A resource allocation method, device, readable medium and electronic device

Abstract

The present invention discloses a resource allocation method, apparatus, readable medium and electronic device. The method includes: obtaining a metadata list provided by a data provider; determining a target user based on the metadata list; determining a mathematical model for the target user based on the data provided by the data provider; determining virtual resources obtained by the target user by invoking the mathematical model; determining the contribution ratio of the data provided by the data provider in the mathematical model; and determining the virtual resource share allocated to the data provider based on the contribution ratio and the virtual resources. In the technical solution provided by the present invention, the target user is determined according to the metadata list provided by the data provider, and only when there is a target user, the mathematical model is constructed, so as to ensure that virtual resources can be obtained according to the mathematical model, so that the data provider can obtain a virtual resource share matching the data it provides, which is reasonable.

Description

Technical Field

[0001] The present invention relates to the field of energy, and particularly to a resource allocation method, apparatus, readable medium and electronic device. Background Art

[0002] With the rapid development of Internet technology, user data has become an increasingly important resource. Based on user data, various prediction models can be trained, and accurate prediction results are the basis for the efficient operation of the energy system. However, not every energy user can collect a large amount of user data and train an accurate prediction model, which makes federated learning a trend. To encourage each energy user to participate in federated learning, it is crucial to determine a reasonable resource allocation method. Summary of the Invention

[0003] The present invention provides a resource allocation method, apparatus, readable medium and electronic device. According to the metadata list provided by the data provider, the target user is determined. Only when there is a target user, a mathematical model is constructed, so as to ensure that virtual resources can be obtained according to the mathematical model, and the data provider can obtain a virtual resource share that matches the data it provides, which is reasonable.

[0004] In a first aspect, the present invention provides a resource allocation method, including:

[0005] Obtain the metadata list provided by the data provider;

[0006] Based on the metadata list, determine the target user;

[0007] Based on the data provided by the data provider, determine a mathematical model for the target user;

[0008] Determine the virtual resources obtained by the target user by invoking the mathematical model;

[0009] Determine the contribution ratio of the data provided by the data provider in the mathematical model;

[0010] Based on the contribution ratio and the virtual resources, determine the virtual resource share allocated to the data provider.

[0011] Preferably,

[0012] The step of determining the virtual resources obtained by the target user by invoking the mathematical model includes:

[0013] Determine the number of times the target user invokes the mathematical model;

[0014] Based on the number of times the target user invokes the mathematical model, determine the virtual resources obtained by the target user by invoking the mathematical model.

[0015] Preferably,

[0016] Determining a target user based on the metadata list includes:

[0017] Determining the model requirements of the candidate target users;

[0018] Determining the matching degree between the model requirements and the metadata list;

[0019] Determining a target user from the candidate target users based on the matching degree.

[0020] Preferably,

[0021] The method further includes:

[0022] Determining the unselected target users from the candidate target users;

[0023] Determining the number of times the unselected target users are not selected;

[0024] If the number of times of not being selected exceeds a set number of times, then based on the model requirements of the unselected target users, using the unselected target users as new target users, determining new data providers for the new target users.

[0025] Preferably,

[0026] Before determining a mathematical model for the target user based on the data provided by the data provider, the method further includes:

[0027] Determining the credit rating of the target user;

[0028] If the credit rating of the target user is lower than a set rating, then updating the target user.

[0029] Preferably,

[0030] Determining the contribution ratio of the data provided by the data provider in the mathematical model includes:

[0031] Determining the degree of decrease of the loss function of the mathematical model before and after the data provided by the data provider is added to the mathematical model;

[0032] Based on the degree of decrease, determining the contribution ratio of the data provided by the data provider in the mathematical model.

[0033] In a second aspect, the present invention provides a resource allocation device, including:

[0034] A list acquisition module, configured to acquire a metadata list provided by a data provider;

[0035] A user determination module, configured to determine a target user based on the metadata list;

[0036] A model determination module, configured to determine a mathematical model for the target user based on the data provided by the data provider;

[0037] A resource determination module, configured to determine the virtual resources obtained by the target user invoking the mathematical model;

[0038] A contribution ratio determination module, configured to determine the contribution ratio of the data provided by the data provider in the mathematical model;

[0039] An allocation determination module, configured to determine the share of virtual resources allocated to the data provider based on the contribution ratio and the virtual resources.

[0040] Preferably,

[0041] The resource determination module includes:

[0042] A frequency determination unit, configured to determine the frequency of the target user invoking the mathematical model;

[0043] A resource determination unit, configured to determine the virtual resources obtained by the target user invoking the mathematical model based on the frequency of the target user invoking the mathematical model.

