A task allocation method and device based on joint learning

Abstract

The present invention discloses a task assignment method, device, readable medium, and electronic device based on federated learning. The method comprises: determining a target user's query task request based on the target user's task assignment qualifications; screening a task list of a federated learning engine based on the query task request to determine a target task list; and assigning a target task to the target user based on the target user's selection of the target task list. The technical solution provided by the present invention determines the target user's query task request, thereby determining a target task list, and assigning a target task to the target user based on the target user's selection of the target task list. This task assignment method based on federated learning is reasonable.

Description

Technical Field

[0001] The present invention relates to the field of energy, and in particular to a task allocation method and device based on joint learning. Background Art

[0002] With the rapid development of internet technology, user data has become an increasingly important resource. Various prediction models can be trained based on this data, and accurate prediction results are essential for the efficient operation of energy systems. However, not every energy user can collect the massive amounts of user data needed to train accurate prediction models. This has led to the emergence of federated learning. To encourage more energy users to participate in federated learning, it is becoming increasingly important to develop a reasonable task allocation method based on federated learning. Summary of the Invention

[0003] The present invention provides a task allocation method, device, readable medium and electronic device based on joint learning. By determining the query task request of the target user, a target task list is determined, and according to the target user's selection result of the target task list, the target task is allocated to the target user. The task allocation method based on joint learning is reasonable.

[0004] In a first aspect, the present invention provides a task allocation method based on joint learning, comprising:

[0005] Determine the target user's query task request based on the target user's task assignment qualifications;

[0006] Based on the query task request, screening the task list of the joint learning engine to determine the target task list;

[0007] Based on the target user's selection result from the target task list, a target task is assigned to the target user.

[0008] Preferably,

[0009] The step of determining the query task request of the target user based on the task assignment qualification of the target user includes:

[0010] Determine whether the target user is eligible for task assignment;

[0011] If the target user has the task assignment qualification, determining the query task request of the target user;

[0012] If the target user does not have the task assignment qualification, the target user is reminded to create a task to obtain the task assignment qualification.

[0013] Preferably,

[0014] The step of screening the task list of the joint learning engine based on the query task request to determine a target task list includes:

[0015] In response to the query task request, determine a task list of the joint learning engine;

[0016] Determine the current filter conditions;

[0017] Based on the current screening conditions, the task list of the joint learning engine is screened to determine a target task list.

[0018] Preferably,

[0019] Determining the current screening condition includes:

[0020] Receive a screening request sent by a target user;

[0021] Information is extracted from the screening request to determine the current screening condition.

[0022] Preferably,

[0023] Determining the current screening condition includes:

[0024] Determine the user filtering criteria sent by the target user;

[0025] Determine the preset center screening conditions corresponding to the federated learning engine;

[0026] Based on the user filtering condition and the central filtering condition, a current filtering condition is determined.

[0027] Preferably,

[0028] The current screening conditions include: industry type, federated learning engine supported algorithms, and task execution status.

[0029] In a second aspect, the present invention provides a task allocation device based on joint learning, comprising:

[0030] A request determination module, configured to determine a query task request of a target user based on the target user's task assignment qualifications;

[0031] A list determination module is used to screen the task list of the joint learning engine based on the query task request and determine the target task list;

[0032] The task assignment module is used to assign a target task to the target user based on the target user's selection result from the target task list.

[0033] Preferably,

[0034] The request determination module includes:

[0035] Qualification judgment unit, used to judge whether the target user is qualified for task assignment;

[0036] a request determining unit, configured to determine the query task request of the target user if the target user has the task assignment qualification;

[0037] The qualification acquisition unit is used to remind the target user to create a task and obtain the task assignment qualification if the target user does not have the task assignment qualification.

[0038] In a third aspect, the present invention provides a readable medium comprising an execution instruction. When a processor of an electronic device executes the execution instruction, the electronic device executes any method described in the first aspect.

[0039] In a fourth aspect, the present invention provides an electronic device comprising a processor and a memory storing execution instructions, wherein when the processor executes the execution instructions stored in the memory, the processor executes any method described in the first aspect.

