CN116340995A - Combined modeling method and device and electronic equipment - Google Patents
Combined modeling method and device and electronic equipment Download PDFInfo
- Publication number
- CN116340995A CN116340995A CN202310188416.XA CN202310188416A CN116340995A CN 116340995 A CN116340995 A CN 116340995A CN 202310188416 A CN202310188416 A CN 202310188416A CN 116340995 A CN116340995 A CN 116340995A
- Authority
- CN
- China
- Prior art keywords
- data
- privacy
- environment
- collaboration
- joint
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000013500 data storage Methods 0.000 claims abstract description 87
- 238000004364 calculation method Methods 0.000 claims abstract description 37
- 238000002955 isolation Methods 0.000 claims abstract description 22
- 238000012502 risk assessment Methods 0.000 claims description 32
- 230000006399 behavior Effects 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 11
- 238000007781 pre-processing Methods 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 10
- 238000012216 screening Methods 0.000 claims description 7
- 238000010586 diagram Methods 0.000 description 11
- 238000012545 processing Methods 0.000 description 11
- 238000005265 energy consumption Methods 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000011156 evaluation Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 238000012954 risk control Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
- G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
-
- 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
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Bioethics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Databases & Information Systems (AREA)
- Development Economics (AREA)
- Software Systems (AREA)
- Educational Administration (AREA)
- Computer Security & Cryptography (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a joint modeling method, a device and electronic equipment, which belong to the technical field of computers, and the joint modeling method of the embodiment of the application comprises the following steps: acquiring privacy data stored in isolation in a privacy data storage environment; the acquired private data is loaded to a cooperative node deployed in the running environment, so that the cooperative node performs multiparty private calculation cooperation with other data cooperative parties, and joint modeling is performed on the basis of the data loaded by each data cooperative party at each cooperative node, so that the local private data can be ensured to be jointly modeled with the other cooperative parties under the condition that the local private data does not leave a domain, the private data can be invisible, the data cooperative sharing can be performed with the other cooperative parties, and the requirements on safety compliance aiming at the private data are met.
Description
Technical Field
The application belongs to the technical field of computers, and particularly relates to a joint modeling method and device and electronic equipment.
Background
When the risk identification is carried out on the enterprise, each department or enterprise related to the enterprise can be butted as a data cooperator, the risk characteristics are self-learned in real time based on related data provided by the data cooperator, a risk identification algorithm is dynamically optimized, and risk warning and evaluation reference for the enterprise is provided.
Due to the requirement of safety compliance of private data, the private data which cannot be externally disclosed is provided by part of data cooperators, so that the method cannot be used for optimizing a risk identification algorithm.
Disclosure of Invention
In view of this, the present application provides a joint modeling method, apparatus, and electronic device, which are used for solving the problem that data provided by a data collaborator cannot be used for optimizing a risk recognition algorithm because the data cannot be disclosed externally.
Specifically, the application is realized by the following technical scheme:
in a first aspect, a joint modeling method is provided, and the joint modeling method is applied to a server of any target data cooperator among a plurality of data cooperators participating in joint modeling, wherein the server comprises an operation environment in a public network and a private data storage environment in a private network; the operation environment is provided with cooperative nodes which cooperate with other data cooperative parties in multiparty privacy computation, and privacy data used for participating in the joint modeling are stored in the privacy data storage environment in an isolated manner; the method comprises the following steps:
acquiring privacy data stored in isolation in a privacy data storage environment;
and loading the acquired privacy data to a collaboration node deployed in the operation environment, so that the collaboration node performs multiparty privacy calculation collaboration with other data collaborators, and performing joint modeling based on the data loaded by each data collaborator at each collaboration node.
Optionally, the server further includes an isolation gatekeeper for isolating the running environment and the private data storage environment, where the running environment and the private data storage environment implement data communication through the isolation gatekeeper.
Optionally, the service end corresponding to the other data collaborators also comprises an operation environment and a private data storage environment; the operation environment is provided with collaboration nodes corresponding to the other data collaborators, and privacy data for participating in multiparty joint modeling is maintained in the privacy data storage environment;
the acquired privacy data is loaded to a collaboration node deployed in the operation environment, so that the collaboration node and other data collaborators perform multiparty privacy computation collaboration, and joint modeling is performed based on the data loaded by each data collaborator at each collaboration node, and the method comprises the following steps:
and loading the acquired privacy data to a collaboration node deployed in the operation environment, so that the collaboration node performs multiparty privacy computation collaboration with the collaboration node deployed in the operation environment of the service end corresponding to at least one other data collaborator, and performing joint modeling based on the privacy data maintained in the privacy data storage environment on the service end of each data collaborator.
Optionally, joint modeling is performed based on data loaded by each data cooperator at each cooperator node, including:
and carrying out joint training by taking the privacy data maintained in the privacy data storage environment on the server side of each data collaborator as a training sample.
Optionally, the acquiring the private data stored in isolation in the private data storage environment includes:
acquiring index data for joint modeling, which is obtained by preprocessing privacy data stored in isolation in the privacy data storage environment;
the loading the acquired privacy data to the collaboration node deployed in the operating environment comprises the following steps:
and loading the index data obtained through processing to a collaboration node deployed in the running environment.
Optionally, the obtaining index data for joint modeling, which is obtained after preprocessing the privacy data stored in isolation in the privacy data storage environment, includes:
screening key data fields for joint modeling from privacy data stored in isolation in the privacy data storage environment;
the data fields are processed into index data for joint modeling.