[0044] In a third aspect, the present invention provides a readable medium, including execution instructions, when a processor of an electronic device executes the execution instructions, the electronic device executes the method according to any one of the first aspects.

[0045] In a fourth aspect, the present invention provides an electronic device, including a processor and a memory storing execution instructions, when the processor executes the execution instructions stored in the memory, the processor executes the method according to any one of the first aspects.

[0046] The present invention provides a resource allocation method, apparatus, readable medium, and electronic device. The method first obtains a metadata list provided by a data provider, determines a target user based on the metadata list, and only after the existence of the target user, determines a mathematical model for the target user according to the data provided by the data provider, and then allocates the mathematical model to the target user, enabling the target user to call the mathematical model and determining the virtual resources that the target user needs to transfer to the joint center due to calling the mathematical model. Further, it determines the contribution ratio of the data provided by the data provider in the mathematical model, and determines the share of virtual resources allocated to the data provider according to the contribution ratio and the virtual resources. In the technical solution provided by the present invention, the target user is determined based on the metadata list provided by the data provider, and only when the target user exists, the mathematical model is constructed, reducing the risk when the data provider provides data, ensuring that virtual resources can be obtained according to the mathematical model, and enabling the data provider to obtain a share of virtual resources that matches the data it provides, which is reasonable. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts.

[0048] Figure 1 It is a schematic flowchart of the first resource allocation method provided in the embodiments of the present invention;

[0049] Figure 2 It is a schematic flowchart of the second resource allocation method provided in the embodiments of the present invention;

[0050] Figure 3 It is a schematic flowchart of the third resource allocation method provided in the embodiments of the present invention;

[0051] Figure 4 It is a schematic flowchart of the fourth resource allocation method provided in the embodiments of the present invention;

[0052] Figure 5 It is a schematic flowchart of the fifth resource allocation method provided in the embodiments of the present invention;

[0053] Figure 6 It is a schematic flowchart of the sixth resource allocation method provided in the embodiments of the present invention;

[0054] Figure 7 It is a schematic structural diagram of a resource allocation apparatus provided in the embodiments of the present invention;

[0055] Figure 8 Schematic diagram of a resource determination module in a resource allocation device provided in an embodiment of the present invention;

[0056] Figure 9 Schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed implementation manners

[0057] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with specific embodiments and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0058] As Figure 1 shown, an embodiment of the present invention provides a resource allocation method, which includes:

[0059] Step 11: Obtain a metadata list provided by a data provider;

[0060] Step 12: Determine a target user based on the metadata list;

[0061] Step 13: Determine a mathematical model for the target user based on the data provided by the data provider;

[0062] Step 14: Determine the virtual resources obtained by the target user by invoking the mathematical model;

[0063] Step 15: Determine the contribution ratio of the data provided by the data provider in the mathematical model;

[0064] Step 16: Determine the virtual resource share allocated to the data provider based on the contribution ratio and the virtual resources.

[0065] In the above embodiments, by first obtaining the metadata list provided by the data provider, determining the target user according to the metadata list, only after the target user exists, determining a mathematical model for the target user according to the data provided by the data provider, allocating the mathematical model to the target user, enabling the target user to call the mathematical model, and determining the virtual resources that the target user needs to transfer to the joint center due to calling the mathematical model, further determining the contribution ratio of the data provided by the data provider in the mathematical model, and determining the virtual resource share allocated to the data provider according to the contribution ratio and the virtual resources. In the technical solution provided by the present invention, the target user is determined according to the metadata list provided by the data provider, and only when the target user exists, the mathematical model is constructed, reducing the risk when the data provider provides data, ensuring that virtual resources can be obtained according to the mathematical model, so that the data provider can obtain the virtual resource share matching the data it provides, which is reasonable.

[0066] As Figure 2 shown, in an embodiment of the present invention, step 12 determines the target user based on the metadata list, including:

[0067] Step 121, determining the model requirements of the candidate target users;

[0068] Step 122, determining the matching degree between the model requirements and the metadata list;

[0069] Step 123, determining the target user from the candidate target users based on the matching degree.

