CN115169992B - Block chain based data element rights and interests allocation method, device and system - Google Patents
Block chain based data element rights and interests allocation method, device and system Download PDFInfo
- Publication number
- CN115169992B CN115169992B CN202211070606.3A CN202211070606A CN115169992B CN 115169992 B CN115169992 B CN 115169992B CN 202211070606 A CN202211070606 A CN 202211070606A CN 115169992 B CN115169992 B CN 115169992B
- Authority
- CN
- China
- Prior art keywords
- data element
- data
- fusion
- model
- block chain
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method, a device and a system for allocating data element rights and interests based on a block chain, and relates to the technical field of block chains. One embodiment of the method comprises: acquiring feature information of the submodel from the block chain according to the demand information provided by the data model demand side; fusing the submodels according to the feature information of the submodels and the current fusion mode selected from the at least two fusion modes; determining a target fusion mode in at least two fusion modes; calling a first intelligent contract in the block chain to calculate the contribution degree of a data element provider according to the feature information and the target fusion mode of at least two submodels; and calling a second intelligent contract in the block chain to distribute right and interest certificates for the data element providers and the trainers of the submodels according to the contribution degree of the data element providers and the right and interest budget provided by the data model demand side. This embodiment can more reasonably assign rights and interests to data element providers and trainers of sub-models.
Description
Technical Field
The present invention relates to the field of blockchain technologies, and in particular, to a method, an apparatus, and a system for allocating rights and interests of data elements based on blockchains.
Background
The circulation of the data elements is participated by a plurality of parties such as a data demand party, a data supply party and the like, and the value of the data elements can be effectively released. To facilitate the circulation of data elements, the prior art encourages more participants to participate in the circulation process through equity allocation mechanisms.
In the prior art, a block link point fuses a plurality of sub-models by a weighted average method, and assigns rights and interests to data element providers based on the data models obtained by fusion. However, the method adopts a fixed fusion mode, and does not consider the difference requirements of the fusion modes in different scenes, which may cause unreasonable rights and interests allocation of the data element provider. In addition, the method only allocates rights to the data element provider, and does not consider the contribution of other participants.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method, an apparatus, and a system for allocating rights and interests of data elements based on a block chain, which can more reasonably allocate rights and interests to a data element provider and a trainer of a sub-model, and improve the enthusiasm of each participant in participating in data element circulation.
In a first aspect, an embodiment of the present invention provides a method for allocating data element rights based on a block chain, where the method is applied to a node device of the block chain, and the method includes:
acquiring characteristic information of at least two sub models from the block chain according to requirement information provided by a data model requirement end; wherein, the sub-model is obtained by data elements or training the data elements;
fusing the at least two sub-models according to the characteristic information of the at least two sub-models and the current fusion mode selected from the at least two fusion modes to generate a fusion model;
determining a target fusion mode in at least two fusion modes corresponding to the at least two fusion models; wherein, the fusion model generated based on the target fusion mode is a data model, and the at least two fusion models include: generating a fusion model in the current node equipment and generating fusion models in other node equipment;
calling a first intelligent contract which is pre-deployed in the block chain to calculate the contribution degree of a data element provider according to the feature information of the at least two submodels and the target fusion mode;
and calling a second intelligent contract which is pre-deployed in the block chain, so as to distribute right certificates for the data element providers and the trainers of the submodels according to the contribution degree of the data element providers and the right budget provided by the data model demand side.
In a second aspect, an embodiment of the present invention provides a device for allocating rights and interests of data elements based on a block chain, where the device is applied to a node device of the block chain, and the device includes:
the acquisition module is configured to acquire the characteristic information of at least two sub models from the block chain according to the demand information provided by the demand end of the data model; wherein, the sub-model is obtained by data elements or training the data elements;
the fusion module is configured to fuse the at least two sub-models according to the characteristic information of the at least two sub-models and a current fusion mode selected from the at least two fusion modes to generate a fusion model;
the determining module is configured to determine a target fusion mode in at least two fusion modes corresponding to the at least two fusion models; wherein, the fusion model generated based on the target fusion mode is a data model, and the at least two fusion models include: the method comprises the steps that a fusion model generated in current node equipment and fusion models generated in other node equipment are obtained;
the calling module is configured to call a first intelligent contract which is pre-deployed in the block chain, so as to calculate the contribution degree of a data element provider according to the feature information of the at least two submodels and the target fusion mode; and calling a second intelligent contract which is pre-deployed in the block chain to distribute right and interest certificates for the data element provider and the trainer of the submodel according to the contribution degree of the data element provider and the right and interest budget provided by the data model demand side.
In a third aspect, an embodiment of the present invention provides a system for allocating data element rights and interests based on a block chain, where the system includes: the system comprises a data model demand end, a data element providing end and a plurality of data element rights and interests distribution devices based on block chains; wherein the block chain-based data element rights allocation device is applied to a node device of the block chain;
the data model demand end is used for providing demand information;
the data element providing end is used for providing data elements;
the block chain-based data element rights and interests allocation device is used for acquiring the characteristic information of at least two sub models from the block chain according to the requirement information provided by the data model requirement end; fusing the at least two sub-models according to the characteristic information of the at least two sub-models and the current fusion mode selected from the at least two fusion modes to generate a fusion model; determining a target fusion mode in at least two fusion modes corresponding to the at least two fusion models; calling a first intelligent contract which is pre-deployed in the block chain to calculate the contribution degree of the data element provider according to the feature information of the at least two submodels and the target fusion mode; calling a second intelligent contract which is pre-deployed in the block chain, and distributing right certificates for the data element providers and the trainers of the submodels according to the contribution degree of the data element providers and the right budget provided by the data model demand side;
wherein the sub-model is the data element or is obtained by training the data element; a fusion model generated based on the target fusion mode is a data model, and the at least two fusion models comprise: the fusion model generated in the current node device and the fusion models generated in other node devices.