Optionally, at least part of the privacy data used for joint modeling comprises energy use data records of energy provided by energy enterprises for the energy enterprises; the joint model obtained by the joint modeling comprises a risk assessment model for performing risk assessment on the energy utilization enterprise.
Optionally, the target data collaborator is the energy enterprise; the joint model obtained by the joint modeling comprises a risk assessment model for performing risk assessment on the energy utilization behavior of the energy utilization enterprise.
Optionally, the target data collaborator is a financial institution; the other data collaborators comprise the energy enterprise; the joint model obtained by joint modeling comprises a risk assessment model for performing risk assessment on financial behaviors of the energy utilization enterprise.
Optionally, the method further comprises:
and after joint modeling is carried out to obtain a joint model, deploying the joint model into the running environment.
Optionally, a trusted execution environment is built in the running environment; the collaboration node is a privacy computing service program running in the trusted execution environment.
In a second aspect, there is provided a joint modeling apparatus, the apparatus comprising:
the data acquisition module is used for acquiring privacy data which are stored in an isolated manner in the privacy data storage environment;
and the privacy calculation module is used for loading the acquired privacy data to the collaboration nodes deployed in the running environment so that the collaboration nodes and other data collaborators perform multiparty privacy calculation collaboration, and joint modeling is performed based on the data loaded by each data collaborator at each collaboration node.
In a third aspect, there is provided a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method of the first aspect.
In a fourth aspect, there is provided an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method of the first aspect when the program is executed.
In the embodiment of the application, the cooperative nodes for performing multiparty privacy calculation cooperation are deployed in the operation environment of the target enterprise, and the private data maintained in the private data storage environment and other cooperative parties are subjected to multiparty privacy calculation cooperation by utilizing the private calculation so as to perform joint modeling, so that the joint modeling with the other cooperative parties can be realized under the condition that local private data does not leave a domain, the private data can be invisible, the data cooperation sharing can be performed by the other cooperative parties, and the requirements on safety compliance for the private data are met.
Drawings
FIG. 1 is a schematic diagram of a system architecture of a joint modeling system according to an exemplary embodiment of the present application;
FIG. 2 is a flow diagram of a joint modeling method according to an exemplary embodiment of the present application;
FIG. 3 is a schematic diagram of a system architecture of another joint modeling system shown in an exemplary embodiment of the present application;
FIG. 4 is a system architecture diagram of another joint modeling method shown in an exemplary embodiment of the present application;
FIG. 5 is a system architecture diagram of another joint modeling method as illustrated in an exemplary embodiment of the present application;
FIG. 6 is a schematic diagram of a joint modeling apparatus according to an exemplary embodiment of the present application;
fig. 7 is a schematic structural diagram of an electronic device according to an exemplary embodiment of the present application.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application as detailed in the accompanying claims.
The terminology used in the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.
It should be understood that although the terms first, second, third, etc. may be used herein to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first message may also be referred to as a second message, and similarly, a second message may also be referred to as a first message, without departing from the scope of the present application. The word "if" as used herein may be interpreted as "at … …" or "at … …" or "responsive to a determination", depending on the context.
In the related technology, a plurality of data cooperators are in butt joint, and a risk recognition algorithm is dynamically optimized based on the real-time self-learning risk characteristics of the public data provided by the plurality of data cooperators, so that risk warning and evaluation references of enterprises to be evaluated can be provided for core enterprises and suppliers. Obviously, if more data cooperators can provide data, more and more comprehensive risk characteristics can be learned, and a risk recognition algorithm is further optimized, so that the risk recognition of enterprises to be evaluated can be more comprehensively performed, and more risk alarms and more accurate evaluation references are provided. However, since the data provided by some data collaborators includes private data, and the private data cannot go out of the domain due to the requirement of data security compliance, that is, cannot be directly docked with the outside and externally disclosed, the private data cannot be used for optimizing the risk recognition algorithm.
In view of this, the present specification proposes a method for deploying, at a server side of each data collaborator, a collaboration node that can be used to perform multiparty privacy computation collaboration, and loading, by multiparty privacy computation collaboration, data of each data collaborator to a corresponding collaboration node for joint modeling, so as to obtain a joint model that can be used for risk recognition.
When the method is realized, the cooperative nodes can be deployed in the operation environment of the server side of any target data cooperative side in the public network, the private data which is stored in the private data storage environment of the server side in the private network is obtained, the obtained private data is loaded to the deployed cooperative nodes in the operation environment, so that the cooperative nodes and other data cooperative sides perform multiparty privacy calculation cooperation, and joint modeling is performed on the basis of the data loaded by each data side in each cooperative node.
In the technical scheme, the cooperative nodes for performing multiparty privacy calculation cooperation are deployed in the operation environment of the target data cooperative party, and private data maintained in the private data storage environment and other cooperative parties are subjected to multiparty privacy calculation cooperation by utilizing the privacy calculation so as to perform joint modeling, so that the joint modeling can be performed with other data cooperative parties under the condition that local private data is ensured not to leave a domain, the private data can be invisible, the data cooperation sharing can be performed with other data cooperative parties, and the requirements on safety compliance of the private data are met.
Referring to fig. 1, fig. 1 is a schematic diagram of a joint modeling system according to an embodiment of the present application.
The system as shown in FIG. 1 includes a plurality of data collaborators that may be involved in joint modeling. Each data collaborator may specifically provide data for joint modeling, including private data. For example, in practice, the plurality of data collaborators may include, in particular, enterprises or departments having respective maintaining private data for participation in the joint modeling, and enterprises or departments having maintaining public data for participation in the joint modeling.