[0070] In the above embodiments, when determining the target user, it is necessary to select according to the model requirements of the candidate target users. Therefore, first determine the model requirements of all candidate target users, where the candidate target users are all users who need to obtain a mathematical model. Specifically, the candidate target users can be determined by receiving the model construction requests of the users. When a user needs a mathematical model, the user sends a model construction request to the joint center, and the joint center marks the user as a candidate target user and determines the model identifiers in the model requirements of each candidate target user, such as the required model type, usage, accuracy, etc. Further determine the matching degree between the model requirements and the metadata list. The metadata list is not real data but a description of real data, which can reduce the risk of data providers providing data. After the data provider provides the metadata list, the type of the model to be constructed and the usage of the model to be constructed can be determined according to the metadata list. Therefore, the target user can be determined according to the matching degree between the metadata list and the model requirements. Specifically, predict the mathematical model to be constructed determined according to the metadata list, determine the model identifier (such as model type, usage, etc.) of the mathematical model to be constructed, determine the number of the same model identifiers between the model identifier of the mathematical model to be constructed and the model requirements of the candidate target users, divide the number of the same identifiers by the total number of identifiers to obtain the matching degree between the model requirements and the metadata list, and determine all candidate target users with a matching degree greater than the set threshold as target users, so as to realize determining the target user according to the requirements of the candidate target users and the metadata list, and ensure that the subsequent constructed mathematical model meets the requirements of the target user.

[0071] As Figure 3 shown, in an embodiment of the present invention, the method further includes:

[0072] Step 17, determining the unselected target users among the candidate target users;

[0073] Step 18, determining the number of times the unselected target users have not been selected;

[0074] Step 19, if the number of times of not being selected exceeds the set number of times, then based on the model requirements of the unselected target users, taking the unselected target users as new target users, determine new data providers for the new target users.

[0075] In the above embodiments, among the candidate target users, the unselected target users are determined, and the number of times the unselected target users are not selected is judged. If the number of times not selected exceeds the set number of times, according to the model requirements of the unselected target user, a new data provider is determined for the unselected target user. After the new data provider is determined, if the unselected target user becomes the new target user, then the data provided by the new data provider is used to determine a new mathematical model for the new target user. Similarly, the virtual resources obtained by the new target user by invoking the new mathematical model are determined, and the contribution ratio of the data provided by the new data provider in the new mathematical model is determined, and then the share of virtual resources allocated to the new data provider is determined. That is to say, after the new data provider and the new target user are determined, steps 14 to 16 are also executed, so as to meet the need to construct a mathematical model for the unselected target user multiple times.

[0076] As Figure 4 shown, in an embodiment of the present invention, the method further includes:

[0077] Step 20, determining the credit rating of the target user;

[0078] Step 21, if the credit rating of the target user is lower than the set rating, then update the target user.

[0079] In the above embodiments, before determining a mathematical model for the target user based on the data provided by the data provider, it is necessary to determine the credit rating of the target user. The credit rating of the target user can be confirmed according to the credit investigation, assets, historical virtual resource transfer situation, etc. of the target user. The credit rating can be divided into levels such as excellent, good, medium, and poor. If the credit rating of the target user is lower than the set rating, such as lower than the medium level, at this time, even if a mathematical model is trained for the target user, it is more likely that virtual assets cannot be transferred from the target user. Therefore, it is necessary to re-select the target user to update the target user, so as to ensure that the joint center and the data provider can obtain virtual resources, where the virtual resources can be points and other contents. Of course, if the credit rating of the target user is higher than the set level, then step 13 is continued.

[0080] As Figure 5 shown, in an embodiment of the present invention, step 14 of determining the virtual resources obtained by the target user by invoking the mathematical model includes:

[0081] Step 141, determining the number of times the target user invokes the mathematical model;

[0082] Step 142, based on the number of times the target user invokes the mathematical model, determining the virtual resources obtained by the target user by invoking the mathematical model.

[0083] In the above embodiments, the virtual resources transferred by the target user to the joint center are related to the number of times the target user calls the mathematical model. Therefore, determine the number of times the target user calls the mathematical model, and determine the virtual resources obtained by the target user due to calling the mathematical model according to this number of times, that is, determine the virtual resources that the target user needs to transfer to the joint center. Specifically, if the number of times the target user calls the mathematical model is more, the virtual resources transferred by the target user to the joint center should be more. In order to determine a reasonable resource allocation scheme and encourage the target user to call the mathematical model more, the number of times the target user calls the mathematical model can be divided into levels, and different levels correspond to different virtual resource transfer ratio coefficients. When the number of times the target user calls the mathematical model is more, the virtual resource transfer ratio coefficient it may correspond to is lower. For example, when the number of times the target user calls the mathematical model is 0 - 5 times, the virtual resource transfer ratio coefficient is 1.15; when the number of times the target user calls the mathematical model is 5 - 10 times, the virtual resource transfer ratio system is 1.13; when the number of times the target user calls the mathematical model is 10 - 20 times, the virtual resource transfer ratio system is 1.11. Thus, by appropriately reducing the number of virtual resources transferred by the target user to the joint center, the target user is encouraged to call the mathematical model more.