In a fourth aspect, an embodiment of the present invention provides an electronic device, including:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the methods as described in the embodiments above.
In a fifth aspect, the present invention provides a computer readable medium, on which a computer program is stored, and when the program is executed by a processor, the method according to the above embodiments is implemented.
One embodiment of the above invention has the following advantages or benefits: and determining a target fusion mode from different fusion modes based on the data model obtained by fusion, taking the difference of the performance of the data model obtained by different fusion modes into consideration, and meeting different requirements of a data model demander. Based on the target fusion mode, rights and interests are distributed to the data element providers and the trainers of the sub-models, rights and interests can be distributed to the participants more reasonably, and the circulation enthusiasm of the participants and the data elements is improved.
Further effects of the above-mentioned non-conventional alternatives will be described below in connection with the embodiments.
Drawings
The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:
fig. 1 is a flowchart of a block chain-based data element equity allocation method according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a block chain-based data element rights allocation apparatus according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a system for assigning rights to data elements based on a blockchain according to an embodiment of the present invention;
fig. 4 is a flowchart of a block chain-based data element equity allocation method according to another embodiment of the present invention;
fig. 5 is a schematic block diagram of a computer system suitable for use in implementing a terminal device or server of an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
As shown in fig. 1, an embodiment of the present invention provides a method for assigning rights to data elements based on a blockchain, where the method is applied to a node device of a blockchain, and the method includes:
step 101: acquiring characteristic information of at least two submodels from a block chain according to requirement information provided by a data model requirement end; wherein, the sub-model is a data element or is obtained by training the data element.
And the data model demand side is a terminal of a data model demand side.
The requirement information may include information of a data element provider, information of a data element, and the like, for example, the data model requester wants to obtain an image recognition model by fusing the data elements a and B, and the requirement information may include identifiers of the data elements a and B, and an identifier of the data element provider to which the data element a belongs and an identifier of the data element provider to which the data element B belongs.
The block chain stores the characteristic information of the submodel, the submodel corresponds to the data elements, and the submodel can be the data elements and can be obtained through data element training. The embodiment of the invention extracts the characteristic information from the submodel and uploads the characteristic information to the block chain. The feature information of the sub-model may be a weight, a hyper-parameter, etc. of the sub-model. The data element providing end can also provide information such as a training party of the sub-model and a source of the data element to the data element right allocation device based on the block chain, and the information is also uploaded to the block chain and stored corresponding to the characteristic information of the sub-model. The feature information of the sub-model may be stored in the blockchain in correspondence with the identification of the data elements. Considering that the submodels used in different transactions may be the same, in an actual application scenario, the block chain-based data element equity allocation device may first query the block chain according to the requirement information provided by the data model requirement end, and if the block chain does not have the feature information of the corresponding submodel, trigger the data element providing end to determine the data element according to the requirement information. Of course, the data element providing end may also determine the data element according to the requirement information, and then obtain the feature information of the sub-model from the block chain based on the data element interest allocation apparatus of the block chain.
Step 102: and fusing the at least two sub-models according to the characteristic information of the at least two sub-models and the current fusion mode selected from the at least two fusion modes to generate a fusion model.
In an actual application scenario, different node devices may correspond to different fusion modes, and a fusion mode may be selected from a plurality of preset fusion modes to fuse the sub-models.
Step 103: determining a target fusion mode in at least two fusion modes corresponding to the at least two fusion models; the fusion model generated based on the target fusion mode is a data model, and the at least two fusion models comprise: the fusion model generated in the current node device and the fusion models generated in other node devices.
In the embodiment of the invention, the target fusion mode can be selected according to model evaluation indexes such as accuracy, precision, recall rate and the like, for example, the fusion mode with the highest accuracy is taken as the target fusion mode, and if a plurality of fusion modes with the highest accuracy exist, the target fusion mode can be selected according to the fusion time.
Step 104: and calling a first intelligent contract which is pre-deployed in the block chain to calculate the contribution degree of the data element provider according to the characteristic information and the target fusion mode of at least two submodels.
In a practical application scenario, the contribution degree of the data element provider can be calculated through a cooperative game model, such as a sharey model. The method in the first intelligent contract comprises the following steps: and calculating the contribution degree of the data element provider according to the feature information of at least two sub models and the target fusion mode.
Step 105: and calling a second intelligent contract which is pre-deployed in the block chain to distribute right certificates for the data element providers and the trainers of the sub-models according to the contribution degree of the data element providers and the right budget provided by the data model demand ends.
The method in the second intelligent contract comprises: and distributing right certificates for the data element providers and the trainers of the sub-models according to the contribution degree of the data element providers and the right budget provided by the data model demand side.
The embodiment of the invention determines the target fusion mode from different fusion modes based on the data model obtained by fusion, considers the difference of the performance of the data model obtained by different fusion modes and meets different requirements of a data model demander. Based on the target fusion mode, rights and interests are distributed to the data element providers and the trainers of the sub-models, rights and interests can be distributed to the participants more reasonably, and the circulation enthusiasm of the participants and the data elements is improved. In addition, the embodiment of the invention can pre-deploy the equity distribution method and the contribution degree calculation method in the intelligent contract in the form of the intelligent contract, thereby improving the equity distribution efficiency. The two methods can be deployed in the same intelligent contract or different intelligent contracts, that is, the first intelligent contract and the second intelligent contract can be the same intelligent contract or two different intelligent contracts.
