CN110825476A - Display method, device, terminal and medium for federal learning workflow interface - Google Patents
Display method, device, terminal and medium for federal learning workflow interface Download PDFInfo
- Publication number
- CN110825476A CN110825476A CN201911057310.6A CN201911057310A CN110825476A CN 110825476 A CN110825476 A CN 110825476A CN 201911057310 A CN201911057310 A CN 201911057310A CN 110825476 A CN110825476 A CN 110825476A
- Authority
- CN
- China
- Prior art keywords
- output
- federal learning
- workflow
- interface
- display
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/451—Execution arrangements for user interfaces
-
- 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
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
Abstract
The invention discloses a display method and a display device of a federated learning workflow interface, terminal equipment and a computer readable storage medium, wherein a visual interface of the federated learning workflow is generated when the federated learning workflow is initiated; detecting an output object of the visual interface, and adjusting the output display state of the visual interface according to the output object; and outputting and displaying the visual interface after the output display state is adjusted to the output object. According to the method and the device, when the federal learning workflow participated in by multiple parties is displayed, different output display states of visual interfaces are displayed for different parties, and the machine learning process of each party is guaranteed not to be known by other parties, so that the purpose of protecting the data privacy and data safety of all parties learnt by the federal is achieved in the process of displaying the federal learning workflow.
Description
Technical Field
The invention relates to the technical field of Fintech (financial technology), in particular to a display method and device of a federated learning workflow interface, a terminal device and a computer readable storage medium.
Background
In the field of machine learning, in order to make the whole operation process of machine learning clear so as to find the abnormality of machine learning in time, and visually displaying the workflow of machine learning has gradually become a research direction which is more and more important in the industry.
However, in the process of federal machine learning, since federal learning involves participation of multiple parties, and the federal learning stages of each party are different, it is necessary to ensure that the machine learning process of each party is not known by other parties for data privacy and data security, so that the purpose of protecting data privacy and data security of the federal learning parties cannot be achieved by using the traditional machine learning workflow display mode.
Disclosure of Invention
The invention mainly aims to provide a display method and device of a federated learning workflow interface, a terminal device and a computer readable storage medium, and aims to solve the technical problem that the data privacy and the data security of federated learning participants cannot be protected in the traditional machine learning workflow display mode.
In order to achieve the above object, the present invention provides a display method for a federal learning workflow interface, which comprises:
when a federal learning workflow is initiated, generating a visual interface of the federal learning workflow;
detecting an output object of the visual interface, and adjusting the output display state of the visual interface according to the output object;
and outputting and displaying the visual interface after the output display state is adjusted to the output object.
Further, the step of adjusting the output display state of the visual interface according to the output object includes:
detecting the role type of the display output object in federal learning;
and adjusting the output display state of the visual interface according to the role type.
Further, the step of adjusting the output display state of the visual interface according to the role type includes:
screening a target working component which is invisible to the output object in the visual interface according to the role type;
in the visual interface, changing display parameters of a target working component to adjust an output display state of the visual interface.
Further, before the step of generating the visual interface of the federal learning workflow at the initiation of the federal learning workflow, the method further includes:
configuring each operational component in the federated learning workflow based on a preset federated learning task,
the step of generating the visual interface of the federal learning workflow comprises:
and correspondingly generating the visual interface according to the operation flow and the display parameters of each operation assembly.
Further, the step of configuring each running component in the federal learning workflow based on a preset federal learning task includes:
reading workflow configuration information carried by the preset federal learning task;
according to the workflow configuration information, configuring an independent operation work assembly in the federal learning workflow, and designating a single-party execution role of the independent operation work assembly, and/or configuring a combined operation work assembly in the federal learning workflow, and designating a multi-party execution role of the combined operation work assembly;
and configuring the operation parameter information of the independent operation work assembly and/or the combined operation work assembly in the federal learning workflow according to the workflow configuration information.
Further, after the step of displaying the output of the visual interface after the adjustment of the output display state to the output object, the method further includes:
and acquiring a request instruction for viewing the output result of the component, and displaying the output result of the running component specified by the request instruction to a target output object.
Further, the step of displaying the output result of the running component specified by the request instruction to the target output object includes:
acquiring an operator of an operation component specified by the request instruction, and detecting whether a trigger end of the request instruction belongs to the operator;
and if so, taking the trigger end as the target output object to output and display the output result.
In addition, to achieve the above object, the present invention further provides a display device for a federal learning workflow interface, where the display device for a federal learning workflow interface includes:
the generation module is used for generating a visual interface of the federal learning workflow when the federal learning workflow is initiated;
the adjusting module is used for detecting an output object of the visual interface and adjusting the output display state of the visual interface according to the output object;
and the display module is used for outputting and displaying the visual interface after the output display state is adjusted to the output object.
The present invention also provides a terminal device, including: the display program of the federal learning workflow interface is stored on the memory and can run on the processor, and when being executed by the processor, the display program of the federal learning workflow interface realizes the steps of the display method of the federal learning workflow interface.
The present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method for displaying a federal learning workflow interface as set forth above.
According to the display method and device of the federal learning workflow interface, the terminal equipment and the computer readable storage medium, when the federal learning workflow is initiated, the visual interface of the federal learning workflow is generated; detecting an output object of the visual interface, and adjusting the output display state of the visual interface according to the output object; and outputting and displaying the visual interface after the output display state is adjusted to the output object. According to the method, when the visual interface of the federal learning workflow is displayed in an output mode, the output display state of the visual interface is correspondingly adjusted according to different output objects of the current visual interface in federal learning, and the visual interface of the federal learning workflow after adjustment is output and displayed to the current display object, so that when the federal learning workflow participating in multiple parties is displayed, different output display states of the visual interface are displayed for different participating parties, the machine learning process of each participating party is guaranteed not to be known by other participating parties, and the purpose of protecting data privacy and data safety of each participating party in federal learning is achieved in the process of displaying the federal learning workflow.
Drawings
FIG. 1 is a schematic diagram of the hardware operation involved in an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a method for displaying a workflow interface for federated learning according to a first embodiment of the present invention;
FIG. 3A is a schematic view of an interface output display scene according to an embodiment of a display method for a federated learning workflow interface of the present invention;
FIG. 3B is a schematic diagram of another interface output display scenario in an embodiment of a display method for a federated learning workflow interface according to the present invention;
FIG. 3C is a schematic diagram of an interface output display scene according to another embodiment of the display method for a federated learning workflow interface of the present invention;
fig. 4 is a schematic structural diagram of a display device of a joint learning workflow interface according to the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in fig. 1, fig. 1 is a schematic structural diagram of a hardware operating environment according to an embodiment of the present invention.
It should be noted that fig. 1 is a schematic structural diagram of a hardware operating environment of the terminal device. The terminal equipment of the embodiment of the invention can be terminal equipment such as a PC, a portable computer and the like.
As shown in fig. 1, the terminal device may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the terminal device configuration shown in fig. 1 is not intended to be limiting of the terminal device and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a kind of computer storage medium, may include therein an operating system, a network communication module, a user interface module, and a distributed task processing program. Among them, the operating system is a program that manages and controls the hardware and software resources of the sample terminal device, a handler that supports distributed tasks, and the execution of other software or programs.
In the terminal apparatus shown in fig. 1, the user interface 1003 is mainly used for data communication with each terminal; the network interface 1004 is mainly used for connecting a background server and performing data communication with the background server; and the processor 1001 may be configured to invoke a display program of the federal learning workflow interface stored in the memory 1005 and perform the following operations:
when a federal learning workflow is initiated, generating a visual interface of the federal learning workflow;
detecting an output object of the visual interface, and adjusting the output display state of the visual interface according to the output object;
and outputting and displaying the visual interface after the output display state is adjusted to the output object.
Further, processor 1001 may invoke a display program of the federal learning workflow interface stored in memory 1005 to also perform the following operations:
detecting the role type of the display output object in federal learning;
and adjusting the output display state of the visual interface according to the role type.
Further, processor 1001 may invoke a display program of the federal learning workflow interface stored in memory 1005 to also perform the following operations:
screening a target working component which is invisible to the output object in the visual interface according to the role type;
in the visual interface, changing display parameters of a target working component to adjust an output display state of the visual interface.
Further, the processor 1001 may call a display program of the federal learning workflow interface stored in the memory 1005, and perform the following operations before generating the visual interface of the federal learning workflow at the time of initiation of the federal learning workflow:
configuring each running component in the federal learning workflow based on a preset federal learning task.
Further, processor 1001 may invoke a display program of the federal learning workflow interface stored in memory 1005 to also perform the following operations:
the step of generating the visual interface of the federal learning workflow comprises:
and correspondingly generating the visual interface according to the operation flow and the display parameters of each operation assembly.
Further, processor 1001 may invoke a display program of the federal learning workflow interface stored in memory 1005 to also perform the following operations:
reading workflow configuration information carried by the preset federal learning task;
according to the workflow configuration information, configuring an independent operation work assembly in the federal learning workflow, and designating a single-party execution role of the independent operation work assembly, and/or configuring a combined operation work assembly in the federal learning workflow, and designating a multi-party execution role of the combined operation work assembly;
and configuring the operation parameter information of the independent operation work assembly and/or the combined operation work assembly in the federal learning workflow according to the workflow configuration information.
Further, the processor 1001 may call a display program of the federal learning workflow interface stored in the memory 1005, and after executing the displaying of the visualization interface output after adjusting the output display state to the output object, further execute the following operations:
and acquiring a request instruction for viewing the output result of the component, and displaying the output result of the running component specified by the request instruction to a target output object.
Further, processor 1001 may invoke a display program of the federal learning workflow interface stored in memory 1005 to also perform the following operations:
acquiring an operator of an operation component specified by the request instruction, and detecting whether a trigger end of the request instruction belongs to the operator;
and if so, taking the trigger end as the target output object to output and display the output result.
Based on the structure, the invention provides various embodiments of the display method of the federal learning workflow interface.
Referring to fig. 2, fig. 2 is a flowchart illustrating a first embodiment of a display method of a federal learning workflow interface according to the present invention.
While a logical order is shown in the flow chart, in some cases, the steps shown or described may be performed in a different order than presented herein.
The display method of the federal learning workflow interface in the embodiment of the present invention is applied to the terminal device, and the terminal device in the embodiment of the present invention may be a terminal device such as a PC, a portable computer, or the like, and is not particularly limited herein.
The display method of the federal learning workflow interface in the embodiment comprises the following steps:
and S100, generating a visual interface of the federal learning workflow when the federal learning workflow is initiated.
In a federal machine learning system constructed by a coordinator, a demander and various data providers, when detecting that the demander starts a work flow initiating current federal machine learning based on the processing requirement of the federal learning task, a visual interface of the current federal machine learning work flow is generated according to the federal learning work flow which is configured and completed by the current demander in advance and is required to process the federal learning task.
It should be noted that, in this embodiment, based on the setting of the role of the federal machine learning participant, the federal machine learning system includes a coordinator (arbiters: arbiters, coordinators), a demander (guest: customers, guests), and each data provider (host: hosts, hosts), and in the federal machine learning system, only the workflow of federal machine learning initiated by the demander guest is supported, that is, the demander guest completes the configuration of the whole federal learning workflow in advance and starts the operation.
And S200, detecting an output object of the visual interface, and adjusting the output display state of the visual interface according to the output object.
Further, step S200 includes:
step S201, detecting the role type of the display output object in federal learning;
and step S202, adjusting the output display state of the visual interface according to the role type.
The method comprises the steps that a workflow for initiating current federal machine learning is started on a demand side of each participant of a federal learning system, and after a visual interface of the current federal machine learning workflow is correspondingly generated, output objects to be output and displayed in the current federal learning system through the visual interface are detected, so that the output display state of the visual interface of the federal machine learning workflow is correspondingly adjusted according to different role types of the output objects in the current federal learning participant role.
Further, step S202 includes:
step S2021, according to the role type, screening the target work component, which is invisible to the output object, in the visual interface.
Specifically, for example, when a currently generated visual interface of a federal machine learning workflow initiated by a demander in the federal learning system needs to be output and displayed to a data provider a in a plurality of data providers in the currently generated federal learning system, each target working component which is not involved in operation by the current data provider a is extracted from the visual interface which maps the whole operation flow of all the current federal machine learning working components, and similarly, when the visual interface needs to be output and displayed to a data provider b in the plurality of data providers, each target working component which is not involved in operation by the data provider b is screened and extracted from all the working components displayed in the visual interface.
In another embodiment, in all the operating components displayed and output by the visual interface, the operating component in which the data provider a (or the data provider b) participates in the operation may also be used as the target operating component, so that when the target operating components in the visual interface are screened, each target operating component in which the data provider a (or the data provider b) participates in the operation is correspondingly screened from all the operating components displayed in the visual interface.
It should be noted that, in this embodiment, whether the visual interface requirement of the federal machine learning workflow needs to be checked may be autonomously determined by each participant in the current federal learning system, the visual interface of the federal machine learning workflow initiated by the currently generated requirement party guest is correspondingly output and displayed, and before the output and display, the output and display state of the visual interface of the federal machine learning workflow is correspondingly adjusted according to different role types of each output object in the role of the current federal learning participant.
Step S2022, in the visual interface, changing a display parameter of the target working component to adjust an output display state of the visual interface.
Specifically, for example, in a visualization interface display scenario as shown in fig. 3A, in a visualization interface of a federal learning workflow to be output and displayed to a data provider a, each target operation component other than a feature normalization component "fed _ feed _ scale" in which the data provider a participates in operation alone, and a vertical federal logistic regression component "head _ fed _ lr" in which the data provider a participates in operation in combination with other data providers (e.g., data provider B), a display status in the current federal learning workflow visualization interface is modified, that is, display parameters such as output display colors of each target operation component are modified (grayed out or modified display transparency) and names of each target operation component are represented by "＊＊＊＊＊＊", further, in a visualization interface display scenario as shown in fig. 3B, display parameters other than data components of the federal learning workflow to be output and displayed to the data provider B are modified, and each data provider B (a plurality of data providers in the current federal learning system) participates in display of the other visualization interfaces of the federal learning workflow, and the display status of each target operation component other data provider B is modified and displayed by other target operation components such as "live" display parameters of the vertical federal learning workflow display interface display components, and data provider B "and data providers (e.g — live feedback components, and data providers" display components participate in the display status of the vertical federal learning workflow display interface display screens of the data providers "and display components.
Further, in another embodiment, when the visualization interface output of the current federal machine learning workflow is displayed to the demanding party gusest in the current federal learning system, all the operating components in the current visualization interface may be displayed to the demanding party gusest by using different display parameters such as output display colors.
In the visualization interface display scenario shown in fig. 3C, when the visualization interface output of the current federal machine learning workflow is displayed to the requiring party gusest (labeled as "requiring party g" in the drawing) in the current federal learning system, since the requiring party gusst configures and initiates the workflow of the current federal machine learning in advance, the requiring party can view all the working components displayed in the visualization interface of the current federal machine learning workflow, that is, all the operating components in the current visualization interface only need to adjust the display parameters such as the output display colors of the working components not operated by the requiring party gusst, and do not need to represent the names of the working components not operated by the requiring party gusst with "＊＊＊＊＊＊".
It should be noted that, in this embodiment, the requester guest in the federal learning system can see the whole structure of the federal learning workflow, but for a component in the federal learning workflow that is not operated by the requester guest, such as a "feature normalized" component, fed _ feature _ scale _ (which is operated by a certain data provider in the federal learning system alone), the component that is not operated by the requester guest will be marked with gray and output for display; the data provider host in the federal learning system cannot look at the component information of the whole federal learning workflow, but only can look at the components only operated by the own and output and display the components by using a clear component state mark, and the rest of the components which are not operated by the own are all represented by ". about.", and the number of input and output ports of other components which are not operated by the own cannot be looked at, so that the data provider can avoid guessing the operating components according to the number of ports specific to the operating components; the coordinator in the federal learning system can only check the status of the working components which are jointly operated with other participants (such as the gust), for example, in the visual interface output display scenario shown in fig. 3A and 3B, respectively, the data provider a can only see the "feature normalized" component, fed _ feature _ scale, which participates in operation, and the "vertical federal logistic regression" component, fed __ fed _ lr; and the data provider b can only see the vertical federal feature binning component, the vertical federal feature fed feature binning component, and the vertical federal logistic regression component, the vertical federal __ fed lr, which participate in the operation.
It should be noted that, in this embodiment, the types of the display parameters of each target operating component that needs to be adjusted and modified include, but are not limited to, a display color, a display shape, and the like, and it should be understood that the display method of the federal learning workload interface according to the present invention does not limit the types of the display parameters of the modified operating components, the modification degree, and the like.
And step S300, outputting and displaying the visual interface after the output display state is adjusted to the output object.
After the display state of the visualization interface of the federal machine learning process initiated by the demand party is adjusted, the visualization interface adjusted according to the role type of the current participant in the federal learning system is output and displayed to the current participant.
Specifically, for example, in the interface display application scenario shown in fig. 3, after the display parameters of each target operating component in the visual interface are adjusted and changed according to the operating conditions of each component (i.e., the operating components that are independently or jointly involved in the operation) in the current federal machine learning process in which the data provider a participates, the visual interface is output and displayed to the terminal device where the data provider a is located after the adjustment according to the data provider a.
In the embodiment, in the federal machine learning system constructed by a coordinator, a demander and data providers, when detecting that the demander starts a work flow initiating the current federal machine learning based on the processing requirement of the own federal learning task, a visual interface of the current federal machine learning work flow is generated according to the federal learning work flow which is configured and completed in advance by the current demander and is required for processing the own federal learning task, after starting the work flow initiating the current federal machine learning by the demander of each participator in the federal learning system and correspondingly generating the visual interface of the current federal machine learning work flow, each output object which is required to be output and displayed by the visual interface in the current federal learning system is detected, so that different role types of each output object in the current federal learning participator roles are determined according to the different role types of each output object in the current federal learning partic, and after the adjustment of the display state of the visual interface of the federal machine learning workflow initiated by the demand party is completed, the visual interface adjusted according to the role type of the current participant in the federal learning system is output and displayed to the current participant.
When the federal learning workflow participated in by multiple parties is displayed, different output display states of visual interfaces are displayed for different participants, and the machine learning process of each participant is guaranteed not to be known by other participants, so that the purpose of protecting the data privacy and the data safety of all the participants in the process of displaying the federal learning workflow is achieved.
Further, based on the first embodiment of the display method of the federal learning workflow interface, the second embodiment of the display method of the federal learning workflow interface is provided.
In a second embodiment of the display method of a federal learning workflow interface according to the present invention, in step S100 of the first embodiment, before the generation of the visual interface of the federal learning workflow when the federal learning workflow is initiated, the display method of a federal learning workflow interface according to the present invention further includes:
and step S400, configuring each running component in the federal learning workflow based on a preset federal learning task.
The method comprises the steps of obtaining a preset federal learning task according to which a demand side starts a visual interface initiating the current federal machine learning workflow, reading the federal learning workflow configuration information of the preset federal learning task, and configuring each operation component in the current federal learning workflow based on the workflow configuration information.
Further, in step S100, the step of generating a visual interface of the federal learning workflow includes:
and S101, correspondingly generating the visual interface according to the operation flow and the display parameters of each operation assembly.
When a demand side starts a work flow initiating current federal machine learning based on the processing requirement of the own federal learning task, a visual interface mapping the current federal machine learning work flow is generated according to the input and output flows of all operation components required by the current demand side for processing the own federal learning task and the display parameters (namely, output display color, display content and the like) of all the operation components, wherein the input and output flows are configured and completed in advance by the current demand side.
Further, step S400 includes:
and S401, reading workflow configuration information carried by the preset federal learning task.
Step S402, according to the workflow configuration information, configuring an independent operation work assembly in the federal learning workflow, and appointing a single-party execution role of the independent operation work assembly, and/or configuring a combined operation work assembly in the federal learning workflow, and appointing a multi-party execution role of the combined operation work assembly.
Specifically, for example, in configuring a federated machine learning workflow, the demander guest, based on data processing tasks, one of the data providers host of the plurality of data providers of the current federal learning system can be designated to independently run the characteristic running components required for the execution of the current data processing task, or, on the other hand, the demander guest can specify a certain data provider host of a plurality of data providers and the coordinator to jointly run the feature running component required by the current model training processing task to execute according to the model training processing task, or the demander guest can execute the feature running component required by the current model training processing task according to the data processing task, while one of the data providers host of the plurality of data providers of the current federal learning system is specified to independently run the feature running components required for the current data processing task to be executed, and a certain data provider host and a coordinator arbiter in the multiple data providers can be appointed to jointly run a characteristic running component required by the execution of the current model training processing task.
Further, in another embodiment, the demander rule may also specify, according to a feature work component (e.g., "feature normalization" component — featured _ feature _ scale), that one of the multiple data providers of the current federated learning system runs the current component alone (i.e., "feature normalization" component), or, according to a feature work component (e.g., "longitudinal federated logistic regression" component — featured _ lr), that one of the multiple data providers and the coordinator arbiter run the current feature work component in combination.
Step S403, configuring the operation parameter information of the independent operation work component and/or the joint operation work component in the federal learning workflow according to the workflow configuration information.
After a requiring party gust specifies and finishes each characteristic operation component independently executed and/or jointly executed by an executing party based on the task configuration information of the federal learning workflow of the federal learning processing task, the operation parameter information of each characteristic operation component negotiated and agreed with a coordinator and each data provider host in the current federal learning system in advance is configured on the corresponding characteristic operation component, and therefore the configuration of the current federal learning workflow is finished.
In this embodiment, when a requiring party starts a visual interface for initiating a current federal machine learning workflow, a federal learning processing task according to the requiring party is obtained, a task type in task attributes of the federal learning processing task is read, and a federal learning workflow required by processing the federal learning task is configured by the requiring party according to the read task type and feature work components of the federal learning processing task, that is, participants in a designated federal learning system operate the current federal learning workflow independently or in combination with each other.
Further, a third embodiment of the display method of the federal learning workflow interface of the present invention is proposed based on the first embodiment of the display method of the federal learning workflow interface.
In a third embodiment of the display method of a federal learning workflow interface according to the present invention, after the step S300 of the first embodiment displays the output of the visual interface after the output display state is adjusted to the output object, the display method of a federal learning workflow interface according to the present invention further includes:
step S500, a request instruction for checking the output result of the component is obtained, and the output result of the running component specified by the request instruction is displayed to a target output object.
Detecting and acquiring any one participant in the current federated learning system, triggering and generating a request instruction for checking the output result of any running component in the federated machine learning workflow, detecting and determining all participants in the current federated learning system, having all the running parties for checking the output result of the running component specified by the request instruction, and outputting and displaying the participant as a target output object of the output result of the current running component when detecting that the participant triggering and generating the request instruction belongs to one of the running parties.
Further, step S500 includes:
step S501, obtaining an operator of the operating component specified by the request instruction, and detecting whether the trigger end of the request instruction belongs to the operator.
Detecting all the operation parties which have the authority of checking the output result of the operation component and appoint the output result of the operation component in all the participation parties (namely, a coordinator, each demander and all data providers) of the current federal learning system, and further detecting whether the participation party (which can be the coordinator, the demander or any data provider) which currently triggers the generation of the request instruction belongs to one of the detected operation parties.
Step S502, using the trigger end as the target output object to output and display the output result.
When detecting that the participant currently triggering the generation request instruction belongs to one of the detected operation parties, taking the participant as a target output object of the output result of the current operation component, and outputting and displaying the output result to the participant currently triggering the generation request instruction.
Further, in another embodiment, when it is detected that the participant currently triggering the generation request instruction does not belong to one of the detected running parties, the participant is discarded as a target output object of the output result of the currently running component, and corresponding prompt information (for example, "does not possess the viewing permission, cannot know the running condition of the component" or the like) is output to the participant currently triggering the generation request instruction.
It should be noted that, in this embodiment, the output results of the running components displayed by the federal machine learning workflow in the visual output manner are correspondingly displayed in the different output manners according to the different roles of the participants (i.e., coordinator, consumer, and data provider host) of the present federal learning system, that is, the output results (output of model, output of data, etc.) included in the output results of each running component are made different in the different roles of the federal learning system, that is, the output results displayed by each running component displayed by the federal machine learning workflow in the visual output manner are different from the view authority and the view content, so as to further protect the data privacy and data security of each participant in the federal learning.
Specifically, for example, for a component that is unilaterally independently operated and displayed in the federal machine learning visual output, the output result of the component is output only to the only executing party of the component; for the components operated jointly, the output result of the component can be displayed to two or more parties output and executed jointly, that is, part of the output result of the component which displays the components participating in the operation can be output and displayed to each executing party (for example, "longitudinal federal logistic regression" component-hetero __ fed _ lr, the part of the model output which displays the respective local longitudinal federal model can be output and displayed to each executing party, and the part of the model output which displays the local logistic regression model of other parties operating jointly is not output and displayed to each executing party, or the output result of the component which displays part of the data provider host participating in the operation can be output and displayed to the demanding party guast in the federal learning system (for example, "longitudinal federal feature binning" component-hetero _ fed _ feature _ binning, for the demanding party guast in the federal learning system, except that binning details obtained according to the local end features of the demanding party can be output and displayed to each demanding party (part of the output result of the longitudinal federal feature binning component ) And can also be output and displayed to participate in the current vertical federal feature binning component-front _ fed _ feature _ binning operation, according to other binning details (part of the output result of the vertical federal feature binning component) of the feature of each data provider host except the feature binning split point, for each data provider host in the federal learning system, only the feature binning split points obtained by the current 'longitudinal federal feature binning' component, namely, the front fed feature binning component, running according to the features of each data provider host can be output and displayed, but not to output thereto display feature binning details such as an iv value (amount of information or information value), woe value (weight of evidence) and the like, therefore, each data provider host is prevented from reversely deducing key information and output results of a 'longitudinal federal feature binning' component, namely, the head _ fed _ feature _ binding, operated by the requester rule in the current federal learning system by using the feature binning details.
In this embodiment, the output results of the running components visually output and displayed by the federal machine learning workflow are correspondingly and differentially output and displayed according to the roles of the different participants of the present federal learning system (namely, the coordinator, the demander and the data provider host), so that the output results (output of the model, output of the data, etc.) included in the output results of each running component are different in the output results of the different roles of the federal learning system, that is, the output results visually output and displayed to each running component of each participant by the federal machine learning are different in view permission and view content, thereby further protecting the data privacy and data security of each participant of the federal learning.
In addition, referring to fig. 4, an embodiment of the present invention further provides a display device for a federal learning workflow interface, where the display device for a federal learning workflow interface includes:
the generation module is used for generating a visual interface of the federal learning workflow when the federal learning workflow is initiated;
the adjusting module is used for detecting an output object of the visual interface and adjusting the output display state of the visual interface according to the output object;
and the display module is used for outputting and displaying the visual interface after the output display state is adjusted to the output object.
Preferably, the adjustment module comprises:
the detection unit is used for detecting the role type of the display output object in federal learning;
and the adjusting unit is used for adjusting the output display state of the visual interface according to the role type.
Preferably, the adjusting unit further includes:
the screening subunit is used for screening the invisible target working component of the output object in the visual interface according to the role type;
and the changing subunit is used for changing the display parameters of the target working assembly in the visual interface so as to adjust the output display state of the visual interface.
Preferably, the display device of the federal learning workflow interface of the present invention further includes:
a configuration module for configuring each operating component in the federated learning workflow based on a preset federated learning task,
the generation module comprises:
and the generating unit is used for correspondingly generating the visual interface according to the operation flow and the display parameters of each operation assembly.
Preferably, the configuration module comprises:
the reading unit is used for reading workflow configuration information carried by the preset federal learning task;
the first configuration unit is used for configuring an independent operation work assembly in the federal learning workflow according to the workflow configuration information and appointing a single-party execution role of the independent operation work assembly, and/or configuring a combined operation work assembly in the federal learning workflow and appointing a multi-party execution role of the combined operation work assembly;
and the second configuration unit is used for configuring the operation parameter information of the independent operation working component and/or the combined operation working component in the federal learning workflow according to the workflow configuration information.
Preferably, the display module of the display device of the federal learning workflow interface is further configured to obtain a request instruction for viewing an output result of the component, and display the output result of the running component specified by the request instruction to the target output object.
Preferably, the display module includes:
the detection confirming unit is used for acquiring the operator of the operation component specified by the request instruction and detecting whether the trigger end of the request instruction belongs to the operator;
and the output display unit is used for taking the trigger end as the target output object so as to output and display the output result.
In addition, an embodiment of the present invention further provides a computer-readable storage medium, which is applied to a computer, and the computer-readable storage medium may be a non-volatile computer-readable storage medium, on which a display program of a federal learning workflow interface is stored, where the display program of the federal learning workflow interface, when executed by a processor, implements the steps of the display method of the federal learning workflow interface as described above.
The steps implemented when the display program of the federal learning workflow interface running on the processor is executed may refer to various embodiments of the display method of the federal learning workflow interface of the present invention, and are not described herein again.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A display method of a federated learning workflow interface is characterized in that the display method of the federated learning workflow interface comprises the following steps:
when a federal learning workflow is initiated, generating a visual interface of the federal learning workflow;
detecting an output object of the visual interface, and adjusting the output display state of the visual interface according to the output object;
and outputting and displaying the visual interface after the output display state is adjusted to the output object.
2. The method of displaying a federal learning workflow interface as claimed in claim 1, wherein said step of adjusting an output display state of said visual interface in accordance with said output object comprises:
detecting the role type of the display output object in federal learning;
and adjusting the output display state of the visual interface according to the role type.
3. The method of displaying a federal learning workflow interface as claimed in claim 2, wherein the step of adjusting the output display status of the visual interface according to the role type comprises:
screening a target working component which is invisible to the output object in the visual interface according to the role type;
in the visual interface, changing display parameters of a target working component to adjust an output display state of the visual interface.
4. The method for displaying a federal learning workflow interface as claimed in claim 3, further comprising, prior to the step of generating a visual interface for a federal learning workflow at the time of initiation of the federal learning workflow:
configuring each operating component in the federal learning workflow based on a preset federal learning task;
the step of generating the visual interface of the federal learning workflow comprises:
and correspondingly generating the visual interface according to the operation flow and the display parameters of each operation assembly.
5. The method of displaying a federal learning workflow interface as claimed in claim 4, wherein the step of configuring each operational component in the federal learning workflow based on a preset federal learning task comprises:
reading workflow configuration information carried by the preset federal learning task;
according to the workflow configuration information, configuring an independent operation work assembly in the federal learning workflow, and designating a single-party execution role of the independent operation work assembly, and/or configuring a combined operation work assembly in the federal learning workflow, and designating a multi-party execution role of the combined operation work assembly;
and configuring the operation parameter information of the independent operation work assembly and/or the combined operation work assembly in the federal learning workflow according to the workflow configuration information.
6. The method for displaying a federal learning workflow interface as claimed in claim 1, wherein after the step of displaying the visual interface output after adjusting the output display status to the output object, the method further comprises:
and acquiring a request instruction for viewing the output result of the component, and displaying the output result of the running component specified by the request instruction to a target output object.
7. The method for displaying a federal learning workflow interface as claimed in claim 1, wherein the step of displaying the output result of the run component specified by the request command to a target output object comprises:
acquiring an operator of an operation component specified by the request instruction, and detecting whether a trigger end of the request instruction belongs to the operator;
and if so, taking the trigger end as the target output object to output and display the output result.
8. The utility model provides a display device on federal study workflow interface, its characterized in that, display device on federal study workflow interface includes:
the generation module is used for generating a visual interface of the federal learning workflow when the federal learning workflow is initiated;
the adjusting module is used for detecting an output object of the visual interface and adjusting the output display state of the visual interface according to the output object;
and the display module is used for outputting and displaying the visual interface after the output display state is adjusted to the output object.
9. A terminal device, characterized in that the terminal device comprises: a memory, a processor, and a display program of a federal learning workflow interface stored on the memory and operable on the processor, the display program of the federal learning workflow interface being executed by the processor to implement the steps of the display method of the federal learning workflow interface as claimed in any one of claims 1 to 7.
10. A storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method for displaying a federal learning workflow interface as claimed in any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911057310.6A CN110825476A (en) | 2019-10-31 | 2019-10-31 | Display method, device, terminal and medium for federal learning workflow interface |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911057310.6A CN110825476A (en) | 2019-10-31 | 2019-10-31 | Display method, device, terminal and medium for federal learning workflow interface |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110825476A true CN110825476A (en) | 2020-02-21 |
Family
ID=69551856
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911057310.6A Pending CN110825476A (en) | 2019-10-31 | 2019-10-31 | Display method, device, terminal and medium for federal learning workflow interface |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110825476A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111553485A (en) * | 2020-04-30 | 2020-08-18 | 深圳前海微众银行股份有限公司 | View display method, device, equipment and medium based on federal learning model |
| WO2021114616A1 (en) * | 2020-05-14 | 2021-06-17 | 平安科技（深圳）有限公司 | Federated learning model training method and related device |
| CN114281231A (en) * | 2021-10-12 | 2022-04-05 | 腾讯科技（深圳）有限公司 | Information presentation method and device, electronic equipment and storage medium |
| CN116029371A (en) * | 2023-03-27 | 2023-04-28 | 北京邮电大学 | Federal learning workflow construction method based on pre-training and related equipment |
-
2019
- 2019-10-31 CN CN201911057310.6A patent/CN110825476A/en active Pending
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111553485A (en) * | 2020-04-30 | 2020-08-18 | 深圳前海微众银行股份有限公司 | View display method, device, equipment and medium based on federal learning model |
| WO2021219080A1 (en) * | 2020-04-30 | 2021-11-04 | 深圳前海微众银行股份有限公司 | Federated learning model-based view display method, apparatus and device, and medium |
| WO2021114616A1 (en) * | 2020-05-14 | 2021-06-17 | 平安科技（深圳）有限公司 | Federated learning model training method and related device |
| CN114281231A (en) * | 2021-10-12 | 2022-04-05 | 腾讯科技（深圳）有限公司 | Information presentation method and device, electronic equipment and storage medium |
| CN114281231B (en) * | 2021-10-12 | 2023-10-20 | 腾讯科技（深圳）有限公司 | Information presentation method, device, electronic equipment and storage medium |
| CN116029371A (en) * | 2023-03-27 | 2023-04-28 | 北京邮电大学 | Federal learning workflow construction method based on pre-training and related equipment |
| CN116029371B (en) * | 2023-03-27 | 2023-06-06 | 北京邮电大学 | Federal learning workflow construction method based on pre-training and related equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110825476A (en) | Display method, device, terminal and medium for federal learning workflow interface | |
| CN105247548B (en) | User in collaboration workspace system based on application defines workflow | |
| CA2874605C (en) | Methods, systems and computer program products for collaborative tax return preparation | |
| US20200036746A1 (en) | Creating notes on lock screen | |
| JP7143283B2 (en) | Emotional expression in virtual environments | |
| US11941561B2 (en) | Automated distribution of subtask assignments to user devices | |
| US11632406B2 (en) | Information processing system, information processing method, and recording medium recording information processing program | |
| US20170075503A1 (en) | System and method for enhanced collaboration | |
| JP2018517952A (en) | Support system capable of supporting problem solving and collaboration in the BIM environment | |
| JP6260585B2 (en) | Information processing apparatus and information processing program | |
| US20190163337A1 (en) | System for Augmenting a Computer Display via a Mobile Device Display | |
| CN111208999A (en) | Template-based instruction generation method and device, terminal equipment and storage medium | |
| CN107729686B (en) | Building model component display method and device, electronic equipment and storage medium | |
| KR102401345B1 (en) | Method for writing contents for a plurality of writers based on user account information and Apparatus thereof | |
| US20170054699A1 (en) | Information processing apparatus, information processing method, program, storage medium, and password entry apparatus | |
| US11830085B2 (en) | Enhanced rating interface and techniques | |
| JP2008146584A (en) | Application sharing screen controller, application sharing screen control program, and communication terminal device | |
| JP2022133902A (en) | Information processing device and information processing program | |
| KR20180060360A (en) | Method and Apparatus of providing user-defined UI in administrative management program provided in cloud computing | |
| JP2021128385A (en) | Information processing system, system, and usage restriction method | |
| JP7369389B1 (en) | Data provision system, data provision program and authority setting method | |
| KR20160143912A (en) | Method and apparatus for managing business using text input | |
| JP6241049B2 (en) | Server apparatus, system and program | |
| CN114254239A (en) | Network station configuration method and device, computer equipment and storage medium | |
| WO2022107261A1 (en) | Operation monitoring device, operation monitoring method, and operation monitoring program |
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 |