[0084] As Figure 6 shown, in an embodiment of the present invention, step 15 of determining the contribution ratio of the data provided by the data provider in the mathematical model includes:

[0085] Step 151, determining the degree of decrease in the loss function of the mathematical model before and after the data provided by the data provider is added to the mathematical model;

[0086] Step 152, based on the degree of decrease, determining the contribution ratio of the data provided by the data provider in the mathematical model.

[0087] In the above embodiments, in order to determine the contribution ratio of the data provided by the data provider in the mathematical model, determine the degree of decrease in the loss function of the mathematical model before and after the data provided by the data provider is added to the mathematical model, and determine the contribution ratio of the data provided by the data provider in the mathematical model according to this degree of decrease. Specifically, the greater the degree of decrease in the loss function, the greater the contribution ratio of the data provided by this data provider to the mathematical model. The greater the contribution ratio of the data provided by the data provider in the mathematical model, the more virtual resource shares the data provider obtains, making the resource allocation reasonable.

[0088] Based on the same inventive concept as the above method, as Figure 7 shown, an embodiment of the present invention provides a resource allocation device, including:

[0089] A list acquisition module 71 for acquiring a metadata list provided by a data provider;

[0090] A user determination module 72 for determining a target user based on the metadata list;

[0091] A model determination module 73 for determining a mathematical model for the target user based on data provided by the data provider;

[0092] A resource determination module 74 for determining virtual resources obtained by the target user by invoking the mathematical model;

[0093] A contribution ratio determination module 75 for determining the contribution ratio of the data provided by the data provider in the mathematical model;

[0094] An allocation determination module 76 for determining the share of virtual resources allocated to the data provider based on the contribution ratio and the virtual resources.

[0095] As Figure 8 shown, in an embodiment of the present invention, the resource determination module 74 includes:

[0096] A frequency determination unit 741 for determining the number of times the target user invokes the mathematical model;

[0097] A resource determination unit 742 for determining virtual resources obtained by the target user by invoking the mathematical model based on the number of times the target user invokes the mathematical model.

[0098] For convenience of description, when describing the above device embodiments, the functions are divided into various units or modules for description respectively. When implementing the present invention, the functions of the units or modules can be realized in one or more software and / or hardware.

[0099] Figure 9It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. At the hardware level, the electronic device includes a processor 901 and a memory 902 storing execution instructions. Optionally, it further includes an internal bus 903 and a network interface 904. Among them, the memory 902 may include a memory 9021, such as a high-speed random access memory (Random-Access Memory, RAM), and may also include a non-volatile memory 9022 (non-volatile memory), such as at least one disk memory, etc.; the processor 901, the network interface 904, and the memory 902 can be interconnected through the internal bus 903, and the internal bus 903 can be an ISA (Industry Standard Architecture, industrial standard architecture) bus, a PCI (Peripheral Component Interconnect, peripheral component interconnect standard) bus, or an EISA (Extended Industry Standard Architecture, extended industrial standard structure) bus, etc.; the internal bus 903 can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, Figure 9 only a two-way arrow is used in the figure, but it does not mean that there is only one bus or one type of bus. Of course, the electronic device may also include other hardware required for other services. When the processor 901 executes the execution instructions stored in the memory 902, the processor 901 executes the method in any one of the embodiments of the present invention and is at least used to execute as Figures 1 to 5 the method shown.

[0100] In a possible implementation manner, the processor reads the corresponding execution instructions from the non-volatile memory into the memory and then runs, or can also obtain the corresponding execution instructions from other devices to form a resource allocation device at the logical level. The processor executes the execution instructions stored in the memory to implement a resource allocation method provided in any one of the embodiments of the present invention through the executed execution instructions.

[0101] A processor may be an integrated circuit chip with the ability to process signals. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in the processor or the instructions in the form of software. The above-mentioned 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. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0102] The embodiments of the present invention also provide a computer-readable storage medium, including execution instructions. When the processor of the electronic device executes the execution instructions, the processor executes the method provided in any one of the embodiments of the present invention. The electronic device may specifically be the electronic device as Figure 9 shown; the execution instructions are the computer program corresponding to a resource allocation device.

