object can determine the number of times each user object selects each service based on historical service selection information, and obtain the maximum and minimum demand for each service for each user object at present. Each service can be processed multiple times, and the benefits obtained by the user can vary with the number of processing times; therefore, the number of selections represents the number of times a user object processes each service. The maximum demand represents the maximum number of services a user object can process at the current time, and the minimum demand represents the minimum number of services a user object needs to process at the current time to maintain its benefits. The server of the publishing object can determine the value of the individual resource transfer parameter corresponding to each user object based on the selection number and the resource value of each service. Furthermore, the server of the publishing object can also determine the demand corresponding to the maximum value of the individual resource transfer parameter based on the resource value of each service, the maximum demand, and the minimum demand, as the optimal demand for each user object for each service.

[0088] Specifically, the server of the publisher object can pre-construct individual utility functions corresponding to each user object:

[0089] in, This represents individual i in the customer group at time t. k The number of purchases of service j; This represents a parameter that changes over time, and its value can be set based on actual conditions. and Let represent the minimum and maximum processing capacity that a user object can handle at time tk (tk∈T), respectively. Clearly, as time tk changes, different... The utility function corresponding to the numerical value It can directly reflect the dynamic needs of each user object for business. To obtain meaningful utility dynamics, the publisher's server assumes, without loss of generality...

[0090] When user object i chooses to make a business selection action from publisher object j, it needs to pay... For the seller, the resource transfer parameters for each individual user are: in This represents the parameters for individual resource transfer.

[0091] Within the blockchain node network communication structure, user objects can connect to form a group. Without loss of generality, let's take the scenario where the buyer group is a single group as an example. After receiving resource values ​​for different services published by the blockchain platform, each user object selects a seller to trade goods. To clarify the user object's selection behavior, the publisher's server can configure it so that each user object must explicitly select a service; users can adjust their selected service at any time; and each user object's selection behavior is independent. As replication dynamics shows, individual strategies within a single group are identical. Therefore, the publisher's server can set service selection information... Indicates time t k The probability that a rational user group φ (φ=1) chooses service j, where and Then when user object i is at time t k When selecting service j for processing, the optimal demand of the user can be obtained from the values ​​of the aforementioned individual resource transfer parameters:

[0092] in, This represents the optimal demand. The publisher's server can also... Indicates time t k The expected demand of user group φ (φ=1) for business j is... The server of the publisher object can obtain a functional expression for the supply-demand ratio based on the above parameters. This functional expression can specifically be: In a stable evolutionary state, the number of business deployments and resource values ​​of the publisher object are fixed constants. Furthermore, as shown in the above formula, the optimal demand is also a fixed constant. Therefore, the parameters in the supply-demand ratio mentioned above are... It is a constant.

[0093] Through the above embodiments, the server of the publishing object can determine the supply-demand ratio of each service based on the optimal demand and the resource values ​​of each service resource. Then, the server of the publishing object can iteratively train the first and second iterative models based on the supply-demand ratio, and publish services based on the resource values ​​and publishing quantity after iteration, so as to achieve the optimal balance of benefits.

[0094] In one embodiment, determining the values ​​of a first resource transfer parameter for each service and a second resource transfer parameter for each service based on historical service selection information, resource values ​​of multiple services, and supply-demand ratio includes: determining the optimal demand of the user group for multiple services based on the optimal demand corresponding to each user object; determining a first parameter based on the comparison result of the supply-demand ratio and a preset threshold; determining the values ​​of the first resource transfer parameters for each service based on the optimal demand of the user group and the first parameter; and determining the values ​​of the second resource transfer parameters for multiple services based on the values ​​of the first resource transfer parameters corresponding to multiple services and historical service selection information.