With continued reference to fig. 1, a target data collaborator 11 and other data collaborators 12 that cooperate with the target data collaborator for multiparty privacy calculations may be included in the system shown in fig. 1. As shown in fig. 1, the other data collaborators 12 may be one or a plurality of data collaborators.
The server side of the target data collaborator 11 may include a pre-built running environment located in the public network and a private data storage environment located in the private network. Wherein the operating environment and the private data storage environment are isolated from each other. In a private data storage environment, private data for participating in joint modeling may be maintained. The public network may be referred to as an extranet, the operating environment located in the public network may be referred to as an extranet operating environment, the private network may be referred to as an intranet, and the private data storage environment located in the private network may be referred to as an intranet operating environment.
The isolation manner between the running environment and the private data storage environment may be various, for example, the server may further include an isolation gatekeeper for isolating the running environment and the private data storage environment, where the isolation gatekeeper may be a dedicated hardware with multiple control functions, and cuts off the connection between the running environment and the private data storage environment on a circuit, so that no physical connection, logical connection, information transmission command, information transmission protocol, etc. of communication exists between the running environment and the private data storage environment. And the running environment and the private data storage environment realize data exchange through the isolation gatekeeper. The data to be exchanged can be obtained from one of the parties and retransmitted to the other party by separate connection to the operating environment or the private data storage environment, respectively, in turn.
In order to further improve the security of the private data storage environment, when the data exchange between the operation environment and the private data storage environment is performed through the quarantine gatekeeper, the exchanged data may be encrypted.
In practical applications, the private data stored in the private data storage environment of the target data collaborator 11 is isolated from each other, and cannot be taken out of the domain in general, based on the requirements on security compliance with respect to the private data. The fact that the private data cannot go out of the domain means that the detail content of the private data cannot be led out of the private data storage environment to perform data calculation.
In order to meet the requirements on security compliance for private data, a collaboration node 111 which can be used for multiparty privacy computation collaboration can be deployed on the server side of the target data collaborator 11, so that a privacy collaboration platform can be formed between the collaboration node deployed on the target data collaborator 11 and the collaboration nodes deployed on the server sides of other data collaborators.
The collaboration node may be a privacy collaboration program corresponding to each data collaboration party in the privacy collaboration platform, and the privacy collaboration programs corresponding to each data collaboration party may perform secure interaction to perform privacy computation of multiple parties.
For example, in one embodiment shown, a TEE (Trusted execution environment ) may be pre-built on the server side of each data collaboration party, and in this case, the data collaboration node may specifically be a manager of the privacy collaboration platform, and a privacy computing service program deployed in the TEE. The privacy computing service program can perform security interaction with the privacy computing service programs corresponding to other cooperators through the established security data channel so as to perform multiparty privacy computation.
With continued reference to fig. 1, the collaboration node 111 corresponding to the target data collaborator 11 may be specifically deployed in an operating environment of a server of the target data collaborator 11.
For example, in one embodiment shown, a TEE (Trusted execution environment ) may be specifically built in advance in the running environment of the server of each data collaborator, where the collaboration node may specifically be a manager of the privacy collaboration platform, and a privacy computing service deployed in the TEE.
It should be noted that, for other data collaborators 12, the collaboration nodes corresponding to the data collaborators may also be deployed in the running environments of the respective servers (not shown in fig. 1). Or, in practical application, if the data which is maintained by one of the other data collaborators 12 and participates in joint modeling is not private data, the service end of the data collaborator may not build a private data storage environment and an operation environment, in this case, the collaboration node corresponding to the data collaborator may be directly deployed on the service end of the data collaborator without distinguishing a specific deployment environment.
In order to enable those skilled in the art to better understand the technical solutions in the present application, the following description will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application.
Referring to fig. 2, fig. 2 illustrates a joint modeling method provided in an embodiment of the present application, where the method may be applied to a server of any target data cooperator among a plurality of data cooperators participating in joint modeling in the system architecture illustrated in fig. 1, and the joint modeling method includes the following steps.
S210, private data which is stored in an isolated mode in the private data storage environment is obtained.
As described above, on the server side of the target data collaborator, an operation environment and a private data storage environment may be built in advance; the operation environment can be provided with a cooperation node which cooperates with other data cooperators in multiparty privacy calculation.
The collaboration node may be an execution body participating in the multiparty privacy calculation collaboration, and in practical application, the collaboration node may be a hardware-form node or a software-form node, which is not particularly limited in the present specification.
For example, in one embodiment, a trusted execution environment (Trusted Execution Environment, TEE) may be pre-installed on the server; and the collaboration node may be a privacy computing service program running in the trusted execution environment. By carrying the TEE, an isolated memory can be allocated in hardware for loading private data for the cooperative node, and multiparty private calculation cooperation is carried out with other data cooperators, and the security of the private data loaded in the cooperative node can be ensured because other parts of the server cannot access the isolated memory.
Privacy data for participating in multi-party joint modeling may be maintained in the privacy data storage environment. The specific manner of maintaining the private data in the private data storage environment is not particularly limited in the present specification; for example, in one embodiment, an intranet data middle station may be implemented in a private data storage environment, and the private data may be stored in the intranet data middle station.
Correspondingly, an external network data center station can be realized in the operation environment, and the external network data center station can exchange data with the internal network data center station through the isolation network gate.
In practical application, the target data collaborators may specifically include enterprises having respective maintained private data for joint modeling. The specific data type of the private data is generally dependent on the type of enterprise that is the data collaborator.