[0103] Those skilled in the art should understand that the embodiments of the present invention may be provided as a method or a computer program product. Therefore, the present invention may adopt the form of a complete hardware embodiment, a complete software embodiment, or a combination of software and hardware.

[0104] The various embodiments in the present invention are described in a progressive manner. The same or similar parts among the various embodiments may be referred to each other, and the differences between each embodiment and other embodiments are emphasized. In particular, for the device embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts may refer to the partial description of the method embodiments.

[0105] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover a non-exclusive inclusion, so that a process, method, commodity or boiler including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, commodity or boiler. Without further limitations, the element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, commodity or boiler including the said element.

[0106] The above are only embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, various modifications and variations can be made to the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the scope of the claims of the present invention.

Claims

1. A resource allocation method, characterized in that, including: obtaining a list of metadata provided by a data provider; determining a target user based on the metadata list; determining a mathematical model for the target user based on data provided by the data provider; determining virtual resources obtained by the target user by invoking the mathematical model; determining the contribution ratio of the data provided by the data provider in the mathematical model; determining the share of virtual resources allocated to the data provider based on the contribution ratio and the virtual resources; wherein determining a target user based on the metadata list includes: obtaining the model requirements of candidate target users and determining the model identifiers in each model requirement; predicting a mathematical model to be constructed according to the metadata list and determining the model identifier of the mathematical model; determining the number of model identifiers in the model requirements of the candidate target users that are the same as the model identifier of the mathematical model to be constructed, and dividing the same number by the total number of model identifiers to obtain the matching degree between the model requirements and the metadata list; determining the candidate target users with a matching degree greater than a set threshold as the target user; determining the contribution ratio of the data provided by the data provider in the mathematical model includes: determining the degree of decrease in the loss function of the mathematical model before and after the data provided by the data provider is added to the mathematical model; determining the contribution ratio of the data provided by the data provider in the mathematical model based on the degree of decrease.

2. The resource allocation method according to claim 1, wherein Determining the virtual resources obtained by the target user by invoking the mathematical model includes; determining the number of times the target user invokes the mathematical model; determining the virtual resources obtained by the target user by invoking the mathematical model based on the number of times the target user invokes the mathematical model.

3. The resource allocation method according to claim 1, characterized in that The method further includes: determining unselected target users among the candidate target users; determining the number of times the unselected target users are not selected; if the number of times of non-selection exceeds a set number of times, then based on the model requirements of the unselected target users, taking the unselected target users as new target users, and determining new data providers for the new target users.

4. The resource allocation method according to claim 1, wherein Before determining a mathematical model for the target user based on data provided by the data provider, the method further includes: determining the credit rating of the target user; if the credit rating of the target user is lower than a set rating, then updating the target user.

5. A resource allocation device, characterized in that, including: a list acquisition module for obtaining a list of metadata provided by a data provider; a user determination module for determining a target user based on the metadata list; a model determination module for determining a mathematical model for the target user based on data provided by the data provider; a resource determination module for determining the virtual resources obtained by the target user by invoking the mathematical model; a ratio determination module for determining the contribution ratio of the data provided by the data provider in the mathematical model; an allocation determination module for determining the share of virtual resources allocated to the data provider based on the contribution ratio and the virtual resources; wherein determining a target user based on the metadata list includes: obtaining the model requirements of candidate target users and determining the model identifiers in each model requirement; Predict the mathematical model to be constructed based on the metadata list, and determine the model identifier of the mathematical model; Determine the number of model identifiers in the model requirements of the to-be-constructed mathematical model that are the same as those in the to-be-selected target users, and divide the number of the same model identifiers by the total number of model identifiers to obtain the matching degree between the model requirements and the metadata list; Determine the to-be-selected target users with a matching degree greater than the set threshold as the target users; Determine the contribution ratio of the data provided by the data provider in the mathematical model, including: Determine the degree of decrease in the loss function of the mathematical model before and after the data provided by the data provider is added to the mathematical model; Based on the degree of decrease, determine the contribution ratio of the data provided by the data provider in the mathematical model.

6. The resource allocation device according to claim 5, wherein The resource determination module includes: A frequency determination unit for determining the frequency of the target user calling the mathematical model; A resource determination unit for determining the virtual resources obtained by the target user calling the mathematical model based on the frequency of the target user calling the mathematical model.

7. A readable medium, including execution instructions, when the processor of the electronic device executes the execution instructions, the electronic device executes the method according to any one of claims 1 to 4.

8. An electronic device, including a processor and a memory storing execution instructions, when the processor executes the execution instructions stored in the memory, the processor executes the method according to any one of claims 1 to 4.

Images