Method, device and equipment for regulating data contributors based on federated learning

Abstract

The present disclosure provides a method, device and equipment for establishing a data contributor based on joint learning. The method comprises: determining the number interval range of the contributors according to the received data of the participants, and constructing a plurality of data contributors according to the number interval range of the contributors; based on the data of the participants, calling the data attribute range matched with the data, using the data attribute range to generate corresponding configuration information for each data contributor, and constructing the behavior strategy corresponding to each data contributor; when executing a data regulation task, establishing a communication channel between the data contributor and other participants, and generating a contributor object corresponding to each data contributor according to the configuration information and the behavior strategy, and executing the data regulation task based on the contributor object. The present disclosure can simplify the creation process of the contributor, reduce the labor cost, and improve the creation efficiency of the contributor in the simulation platform.

Description

Technical Field

[0001] This disclosure relates to the field of collaborative learning technology, and in particular to a method, apparatus, and device for regulating data contributors based on collaborative learning. Background Technology

[0002] With the continuous development of computer technology, the application of artificial intelligence is becoming increasingly widespread. Joint learning, which involves collaborating different stakeholders to conduct machine learning, has become a mainstream trend in training AI models. As a novel distributed machine learning framework, joint learning meets the needs of multiple clients for model training while maintaining data security.

[0003] Before a true collaborative learning ecosystem is established, it is necessary to verify the rationality and effectiveness of the incentive allocation mechanism design, compare the differences in effects brought about by different incentive mechanism options, and identify shortcomings or loopholes in the incentive allocation mechanism design. Therefore, a simulation verification platform for collaborative learning incentive allocation mechanisms needs to be designed. Existing simulation verification platforms for incentive allocation mechanisms require significant manpower to establish data contributors based on collaborative learning and simulation tasks. Furthermore, the process of establishing data contributors is complex, and errors are prone to occur when creating data contributors manually, reducing the efficiency of data contributor creation. Summary of the Invention

[0004] In view of this, the present disclosure provides a control method, apparatus and device for establishing data contributors based on joint learning, so as to solve the problems of the prior art that the process of establishing data contributors is complicated, requires high human resources, is prone to errors in the creation of data contributors and has low creation efficiency.

[0005] A first aspect of this disclosure provides a method for regulating data contributors based on joint learning, comprising: determining a range of the number of contributors based on data received from participating parties, and constructing multiple data contributors based on the range of the number of contributors; retrieving a range of data attributes matching the data based on the data from the participating parties, generating corresponding configuration information for each data contributor using the data attribute range, and constructing a behavioral strategy corresponding to each data contributor; when executing a data regulation task, establishing a communication channel between the data contributors and other participating parties, and generating a contributor object corresponding to each data contributor based on the configuration information and the behavioral strategy, and executing the data regulation task based on the contributor object.

[0006] A second aspect of this disclosure provides a control device for establishing data contributors based on joint learning, comprising: a determining module configured to determine a range of the number of contributors based on received data from participating parties, and to construct multiple data contributors based on the range of the number of contributors; a generating module configured to retrieve a range of data attributes matching the data based on the data from the participating parties, generate corresponding configuration information for each data contributor using the data attribute range, and construct a behavior strategy corresponding to each data contributor; and a control module configured to establish a communication channel between the data contributors and other participating parties when performing a data control task, and to generate a contributor object corresponding to each data contributor based on the configuration information and the behavior strategy, and to perform the data control task based on the contributor object.

[0007] A third aspect of this disclosure provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the above-described method.

[0008] A fourth aspect of this disclosure provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described method.

[0009] The above-described at least one technical solution adopted in the embodiments of this disclosure can achieve the following beneficial effects:

[0010] By determining the range of contributors based on the received data from participating parties, and constructing multiple data contributors according to this range, the system retrieves matching data attribute ranges based on the participant data. Using these data attribute ranges, it generates corresponding configuration information for each data contributor and constructs a corresponding behavior strategy for each contributor. When executing a data control task, it establishes communication channels between the data contributors and other participating parties, and generates a contributor object corresponding to each data contributor based on the configuration information and behavior strategy. The data control task is then executed based on these contributor objects. This disclosure can automatically create contributors for simulation tasks within a simulation platform, requiring less human intervention, simplifying the contributor creation process, reducing the error rate of contributor creation, and improving the efficiency of contributor creation. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a schematic diagram of a joint learning architecture provided in an embodiment of this disclosure;

[0013] Figure 2 This is a flowchart illustrating the control method for establishing data contributors based on joint learning, provided in an embodiment of this disclosure.