In one embodiment of the invention, a data element provider may provide at least three forms of data elements:
(1) The data elements include: publishing the data;
at this time, the method further includes:
acquiring public data provided by a data element providing end;
training based on public data to obtain a sub-model;
and extracting the characteristic information of the submodel and uploading the characteristic information of the submodel to the block chain.
The public data can be disclosed externally and can be directly acquired externally. And if the data element is public data, the data element providing end sends the public data to the data element equity allocation device based on the block chain, and the data element equity allocation device based on the block chain trains the sub-model according to the public data. The data element rights and interests distribution device based on the block chain can train the submodels according to the requirement information provided by the data model requirement end.
(2) The data elements include: private data.
At this time, the method further includes:
acquiring a submodel provided by a data element providing end; wherein the sub-model is obtained by training a data element providing end based on private data;
and extracting the characteristic information of the submodel and uploading the characteristic information of the submodel to the block chain.
The private data can not be exported, and the data element providing end can train the sub-model according to the requirement information provided by the data model requirement end and then provide the sub-model to the data element interest allocation device based on the block chain.
(3) The data elements include: a sub-model;
the method further comprises the following steps:
acquiring a submodel provided by a data element providing end;
and extracting the characteristic information of the submodel and uploading the characteristic information of the submodel to the block chain.
The data element provider may also directly provide the trained submodel, which may be pre-trained by the data element provider or other participant's terminal, to the blockchain-based data element equity assignment device.
Through the embodiment of the invention, the data element providing end can provide data elements in different forms, and the circulation range and the use scene of the data elements are widened.
In an embodiment of the present invention, determining a target fusion mode in at least two fusion modes corresponding to at least two fusion models includes:
calculating the accuracy of each fusion model;
and determining a target fusion mode in at least two fusion modes corresponding to the at least two fusion models according to the accuracy of each fusion model.
The requirement information can also comprise an accuracy lower limit preset by a data model demander, the accuracy of the fusion model obtained in the target fusion mode is not lower than the accuracy lower limit, and if the accuracy corresponding to each fusion mode is lower than the accuracy lower limit, the method can also send prompt information to the data model demander so as to prompt the data model demander that the fusion model cannot meet the requirements. The demand information can also comprise a fusion time upper limit preset by a data model demand side, the fusion time corresponding to the target fusion mode is not longer than the fusion time upper limit, and if the fusion time corresponding to each fusion mode is longer than the fusion time upper limit, the method can also send prompt information to a data model demand side to prompt that the fusion model of the data model demand side cannot meet the requirements.
The embodiment of the invention can select the fusion model with higher accuracy and improve the quality of the fusion model.
In one embodiment of the invention, the feature information of the submodel includes: weight of the submodel;
calculating the contribution degree of a data element provider according to the feature information and the target fusion mode of at least two sub models, and the method comprises the following steps:
calculating a Shapley value of a data element provider according to the weights of at least two sub-models and a target fusion mode; wherein the sharley value of the data element provider is used to characterize the contribution of the data element provider.
The embodiment of the invention calculates the Shapley value of the data element provider based on formula 1.
Wherein the content of the first and second substances,
a sharey value for characterizing the kth data element provider, i.e., the contribution of the kth data element provider; i is a collection of data element providers,
is the set formed by all subsets of I that contain member k,
is the number of elements in the set s,
for a set s with the element k removed,
in order to be a function of the loss,
is the weight of the sub-model,
is a target fusion mode. A loss function mayTo select the existing absolute loss function, square sum loss function, etc.
In one embodiment of the present invention, assigning equity certificates to the data element providers and the trainers of the sub-models according to the contribution degree of the data element providers and the equity budget provided by the data model demanders comprises:
calculating the total equity value of the data element provider and the total equity value of the training party of the submodel according to the equity budget provided by the data model demand side, the weight of the preset data element provider and the weight of the training party of the submodel;
calculating the equity value of each data element provider according to the total equity value of the data element providers and the contribution degrees of at least two data element providers;
calculating the equity value of the training party of each submodel according to the resource amount consumed by the training party of at least two submodels in the process of training the submodel and the total equity value of the training party of the submodel;
distributing right certificates for the data element providers according to the right values of the data element providers;
and distributing the equity certificate for the training party of each submodel according to the equity value of the training party of each submodel.
The data model demander can preset the weight of the data element provider and the weight of the trainer of the submodel according to the requirement of the data model demander, and determine the total interest value of the data element provider and the total interest value of the trainer of the submodel according to the weight of the data element provider and the weight of the trainer of the submodel. The data model demander can preset the weight of the block node provider and the weight of the supervision auditor according to the self requirements.
The equity value of the data element provider is the product of the total equity value of the data element provider and the contribution of the data element provider.
The resource amount can be the CPU utilization rate, the memory capacity and the like, and the right value of the training party of the submodel can be calculated by the formula 2.
Wherein the content of the first and second substances,
is the amount of resources consumed by the trainer of the jth sub-model in training the sub-models,
the equity value of the training party for the jth sub-model,
is the value of the total interest of the trainer of the submodel.
The rights and interests voucher can be a token, a virtual currency and the like, and the participator can exchange the rights and interests voucher into a legal currency under the online condition.
The embodiment of the invention not only can consider the contribution degree of the data element provider, but also can consider the resource consumption of the trainer of the sub-model in the training process, thereby more reasonably distributing rights and interests for the data element provider and the trainer of the sub-model.