[0040] The present invention provides a task assignment method, device, readable medium, and electronic device based on federated learning. The method determines a target user's task assignment request based on the target user's task assignment qualifications. Based on the query task request, the method then screens the task list of a federated learning engine to determine a target task list. The target task list is sent to the target user, allowing the target user to select a target task from the target task list. Based on the target user's selection of the target task list, a target task is assigned to the target user. The technical solution provided by the present invention allows the target user to perform a task query and determines a target task list related to the target user in the task list of the federated learning engine. This ensures that the target task assigned to the target user is relevant to the target user, thereby meeting the target user's task requirements and being reasonable. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0042] Figure 1 This is a flow chart of a first task allocation method based on joint learning provided in an embodiment of the present invention;

[0043] Figure 2 Schematic diagram of the flow of a second task allocation method based on joint learning provided in an embodiment of the present invention;

[0044] Figure 3 Schematic diagram of the process of the third task allocation method based on joint learning provided in an embodiment of the present invention;

[0045] Figure 4 A schematic diagram of the structure of a task allocation device based on joint learning provided in an embodiment of the present invention;

[0046] Figure 5 Schematic diagram of the structure of a request determination module in a task allocation device based on joint learning provided in an embodiment of the present invention;

[0047] Figure 6 The figure is a schematic structural diagram of an electronic device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0048] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0049] like Figure 1 As shown, an embodiment of the present invention provides a task allocation method based on joint learning, the method comprising:

[0050] Step 11: determining the query task request of the target user based on the task assignment qualifications of the target user;

[0051] Step 12: Based on the query task request, screen the task list of the joint learning engine to determine a target task list;

[0052] Step 13: assign a target task to the target user based on the target user's selection result from the target task list.

[0053] In the above embodiment, based on the target user's task assignment qualifications, a query task request from the target user is determined, where the task assignment qualification is a permission to perform a task query, and the query task request is an instruction for triggering the task query. The query task request may carry the target user's identification information or requirement information. Then, based on the query task request, the task list of the joint learning engine is screened to determine a target task list. The target task list is a list corresponding to the target tasks selected from the task list. For example, the task information in the task list is determined, and the target tasks whose task information meets the identification information or requirement information carried by the query task request are selected. The list consisting of the selected target tasks is the target task list. The target task list is sent to the target user, allowing the target user to select a target task from the target task list. Based on the target user's selection result from the target task list, the target task is assigned to the target user. The technical solution provided by this embodiment allows the target user to perform a task query and determines the target task list related to the target user in the task list of the joint learning engine, so that the target task assigned to the target user is relevant to the target user and can meet the target user's task requirements, which is reasonable.

[0054] Specifically, the target tasks assigned to the target users can be training tasks for load forecasting models, training tasks for fault prediction models, and training tasks for operation and maintenance management models. That is, after completing the tasks, the target users can obtain the corresponding load forecasting models, fault prediction models, and operation and maintenance management models. Of course, training tasks for other models can also be included, and users can adjust the models according to actual application scenarios.

[0055] like Figure 2 As shown, in one embodiment of the present invention, step 11 determines the query task request of the target user based on the task assignment qualification of the target user, including:

[0056] Step 111, determining whether the target user is eligible for task assignment;

[0057] Step 112: If the target user has the task assignment qualification, then determine the target user's query task request;

[0058] Step 113: If the target user does not have the task assignment qualification, the target user is reminded to create a task and obtain the task assignment qualification.

[0059] In the above embodiment, a determination is made as to whether the target user is eligible for task assignment. If the target user is eligible for task assignment, the target user's query task request is confirmed. If the target user is not eligible for task assignment, the target user is prompted to create a task. After creating the task, the target user can obtain task assignment eligibility. In one possible implementation, the target user sends a task creation request containing the target user's requirement parameter information, where the requirement parameter information includes the target user's required algorithm, computing power, metadata, and other information. The joint learning engine receives the task creation request and determines whether the target user's requirement parameter information is met. If so, the task creation is successful and the target user obtains task assignment eligibility. Otherwise, the task creation fails.

[0060] like Figure 3 As shown, in one embodiment of the present invention, step 12 screens the task list of the joint learning engine based on the query task request to determine the target task list, including:

[0061] Step 121, responding to the query task request, determining a task list of the joint learning engine;

[0062] Step 122, determining the current screening condition;

[0063] Step 123: Based on the current screening condition, screen the task list of the joint learning engine to determine a target task list.