[0095] In this embodiment, the server of the publishing object can determine the values ​​of the first resource transfer parameter and the second resource transfer parameter when adjusting the service selection strategy in the first iterative model. The server of the publishing object can pre-determine the optimal demand of the user group for multiple services based on the optimal demand of each user object. It then obtains the comparison result between the aforementioned supply-demand ratio and a preset threshold, and determines the first parameter based on this comparison result. For example, in some embodiments, if the supply-demand ratio is greater than or equal to the preset threshold, the server of the publishing object can determine the first parameter as a preset first value; otherwise, if the supply-demand ratio is greater than zero and less than the preset threshold, the server of the publishing object can determine the value of the first parameter based on the supply-demand ratio and the square of the supply-demand ratio.

[0096] The publisher's server can determine the values ​​of the first resource transfer parameters for each service based on the optimal demand of the user group and the aforementioned first parameters. Furthermore, the publisher's server can also determine the values ​​of the second resource transfer parameters for multiple services based on the values ​​of the first resource transfer parameters corresponding to multiple services and the aforementioned historical service selection information.

[0097] Specifically, the aforementioned first resource transfer parameter can also be called the net transfer function of the user group φ (φ = 1), which can be used as... This indicates that the user group in t specifically means... k The net resource transfer value of time to business j. For different values ​​of λ, the value of the first resource transfer parameter for the user group can also be different. For example, taking a preset threshold of 1 as an example, when... If the number of service releases exceeds the total number of user choices, then the value of the first resource transfer parameter for the user group is:

[0098] when If the number of service releases is less than the total number of user choices, then the number of user choices becomes... At this time, the value of the first resource transfer parameter mentioned above is:

[0099]

[0100] The server of the publishing object can then simplify the expression of the first resource transfer parameter based on the various first resource transfer parameters under the different conditions described above: As can be seen from the above. It is a constant. Representing time t k For the first parameter of business j, Specifically, it can be expressed as:

[0101] Since the server of the publishing object determines the average dynamic differential equation of the user's evolutionary game model based on the aforementioned first resource transfer parameter, the expression for the value of the second resource transfer parameter is as follows: It can be:

[0102]

[0103] Through the above embodiments, the server of the publisher object can determine the value of the first resource transfer parameter based on the optimal demand and supply-demand ratio of the user group, and determine the value of the second resource transfer parameter based on the values ​​of multiple first resource transfer parameters. Thus, the server of the publisher object can perform iterative training through the first iterative model based on the values ​​of the first and second resource transfer parameters, and perform business publishing based on the iterative resource values ​​and publishing quantity to achieve optimal benefit balance.

[0104] In one embodiment, based on the business selection information stored in the consortium blockchain, a second iterative model is used to determine the new resource values ​​and new release quantities for each business. This includes: inputting the business selection information stored in the consortium blockchain into the second iterative model; obtaining the difference between the supply-demand ratio and the value corresponding to the supply-demand balance through the second iterative model; outputting the new resource values ​​based on the sum of the difference and the resource values; determining the value of the cost parameters corresponding to the business based on the release quantities; determining the new release quantities for each business based on the resource values ​​and the cost parameters; and ensuring that the supply-demand ratio and business selection information obtained based on the new resource values ​​and new release quantities for each business tend to stabilize.

[0105] In this embodiment, the publisher's server can also iteratively train the resource values ​​and publishing quantities for each service using a second iterative model. The aforementioned consortium blockchain can store the service selection information of user objects in each iteration. The publisher's server can input this stored service selection information into the second iterative model, and the publisher's server can determine a value corresponding to supply and demand balance, for example, the value corresponding to supply and demand balance can be 1. The publisher's server obtains the difference between the supply-demand ratio and the value corresponding to supply and demand balance using the second iterative model, and outputs a new resource value based on the sum of this difference and the resource value from the previous iteration.

[0106] The server of the publisher object can also predetermine the cost function for each service. Based on the aforementioned release quantity, the server of the publisher object can determine the value of the cost parameter corresponding to the aforementioned service, and determine the new release quantity for each service based on the resource values ​​and cost parameter values ​​of the previous iteration. The supply-demand ratio and service selection information obtained by the server of the publisher object based on the new resource values ​​and new release quantities for each service tend to stabilize.