In one embodiment of the present invention, the node device corresponding to the target fusion mode is a block output node;
the method further comprises the following steps:
calculating the rights value of the block node provider according to the rights budget and the preset weight of the block node provider;
and distributing the right voucher for the block node provider according to the right value of the block node provider.
In order to encourage the node device provider to provide a better fusion service, the embodiment of the invention allocates rights and interests to the block-out node provider according to the preset weight of the block-out node provider.
In one embodiment of the invention, the method further comprises:
calculating the rights and interests value of the supervision auditor according to the rights and interests budget and the preset weight of the supervision auditor; the equity value of the supervision auditor is used for the supervision auditor to adjust the equity value of the data element provider, the equity value of the trainer of the sub-model or the equity value of the block node provider.
After the transaction is finished, the supervision auditor can audit the transaction according to the transaction records in the block chain and replenish accounts for the data element providers and other participants according to the own rights and interests. For example, the supervision auditor audits to find that the compliance of the data element A is far better than that of other data elements, but the right and profit is low, and the supervision auditor can subsidize the data element A by using the own right and profit value. The supervision auditor can also adjust the weight of the data element provider, the weight of the sub-model trainer, the weight of the block-out node provider or the weight of the supervision auditor in the second intelligent contract according to the auditing result. The embodiment of the invention can ensure the fairness and the rationality of the equity allocation in the process of data element circulation.
As shown in fig. 2, an embodiment of the present invention provides a device for allocating data element rights based on a block chain, where the device is applied to a node device of the block chain, and the device includes:
an obtaining module 201, configured to obtain feature information of at least two submodels from a block chain according to requirement information provided by a data model requirement end; wherein, the sub-model is a data element or is obtained by training the data element;
the fusion module 202 is configured to fuse the at least two sub-models according to the feature information of the at least two sub-models and a current fusion mode selected from the at least two fusion modes to generate a fusion model;
a determining module 203 configured to determine a target fusion mode among at least two fusion modes corresponding to the at least two fusion models; the fusion model generated based on the target fusion mode is a data model, and the at least two fusion models comprise: the method comprises the steps that a fusion model generated in current node equipment and fusion models generated in other node equipment are obtained;
the calling module 204 is configured to call a first intelligent contract which is deployed in advance in the block chain, so as to calculate the contribution degree of a data element provider according to the feature information of at least two sub models and a target fusion mode; and calling a second intelligent contract which is pre-deployed in the block chain to distribute right certificates for the data element providers and the trainers of the sub-models according to the contribution degree of the data element providers and the right budget provided by the data model demand ends.
In one embodiment of the invention, the data elements include: disclosing the data;
an obtaining module 201 configured to obtain public data provided by a data element providing end; training based on public data to obtain a sub-model; and extracting the characteristic information of the submodel and uploading the characteristic information of the submodel to the block chain.
In one embodiment of the invention, the data elements include: private data;
an obtaining module 201 configured to obtain a sub-model provided by a data element providing end; wherein the sub-model is obtained by training a data element providing end based on private data; and extracting the characteristic information of the submodel and uploading the characteristic information of the submodel to the block chain.
In one embodiment of the invention, the data elements include: a sub-model;
an obtaining module 201 configured to obtain a sub-model provided by a data element providing end; and extracting the characteristic information of the submodel and uploading the characteristic information of the submodel to the block chain.
In one embodiment of the invention, the determining module 203 is configured to calculate an accuracy of each fusion model; and determining a target fusion mode in at least two fusion modes corresponding to the at least two fusion models according to the accuracy of each fusion model.
In one embodiment of the invention, the feature information of the submodel includes: weight of the submodel;
the calling module 204 is configured to calculate a sharley value of a data element provider according to the weights of the at least two sub models and the target fusion mode; wherein the sharley value of the data element provider is used to characterize the contribution of the data element provider.
In an embodiment of the present invention, the invoking module 204 is configured to calculate an overall equity value of the data element provider and an overall equity value of the trainer of the submodel according to an equity budget provided by the data model demander, a preset weight of the data element provider and a preset weight of the trainer of the submodel; calculating the equity value of each data element provider according to the total equity value of the data element providers and the contribution degrees of at least two data element providers; calculating the equity value of the training party of each submodel according to the resource amount consumed by the training party of at least two submodels in the process of training the submodels and the total equity value of the training party of the submodels; distributing right certificates for the data element providers according to the right values of the data element providers; and distributing the equity certificate for the training party of each submodel according to the equity value of the training party of each submodel.
In one embodiment of the present invention, the node device corresponding to the target fusion mode is a block output node;
the calling module 204 is configured to calculate the equity value of the block node provider according to the equity budget and the preset weight of the block node provider; and distributing the right voucher for the block node provider according to the right value of the block node provider.
In an embodiment of the present invention, the invoking module 204 is configured to calculate a rights value of the supervision auditor according to the rights budget and a preset weight of the supervision auditor; the equity value of the supervision auditor is used for the supervision auditor to adjust the equity value of the data element provider, the equity value of the trainer of the sub-model or the equity value of the block node provider.