[0064] In the above embodiment, after receiving a task query request, the task list of the federated learning engine is determined in response to the query task request, where the task list includes tasks currently being executed and tasks that have already been completed. Current filtering conditions are determined, which refer to the filtering conditions corresponding to the current moment. Based on the determined current filtering conditions, the task list of the federated learning engine is filtered to determine a target task list. Specifically, the current filtering conditions include: industry type, algorithms supported by the federated learning engine, and task execution status.

[0065] In one possible implementation, the current filtering conditions are determined by the target user. The target user sends a filtering request that carries the current filtering conditions. Therefore, after receiving the filtering request, information is extracted from the filtering request to determine the current filtering conditions. In another possible implementation, the filtering conditions can be jointly determined by the target user and the federated learning engine center. Specifically, the user filtering conditions sent by the target user are received and combined with the preset center filtering conditions corresponding to the federated learning engine to jointly determine the current filtering conditions. For example, the user filtering conditions only filter the federated learning engine supported algorithms, where the filtering algorithm is A, while the preset center filtering conditions not only filter the federated learning engine supported algorithms, where the filtering algorithms are A and B, but also filter the industry type and task execution status. In this case, combining the target user's user filtering conditions and the preset center filtering conditions, it can be determined that the current filtering conditions are the federated learning engine supported algorithms, where the filtering algorithm is A, and also filter the industry type and task execution status. When the scope of the user filtering conditions differs from the scope of the preset center filtering conditions, the current filtering conditions are determined primarily based on the user filtering conditions. Of course, in a possible implementation, the current filtering condition is the preset center filtering condition. After obtaining the query task request, the joint learning engine will automatically filter according to the preset center filtering condition.

[0066] Based on the same inventive concept as the above method, Figure 4 As shown, an embodiment of the present invention provides a task allocation device based on joint learning, including:

[0067] A request determination module 41 is used to determine a query task request of a target user based on the task assignment qualifications of the target user;

[0068] A list determination module 42 is configured to filter the task list of the joint learning engine based on the query task request and determine a target task list;

[0069] The task assignment module 43 is configured to assign a target task to the target user based on the target user's selection result from the target task list.

[0070] like Figure 5 As shown, in one embodiment of the present invention,

[0071] The request determination module 41 includes:

[0072] Qualification determination unit 411, used to determine whether the target user is qualified for task assignment;

[0073] a request determining unit 412, configured to determine the query task request of the target user if the target user has the task assignment qualification;

[0074] The qualification acquisition unit 413 is configured to remind the target user to create a task and acquire the task assignment qualification if the target user does not have the task assignment qualification.

[0075] For the convenience of description, the above device embodiments are described as various units or modules according to their functions. When implementing the present invention, the functions of each unit or module can be implemented in the same or multiple software and / or hardware.

[0076] Figure 6 It is a structural diagram of an electronic device provided by an embodiment of the present invention. At the hardware level, the electronic device includes a processor 601 and a memory 602 storing execution instructions, and optionally also includes an internal bus 603 and a network interface 604. Among them, the memory 602 may include a memory 6021, such as a high-speed random access memory (Random-Access Memory, RAM), and may also include a non-volatile memory 6022 (non-volatile memory), such as at least one disk storage, etc.; the processor 601, the network interface 604 and the memory 602 can be interconnected through an internal bus 603, and the internal bus 603 can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc.; the internal bus 603 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 The figure shows only one bidirectional arrow, but it does not mean that there is only one bus or one type of bus. Of course, the electronic device may also include hardware required for other services. When the processor 601 executes the execution instructions stored in the memory 602, the processor 601 executes the method in any embodiment of the present invention and is at least used to perform the following steps: Figures 1 to 3 The method shown.

[0077] In one possible implementation, a processor reads corresponding execution instructions from a non-volatile memory into a memory and then executes them. Alternatively, the processor may obtain corresponding execution instructions from other devices to logically form a task allocation device based on federated learning. The processor executes the execution instructions stored in the memory to implement a task allocation method based on federated learning provided in any embodiment of the present invention.

[0078] The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by an integrated logic circuit of the hardware in the processor or instructions in the form of software. The above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The various methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0079] The embodiment of the present invention further provides a computer-readable storage medium, including an execution instruction. When a processor of an electronic device executes the execution instruction, the processor executes the method provided in any embodiment of the present invention. The electronic device may be specifically as follows: Figure 6 The electronic device shown; the execution instruction is a computer program corresponding to a task allocation device based on joint learning.

[0080] Those skilled in the art will appreciate that the embodiments of the present invention may be provided as methods or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or a combination of software and hardware.

[0081] The various embodiments of the present invention are described in a progressive manner. Similar portions between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the device embodiments are generally similar to the method embodiments, so their description is relatively simple. For relevant portions, refer to the description of the method embodiments.

[0082] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, product, or boiler comprising a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, product, or boiler. In the absence of further limitations, an element defined by the phrase "comprising a..." does not preclude the presence of additional identical elements in the process, method, product, or boiler comprising the element.

[0083] The foregoing is merely an embodiment of the present invention and is not intended to limit the present invention. It will be apparent to those skilled in the art that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention are intended to be included within the scope of the claims of the present invention.

Claims

1. A task allocation method based on joint learning, characterized in that: include: Determine the target user's query task request based on the target user's task assignment qualifications; Based on the query task request, screening the task list of the joint learning engine to determine the target task list; Allocating a target task to the target user based on the target user's selection result of the target task list; The step of determining the query task request of the target user based on the task assignment qualification of the target user includes: Determine whether the target user is eligible for task assignment; If the target user has the task assignment qualification, determining the query task request of the target user; If the target user does not have the task assignment qualification, the target user is reminded to create a task to obtain the task assignment qualification; The step of reminding the target user to create a task and obtain the task assignment qualification includes: Receive a task creation request sent by a target user, wherein the task creation request includes the target user's requirement parameter information, and the requirement parameter information includes the algorithm, computing power, and metadata information required by the target user; Determine whether the target user's requirement parameter information can be met. If so, the task is created successfully and the task assignment qualification is obtained.

2. The task allocation method based on joint learning according to claim 1, characterized in that: The step of screening the task list of the joint learning engine based on the query task request to determine a target task list includes: In response to the query task request, determine a task list of the joint learning engine; Determine the current filter conditions; Based on the current screening conditions, the task list of the joint learning engine is screened to determine a target task list.

3. The task allocation method based on joint learning according to claim 2, characterized in that: Determining the current screening condition includes: Receive a screening request sent by a target user; Information is extracted from the screening request to determine the current screening condition.

4. The task allocation method based on joint learning according to claim 2, characterized in that: Determining the current screening condition includes: Determine the user filtering criteria sent by the target user; Determine the preset center screening conditions corresponding to the federated learning engine; Based on the user filtering condition and the central filtering condition, a current filtering condition is determined.

5. The task allocation method based on joint learning according to claim 2, characterized in that: The current screening conditions include: industry type, federated learning engine supported algorithms, and task execution status.

6. A task allocation device based on joint learning, characterized in that: include: A request determination module, configured to determine a query task request of a target user based on the target user's task assignment qualifications; A list determination module is used to screen the task list of the joint learning engine based on the query task request and determine the target task list; A task assignment module is used to assign a target task to the target user based on the target user's selection result from the target task list; The request determination module includes: Qualification judgment unit, used to judge whether the target user is qualified for task assignment; a request determining unit, configured to determine the query task request of the target user if the target user has the task assignment qualification; a qualification obtaining unit, configured to remind the target user to create a task and obtain the task assignment qualification if the target user does not have the task assignment qualification; The qualification acquisition unit is specifically used to: receive a task creation request sent by a target user, the task creation request includes the target user's requirement parameter information, the requirement parameter information includes the algorithm, computing power, and metadata information required by the target user; determine whether the target user's requirement parameter information can be met, if so, the task is created successfully and the task assignment qualification is obtained. 7 . A readable medium comprising an execution instruction, wherein when a processor of an electronic device executes the execution instruction, the electronic device executes the method according to claim 1 .

8. An electronic device comprising a processor and a memory storing execution instructions, wherein when the processor executes the execution instructions stored in the memory, the processor executes the method according to any one of claims 1 to 5.

Images