[0014] Figure 3 This is a schematic diagram of the structure of the control device for establishing data contributors based on joint learning, provided in an embodiment of this disclosure;

[0015] Figure 4 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this disclosure. Detailed Implementation

[0016] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, so as to provide a thorough understanding of the embodiments of this disclosure. However, those skilled in the art will understand that this disclosure may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this disclosure with unnecessary detail.

[0017] Federation learning refers to the comprehensive utilization of multiple AI (Artificial Intelligence) technologies, under the premise of ensuring data security and user privacy, to collaboratively explore the value of data and foster new intelligent business forms and models based on joint modeling. Federation learning has at least the following characteristics:

[0018] (1) Participating nodes control their own data in a weakly centralized joint training mode to ensure data privacy and security in the process of co-creating intelligence.

[0019] (2) In different application scenarios, various model aggregation optimization strategies are established by using screening and / or combination of AI algorithms and privacy-preserving computing to obtain high-level and high-quality models.

[0020] (3) Under the premise of ensuring data security and user privacy, based on multiple model aggregation optimization strategies, obtain methods to improve the performance of the federated learning engine. The performance methods can be improved by solving problems such as parallel computing architecture, information interaction under large-scale cross-domain networks, intelligent perception, and anomaly handling mechanisms.

[0021] (4) Obtain the needs of multiple users in various scenarios, determine the true contribution of each joint participant through a mutual trust mechanism, and allocate incentives accordingly.

[0022] Based on the above approach, an AI technology ecosystem based on collaborative learning can be established, fully leveraging the value of industry data and promoting the implementation of scenarios in vertical fields.

[0023] A joint learning training method and apparatus according to an embodiment of the present disclosure will now be described in detail with reference to the accompanying drawings.

[0024] Figure 1 This is a schematic diagram of a joint learning architecture provided in an embodiment of this disclosure. Figure 1 As shown, the architecture of joint learning may include a server (central node) 101 and participants 102, 103 and 104.

[0025] In the joint learning process, a basic model can be established through server 101, which then sends this model to participants 102, 103, and 104 with whom it has established a communication connection. Alternatively, any participant can establish the basic model and upload it to server 101, which then sends it to other participants with whom it has established a communication connection. Participants 102, 103, and 104 construct models based on the downloaded basic structure and model parameters, train the models using local data, obtain updated model parameters, and encrypt and upload these updated model parameters to server 101. Server 101 aggregates the model parameters sent by participants 102, 103, and 104 to obtain global model parameters, which are then transmitted back to participants 102, 103, and 104. Participants 102, 103, and 104 iterate on their respective models based on the received global model parameters until the models converge, thus achieving model training. During the collaborative learning process, the data uploaded by participants 102, 103, and 104 are model parameters. Local data is not uploaded to server 101, and all participants can share the final model parameters. Therefore, collaborative modeling can be achieved while ensuring data privacy. It should be noted that the number of participants is not limited to the three mentioned above, but can be set as needed. This embodiment of the disclosure does not impose any restrictions on this.

[0026] Figure 2 This is a flowchart illustrating the contributor establishment method based on a simulation platform provided in this embodiment of the disclosure. Figure 2 The contributor creation method based on the simulation platform can be executed by the simulation platform's server. For example... Figure 2 As shown, the method for establishing contributors based on the simulation platform may specifically include:

[0027] S201, Based on the data received from the participants, determine the range of the number of contributors, and construct multiple data contributors based on the range of the number of contributors;

[0028] S202, Based on the data of the participants, retrieve the range of data attributes that match the data, use the range of data attributes to generate corresponding configuration information for each data contributor, and construct the corresponding behavior strategy for each data contributor;

[0029] S203, When performing data regulation tasks, establish a communication channel between data contributors and other participants, and generate contributor objects corresponding to each data contributor based on configuration information and behavior strategies, and perform data regulation tasks based on contributor objects.

[0030] Specifically, the application scenario of this disclosure embodiment will be briefly described first. In the field of federated learning, when clients participate in federated learning, they inevitably consume device resources, including computing resources, communication resources, and energy. Therefore, without sufficient rewards, clients may be unwilling to participate in or share their models. Thus, federated learning requires the design of an incentive mechanism to compensate for the aforementioned consumption, either numerically or in terms of models. There are two important objectives in designing a federated learning incentive mechanism: first, to evaluate the contribution of each client; and second, to design a reasonable reward to attract and retain more clients.

[0031] Furthermore, in this embodiment of the disclosure, the contributor refers to the virtual participant in joint learning established through a simulation platform. Since the simulation platform is used to simulate and verify the allocation incentive mechanism of joint learning, the contributor here can also be considered as the data contributor in joint learning, that is, the virtualized data contributor in the simulation task.

[0032] Furthermore, the application scenario of this disclosure embodiment can be considered as follows: when the computer program of the simulation platform starts and a new simulation environment begins, a simulation environment object is generated in the memory of the computer program, and based on the simulation environment object, various entities (including the entity corresponding to the contributor) are created sequentially. In practical applications, the construction of each entity is decoupled and does not depend on other entities for construction.

[0033] According to the technical solution provided in this disclosure, the number range of contributors is determined based on the data received from participating parties, and multiple data contributors are constructed based on this range. Based on the participating parties' data, a range of data attributes matching the data is retrieved. Using this range of data attributes, corresponding configuration information is generated for each data contributor, and a behavioral strategy is constructed for each data contributor. When executing a data control task, a communication channel is established between the data contributors and other participating parties. Based on the configuration information and behavioral strategy, a contributor object corresponding to each data contributor is generated, and the data control task is executed based on the contributor object. This disclosure can automatically create contributors for simulation tasks in a simulation platform, requiring less human intervention, simplifying the contributor creation process, reducing the error rate of contributor creation, and improving the efficiency of contributor creation.

[0034] In some embodiments, the data regulation task includes a data simulation task. Before determining the range of the number of contributors based on the data received from the participants, the method further includes: determining a preset allocation incentive mechanism related to joint learning; creating a data simulation task corresponding to the allocation incentive mechanism based on the allocation incentive mechanism; and generating a simulation environment object corresponding to the data simulation task in the data simulation platform. The data simulation task is used to simulate and verify the allocation incentive mechanism of joint learning.

[0035] Specifically, the incentive allocation mechanism is used to encourage participants in collaborative learning to engage more in the collaborative learning process. After designing the incentive allocation mechanism, its effectiveness needs to be verified. Therefore, executing corresponding simulation tasks through a simulation platform is of great significance for verifying the effectiveness of the incentive allocation mechanism and for identifying any shortcomings or loopholes in its design.

[0036] In some embodiments, based on the data of the participants, a range of data attributes matching the data is retrieved, and corresponding configuration information is generated for each data contributor using the range of data attributes. This includes: retrieving a range of data attributes matching the identification information from a pre-configured range of data attributes based on the identification information of each participant, and generating corresponding configuration information for each data contributor using the range of data attributes. The configuration information includes the following information: data type, data volume, data quality, machine resource quantity, data and computing resource cost, and simulation time step.

[0037] Specifically, a random integer value n ~ [1, MaxN] is generated based on the simulation task. Based on this integer value, n data contributors (hereinafter referred to as contributors) are constructed, and then objects for each contributor are created. First, the configuration information of each contributor is read. The configuration information can be manually preset, and the computer program uses the manually preset values ​​or randomly generates a series of values ​​within the manually preset range.

[0038] Furthermore, the following is a list and explanation of the contents included in the configuration information:

[0039] Data types: such as images, text, or time series;

[0040] The amount of data: such as the number of images, the number of text sentences, the length of the time series, etc.;

[0041] Data quality: such as the quality level of each piece of data, which can be represented by a number between [-1, 1], with the larger the number, the higher the quality;

[0042] Machine resources: such as CPU, GPU, memory, hard drive, network bandwidth, etc.;

[0043] Data and computing resource costs: such as the cost per unit of data usage and the cost per unit of resource usage time;

[0044] Simulation time step: such as setting the time interval for each simulation step, for example, performing a simulation operation every few seconds.

[0045] In some embodiments, constructing a behavioral strategy for each data contributor includes: setting a corresponding behavioral strategy for each data contributor based on a pre-defined behavioral strategy and a data simulation task, wherein the behavioral strategy includes whether to truthfully declare data and computing resources, and whether to truthfully declare prices based on costs.

[0046] Specifically, the behavioral strategy of a data contributor refers to the strategy chosen by the data contributor when submitting data or price declarations during the simulation process. In practical applications, the behavioral strategy of a data contributor includes, but is not limited to, the following: whether to truthfully declare data and computing resources (if not, a random bias of (0, rate*Number] is added to the actual data), and whether to declare prices based on cost (if not, a random bias of (0, rate*Price] is added to the price).

[0047] In some embodiments, when performing a data regulation task, establishing a communication channel between the data contributor and other participants includes: when determining that a data simulation task is to be performed, establishing a communication channel between the data contributor and other simulation entities based on the data contributors currently established in the data simulation platform, wherein the simulation entities include a central node created based on a joint learning architecture, and the communication channel is used to transmit model information, allocation of funds information, and public information in the simulation environment.

[0048] Specifically, after generating corresponding configuration information for each data contributor and constructing the behavioral strategy for each data contributor, it is also necessary to construct communication channels between the data contributor and other simulation subjects, and to transmit model information, allocate funding information, and other publicly available information in the simulation environment based on these communication channels.

[0049] Furthermore, the other simulation entities used to establish communication channels with data contributors can be either central nodes created based on a joint learning architecture, or simulation entities corresponding to other contributors in the simulation task. In other words, contributors can communicate not only with the central node, but also with each other.

[0050] In some embodiments, generating a contributor object corresponding to each data contributor based on configuration information and behavior strategy includes: using the pre-generated configuration information and behavior strategy of the data contributor, configuring the parameters of the data structure stored in the memory of the data simulation platform so as to adjust the initial configuration information and initialization parameters corresponding to the initial behavior strategy in the data structure to the latest parameters, and using the data structure corresponding to the contributor after parameter adjustment as the contributor object corresponding to the data contributor.

[0051] Specifically, after establishing a communication channel between the data contributor and other simulation subjects, a data structure is generated for each contributor in the memory of the computer program corresponding to the data simulation platform. The initialization parameters in the data structure are adjusted using the configuration information and behavior strategy generated above. That is, the original parameters in the data structure are modified using the configuration information and behavior strategy parameters generated above to obtain the final contributor object.

[0052] In some embodiments, performing data control tasks based on contributor objects includes: adding contributor objects to the simulation environment object corresponding to the data simulation task, controlling contributor objects to start listening to the communication channel through instructions so that data contributors corresponding to contributor objects can exchange information with other simulation subjects, and causing data contributors to generate output results corresponding to the simulation time step according to the simulation time step and the received external information.

[0053] Specifically, after creating the contributor object, it is added to the pre-created simulation environment (i.e., the simulation environment object), thus completing the entire contributor creation process based on the simulation platform. After adding the contributor object to the simulation environment, instructions are sent to each contributor to control them to start listening to the communication channel and exchange information with other simulation entities.

[0054] Furthermore, during the execution of the simulation task, according to the preset simulation time step corresponding to the simulation task, each contributor generates an output in each simulation time step using the received external information.

[0055] The following are embodiments of the apparatus disclosed herein, which can be used to execute embodiments of the method disclosed herein. For details not disclosed in the apparatus embodiments of this disclosure, please refer to the embodiments of the method disclosed herein.

[0056] Figure 3 This is a schematic diagram of the structure of the control device for establishing data contributors based on joint learning, provided in an embodiment of this disclosure. Figure 3 As shown, the control device for establishing data contributors based on joint learning includes:

[0057] The determination module 301 is configured to determine the range of the number of contributors based on the data received from the participants, and to construct multiple data contributors based on the range of the number of contributors.

[0058] The generation module 302 is configured to retrieve the range of data attributes that match the data based on the data of the participants, use the range of data attributes to generate corresponding configuration information for each data contributor, and construct the corresponding behavior strategy for each data contributor.

[0059] The control module 303 is configured to establish a communication channel between the data contributor and other participants when performing data control tasks, and generate a contributor object corresponding to each data contributor based on the configuration information and behavior strategy, and perform data control tasks based on the contributor object.

[0060] In some embodiments, the data control task includes a data simulation task. Figure 3 Before determining the range of the number of contributors based on the data from the receiving participants, the determination module 301 determines a preset allocation incentive mechanism related to joint learning. Based on the allocation incentive mechanism, it creates a data simulation task corresponding to the allocation incentive mechanism and generates a simulation environment object corresponding to the data simulation task in the data simulation platform. The data simulation task is used to simulate and verify the allocation incentive mechanism of joint learning.

[0061] In some embodiments, Figure 3The generation module 302 retrieves the data attribute range that matches the identification information from the pre-configured data attribute range library based on the identification information of each participant, and uses the data attribute range to generate corresponding configuration information for each data contributor; wherein, the configuration information includes the following information: data type, data volume, data quality, machine resource volume, data and computing resource cost, and simulation time step.

[0062] In some embodiments, Figure 3 The generation module 302 sets corresponding behavior strategies for each data contributor based on the pre-set behavior strategies and data simulation tasks. The behavior strategies include whether to truthfully declare data and computing resources, and whether to truthfully declare prices according to costs.

[0063] In some embodiments, Figure 3 When the control module 303 determines to execute a data simulation task, it establishes a communication channel between the data contributor and other simulation entities based on the data contributor currently established in the data simulation platform. The simulation entities include a central node created based on a joint learning architecture. The communication channel is used to transmit model information, fund allocation information, and public information in the simulation environment.

[0064] In some embodiments, Figure 3 The control module 303 uses the pre-generated configuration information and behavior strategy of the data contributor to configure the parameters of the data structure stored in the memory of the data simulation platform, so as to adjust the initial configuration information and initialization parameters corresponding to the initial behavior strategy in the data structure to the latest parameters, and use the data structure after parameter adjustment as the contributor object corresponding to the data contributor.

[0065] In some embodiments, Figure 3 The control module 303 adds the contributor object to the simulation environment object corresponding to the data simulation task, and controls the contributor object to start listening to the communication channel through instructions, so that the data contributor corresponding to the contributor object can exchange information with other simulation subjects, and enables the data contributor to generate the output result corresponding to the simulation time step according to the simulation time step and the received external information.

[0066] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this disclosure.

[0067] Figure 4 This is a schematic diagram of the structure of the electronic device 4 provided in an embodiment of this disclosure. For example... Figure 4As shown, the electronic device 4 of this embodiment includes a processor 401, a memory 402, and a computer program 403 stored in the memory 402 and executable on the processor 401. When the processor 401 executes the computer program 403, it implements the steps in the various method embodiments described above. Alternatively, when the processor 401 executes the computer program 403, it implements the functions of each module / unit in the various device embodiments described above.

[0068] For example, computer program 403 may be divided into one or more modules / units, which are stored in memory 402 and executed by processor 401 to perform the present disclosure. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of computer program 403 in electronic device 4.

[0069] Electronic device 4 can be a desktop computer, laptop, handheld computer, cloud server, or other electronic device. Electronic device 4 may include, but is not limited to, processor 401 and memory 402. Those skilled in the art will understand that... Figure 4 This is merely an example of electronic device 4 and does not constitute a limitation on electronic device 4. It may include more or fewer components than shown, or combine certain components, or different components. For example, electronic device may also include input / output devices, network access devices, buses, etc.

[0070] Processor 401 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0071] The memory 402 can be an internal storage unit of the electronic device 4, such as a hard disk or RAM. The memory 402 can also be an external storage device of the electronic device 4, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the memory 402 can include both internal and external storage units of the electronic device 4. The memory 402 is used to store computer programs and other programs and data required by the electronic device. The memory 402 can also be used to temporarily store data that has been output or will be output.

[0072] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0073] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0074] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this disclosure.

[0075] In the embodiments provided in this disclosure, it should be understood that the disclosed apparatus / computer devices and methods can be implemented in other ways. For example, the apparatus / computer device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. Multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0076] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0077] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0078] If an integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program may include computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. A computer-readable medium may include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in a computer-readable medium may be appropriately added to or subtracted according to the requirements of legislation and patent practice in a jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media may not include electrical carrier signals and telecommunication signals.

[0079] The above embodiments are only used to illustrate the technical solutions of this disclosure, and are not intended to limit it. Although this disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this disclosure, and should all be included within the protection scope of this disclosure.

Claims

1. A method for regulating data contributors based on joint learning, characterized in that, include: Based on the data received from the participants, determine the range of the number of contributors, and construct multiple data contributors according to the range of the number of contributors. Based on the data of the participants, retrieve the range of data attributes that match the data, use the range of data attributes to generate corresponding configuration information for each data contributor, and construct a behavior strategy for each data contributor. When performing a data regulation task, a communication channel is established between the data contributor and other participants. Based on the configuration information and the behavior strategy, a contributor object corresponding to each data contributor is generated, and the data regulation task is performed based on the contributor object. The data control task includes a data simulation task. Before determining the range of contributor numbers based on the data from the receiving participants, the method further includes: A preset allocation incentive mechanism related to joint learning is determined. Based on the allocation incentive mechanism, a data simulation task corresponding to the allocation incentive mechanism is created, and a simulation environment object corresponding to the data simulation task is generated in the data simulation platform. The data simulation task is used to simulate and verify the allocation incentive mechanism of joint learning.

2. The method according to claim 1, characterized in that, Based on the data from the participants, the system retrieves a range of data attributes that match the data, and uses this range of data attributes to generate corresponding configuration information for each data contributor, including: Based on the identification information of each participant, a data attribute range matching the identification information is retrieved from a pre-configured data attribute range library, and the corresponding configuration information is generated for each data contributor using the data attribute range; The configuration information includes the following: data type, data volume, data quality, machine resource quantity, data and computing resource cost, and simulation time step.

3. The method according to claim 1, characterized in that, The construction of the behavioral strategy corresponding to each data contributor includes: Based on the pre-set behavioral strategy and the data simulation task, a corresponding behavioral strategy is set for each data contributor, wherein the behavioral strategy includes whether to truthfully report data and computing resources, and whether to truthfully report prices according to costs.

4. The method according to claim 1, characterized in that, When performing data regulation tasks, establishing a communication channel between the data contributor and other participants includes: When a data simulation task is to be executed, a communication channel is established between the data contributor and other simulation entities based on the data contributor currently established in the data simulation platform. The simulation entities include a central node created based on a joint learning architecture. The communication channel is used to transmit model information, allocation of funds information, and public information in the simulation environment.

5. The method according to claim 1, characterized in that, The step of generating a contributor object corresponding to each data contributor based on the configuration information and the behavior strategy includes: Using the pre-generated configuration information and behavior strategy of the data contributor, the parameters of the data structure stored in the memory of the data simulation platform are configured so that the initial configuration information and initialization parameters corresponding to the initial behavior strategy in the data structure are adjusted to the latest parameters, and the data structure with adjusted parameters is used as the contributor object corresponding to the data contributor.

6. The method according to claim 1, characterized in that, The execution of the data regulation task based on the contributor object includes: The contributor object is added to the simulation environment object corresponding to the data simulation task, and the contributor object is controlled by instructions to start listening to the communication channel so that the data contributor corresponding to the contributor object can exchange information with other simulation subjects, and the data contributor generates the output result corresponding to the simulation time step according to the simulation time step and the received external information.

7. A control device for establishing data contributors based on joint learning, characterized in that, include: The determination module is configured to determine the range of the number of contributors based on the data received from the participants, and to construct multiple data contributors based on the range of the number of contributors. The generation module is configured to retrieve a range of data attributes that match the data based on the data of the participants, use the range of data attributes to generate corresponding configuration information for each data contributor, and construct a behavioral strategy for each data contributor. The control module is configured to establish a communication channel between the data contributor and other participants when performing a data control task, and generate a contributor object corresponding to each data contributor according to the configuration information and the behavior strategy, and execute the data control task based on the contributor object. The data control task includes a data simulation task. The determining module is used to determine a preset allocation incentive mechanism related to joint learning before determining the range of the number of contributors based on the data received from the participants. Based on the allocation incentive mechanism, a data simulation task corresponding to the allocation incentive mechanism is created, and a simulation environment object corresponding to the data simulation task is generated in the data simulation platform. The data simulation task is used to simulate and verify the allocation incentive mechanism of the joint learning.

8. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 6.

Images