In one embodiment, the target data collaborator may be an energy enterprise; such as power energy enterprises, etc. Accordingly, the privacy data may include a usage data record of energy provided by a usage enterprise for the energy enterprise; for example, the energy usage data record may be an energy usage data record of each power usage enterprise maintained by the power energy enterprise. The energy usage data record may reflect the production and management of the energy usage enterprise.
In practical applications, when a target data collaborator or other data collaborators have a requirement of joint modeling under multi-party collaboration, the target data collaborator can acquire privacy data maintained in a privacy data storage environment.
For example, in one embodiment, an intranet data middle station may be deployed in a private data storage environment, an extranet data middle station may be deployed in an operating environment, and the private data may be maintained by the intranet data middle station; in this case, the target data collaborator may read the private data from the intranet data center station through the quarantine gatekeeper as described above, and save the private data to the extranet data center station.
S220, the acquired privacy data are loaded to the collaboration nodes deployed in the operation environment, so that the collaboration nodes and other data collaborators perform multiparty privacy calculation collaboration, and joint modeling is performed based on the data loaded by each data collaborator in each collaboration node.
In the operation environment on the server side of the target data collaborator, a collaboration node for performing multiparty privacy computation collaboration with other data collaborators can be deployed in advance.
For example, in one embodiment, a trusted execution environment is pre-built in the running environment; and the collaboration node may be a privacy computing service program running in the trusted execution environment.
After the target data cooperator acquires the privacy data, the privacy data can be loaded to the cooperator node.
In order to meet the requirement of security compliance of the private data, that is, the detail content of the private data cannot be exported from the private data storage environment where the private data is located, when the private data stored in the private data storage environment in an isolated manner is acquired in step S210, the private data needs to be preprocessed in advance, and the private data is processed into data that can be disclosed or allowed to be loaded into the running environment. For example, in one embodiment, the private data may be first preprocessed in the private data storage environment to obtain index data for joint modeling; the method comprises the steps that an operation environment obtains index data for joint modeling, which is obtained by preprocessing privacy data stored in isolation in a privacy data storage environment, from the privacy data storage environment, and then the index data is loaded to a collaboration node deployed in the operation environment.
Taking the private data storage environment as an example of deployment of an intranet data middle station and an operation environment as an example of deployment of an extranet data middle station, preprocessing the private data maintained by the intranet data middle station in the private data storage environment to obtain index data for joint modeling; then reading the index data from the privacy data storage environment through an isolation gatekeeper in the operation environment and storing the index data into an external network data center; and when joint modeling is needed, loading the index data from the external network data middle station to the cooperative node. If the collaboration node is deployed in the carried TEE, the index data is loaded into an isolated memory corresponding to the TEE, and multiparty privacy computation collaboration is carried out with other data collaborators.
The method of preprocessing the privacy data into the instruction data may be various, for example, processing the privacy data into the index data that can be exported into the running environment through ciphertext calculation may be included. The index data can be obtained according to specific business requirement information, modeling information, enterprise credit information and the like.
The business requirement information, modeling information, enterprise credit information and the like can be acquired from other enterprises and kept synchronous with each cooperative party, for example, an air control node or an instance can be deployed in an external operation environment of a service end of each cooperative party and used for maintaining the business requirement information, modeling information, enterprise credit information and the like.
The index data is obtained from the private data storage environment through obtaining processing and then is loaded to the cooperative nodes deployed in the operation environment instead of directly obtaining the private data, and the private data is loaded to the cooperative nodes deployed in the operation environment, so that joint modeling can be carried out with other data cooperators under the condition that the local private data meets the requirement of safety compliance, and the fact that the private data is available and invisible is achieved.
Because the private data stored in the private data storage environment is huge, for example, the massive energy consumption data records of the energy enterprises are recorded in the intranet data center of the energy enterprises, which is far beyond the data loading capacity of each cooperative node when the multiparty private calculation cooperation is performed, when the obtained private data is preprocessed in step S210, the method can also comprise the step of screening the obtained massive private data in advance.
For example, in one embodiment, key data fields for joint modeling are screened from the private data stored in isolation in the private data storage environment; the data fields are then processed into index data for joint modeling.
Taking the private data storage environment as an example of deployment of an intranet data middle station and an operation environment as an example of deployment of an extranet data middle station, firstly, in the private data storage environment, carrying out data screening on private data maintained by the intranet data middle station, screening out a link-related data field for joint modeling, and then processing the key data field into index data for joint modeling; then reading the index data from the privacy data storage environment through an isolation gatekeeper and storing the index data into an external network data center; and when joint modeling is needed, loading the index data from the external network data middle station to the cooperative node. If the collaboration node is deployed in the carried TEE, the index data is loaded into an isolated memory corresponding to the TEE, and multiparty privacy computation collaboration is carried out with other data collaborators.
The index data obtained by preprocessing is enabled to be in the data loading capacity range of the cooperative nodes through screening the privacy data in advance, so that real-time self-learning can be carried out based on the provided privacy data in the process of carrying out the joint model.
After the target data cooperators load the read privacy data or index data to the cooperators deployed in the running environment, the data loaded by other data cooperators at the respective cooperators can be jointly modeled through the privacy cooperators platform. The joint modeling can also be called federal learning, and the data loaded by each cooperative node is subjected to available invisible joint analysis and modeling based on privacy rules through a privacy cooperation platform. For example, the data loaded by each data cooperator at each cooperator node is used as a training sample to perform joint training.
The privacy cooperation calculation mode can be set according to actual needs, and privacy protection distributed cooperation calculation in the cryptography field can be realized, so that each data cooperation party can participate in cooperation calculation under the condition that the other party content is not known, and joint modeling is realized.
As described above, the data for joint modeling maintained by the other data collaborators may be private data or index data obtained based on the private data, and may also be public data. Referring to fig. 3, in one embodiment, the other servers corresponding to the data collaborators 12 may also include an operation environment and a private data storage environment; and the operation environment is provided with collaboration nodes corresponding to the other data collaborators, and the privacy data storage environment maintains privacy data for participating in multiparty joint modeling. Accordingly, step S220 may include: and loading the acquired privacy data or index data to a collaboration node deployed in the operation environment, so that the collaboration node performs multiparty privacy computation collaboration with the collaboration node deployed in the operation environment of the service end corresponding to at least one other data collaborator, and performing joint modeling based on the privacy data maintained in the privacy data storage environment on the service end of each data collaborator.
Based on the joint modeling manner in the above embodiment, the privacy data maintained in the privacy data storage environment on the server side of each data collaborator can be used as a training sample for joint training.
In joint modeling by the privacy collaboration platform, joint modeling may be performed by using all collaboration nodes on the privacy collaboration platform, or only by using the collaboration nodes specified in the privacy collaboration platform, for example, by using the specified collaboration nodes in the privacy collaboration platform that provide the privacy data for joint modeling.
After the joint modeling is completed based on the data loaded by each data cooperator at each cooperator node, a joint model for risk identification can be obtained, and the joint model can be deployed according to the actual situation.
For example, in one embodiment, the federation model may be deployed on a privacy collaboration platform for each data collaborator to invoke or deploy according to their respective needs.
For example, in one implementation, after performing joint modeling to obtain a joint model, the joint model is deployed to an operating environment of a server side of the target data collaborator, so that the other enterprises can perform model calling.
The method specifically means that other enterprises can call the joint model or call the risk assessment result of the joint model from the running environment of the server side of the target data collaborator. In order to facilitate model calling of other enterprises, the completed joint model can be packaged and deployed in the operation environment of the server side of the target enterprise, and an open interface and a use interface are externally provided, so that other enterprises can obtain risk assessment results through the interface or the interface.
According to the embodiment of the application, the cooperative nodes for performing multiparty privacy calculation cooperation are deployed in the operation environment of the target enterprise, the private data maintained in the private data storage environment is used for performing multiparty privacy calculation cooperation with other cooperative parties by utilizing the privacy calculation, so that joint modeling is performed, and the private data can be combined with the other cooperative parties to realize that the private data is invisible under the condition that the local private data does not leave the domain, so that the private data can be shared in a data cooperation way with the other cooperative parties, and the requirements on safety compliance of the private data are met.
Based on the above embodiments, the plurality of data collaborators participating in the joint modeling include enterprises or departments that provide data for performing the joint modeling, e.g., energy enterprises, administrators of privacy collaboration platforms, financial institutions, related government departments, and the like. The data provided by the plurality of data collaborators may include private data. For example, in one embodiment, at least a portion of the privacy data used to conduct the joint modeling includes a usage data record of energy provided by the energy enterprise for the energy enterprise, which may specifically be a usage data record provided by the energy enterprise as a data collaborator.
The joint model obtained after joint modeling can perform risk assessment on the behavior or credit conditions of the specific aspects of the enterprise according to actual requirements, such as business requirements and the like.
For example, in one embodiment, where the privacy data includes a usage data record of energy provided by a utility for an energy utility, the joint model resulting from the joint modeling includes a risk assessment model for risk assessment of the utility.
For another example, in one embodiment, at least a portion of the privacy data used to conduct the joint modeling includes financial data records of the business, and accordingly, the joint modeling may include a risk assessment model for risk assessment of financial behavior of the business.
Referring to fig. 4, fig. 4 is a schematic diagram of a joint modeling system according to an embodiment of the present application.
As shown in fig. 4, the system includes an energy enterprise 41 as a target data collaborator and other data collaborators 42, where a service end of the energy enterprise 41 includes a pre-built operation environment and a private data storage environment; in a private data storage environment, private data for participating in joint modeling may be maintained, including a usage data record of energy provided by the energy enterprises 43 for the energy enterprises 41; in the operating environment, a collaboration node is deployed that is operable to perform multi-party privacy computing collaboration, and may form a privacy collaboration platform 40 with collaboration nodes deployed on the servers of other data collaborators 42.
The energy enterprise 41 acquires the privacy data maintained in the privacy data storage environment; after preprocessing the privacy data, the obtained index data is loaded to the collaboration nodes deployed in the running environment, so that the collaboration nodes and other data collaborators 42 perform multiparty privacy calculation collaboration, and joint modeling is performed through the data collaboration platform 40 based on the data loaded by each data collaborator at each collaboration node. The joint model resulting from the joint modeling includes a risk assessment model for performing risk assessment on the energy usage enterprise 43. The federated model is deployed to the operating environment of the server of the energy enterprise 41. Based on the joint model, risk assessment can be performed on the energy consumption enterprises 43, risks of the energy consumption enterprises 43 in a supply chain can be identified, and corresponding risk alarming and evaluation references are provided for management of the suppliers 44.
Referring to fig. 5, fig. 5 is a schematic diagram illustrating a joint modeling system according to an embodiment of the present application.
As shown in fig. 5, the system includes a financial institution 45 as a target data collaborator, an energy enterprise 41, and other data collaborators 42. The server side of the financial institution 45 comprises a pre-built running environment and a private data storage environment; in a private data storage environment, private data for participating in joint modeling may be maintained, including financial data for financial institutions 45 by energy enterprises 43; in the operating environment, a collaboration node that can be used to perform multiparty privacy computing collaboration is deployed, and the collaboration node may form a privacy collaboration platform 40 with collaboration nodes deployed on the servers of the energy enterprises 41 and other data collaborators 42.
The financial institution 45 obtains the privacy data maintained in the privacy data storage environment; after preprocessing the privacy data, the obtained index data is loaded to the collaboration nodes deployed in the operation environment, so that the collaboration nodes, the energy enterprises 41 and other data collaborators 42 perform multiparty privacy calculation collaboration, and joint modeling is performed through the data collaboration platform 40 based on the data loaded by each data collaborator at each collaboration node. The joint model resulting from the joint modeling includes a risk assessment model for risk assessment of the financial behavior of the energy usage enterprise 43. The federated model is deployed to the operating environment of the server of the energy enterprise 41 or financial institution 45. Based on the joint model, risk assessment can be performed on the energy consumption enterprises 43, risks of the energy consumption enterprises 43 on financial behaviors can be identified, the financial institutions 45 are helped to identify risks of the energy consumption enterprises, risk control quality on the financial behaviors is improved, and the energy consumption enterprises are assisted and generalized.
The privacy data of the energy enterprises are used for participating in joint modeling through the privacy collaboration platform, so that the obtained joint model can simultaneously consider the energy utilization behaviors of the energy enterprises, and can identify corresponding risks, and the obtained risk assessment result is more accurate.
Corresponding to the previous embodiments of the joint modeling method, the present application also provides embodiments of a joint modeling apparatus.
As shown in fig. 6, the joint modeling apparatus includes: a data acquisition module 601 and a privacy calculation module 602.
The data acquisition module 601 is configured to acquire private data maintained in a private data storage environment; the privacy computing module 602 is configured to load the obtained privacy data to a collaboration node deployed in the operating environment, so that the collaboration node performs multiparty privacy computing collaboration with other data collaborators, and performs joint modeling based on data loaded by each data collaborator at each collaboration node.
Optionally, the service end corresponding to the other data collaborators also comprises an operation environment and a private data storage environment; the operation environment is provided with collaboration nodes corresponding to the other data collaborators, and privacy data for participating in multiparty joint modeling is maintained in the privacy data storage environment;
the privacy calculation module 602 is configured to: and loading the acquired privacy data to a collaboration node deployed in the operation environment, so that the collaboration node performs multiparty privacy computation collaboration with the collaboration node deployed in the operation environment of the service end corresponding to at least one other data collaborator, and performing joint modeling based on the privacy data maintained in the privacy data storage environment on the service end of each data collaborator.
Optionally, the privacy calculation module 602 is configured to: and carrying out joint training by taking the privacy data maintained in the privacy data storage environment on the server side of each data collaborator as a training sample.
Optionally, the data obtaining module 601 is configured to obtain index data for joint modeling, where the index data is obtained by preprocessing privacy data that is stored in the privacy data storage environment in an isolated manner;
the privacy computation module 602 is configured to load the index data to a collaboration node deployed in the runtime environment.
Optionally, the data acquisition module 601 is configured to:
screening key data fields for joint modeling from privacy data stored in isolation in the privacy data storage environment;
the data fields are processed into index data for joint modeling.
Optionally, at least part of the privacy data used for joint modeling comprises energy use data records of energy provided by energy enterprises for the energy enterprises; the joint model obtained by the joint modeling comprises a risk assessment model for performing risk assessment on the energy utilization enterprise.
Optionally, the target data collaborator is the energy enterprise; the joint model obtained by the joint modeling comprises a risk assessment model for performing risk assessment on the energy utilization behavior of the energy utilization enterprise.
Optionally, the target data collaborator is a financial institution; the other data collaborators comprise the energy enterprise; the joint model obtained by joint modeling comprises a risk assessment model for performing risk assessment on financial behaviors of the energy utilization enterprise.
Optionally, the privacy calculation module 602 is further configured to: and after joint modeling is carried out to obtain a joint model, deploying the joint model into the running environment.
Optionally, a trusted execution environment is built in the running environment; the collaboration node is a privacy computing service program running in the trusted execution environment.
According to the embodiment of the application, the cooperative nodes for performing multiparty privacy calculation cooperation are deployed in the operation environment of the target enterprise, the private data maintained in the private data storage environment is used for performing multiparty privacy calculation cooperation with other cooperative parties by utilizing the privacy calculation, so that joint modeling is performed, and the private data can be combined with the other cooperative parties to realize that the private data is invisible under the condition that the local private data does not leave the domain, so that the private data can be shared in a data cooperation way with the other cooperative parties, and the requirements on safety compliance of the private data are met.
Embodiments of the joint modeling apparatus may be applied to an electronic device. The apparatus embodiments may be implemented by software, or may be implemented by hardware or a combination of hardware and software. Taking software implementation as an example, the device in a logic sense is formed by reading corresponding computer program instructions in a nonvolatile memory into a memory by a processor of an electronic device where the device is located for operation. In terms of hardware, as shown in fig. 7, a hardware structure diagram of an electronic device where the joint modeling apparatus of the present application is located is shown in fig. 7, and the electronic device where the apparatus is located in the embodiment may include other hardware besides the processor, the memory, the network interface, and the nonvolatile memory shown in fig. 7 according to the actual function of the electronic device, which is not described herein again.
The implementation process of the functions and roles of each unit in the above device is specifically shown in the implementation process of the corresponding steps in the above method, and will not be described herein again.
For the device embodiments, reference is made to the description of the method embodiments for the relevant points, since they essentially correspond to the method embodiments. The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purposes of the present application. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
The embodiment of the application further provides a computer readable storage medium, on which a computer program is stored, where the program when executed by a processor implements the steps of the joint modeling method as described above, and the same technical effects can be achieved, so that repetition is avoided, and no further description is given here.
Embodiments of the subject matter and the functional operations described in this specification can be implemented in: digital electronic circuitry, tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this specification and structural equivalents thereof, or a combination of one or more of them. Embodiments of the subject matter described in this specification can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on a tangible, non-transitory program carrier for execution by, or to control the operation of, data processing apparatus. Alternatively or additionally, the program instructions may be encoded on a manually-generated propagated signal, e.g., a machine-generated electrical, optical, or electromagnetic signal, that is generated to encode and transmit information to suitable receiver apparatus for execution by data processing apparatus. The computer storage medium may be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or a combination of one or more of them.
The processes and logic flows described in this specification can be performed by one or more programmable computers executing one or more computer programs to perform corresponding functions by operating on input data and generating output. The processes and logic flows can also be performed by, and apparatus can also be implemented as, special purpose logic circuitry, e.g., an FPGA (field programmable gate array) or an ASIC (application-specific integrated circuit).
Computers suitable for executing computer programs include, for example, general purpose and/or special purpose microprocessors, or any other type of central processing unit. Typically, the central processing unit will receive instructions and data from a read only memory and/or a random access memory. The essential elements of a computer include a central processing unit for carrying out or executing instructions and one or more memory devices for storing instructions and data. Typically, a computer will also include, or be operatively coupled to receive data from or transfer data to, or both, one or more mass storage devices for storing data, e.g., magnetic, magneto-optical disks, or optical disks, etc. However, a computer does not have to have such a device. Furthermore, the computer may be embedded in another device, such as a mobile phone, a Personal Digital Assistant (PDA), a mobile audio or video player, a game console, a Global Positioning System (GPS) receiver, or a portable storage device such as a Universal Serial Bus (USB) flash drive, to name a few.
Computer readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media and memory devices including, for example, semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices), magnetic disks (e.g., internal hard disk or removable disks), magneto-optical disks, and CD-ROM and DVD-ROM disks. The processor and the memory can be supplemented by, or incorporated in, special purpose logic circuitry.
While this specification contains many specific implementation details, these should not be construed as limitations on the scope of any invention or of what may be claimed, but rather as descriptions of features of specific embodiments of particular inventions. Certain features that are described in this specification in the context of separate embodiments can also be implemented in combination in a single embodiment. On the other hand, the various features described in the individual embodiments may also be implemented separately in the various embodiments or in any suitable subcombination. Furthermore, although features may be acting in certain combinations and even initially claimed as such, one or more features from a claimed combination can in some cases be excised from the combination, and the claimed combination may be directed to a subcombination or variation of a subcombination.
Similarly, although operations are depicted in the drawings in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In some cases, multitasking and parallel processing may be advantageous. Moreover, the separation of various system modules and components in the embodiments described above should not be understood as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.
Thus, particular embodiments of the subject matter have been described. Other embodiments are within the scope of the following claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve desirable results. Furthermore, the processes depicted in the accompanying drawings are not necessarily required to be in the particular order shown, or sequential order, to achieve desirable results. In some implementations, multitasking and parallel processing may be advantageous.
The foregoing description of the preferred embodiments of the present invention is not intended to limit the invention to the precise form disclosed, and any modifications, equivalents, improvements and alternatives falling within the spirit and principles of the present invention are intended to be included within the scope of the present invention.
Claims (14)
1. The joint modeling method is characterized by being applied to a server of any target data cooperator among a plurality of data cooperators participating in joint modeling, wherein the server comprises an operation environment in a public network and a private data storage environment in a private network; the operation environment is provided with cooperative nodes which cooperate with other data cooperative parties in multiparty privacy computation, and privacy data used for participating in the joint modeling are stored in the privacy data storage environment in an isolated manner; the method comprises the following steps:
acquiring privacy data stored in isolation in a privacy data storage environment;
and loading the acquired privacy data to a collaboration node deployed in the operation environment, so that the collaboration node performs multiparty privacy calculation collaboration with other data collaborators, and performing joint modeling based on the data loaded by each data collaborator at each collaboration node.
2. The method of claim 1, wherein the server further comprises a quarantine gatekeeper for quarantining the operating environment and the private data storage environment, the operating environment and the private data storage environment implementing data exchange through the quarantine gatekeeper.
3. The method of claim 1, wherein the servers corresponding to the other data collaborators also include an operating environment and a private data storage environment; the operation environment is provided with collaboration nodes corresponding to the other data collaborators, and privacy data for participating in multiparty joint modeling is maintained in the privacy data storage environment;
the acquired privacy data is loaded to a collaboration node deployed in the operation environment, so that the collaboration node and other data collaborators perform multiparty privacy computation collaboration, and joint modeling is performed based on the data loaded by each data collaborator at each collaboration node, and the method comprises the following steps:
and loading the acquired privacy data to a collaboration node deployed in the operation environment, so that the collaboration node performs multiparty privacy computation collaboration with the collaboration node deployed in the operation environment of the service end corresponding to at least one other data collaborator, and performing joint modeling based on the privacy data maintained in the privacy data storage environment on the service end of each data collaborator.