As shown in fig. 3, an embodiment of the present invention provides a system for allocating rights to data elements based on a blockchain, where the system includes: the system comprises a data model demand end, a data element providing end and a plurality of data element rights and interests distribution devices based on block chains; the block chain-based data element rights and interests allocation device is applied to the node equipment of the block chain;
the data model demand end is used for providing demand information;
a data element providing end for providing data elements;
the device comprises a block chain-based data element rights and interests allocation device, a block chain-based data element rights and interests allocation device and a block chain management device, wherein the block chain-based data element rights and interests allocation device is used for acquiring the characteristic information of at least two sub models from the block chain according to the requirement information provided by a data model requirement end; fusing the at least two sub-models according to the characteristic information of the at least two sub-models and the current fusion mode selected from the at least two fusion modes to generate a fusion model; determining a target fusion mode in at least two fusion modes corresponding to the at least two fusion models; calling a first intelligent contract which is pre-deployed in a block chain to calculate the contribution degree of a data element provider according to the characteristic information and the target fusion mode of at least two submodels; calling a second intelligent contract which is pre-deployed in the block chain to distribute right and interest certificates for the data element providers and the trainers of the submodels according to the contribution degree of the data element providers and the right and interest budget provided by the data model demand side;
wherein, the sub-model is a data element or is obtained by training the data element; the fusion model generated based on the target fusion mode is a data model, and at least two fusion models comprise: the fusion model generated in the current node device and the fusion models generated in other node devices.
The data element provider is a terminal used by the data element provider. The embodiment of the invention can meet different requirements of data model demanders, more reasonably distributes rights and interests to the participators, and improves the circulation enthusiasm of the participators and the data elements. For the description of the node device, reference is made to the foregoing embodiments, which are not described in detail herein.
The data transaction details in fig. 3 may include requirement information and equity budget of a data model demander, feature information and trainer of a submodel, source of a data element, contribution degree of a data element provider, and the like, which are stored in the book of the block chain a. Various information generated in the data element circulation process can be stored in the block chain, so that a supervision auditor can check the information conveniently. If the data element is an existing submodel, the related information of the submodel can be stored in the ledger of the block chain B.
In one embodiment of the invention, the data elements include: disclosing the data;
and the data element providing end is used for providing the public data to the data element interest allocation device based on the block chain.
The data element providing end can determine the public data according to the requirement information and provide the public data to the data element rights and interests distribution device based on the block chain.
In one embodiment of the invention, the data elements include: private data;
and the data element providing end is used for training based on the private data to obtain the sub-model and providing the sub-model to the data element rights and interests distribution device based on the block chain.
The data element providing end can determine private data according to the requirement information, train on the basis of the private data to obtain a sub-model, and provide the sub-model to the data element interest allocation device based on the block chain.
In one embodiment of the invention, the data elements include: a sub-model;
and the data element providing end is used for providing the submodel to the data element right assignment device based on the block chain.
The data element providing end can determine the submodel according to the requirement information and provide the submodel to the data element right assignment device based on the block chain.
In one embodiment of the invention, the system further comprises: monitoring an audit terminal;
the block chain-based data element rights and interests distribution device is used for acquiring the source of the data element from the data element providing end and uploading the source of the data element to the block chain; the supervision auditing end is used for scoring the source of the data elements and identifying whether the source of the data elements is legal or not according to the score of the source of the data elements; the sub-model is obtained by training data elements with legal sources or data elements with legal sources.
The supervision auditing end is a terminal used by the supervision auditing party. The supervision and audit end can determine whether the source of the data element is legal or not according to the score, and the source of the data element can be a data element provider or other platforms. If the data element is public data or private data, the source of the data element is a data element provider, and if the data element is a submodel, the source of the data element is a trainer of the submodel. For sources of illegal data elements, participation in the circulation of the data elements will be stopped. The embodiment of the invention can ensure the safety of data element circulation. In an actual application scenario, the supervision audit end can also score the training party of the sub-model to identify whether the training party of the sub-model is legal or not.
As shown in fig. 4, an embodiment of the present invention provides a method for allocating rights to data elements based on a block chain, which is applied to a system for allocating rights to data elements based on a block chain, and the method includes:
step 401: the data element providing end 1 determines public data according to the requirement information provided by the data model requirement end, and provides the public data to the data element right and benefit distribution device 1 based on the block chain; the data element providing end 2 determines private data according to the requirement information, obtains a sub-model 2 based on private data training, and provides the sub-model 2 to the data element rights and interests distribution device 2 based on the block chain; the data element provider 3 determines an existing sub-model 3 from the demand information, and provides the sub-model 3 to the block chain-based data element right assignment device 3.
A block chain based data element rights allocation system is shown with reference to fig. 3.
Step 402: the data element equity allocation device 1 based on the block chain is trained based on public data to obtain a sub-model 1, information of the sub-model 1 is extracted, and the information of the sub-model 1 is uploaded to the block chain; extracting the information of the submodel 2 by the data element rights and interests distribution device 2 based on the block chain, and uploading the information of the submodel 2 to the block chain; the data element right assignment means 3 based on the block chain provides information of the submodel 3, and uploads the information of the submodel 3 to the block chain.
Step 403: the block chain-based data element rights and interests allocation device 1 fuses the submodels 1-3 according to an arithmetic mean method to obtain a fusion model 1, and calculates the accuracy of the fusion model 1; the block chain-based data element rights and interests allocation device 2 fuses the submodels 1-3 according to a geometric mean method to obtain a fusion model 2, and the accuracy of the fusion model 2 is calculated; and the data element rights and interests distribution device 3 based on the block chain fuses the submodels 1-3 according to a weighted average method to obtain a fusion model 3, and the accuracy of the fusion model 3 is calculated.
Step 404: the node devices 1-3 communicate with each other, and the data element rights and interests allocation device based on the block chain determines the target fusion mode with the highest accuracy in an arithmetic average method, a geometric average method and a weighted average method.
Step 405: and calling a first intelligent contract which is pre-deployed in the block chain to calculate the Shapley value of each data element provider according to the weight of the submodels 1-3 and the target fusion mode.