[0107] Specifically, the cost function of the publisher object can be expressed as: Where a, b, c > 0 and are all constants. Since the publisher object possesses external reputation, which influences business choices, the publisher object's server can incorporate the user object's business choice strategy into the participants' game outcomes through information entropy. Therefore, for business j at time t... k payment function It can be represented as:

[0108] in, τ > 0 and is a constant, where I(·) represents the information entropy function regarding the user's business choice behavior strategy, and "·" represents the user's business choice behavior strategy. Furthermore, there can be multiple publishers mentioned above, and the competition among the publisher groups is modeled as a non-cooperative game, G = {Г, l}.t ,O(l t )} t∈T .

[0109] Among them, the non-cooperative game model of the aforementioned publishing group has a Nash equilibrium solution, which is why the second iterative model can be determined to iterate to a stable state. The specific proof is as follows: when the supply-demand ratio in the non-cooperative game of the publishing group... At that time, the game between the publishing parties ends. Therefore, when Let the corresponding optimal cost be... Right now:

[0110] At this point, the optimal cost is... The corresponding payment function for the publisher object is The server of the publisher object can be adjusted to ensure the payment function of the publisher object. Then when the resource value At this time, we can have: when At the optimal cost Below are:

[0111] Therefore, about Monotonically decreasing, that is, in the above formula because It can be obtained therefore Combining the above formulas, we can determine that:

[0112] That is, the payment function of the publisher object determines the resource value strategy set. The above is continuous, and it relates to the strategy for determining resource values. It exhibits quasi-concaveness. Furthermore, in the non-cooperative game model of the publisher group, the resource value determination strategy set of the publisher objects is a non-empty bounded closed convex set. Therefore, according to the Nash equilibrium existence theorem, this game model has a Nash equilibrium solution, and the second iterative model can be iterated to a stable state.

[0113] Specifically, the server of the publisher object can iteratively optimize the algorithm by determining the resource values ​​of the publisher group with information entropy. As shown in the above formula, when... At that time, the publisher should increase the resource value of the business to improve the resource value obtained by the payment function. Similarly, when At this time, the resource values ​​for the business should be reduced. The server of the publisher object can define an iterative function to determine the resource value strategy and optimal cost based on the changes in the user object's business selection strategy, which is the second iterative model mentioned above, as shown below:

[0114] Where T represents the number of iterations, and k2 represents the adjustment parameter. And when the supply-demand ratio... At this time, it indicates that the number of business items of the publisher exactly meets the demand of the user; at the same time, as the user's purchase strategy tends to evolve into a stable strategy, that is... This is a pure strategy vector. At this point, the non-cooperative game within the publisher group ends. Therefore, the publisher's server uses the second preset condition as a benchmark. The second preset condition is that both the supply-demand ratio and business selection information reach a preset convergence target, specifically... For the convergent state, and Based on the assumption that the evolution is in a stable state, the convergence condition is constructed as follows:

[0115] Where ε2 and ε3 are any small constants > 0. The server of the publisher object is based on...

[0116] The optimization iterative algorithm for the Nash equilibrium publisher resource value determination strategy, i.e., the iterative training process of the second iteration model, can be described as follows: The server of the publisher object can initialize the iteration number T=0 and initialize the resource values. and number of releases Let T = T + 1, then based on the supply-demand ratio function, we can obtain... The publisher's server obtains user group business selection information based on blockchain transaction data backup. Therefore, the server of the publishing object can obtain new resource values ​​through the second iteration model update. and number of releases The server of the publishing object executes algorithms such as consensus incentive mechanisms, repeats the above steps, and obtains the target resource value and target publishing quantity when the second preset condition is met.

[0117] Through the above embodiments, the server of the publishing object can obtain the target resource value and target publishing quantity of the service by iteratively training the second iterative model, and then publish the service based on the target resource value and target publishing quantity to achieve the optimal balance of benefits.

[0118] In one embodiment, an application example of a business publishing method is provided. The server of the publishing object can conduct simulation experiments in MATLAB on the evolutionary game model and the non-cooperative game model in the first iterative model and the second iterative model, respectively. Specifically, the following parameters can be set: n L :2,m φ :7,z i: 0.7, a: [0.2, 0.3], b: 0.7, c: 0, ω: [3, 10]. After the server of the publisher object performs evolutionary simulation on the business selection strategies of 7 user objects and 2 publisher objects through the first iterative model, the following can be obtained: Figure 3 and Figure 4 The image shown, Figure 3 This is a schematic diagram of the service selection information iteration steps in one embodiment. Figure 4 This is a schematic diagram of the service selection information iteration steps in another embodiment. In this embodiment, the server of the publisher object can set the initial selection strategy for each user object. Both are 0.5. Figure 3 This describes the evolution of the selection strategy for Service Number 1 for various user objects. Figure 4 This describes the evolution of each user's selection strategy for Service 2. During the evolution, each user adjusts their service selection strategy according to the different resource values ​​of the service, eventually maintaining a relatively stable level. The probability of selecting Service 1 remains between [0.35, 0.6], while the probability of selecting Service 2 remains between [0.4, 0.65].

[0119] And, as Figure 5 As shown, Figure 5 This is a schematic diagram of the information entropy convergence step in one embodiment. During the evolution process, the information entropy I(θ) of the user object... t Changes can also converge, for example... Figure 5 In this process, the information entropy of an individual user eventually reaches a stable state. Additionally, as... Figure 6 As shown, Figure 6 This is a schematic diagram of the business information convergence step in one embodiment. As the business selection strategies of user objects gradually stabilize, the resource values ​​of the publishing objects also tend to stabilize. When the business selection information of the user group reaches evolutionary stability, the corresponding information entropy change also reaches a stable state. Therefore, the simulation results of the non-cooperative game model between publishing objects can be as follows: Figure 6 As shown, by Figure 6 It can be seen that when the resource values ​​of Business 1 and Business 2 change, the business selection strategy of the user object changes accordingly. When the resource values ​​of Business 1 and Business 2 are stable, the business selection strategy of the user object tends to be stable, and the business selection probability of the user object tends to be stable in the range of about 0.5. This means that when the publishing object has the user's business selection information, it adjusts the current resource value and achieves a consistent resource value through the Nash equilibrium of the non-cooperative game model.

[0120] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0121] Based on the same inventive concept, this application also provides a service publishing apparatus for implementing the service publishing method described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in one or more service publishing apparatus embodiments provided below can be found in the limitations of the service publishing method described above, and will not be repeated here.

[0122] In one embodiment, such as Figure 7 As shown, a service publishing device is provided, including: an acquisition module 500, a first iteration module 502, a second iteration module 504, a training module 506, and a publishing module 508, wherein:

[0123] The acquisition module 500 is used to acquire the business information to be published by the publisher object, synchronize the business information to the pre-built consortium blockchain, and broadcast it to the nodes of the user group through the consortium blockchain. The business information includes the publisher object information, resource values ​​and publication quantity of each business. The consortium blockchain includes a publisher group consisting of multiple nodes corresponding to multiple publisher objects, and a user group consisting of multiple nodes corresponding to multiple user objects.

[0124] The first iteration module 502 is used to simulate the business selection information of each user object based on the business information stored in the consortium blockchain through the first iteration model, and save the business selection information to the consortium blockchain; the first iteration model is used to adjust the selection strategy of each user object for each business based on the current business information stored in the consortium blockchain, and simulate the business selection information of each user object under the current business information.

[0125] The second iteration module 504 is used to determine the new resource values ​​and new release quantities for each business based on the business selection information stored in the consortium blockchain, and update the new resource values ​​and new release quantities to the consortium blockchain, and broadcast them to the user group through the consortium blockchain; the second iteration model is used to determine the current preferences of the user group and the supply-demand ratio of each business based on the latest business selection information and the release quantity and resource values ​​of each business stored in the consortium blockchain, and update the resource values ​​and release quantities of each business according to the current preference information and the current supply-demand ratio.

[0126] The training module 506 is used to return the business selection information of each user object simulated by the first iterative model and save the business selection information to the consortium blockchain. Based on the output of the first iterative model and the output of the second iterative model, the first iterative model and the second iterative model are trained in a game-theoretic manner in the consortium blockchain until the first iterative model meets the first preset condition and the second iterative model meets the second preset condition.

[0127] The publishing module 508 is used to publish multiple services to the consortium blockchain based on the target resource value and target publishing quantity obtained when the second iterative model meets the second preset conditions.

[0128] In one embodiment, the first iteration module 502 is used to input the business information stored in the consortium blockchain into the first iteration model, determine the supply-demand ratio of each business through the first iteration model, and determine the values ​​of the first resource transfer parameters and the second resource transfer parameters of the user group for each business based on the historical business selection information of each user object in the previous iteration, the resource values ​​of multiple businesses, and the supply-demand ratio. The module then adjusts the business selection strategy based on the values ​​of the first and second resource transfer parameters, and simulates the business selection information of each user object under the current business information in the current iteration based on the business selection strategy. The value of the second resource transfer parameter is the average value of the values ​​of the multiple first resource transfer parameters corresponding to multiple businesses. The adjustment objective of the business selection strategy is to reduce the difference between the values ​​of the first and second resource transfer parameters.

[0129] In one embodiment, the first iteration module 502 is used to determine the optimal demand for each service by each user object based on the historical service selection information of each user object and the resource value of each service; determine the demand expectation of the user group for each service based on the historical service selection information and the optimal demand; and determine the supply-demand ratio corresponding to each service based on the ratio of the number of services released to the demand expectation.

[0130] In one embodiment, the first iteration module 502 is used to determine the number of times each user object selects each service based on historical service selection information, and to obtain the current maximum and minimum demand of each user object for each service; to determine the value of the individual resource transfer parameter corresponding to each user object based on the number of selections and the resource value of each service; and to determine the demand corresponding to maximizing the value of the individual resource transfer parameter based on the resource value, maximum demand, and minimum demand of each service, as the optimal demand of each user object for each service.

[0131] In one embodiment, the first iteration module 502 is used to determine the optimal demand of a user group for multiple services based on the optimal demand corresponding to each user object; determine a first parameter based on the comparison result of the supply-demand ratio and a preset threshold; determine the value of a first resource transfer parameter for each service based on the optimal demand of the user group and the first parameter; and determine the value of a second resource transfer parameter for multiple services based on the value of the first resource transfer parameter corresponding to multiple services and historical service selection information.

[0132] In one embodiment, the first iteration module 502 is used to determine the first parameter as a preset first value if the supply-demand ratio is greater than or equal to a preset threshold; otherwise, it determines the value of the first parameter based on the supply-demand ratio and the square of the supply-demand ratio.

[0133] In one embodiment, the first iteration module 502 is used to obtain the difference between the value of the first resource transfer parameter and the value of the second resource transfer parameter through the first iteration model; and determine the output information of the first iteration model based on the product of the difference and the historical service selection information, and the sum of the product and the historical service selection information, as the service selection information of each user object under the current service information in this iteration.

[0134] In one embodiment, the second iteration module 504 is used to input the business selection information stored in the consortium blockchain into the second iteration model, obtain the difference between the supply-demand ratio and the value corresponding to the supply-demand balance through the second iteration model, and output a new resource value based on the sum of the difference and the resource value; determine the value of the cost parameter corresponding to the business based on the number of releases; determine the new number of releases for each business based on the resource value and the cost parameter value; and the supply-demand ratio and business selection information obtained based on the new resource value and the new number of releases for each business tend to stabilize.

[0135] Each module in the aforementioned business publishing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0136] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 8 As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a business publishing method. The display unit of the computer device forms a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink display screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device casing, or an external keyboard, touchpad, or mouse.

[0137] Those skilled in the art will understand that Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0138] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-described business publishing method.

[0139] In one embodiment, a computer-readable storage medium is provided on which a computer program is stored, which, when executed by a processor, implements the above-described business publishing method.

[0140] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the business publishing method described above.

[0141] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0142] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0143] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0144] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A service publishing method, characterized in that, The method includes: The system obtains the business information to be published by the publisher object, synchronizes the business information to a pre-built consortium blockchain, and broadcasts it to the nodes of the user group through the consortium blockchain. The business information includes the publisher object information, resource value, and publication quantity of each business. The consortium blockchain includes a publisher group consisting of multiple nodes corresponding to multiple publisher objects, and a user group consisting of multiple nodes corresponding to multiple user objects. Based on the business information stored in the consortium blockchain, the business selection information of each user object is simulated through a first iterative model, and the business selection information is saved to the consortium blockchain; the first iterative model is used to adjust the selection strategy of each user object for each business based on the current business information stored in the consortium blockchain, and to simulate the business selection information of each user object under the current business information. Based on the business selection information stored in the consortium blockchain, a second iterative model is used to determine the new resource values ​​and new release quantities for each business, and the new resource values ​​and new release quantities are updated to the consortium blockchain and broadcast to the user group through the consortium blockchain; the second iterative model is used to determine the current preferences of the user group and the supply-demand ratio of each business based on the latest business selection information and the release quantity and resource values ​​of each business stored in the consortium blockchain, and to update the resource values ​​and release quantities of each business according to the current preference information and the current supply-demand ratio; Returning to the step of simulating the business selection information of each user object through the first iterative model and saving the business selection information to the consortium blockchain, based on the output of the first iterative model and the output of the second iterative model, the first iterative model and the second iterative model are subjected to game-theoretic iterative training in the consortium blockchain until the first iterative model meets the first preset condition and the second iterative model meets the second preset condition; Based on the target resource value and target release quantity obtained when the second iterative model meets the second preset condition, the multiple services are released to the consortium blockchain.

2. The method according to claim 1, characterized in that, The process of simulating the business selection information of each user object through a first iterative model based on the business information stored in the consortium blockchain includes: The business information stored in the consortium blockchain is input into the first iterative model. The supply-demand ratio of each business is determined through the first iterative model. Based on the historical business selection information of each user object in the previous iteration, the resource values ​​of multiple businesses, and the supply-demand ratio, the values ​​of the first resource transfer parameter and the second resource transfer parameter of the user group for each business are determined. The business selection strategy is adjusted according to the values ​​of the first and second resource transfer parameters. Based on the business selection strategy, the business selection information of each user object under the current business information is simulated in the current iteration. The second resource transfer parameter is the average value of the values ​​of the first resource transfer parameters corresponding to multiple services; the adjustment objective of the service selection strategy is to reduce the difference between the values ​​of the first resource transfer parameter and the second resource transfer parameter.

3. The method according to claim 2, characterized in that, The step of determining the supply-demand ratio of each business using the first iterative model includes: Based on the historical service selection information of each user object and the resource values ​​of each service, determine the optimal demand of each user object for each service; Based on the historical service selection information and the optimal demand, the user group's demand expectations for each service are determined; The supply-demand ratio for each service is determined based on the ratio of the number of services released to the expected demand.

4. The method according to claim 3, characterized in that, The step of determining the optimal demand for each service for each user based on the historical service selection information and resource values ​​of each service includes: Based on the historical service selection information, determine the number of times each user selects each service, and obtain the current maximum and minimum demand for each service for each user. Based on the selected quantity and the resource values ​​of each service, determine the value of the individual resource transfer parameter corresponding to each user object; Based on the resource values ​​of each service, the maximum demand, and the minimum demand, the demand corresponding to maximizing the value of the individual resource transfer parameter is determined, which serves as the optimal demand for each user object for each service.

5. The method according to claim 4, characterized in that, The step of determining the values ​​of the first resource transfer parameter for each service and the second resource transfer parameter for the user group for multiple services based on the historical service selection information, resource values ​​of multiple services, and the supply-demand ratio includes: Based on the optimal demand for each user object, determine the optimal demand for the user group for multiple services; Based on the comparison result between the supply and demand ratio and the preset threshold, a first parameter is determined. Based on the optimal demand of the user group and the first parameter, the value of the first resource transfer parameter for each service of the user group is determined. Based on the values ​​of the first resource transfer parameters corresponding to multiple services and the historical service selection information, the values ​​of the second resource transfer parameters for the user group for multiple services are determined.

6. The method according to claim 5, characterized in that, The step of determining the first parameter based on the comparison result of the supply-demand ratio and the preset threshold includes: If the supply-demand ratio is greater than or equal to the preset threshold, the first parameter is determined to be a preset first value. Otherwise, the value of the first parameter is determined based on the supply-demand ratio and the square of the supply-demand ratio.

7. The method according to claim 2, characterized in that, The historical service selection information represents the selection probability of each user for each service; adjusting the service selection strategy based on the values ​​of the first resource transfer parameter and the second resource transfer parameter, and outputting the service selection information of each user under the current service information based on the service selection strategy, includes: The difference between the value of the first resource transfer parameter and the value of the second resource transfer parameter is obtained through the first iterative model. Based on the product of the difference and the historical service selection information, and the sum of the product and the historical service selection information, the output information of the first iterative model is determined, which serves as the service selection information for each user object under the current service information in this iteration.

8. The method according to claim 2, characterized in that, The process of determining the new resource values ​​and new release quantities for each service based on the service selection information stored in the consortium blockchain, using a second iterative model, includes: The business selection information stored in the consortium blockchain is input into the second iterative model. The difference between the supply-demand ratio and the value corresponding to the supply-demand balance is obtained through the second iterative model. Based on the sum of the difference and the resource value, a new resource value is output. Based on the number of releases, determine the value of the cost parameter corresponding to the business; Based on the resource values ​​and cost parameters, the new release quantity for each service is determined; the supply-demand ratio and service selection information obtained based on the new resource values ​​and new release quantities for each service tend to stabilize.

9. The method according to claim 2, characterized in that, The first preset condition is that the difference between the value of the first resource transfer parameter and the value of the second resource transfer parameter is less than a preset threshold. The second preset condition is that both the supply-demand ratio and the business selection information reach a preset convergence target.

10. A business publishing device, characterized in that, The device includes: The acquisition module is used to acquire the business information to be published by the publisher object, synchronize the business information to the pre-built consortium blockchain, and broadcast it to the nodes of the user group through the consortium blockchain; the business information includes the publisher object information, resource value and publication quantity of each business; the consortium blockchain includes a publisher group consisting of multiple nodes corresponding to multiple publisher objects, and a user group consisting of multiple nodes corresponding to multiple user objects. The first iteration module is used to simulate the business selection information of each user object based on the business information stored in the consortium blockchain through a first iteration model, and save the business selection information to the consortium blockchain; the first iteration model is used to adjust the selection strategy of each user object for each business based on the current business information stored in the consortium blockchain, and simulate the business selection information of each user object under the current business information. The second iteration module is used to determine the new resource values ​​and new release quantities for each service based on the service selection information stored in the consortium blockchain, and update the new resource values ​​and new release quantities to the consortium blockchain, and broadcast them to the user group through the consortium blockchain; the second iteration model is used to determine the current preferences of the user group and the supply-demand ratio of each service based on the latest service selection information and the release quantity and resource values ​​of each service stored in the consortium blockchain, and update the resource values ​​and release quantities of each service according to the current preference information and the current supply-demand ratio; The training module is used to return the business selection information of each user object simulated by the first iterative model and save the business selection information to the consortium blockchain. Based on the output of the first iterative model and the output of the second iterative model, the first iterative model and the second iterative model are trained in a game-theoretic manner in the consortium blockchain until the first iterative model meets the first preset condition and the second iterative model meets the second preset condition. The publishing module is used to publish the multiple services to the consortium blockchain based on the target resource value and target publishing quantity obtained when the second iterative model meets the second preset condition.

11. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 9.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 9.

13. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 9.

Images