4. The method of claim 1, wherein jointly modeling based on data loaded by each data collaborator at a respective collaboration node comprises:
And carrying out joint training by taking the privacy data maintained in the privacy data storage environment on the server side of each data collaborator as a training sample.
5. The method of claim 1, wherein the obtaining private data stored in isolation in the private data storage environment comprises:
acquiring index data for joint modeling, which is obtained by preprocessing privacy data stored in isolation in the privacy data storage environment;
the loading the acquired privacy data to the collaboration node deployed in the operating environment comprises the following steps:
and loading the index data to a collaboration node deployed in the running environment.
6. The method according to claim 5, wherein the obtaining index data for joint modeling obtained by preprocessing the privacy data stored in the privacy data storage environment includes:
screening key data fields for joint modeling from privacy data stored in isolation in the privacy data storage environment;
the data fields are processed into index data for joint modeling.
7. The method of claim 1, wherein at least a portion of the privacy data used to conduct the joint modeling includes a record of energy usage data for energy provided by the energy enterprise for the energy enterprise; the joint model obtained by the joint modeling comprises a risk assessment model for performing risk assessment on the energy utilization enterprise.
8. The method of claim 7, wherein the target data collaborator is the energy enterprise; the joint model obtained by the joint modeling comprises a risk assessment model for performing risk assessment on the energy utilization behavior of the energy utilization enterprise.
9. The method of claim 7, wherein the target data collaborator is a financial institution; the other data collaborators comprise the energy enterprise; the joint model obtained by joint modeling comprises a risk assessment model for performing risk assessment on financial behaviors of the energy utilization enterprise.
10. The method according to claim 1, wherein the method further comprises:
and after joint modeling is carried out to obtain a joint model, deploying the joint model into the running environment.
11. The method of claim 1, wherein a trusted execution environment is built in the execution environment; the collaboration node is a privacy computing service program running in the trusted execution environment.
12. A joint modeling apparatus, the apparatus comprising:
the data acquisition module is used for acquiring privacy data which are stored in an isolated manner in the privacy data storage environment;
And the privacy calculation module is used for loading the acquired privacy data to a collaboration node deployed in the operation environment so that the collaboration node performs multiparty privacy calculation collaboration with other data collaborators, and performs joint modeling based on the data loaded by each data collaborator at each collaboration node.
13. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the steps of the method of any of claims 1-11.
14. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method of any of claims 1-11 when the program is executed by the processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310188416.XA CN116340995A (en) | 2023-03-01 | 2023-03-01 | Combined modeling method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310188416.XA CN116340995A (en) | 2023-03-01 | 2023-03-01 | Combined modeling method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116340995A true CN116340995A (en) | 2023-06-27 |
Family
ID=86888586
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310188416.XA Pending CN116340995A (en) | 2023-03-01 | 2023-03-01 | Combined modeling method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116340995A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116502732A (en) * | 2023-06-29 | 2023-07-28 | 杭州金智塔科技有限公司 | Federal learning method and system based on trusted execution environment |
-
2023
- 2023-03-01 CN CN202310188416.XA patent/CN116340995A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116502732A (en) * | 2023-06-29 | 2023-07-28 | 杭州金智塔科技有限公司 | Federal learning method and system based on trusted execution environment |
| CN116502732B (en) * | 2023-06-29 | 2023-10-20 | 杭州金智塔科技有限公司 | Federal learning method and system based on trusted execution environment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021164365A1 (en) | Graph neural network model training method, apparatus and system | |
| CN113159327B (en) | Model training method and device based on federal learning system and electronic equipment | |
| CN113505882B (en) | Data processing method based on federal neural network model, related equipment and medium | |
| CN109118214A (en) | The method and apparatus for running intelligent contract | |
| Hayes | Connecting the dots | |
| US11843586B2 (en) | Systems and methods for providing a modified loss function in federated-split learning | |
| CN111368319A (en) | Block chain-based data security access method in federated learning environment | |
| CN114401079A (en) | Multi-party joint information value calculation method, related equipment and storage medium | |
| CN112989399B (en) | Data processing system and method | |
| CN116340995A (en) | Combined modeling method and device and electronic equipment | |
| CN112288094A (en) | Federal network representation learning method and system | |
| CN112100642B (en) | Model training method and device for protecting privacy in distributed system | |
| CN112948885B (en) | Method, device and system for realizing privacy protection of multiparty collaborative update model | |
| WO2023174018A1 (en) | Vertical federated learning methods, apparatuses, system and device, and storage medium | |
| CN111353554B (en) | Method and device for predicting missing user service attributes | |
| Ilias et al. | Machine learning for all: A more robust federated learning framework | |
| CN113807157A (en) | Method, device and system for training neural network model based on federal learning | |
| Dufty | How can we improve community engagement for floodplain management | |
| CN115564447A (en) | Credit card transaction risk detection method and device | |
| WO2022081539A1 (en) | Systems and methods for providing a modified loss function in federated-split learning | |
| CN113487423A (en) | Personal credit risk prediction model training method and device | |
| Butt et al. | Hidden members and key players detection in covert networks using multiple heterogeneous layers | |
| Westerlund | Decentralized reservation of spatial volumes by autonomous vehicles: Investigating the applicability of blockchain and smart contracts | |
| Xu | Functional encryption based approaches for practical privacy-preserving machine learning | |
| Beebe | A Complete Bibliography of Publications in Future Internet |
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 |