Step 406: calling a second intelligent contract which is pre-deployed in a block chain, calculating a total interest value of a data element provider, a total interest value of a sub-model trainer, an interest value of a yielding node provider and an interest value of a supervision auditor respectively according to an interest budget provided by a data model demand end, preset weights of the data element provider, weights of sub-model trainers, weights of the yielding node provider and weights of supervision designers, calculating an interest value of each data element provider according to the total interest value of the data element provider and a sharey value of each data element provider, calculating an interest value of each trainer of the sub-model according to the total interest value of the sub-model trainer and a CPU utilization rate of each sub-model trainer in the process of training the sub-model, and distributing supervision evidence for each data element provider, each training right value of the sub-model trainer, each yielding node provider and each supervision auditor sub-model auditor.
The total equity value of the data element provider, the total equity value of the trainer of the sub-model, the equity value of the out-block node provider and the equity value of the supervision auditor satisfy equation 3.
Wherein, the first and the second end of the pipe are connected with each other,
、
、
and
respectively used for representing the weight of a data element provider, the weight of a trainer of the submodel, the weight of a block node provider and the weight of a supervision auditor,
a total equity value used to characterize the data element provider,
for characterizing the equity value of the block node provider,
for characterizing the equity value of the supervising auditor,
the method is used for representing the equity budget provided by the demand side of the data model.
The equity value of the data element provider is calculated based on equation 4.
Wherein, the first and the second end of the pipe are connected with each other,
a equity value used to characterize the kth data element provider,
a sharey value used to characterize the kth data element provider.
The embodiment of the invention can process various types of data elements and screen out a target fusion mode from different fusion modes, thereby more reasonably distributing rights and interests to a data element provider, a block node provider and the like and improving the enthusiasm of each participant in participating in data element circulation.
An embodiment of the present invention provides an electronic device, including:
one or more processors;
a storage device for storing one or more programs,
when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method of any of the embodiments as described above.
An embodiment of the present invention provides a computer-readable medium, on which a computer program is stored, wherein the computer program is configured to implement the method according to any one of the above embodiments when executed by a processor.
Referring now to FIG. 5, shown is a block diagram of a computer system 500 suitable for use with a terminal device implementing an embodiment of the present invention. The terminal device shown in fig. 5 is only an example, and should not bring any limitation to the functions and the use range of the embodiment of the present invention.
As shown in fig. 5, the computer system 500 includes a Central Processing Unit (CPU) 501 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 502 or a program loaded from a storage section 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data necessary for the operation of the system 500 are also stored. The CPU 501, ROM 502, and RAM 503 are connected to each other via a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
The following components are connected to the I/O interface 505: an input portion 506 including a keyboard, a mouse, and the like; an output portion 507 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 508 including a hard disk and the like; and a communication section 509 including a network interface card such as a LAN card, a modem, or the like. The communication section 509 performs communication processing via a network such as the internet. A drive 510 is also connected to the I/O interface 505 as needed. A removable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 510 as necessary, so that a computer program read out therefrom is mounted into the storage section 508 as necessary.
In particular, according to embodiments of the present disclosure, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer-readable medium, the computer program comprising program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 509, and/or installed from the removable medium 511. The computer program performs the above-described functions defined in the system of the present invention when executed by the Central Processing Unit (CPU) 501.
It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present invention, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present invention may be implemented by software or hardware. The described modules may also be provided in a processor, which may be described as: a processor includes a sending module, an obtaining module, a determining module, and a first processing module. The names of these modules do not form a limitation on the modules themselves in some cases, and for example, the sending module may also be described as a "module sending a picture acquisition request to a connected server".
The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (13)
1. A method for assigning rights and interests of data elements based on block chains is characterized in that the method is applied to node equipment of the block chains and comprises the following steps:
acquiring characteristic information of at least two sub models from the block chain according to requirement information provided by a data model requirement end; wherein, the sub-model is a data element or is obtained by training the data element;
fusing the at least two sub-models according to the characteristic information of the at least two sub-models and the current fusion mode selected from the at least two fusion modes to generate a fusion model;
determining a target fusion mode in at least two fusion modes corresponding to the at least two fusion models; wherein, the fusion model generated based on the target fusion mode is a data model, and the at least two fusion models include: generating a fusion model in the current node equipment and generating fusion models in other node equipment;
calling a first intelligent contract which is pre-deployed in the block chain to calculate the contribution degree of a data element provider according to the feature information of the at least two submodels and the target fusion mode;
and calling a second intelligent contract which is pre-deployed in the block chain, so as to distribute right certificates for the data element providers and the trainers of the submodels according to the contribution degree of the data element providers and the right budget provided by the data model demand side.
2. The method of claim 1,
the data elements include: disclosing the data;
the method further comprises the following steps:
acquiring the public data provided by the data element providing end;
training to obtain the sub-model based on the public data;
extracting the characteristic information of the submodel and uploading the characteristic information of the submodel to the block chain;
and/or the presence of a gas in the atmosphere,
the data elements include: private data;
the method further comprises the following steps:
acquiring the submodel provided by the data element providing end; wherein the sub-model is trained from the data element providing base based on the private data;
extracting the characteristic information of the submodel and uploading the characteristic information of the submodel to the block chain;
and/or the presence of a gas in the gas,
the data elements include: the sub-model;
the method further comprises the following steps:
acquiring the submodel provided by the data element providing end;
and extracting the characteristic information of the submodel, and uploading the characteristic information of the submodel to the block chain.
3. The method of claim 1,
determining a target fusion mode in at least two fusion modes corresponding to the at least two fusion models, including:
calculating the accuracy of each fusion model;
and determining a target fusion mode in at least two fusion modes corresponding to the at least two fusion models according to the accuracy of each fusion model.
4. The method of claim 1,
the feature information of the sub-model includes: a weight of the submodel;
calculating the contribution degree of a data element provider according to the characteristic information of the at least two submodels and the target fusion mode, wherein the method comprises the following steps:
calculating a Shapley value of the data element provider according to the weight of the at least two submodels and the target fusion mode; wherein the sharley value of the data element provider is used to characterize the contribution of the data element provider.
5. The method of claim 1,
distributing right certificates for the data element providers and trainers of the sub-models according to the contribution degree of the data element providers and the right budget provided by the data model demander, comprising the following steps:
calculating the total equity value of the data element provider and the total equity value of the trainer of the submodel according to the equity budget provided by the data model demand side, the preset weight of the data element provider and the preset weight of the trainer of the submodel;
calculating a rights value for each of the data element providers based on the total rights value for the data element provider and the contribution of at least two of the data element providers;
calculating the equity value of the training party of each submodel according to the resource amount consumed by the training party of at least two submodels in the process of training the submodels and the total equity value of the training party of the submodels;
distributing right certificates for the data element providers according to the right values of the data element providers;
and distributing a equity certificate for the training party of each submodel according to the equity value of the training party of each submodel.
6. The method of claim 5,
the node equipment corresponding to the target fusion mode is a block outlet node;
the method further comprises the following steps:
calculating the rights value of the block-out node provider according to the rights budget and the preset weight of the block-out node provider;
and distributing a rights voucher for the block-out node provider according to the rights value of the block-out node provider.
7. The method of claim 6, further comprising:
calculating the rights value of the supervision auditor according to the rights budget and the preset weight of the supervision auditor; wherein the equity value of the supervision auditor is used for the supervision auditor to adjust the equity value of the data element provider, the equity value of the trainer of the sub-model, or the equity value of the egress node provider.
8. An apparatus for assigning rights and interests of data elements based on a block chain, the apparatus being applied to a node device of the block chain, the apparatus comprising:
the acquisition module is configured to acquire the characteristic information of at least two sub models from the block chain according to the demand information provided by the demand end of the data model; wherein, the sub-model is a data element or is obtained by training the data element;
the fusion module is configured to fuse the at least two sub-models according to the characteristic information of the at least two sub-models and a current fusion mode selected from the at least two fusion modes to generate a fusion model;
the determining module is configured to determine a target fusion mode in at least two fusion modes corresponding to the at least two fusion models; wherein, the fusion model generated based on the target fusion mode is a data model, and the at least two fusion models include: the method comprises the steps that a fusion model generated in current node equipment and fusion models generated in other node equipment are obtained;
the calling module is configured to call a first intelligent contract which is pre-deployed in the block chain, so as to calculate the contribution degree of a data element provider according to the feature information of the at least two submodels and the target fusion mode; and calling a second intelligent contract which is pre-deployed in the block chain, so as to distribute right certificates for the data element providers and the trainers of the submodels according to the contribution degree of the data element providers and the right budget provided by the data model demand side.
9. A block chain based data element rights allocation system, the system comprising: the system comprises a data model demand end, a data element providing end and a plurality of data element rights and interests distribution devices based on block chains; wherein the block chain-based data element rights allocation apparatus is applied to the node devices of the block chain;
the data model demand end is used for providing demand information;
the data element providing end is used for providing data elements;
the block chain-based data element rights and interests allocation device is used for acquiring the characteristic information of at least two sub models from the block chain according to the requirement information provided by the data model requirement end; fusing the at least two sub-models according to the characteristic information of the at least two sub-models and the current fusion mode selected from the at least two fusion modes to generate a fusion model; determining a target fusion mode in at least two fusion modes corresponding to the at least two fusion models; calling a first intelligent contract which is pre-deployed in the block chain to calculate the contribution degree of the data element provider according to the feature information of the at least two submodels and the target fusion mode; calling a second intelligent contract which is pre-deployed in the block chain, and distributing right certificates for the data element providers and trainers of the submodels according to the contribution degree of the data element providers and the right budget provided by the data model demand side;
wherein the submodel is the data element or is obtained by training the data element; the fusion model generated based on the target fusion mode is a data model, and the at least two fusion models comprise: the fusion model generated in the current node device and the fusion models generated in other node devices.
10. The system of claim 9,
the data elements include: disclosing the data;
the data element providing end is used for providing the public data to the block chain-based data element rights allocation device;
and/or the presence of a gas in the gas,
the data elements include: private data;
the data element providing terminal is used for training to obtain the sub-model based on the private data and providing the sub-model to the block chain-based data element rights and interests distribution device;
and/or the presence of a gas in the gas,
the data elements include: the sub-model;
the data element providing end is used for providing the sub-model to the block chain-based data element right assignment device.
11. The system of claim 9, further comprising: monitoring an audit terminal;
the block chain-based data element rights and interests distribution device is used for acquiring the source of the data element from the data element providing end and uploading the source of the data element to the block chain;
the supervision auditing end is used for scoring the source of the data elements and identifying whether the source of the data elements is legal or not according to the score of the source of the data elements; the sub-model is obtained by training data elements with legal sources or data elements with legal sources.
12. An electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method recited in any of claims 1-7.
13. A computer-readable medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211070606.3A CN115169992B (en) | 2022-09-02 | 2022-09-02 | Block chain based data element rights and interests allocation method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211070606.3A CN115169992B (en) | 2022-09-02 | 2022-09-02 | Block chain based data element rights and interests allocation method, device and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115169992A CN115169992A (en) | 2022-10-11 |
| CN115169992B true CN115169992B (en) | 2023-01-17 |
Family
ID=83480820
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211070606.3A Active CN115169992B (en) | 2022-09-02 | 2022-09-02 | Block chain based data element rights and interests allocation method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115169992B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115242250B (en) * | 2022-09-21 | 2023-04-07 | 成都工业学院 | Encoding and decoding method for single-full mapping of multi-value chain data element allocation |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108985644A (en) * | 2018-07-27 | 2018-12-11 | 阿里巴巴集团控股有限公司 | Mining rights method and device, electronic equipment |
| CN110766458A (en) * | 2019-10-18 | 2020-02-07 | 支付宝(杭州)信息技术有限公司 | Data processing method and device based on block chain |
| WO2020224248A1 (en) * | 2019-05-06 | 2020-11-12 | 深圳壹账通智能科技有限公司 | Blockchain-based virtual certificate value allocation method and contract operation apparatus, and storage medium |
| CN112347495A (en) * | 2020-11-15 | 2021-02-09 | 北京物资学院 | Trusted privacy intelligent service computing system and method based on block chain |
| CN113138847A (en) * | 2020-01-19 | 2021-07-20 | 京东数字科技控股有限公司 | Computer resource allocation scheduling method and device based on federal learning |
| CN113434269A (en) * | 2021-06-10 | 2021-09-24 | 湖南天河国云科技有限公司 | Block chain-based distributed privacy calculation method and device |
| CN113792347A (en) * | 2021-08-24 | 2021-12-14 | 上海点融信息科技有限责任公司 | Block chain-based federal learning method, device, equipment and storage medium |
| CN114971170A (en) * | 2022-04-14 | 2022-08-30 | 大凯投资(深圳)合伙企业(有限合伙) | Block chain-based multi-level multi-system pan-center cooperation platform system and method |
-
2022
- 2022-09-02 CN CN202211070606.3A patent/CN115169992B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108985644A (en) * | 2018-07-27 | 2018-12-11 | 阿里巴巴集团控股有限公司 | Mining rights method and device, electronic equipment |
| WO2020224248A1 (en) * | 2019-05-06 | 2020-11-12 | 深圳壹账通智能科技有限公司 | Blockchain-based virtual certificate value allocation method and contract operation apparatus, and storage medium |
| CN110766458A (en) * | 2019-10-18 | 2020-02-07 | 支付宝(杭州)信息技术有限公司 | Data processing method and device based on block chain |
| CN113138847A (en) * | 2020-01-19 | 2021-07-20 | 京东数字科技控股有限公司 | Computer resource allocation scheduling method and device based on federal learning |
| CN112347495A (en) * | 2020-11-15 | 2021-02-09 | 北京物资学院 | Trusted privacy intelligent service computing system and method based on block chain |
| CN113434269A (en) * | 2021-06-10 | 2021-09-24 | 湖南天河国云科技有限公司 | Block chain-based distributed privacy calculation method and device |
| CN113792347A (en) * | 2021-08-24 | 2021-12-14 | 上海点融信息科技有限责任公司 | Block chain-based federal learning method, device, equipment and storage medium |
| CN114971170A (en) * | 2022-04-14 | 2022-08-30 | 大凯投资(深圳)合伙企业(有限合伙) | Block chain-based multi-level multi-system pan-center cooperation platform system and method |
Non-Patent Citations (1)
| Title |
|---|
| 2022年数据要素权益配置研究报告;中国信通院等;《https://www.vzkoo.com/read/2022080981750f2e82813eae677658d7.html》;20220809;1-7 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115169992A (en) | 2022-10-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107483211B (en) | Individualized k-anonymous privacy protection and excitation method based on block chain | |
| CN108805627B (en) | Media resource allocation method, device, system, medium and equipment | |
| CN106682825A (en) | System and method for evaluating credit of Social Internet of Things based on block chain | |
| CN108416615B (en) | Resource allocation method based on tree | |
| CN107483986A (en) | A kind of method and system of gifts | |
| CN108470277A (en) | Reward settlement method, system, readable storage medium storing program for executing and the computing device of block chain | |
| CN110599178A (en) | Data processing method and device based on intelligent contract and storage medium | |
| CN106817401B (en) | Resource allocation method in cloud environment | |
| CN115169992B (en) | Block chain based data element rights and interests allocation method, device and system | |
| CN109191129A (en) | A kind of air control method, system and computer equipment | |
| CN110928951A (en) | Data sharing and arbitration method based on block chain | |
| JP2022535636A (en) | Financial product recommendation method, device, electronic device and program | |
| CN114372589A (en) | Federated learning method and related device | |
| CN106888156A (en) | A kind of method and device for playing reward distribution | |
| CN113364831A (en) | Multi-domain heterogeneous computing network resource credible cooperation method based on block chain | |
| CN117544661A (en) | Self-adaptive digital twin deployment and transfer method for view networking calculation | |
| CN109544158B (en) | Block data processing method and computer storage medium | |
| CN110599337A (en) | Alliance chain safety incentive method based on crowd sensing technology | |
| CN110795132A (en) | Third-party application processing method, system and storage medium | |
| CN116302874A (en) | Model capability test method and device, electronic equipment, storage medium and product | |
| CN106657058B (en) | Event resource allocation method and device | |
| CN112732470B (en) | Federal learning reliability assessment method and device for electric energy data | |
| CN109658098A (en) | The logical card circulation method of one kind, system, electronic equipment and storage medium | |
| CN114219338A (en) | Resource allocation method and device based on joint learning | |
| KR20100138135A (en) | Distributing system for ownership of collective creation in network community and method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |