CN113946406A - Model data processing method and device, electronic equipment and storage medium - Google Patents
Model data processing method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113946406A CN113946406A CN202111197113.1A CN202111197113A CN113946406A CN 113946406 A CN113946406 A CN 113946406A CN 202111197113 A CN202111197113 A CN 202111197113A CN 113946406 A CN113946406 A CN 113946406A
- Authority
- CN
- China
- Prior art keywords
- modeling
- target
- container
- model
- virtual interface
- 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
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45504—Abstract machines for programme code execution, e.g. Java virtual machine [JVM], interpreters, emulators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/60—Software deployment
- G06F8/61—Installation
- G06F8/63—Image based installation; Cloning; Build to order
-
- 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
- G06F9/452—Remote windowing, e.g. X-Window System, desktop virtualisation
-
- 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
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
-
- 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
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
- G06F2009/45562—Creating, deleting, cloning virtual machine instances
Abstract
The embodiment of the application discloses a model data processing method and device, electronic equipment and a storage medium, and is applied to the technical field of model hosting. The method comprises the following steps: when a container creating request sent by first equipment is detected, container configuration data indicated by the container creating request is obtained, a first image file which is matched with the container configuration data is obtained from a modeling image library according to identification information of a modeling tool and identification information of a modeling environment, a target modeling container is created according to the first image file, if a calling instruction for the target modeling container is received, a modeling virtual interface is output through the first equipment, a modeling operation of the first equipment for a display control corresponding to the modeling tool in the modeling virtual interface is responded, a target model indicated by the modeling operation is generated in the target modeling container, and the target model is output in the modeling virtual interface. By adopting the embodiment of the application, the modeling efficiency can be improved. This application relates to blockchain techniques, such as target models can be written to a blockchain.
Description
Technical Field
The application relates to the technical field of model hosting, in particular to a model data processing method and device, electronic equipment and a storage medium.
Background
At present, the model can be built by a modeler through writing scripts in a plurality of modeling tools respectively. However, resources of a plurality of modeling tools are scattered, and may not be communicated, and the operation steps are tedious and time-consuming, so that the model building efficiency is low, and therefore how to simplify the modeling process and improve the modeling efficiency becomes a problem to be solved urgently.
Disclosure of Invention
The embodiment of the application provides a model data processing method and device, electronic equipment and a storage medium, which can effectively simplify a modeling process and improve modeling efficiency.
In one aspect, an embodiment of the present application provides a model data processing method, including:
when a container creation request sent by first equipment is detected, obtaining container configuration data indicated by the container creation request; the container configuration data includes at least identification information of a modeling tool and identification information of a modeling environment;
acquiring a first image file which is adapted from a modeling image library according to the identification information of the modeling tool and the identification information of the modeling environment, and creating a target modeling container according to the first image file; the target modeling container comprises a modeling virtual interface aiming at first equipment, and the modeling virtual interface comprises a display control corresponding to the modeling tool;
if a calling instruction for the target modeling container is received, outputting the modeling virtual interface through the first equipment;
in response to a modeling operation of the first device on a display control corresponding to the modeling tool in the modeling virtual interface, generating a target model indicated by the modeling operation in the target modeling container;
outputting the target model in a modeled virtual interface of the first device.
In one aspect, an embodiment of the present application provides a model data processing apparatus, where the apparatus includes:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring container configuration data indicated by a container creation request when the container creation request sent by first equipment is detected; the container configuration data includes at least identification information of a modeling tool and identification information of a modeling environment;
the creating unit is used for acquiring a first image file which is adapted from a modeling image library according to the identification information of the modeling tool and the identification information of the modeling environment, and creating a target modeling container according to the first image file; the target modeling container comprises a modeling virtual interface aiming at first equipment, and the modeling virtual interface comprises a display control corresponding to the modeling tool;
the output unit is used for outputting the modeling virtual interface through the first equipment if a calling instruction aiming at the target modeling container is received;
a generating unit, configured to generate, in response to a modeling operation of the first device in the modeling virtual interface for a display control corresponding to the modeling tool, a target model indicated by the modeling operation in the target modeling container;
the output unit is further configured to output the target model in a modeling virtual interface of the first device.
In one aspect, an embodiment of the present application provides an electronic device, which includes a processor and a memory, where the memory is used to store a computer program, and the computer program includes program instructions, and the processor is configured to call the program instructions to execute some or all of the steps in the method.
In one aspect, the present application provides a computer-readable storage medium, which stores a computer program, where the computer program includes program instructions, and the program instructions, when executed by a processor, are used to perform some or all of the steps of the above method.
In the embodiment of the application, when a container creation request sent by a first device is detected, container configuration data indicated by the container creation request is obtained, a first image file which is adapted is obtained from a modeling image library according to identification information of a modeling tool and identification information of a modeling environment, a target modeling container is created according to the first image file, if a call instruction for the target modeling container is received, a modeling virtual interface is output through the first device, a target model indicated by the modeling operation is generated in the target modeling container in response to the modeling operation of the first device for a display control corresponding to the modeling tool in the modeling virtual interface, and the target model is output in the modeling virtual interface of the first device. By implementing the method provided by the embodiment of the application, the target modeling container can be created by configuring the container, the modeling virtual interface matched with the target modeling container is generated, the modeling operation aiming at the modeling tools is unified on the modeling virtual interface, the corresponding target model is generated, the needed resources among the modeling tools are communicated, the modeling operation steps are simplified, the modeling process is simplified, and the modeling efficiency is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic diagram of an application architecture according to an embodiment of the present application;
fig. 2 is a schematic flowchart of a model data processing method according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a modeling virtual interface provided by an embodiment of the present application;
fig. 4 is a schematic flowchart of a model data processing method according to an embodiment of the present application;
FIG. 5 is a schematic illustration of a container configuration interface provided by an embodiment of the present application;
fig. 6 is a schematic structural diagram of a model data processing apparatus according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.
The model data processing method provided by the embodiment of the application is realized in electronic equipment, and the electronic equipment can be terminal equipment or a server. The terminal device can be a smart phone, a tablet computer, a notebook computer, a desktop computer and the like. The server may be an independent server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), a big data and artificial intelligence platform, but is not limited thereto. The present application relates to a block chain technology, and an electronic device may write related data, such as identification information of a target interface, or a prediction result for data to be predicted obtained through a target model, into a block chain, so that the electronic device may obtain required information, such as identification information of the target interface, on the block chain.
Referring to fig. 1, fig. 1 is a schematic view of an application architecture provided in an embodiment of the present application, through which a model data processing method provided in the present application can be executed. Specifically, fig. 1 may include an electronic device, a first device, and a second device. The electronic device can receive a container creation request sent by the first device to create a target modeling container and output a corresponding modeling virtual interface to the first device, generate a target model in the target modeling container based on modeling operation of the first device in the modeling virtual interface and output the target model in the first device, and the electronic device can further encapsulate the target model to obtain identification information of the target interface for calling the target model, and the second device can call the target model through the target interface to perform data prediction, that is, when receiving a call request for the target model sent by the second device, the electronic device can call the target interface to enable the target model to process data to be predicted to obtain a prediction result and return the prediction result to the second device. Alternatively, the first device and the second device may be terminal devices, and the first device and the second device are not limited herein.
It should be understood that fig. 1 merely represents an application architecture provided by the present technical solution by way of example, and does not limit the specific architecture of the present technical solution, that is, the present technical solution may also provide other forms of application architectures.
In some embodiments, the electronic device may execute the model data processing method according to actual business requirements to improve modeling efficiency. The technical scheme of the application can be applied to any model construction scene. For example, the electronic device may obtain container configuration data configured in the first device by the target user when detecting a container creation request sent by the first device, construct a target modeling container based on the container configuration data, and output a modeling virtual interface matching the container configuration data, and the subsequent first device may perform modeling operation on the modeling tool in the modeling virtual interface, and the electronic device may generate and output a corresponding target model based on the modeling operation in the target modeling container, and perform the modeling operation uniformly through the provided modeling virtual interface, thereby simplifying the modeling flow.
It should be understood that the foregoing scenarios are only examples, and do not constitute a limitation on application scenarios of the technical solutions provided in the embodiments of the present application, and the technical solutions of the present application may also be applied to other scenarios. For example, as can be known by those skilled in the art, with the evolution of system architecture and the emergence of new service scenarios, the technical solution provided in the embodiments of the present application is also applicable to similar technical problems.
Based on the above description, the present application embodiment proposes a model data processing method, which may be executed by the above-mentioned electronic device. As shown in fig. 2, a flow of the model data processing method according to the embodiment of the present application may include the following steps:
201. when a container creation request sent by the first device is detected, container configuration data indicated by the container creation request is obtained.
Wherein the container configuration data comprises at least identification information of the modeling tool and identification information of the modeling environment. The modeling tool may refer to a tool required in a model building stage, such as a data query tool, a model training tool, and the like, and the modeling environment may refer to a modeling language scenario used in building a model node, such as a Python scenario. The identification information of the modeling tool may be a unique ID or name corresponding to the modeling tool, and the like, and the identification information of the modeling environment may be a unique ID or name corresponding to the modeling environment, and the like.
In some embodiments, the first device may generate corresponding container configuration data based on a container configuration operation of a first user to which the first device belongs, where the first user may be any user that needs model building, and the container configuration data may include identification information of a modeling tool specified by the first user and identification information of a specified modeling environment, the first device may generate a container creation request and send the container creation request to the electronic device when generating the container configuration data, or generate the container creation request by triggering a specified control (e.g., a preconfigured container creation control, etc.) after generating the container configuration data. The electronic device may obtain the container configuration data indicated by the container creation request from data carried by the container creation request, or may obtain storage address information, such as a designated database, of the container configuration data carried by the container creation request, and the electronic device may obtain the corresponding container configuration data according to the storage address information.
202. And acquiring the adapted first image file from the modeling image library according to the identification information of the modeling tool and the identification information of the modeling environment, and creating a target modeling container according to the first image file.
The target modeling container can include a modeling virtual interface for the first device, the modeling virtual interface includes a display control corresponding to the modeling tool, and the first device can trigger the display control corresponding to the modeling tool to perform modeling operation, so that the electronic device generates a target model after receiving the modeling operation.
In one possible embodiment, a plurality of first image files for creating the container are configured in the modeling image library, and each first image file may correspond to one modeling tool or modeling environment. The first image file is provided with a running program of a modeling tool or a running program of a modeling environment. The electronic equipment can acquire a first image file matched with the modeling tool from the modeling image library according to the identification information of the modeling tool, acquire the first image file matched with the modeling environment from the modeling image library according to the identification information of the modeling environment, and acquire the first image file matched with the container configuration data; there may be one or more modeling tools designated by the first user, and accordingly, there may be one or more first image files matching the identification information of the modeling tools.
In some embodiments, the electronic device may create a corresponding target modeling container from the first image file, may perform the construction of the specified model through the target modeling container, and may obtain a corresponding modeling virtual interface when creating the target modeling container. In addition, different first users may correspond to different target modeling containers, based on container configuration operations of the different first users, the first devices corresponding to the different first users may generate different container configuration data, and then the electronic device may create a target modeling container dedicated to each first user, and spatial isolation is implemented between the target modeling containers of each first user, that is, each user may use modeling resources in the electronic device together, but data security and confidentiality when the different users perform model building may be ensured through the spatial isolation. Correspondingly, the target modeling container is matched with the modeling virtual interface, different target modeling containers have different modeling virtual interfaces, and the target modeling container and the modeling virtual interface which are respectively adapted to each first user can be generated through the modeling tools and the modeling environments which are specified by different first users in the corresponding first devices, so that the flexibility and the adaptability of modeling can be improved.
203. And if a calling instruction aiming at the target modeling container is received, outputting a modeling virtual interface through the first equipment.
The modeling virtual interface comprises a display control corresponding to the modeling tool, the modeling virtual interface can be as shown in fig. 3, and the first device can trigger the display control on the modeling virtual interface to perform modeling operation.
In one possible implementation manner, after the electronic device completes creation of the target modeling container according to the first image file, the electronic device outputs creation completion prompt information for the target modeling container and a calling control for the target modeling container at the first device, and when detecting that the calling control is triggered, the first device generates a calling instruction for the target modeling container and sends the calling instruction to the electronic device. When the electronic equipment receives the calling instruction, the display data aiming at the modeling virtual interface is obtained from the target modeling container, and the modeling virtual interface is output in the first equipment based on the display data aiming at the modeling virtual interface. Optionally, the modeling virtual interface may be a cloud desktop displayed when the first device calls the target modeling container, and the first device may implement remote control of the electronic device to construct the target model through the cloud desktop. Alternatively, the modeled virtual interface may be displayed by an object program in the first device, which may be a web program, an application program or an applet, or the like.
204. And in response to the modeling operation of the first device on the display control corresponding to the modeling tool in the modeling virtual interface, generating the target model indicated by the modeling operation in the target modeling container.
In some embodiments, in response to a modeling operation of the first device on a display control corresponding to the modeling tool in the modeling virtual interface, the electronic device may call the corresponding modeling tool in the target modeling container to perform a modeling step indicated by the modeling operation, and then generate a target model indicated by the modeling operation.
For example, the modeling operation of the electronic device in the modeling virtual interface for the modeling tool in response to the first device may be that the modeling tool comprises a data query tool (set to comprise a data asset management platform, a data sandbox platform), a data processing tool (set to be a big data processing platform), a model training tool (set to be a model training platform), thus, (1) the electronic device responds to a login operation of the first device at the data asset management platform, accessing the data asset management platform in the target modeling container, inquiring the storage address of the required data and applying for data inquiry authority, after the storage address and the data query authority are acquired, the electronic device responds to the data query operation, accessing a data sandbox platform in a target modeling container, and inquiring and acquiring training data based on a storage address of required data and application data inquiry authority; (2) the electronic equipment responds to data operation of the first equipment on the big data processing platform, accesses the big data processing platform into a target modeling container, performs data integration, cleaning and other operations on the obtained training data to obtain data derivative labels, and takes the training data and the data derivative labels as target training data, or responds to data uploading operation of the first equipment in a modeling virtual interface, and accesses a local database in the first equipment to obtain the training data or the target training data from the local database; (3) the electronic equipment responds to the training model operation of the first equipment on the model training platform, and the model training platform is accessed into the target modeling container to build and train the model according to the instruction of the training model operation and based on the indicated modeling environment to obtain the target model.
205. The target model is output in a modeled virtual interface of the first device.
In some embodiments, after the electronic device completes the construction of the target model, the target model is output in the modeling virtual interface of the first device, and then a model decision operation, such as a model encapsulation operation, a model analysis operation, or the like, may be performed on the target model. And the target model can be deployed online, so that a second user can call the target model through second equipment to realize data prediction. The second user may be any user that needs to make use of the model.
In this embodiment of the application, when detecting a container creation request sent by a first device, an electronic device may obtain container configuration data indicated by the container creation request, obtain an adapted first image file from a modeling image library according to identification information of a modeling tool and identification information of a modeling environment, create a target modeling container according to the first image file, output a modeling virtual interface through the first device if a call instruction for the target modeling container is received, generate a target model indicated by the modeling operation in the target modeling container in response to a modeling operation of the first device for a display control corresponding to the modeling tool in the modeling virtual interface, and output the target model in the modeling virtual interface of the first device. By implementing the method provided by the embodiment of the application, the target modeling container can be created by configuring the container, the modeling virtual interface matched with the target modeling container is generated, the modeling operation aiming at the modeling tools is unified on the modeling virtual interface, the corresponding target model is generated, the needed resources among the modeling tools are communicated, the modeling operation steps are simplified, the modeling process is simplified, and the modeling efficiency is improved.
Referring to fig. 4, fig. 4 is a flowchart illustrating a method for processing model data according to an embodiment of the present application, where the method can be executed by the above-mentioned electronic device. As shown in fig. 4, the flow of the model data processing method in the embodiment of the present application may include the following steps:
401. when a container creation request sent by the first device is detected, container configuration data indicated by the container creation request is obtained.
In some embodiments, the container configuration data may include mirrored information, such as names, in addition to the identification information of the modeling tools and the identification information of the modeling environment. When the electronic device detects a container configuration request sent by the first device, a container configuration interface is output to the first device, the container configuration interface comprises a plurality of configuration items for configuring the target modeling container, and the first device can configure the target modeling container according to the plurality of configuration items for configuring the target modeling container included in the container configuration interface and generate corresponding container configuration data. The configuration items can comprise a selection control corresponding to the modeling tool and a selection control corresponding to the modeling environment. For example, as shown in fig. 5, fig. 5 is a schematic diagram of a container configuration interface provided in an embodiment of the present application; the first user can select a modeling scene and a modeling tool in the container configuration interface, can also input the name of the configured target modeling container, and generates corresponding container configuration data by triggering the 'generating configuration' control.
402. And acquiring the adapted first image file from the modeling image library according to the identification information of the modeling tool and the identification information of the modeling environment, and creating a target modeling container according to the first image file.
In a possible implementation manner, the electronic device may obtain the first image file corresponding to the modeling tool according to the identification information of the modeling tool, and obtain the first image file corresponding to the modeling environment according to the identification information of the modeling environment, so as to obtain the adapted first image file. The electronic device can create a target modeling container from the adapted first image file, the target modeling container including a modeling virtual interface for the first device.
In some embodiments, the electronic device may acquire the display data of the modeling virtual interface when creating the target modeling container, and may subsequently perform output of the modeling virtual interface based on the display data of the modeling virtual interface. Specifically, the electronic device may obtain initial display data of the modeling virtual interface, obtain modeling tool display data according to identification information of the modeling tool, determine the initial display data and the modeling tool display data as display data of the modeling virtual interface, and encapsulate the display data of the modeling virtual interface in the target modeling container. Optionally, the initial display data represents display data corresponding to interfaces other than the display control corresponding to the modeling tool in the modeling virtual interface, that is, display data corresponding to the initialized modeling virtual interface is understood, the modeling tool display data represents display data of the display control corresponding to the modeling tool, and the initialized modeling virtual interface and the display control corresponding to the modeling tool form a modeling virtual interface corresponding to the target modeling container and used for displaying and outputting in the first device. The initial display data corresponding to different target modeling containers may be the same, and the modeling tool display data corresponding to different target modeling containers may be the same or different.
403. And if a calling instruction aiming at the target modeling container is received, outputting a modeling virtual interface through the first equipment.
In one possible implementation, when the first device detects that the calling control for the target modeling container is triggered, a calling instruction for the target modeling container is generated and sent to the electronic device. When the electronic equipment receives the call instruction, the corresponding target modeling container is obtained according to the instruction of the call instruction, and a modeling virtual interface in the target modeling container is output through the first equipment.
In some embodiments, the electronic device may specifically output the modeling virtual interface through the first device by acquiring display data of the modeling virtual interface from the target modeling container, generating the modeling virtual interface according to the display data of the modeling virtual interface, and sending the modeling virtual interface to the first device, so that the first device displays the modeling virtual interface.
Optionally, after the electronic device obtains the display data of the modeling virtual interface, the display data of the modeling virtual interface is sent to the first device, so that the first device generates the corresponding modeling virtual interface according to the display data of the modeling virtual interface, and displays and outputs the modeling virtual interface.
404. And in response to the modeling operation of the first device on the display control corresponding to the modeling tool in the modeling virtual interface, generating the target model indicated by the modeling operation in the target modeling container.
405. The target model is output in a modeled virtual interface of the first device. The specific implementation of steps 404 and 405 can be referred to in the related description of steps 204 and 205, and will not be described herein again.
406. And responding to a model decision instruction aiming at the target model, and acquiring the adapted second image file from the decision image library.
In one possible embodiment, after the electronic device generates the target model, the electronic device may also perform a model decision operation on the target model, such as a model packaging operation, a model analysis operation, and the like. The decision mirror library is configured with a plurality of second mirror files for performing model decision on the target model in the target modeling container, and each second mirror file may correspond to one model decision type. And the second image file is configured with an operating program of a model decision function corresponding to the model decision operation. The electronic device may obtain a corresponding second image file from the decision image library in response to a model decision instruction for the target model sent by the first device. The first device may generate a corresponding model decision instruction based on a specified decision operation of the first user with respect to the target model.
407. And calling the second mirror image file in the target modeling container to execute the model decision operation indicated by the model decision instruction on the target model to obtain a model operation result aiming at the target model.
In some embodiments, after acquiring the second image file, the electronic device may call the second image file in the target modeling container to perform the model decision operation indicated by the model decision instruction on the target model, and obtain a model operation result for the target model. The model operation result represents result data obtained after a specified model decision operation is performed on the target model.
Optionally, if the model decision instruction includes a model analysis instruction, the adapted second image file may be an image file configured with a model analysis function, the model decision operation may be a model analysis operation, and the result of the model operation may include analysis data for the target model, such as training effect data of the target model. The electronic device may send the analytical data for the target model to the first device, and the first device may combine the analytical data and debug the target model using the modeling tool.
Optionally, if the model decision instruction includes a model encapsulation instruction, the adapted second image file may be an image file configured with a model encapsulation function, the model decision operation may be a model encapsulation operation, and the model operation result may include a target interface used for calling the target model and identification information of the target interface. The electronic device may send the identification information of the target interface to the first device and/or the second device, and the first device and/or the second device may generate a corresponding call request for the target model according to the identification of the target interface, so as to implement data prediction by calling the target model, and may directly implement online deployment of the target model and online provision of the target interface.
In a possible implementation manner, after receiving or querying the identification information of the target interface, the first device and/or the second device may generate a call request for the target model, where the call request includes the identification information of the target interface, for example, the second device may then send the call request carrying the data to be predicted to the electronic device, or send the call request carrying the storage address information of the data to be predicted to the electronic device. Optionally, taking the second device as an example, when the electronic device obtains a call request for the target model sent by the second device, the electronic device directly or indirectly obtains the data to be predicted indicated by the call request and the identification information of the target interface, calls the target interface according to the identification information of the target interface, so as to implement processing on the data to be predicted by calling the target model, obtain a prediction result for the data to be predicted, and returns the prediction result to the second device. Namely, the electronic device can call a target model, input data to be predicted into the target model, and perform data prediction on the data to be predicted by the target model to obtain a corresponding prediction result. For example, the target model is used to generate a corresponding risk value according to user data, the second device may send a call request for the target model and user data of the user to be predicted to the electronic device, after receiving the call request, the electronic device obtains identification information of a target interface of the target model, calls the target interface according to the identification information to call the target model, inputs the user data of the user to be predicted into the target model to perform prediction, obtains a predicted risk value of the user to be predicted, and returns the predicted risk value to the second device.
In this embodiment, the electronic device may, when detecting a container creation request sent by a first device, obtain container configuration data indicated by the container creation request, obtain an adapted first image file from a modeling image library according to identification information of a modeling tool and identification information of a modeling environment, create a target modeling container according to the first image file, output a modeling virtual interface through the first device if a call instruction for the target modeling container is received, generate a target model indicated by the modeling operation in the target modeling container in response to a modeling operation of the first device for a display control corresponding to the modeling tool in the modeling virtual interface, output the target model in the modeling virtual interface of the first device, and obtain an adapted second image file from the decision image library in response to a model decision instruction for the target model, and calling a second image file in the target modeling container to execute the model decision operation indicated by the model decision instruction on the target model to obtain a model operation result aiming at the target model. By implementing the method provided by the embodiment of the application, the target modeling container can be created by configuring the container, the modeling virtual interface matched with the target modeling container is generated, the modeling operation aiming at the modeling tools is unified on the modeling virtual interface, the corresponding target model is generated, the needed resources among the modeling tools are communicated, the modeling operation steps are simplified, the modeling process is simplified, and the modeling efficiency is improved.
Referring to fig. 6, fig. 6 is a schematic structural diagram of a model data processing apparatus provided in the present application. It should be noted that the model data processing apparatus shown in fig. 6 is used for executing the method of the embodiment shown in fig. 2 and 4 of the present application, and for convenience of description, only the portion related to the embodiment of the present application is shown, and details of the specific technology are not disclosed, and reference is made to the embodiment shown in fig. 2 and 4 of the present application. The model data processing apparatus 600 may include: an acquisition unit 601, a creation unit 602, an output unit 603, and a generation unit 604. Wherein:
an obtaining unit 601, configured to, when a container creation request sent by a first device is detected, obtain container configuration data indicated by the container creation request; the container configuration data includes at least identification information of a modeling tool and identification information of a modeling environment;
a creating unit 602, configured to obtain an adapted first image file from a modeling image library according to the identification information of the modeling tool and the identification information of the modeling environment, and create a target modeling container according to the first image file; the target modeling container comprises a modeling virtual interface aiming at first equipment, and the modeling virtual interface comprises a display control corresponding to the modeling tool;
an output unit 603, configured to output the modeling virtual interface through the first device if a call instruction for the target modeling container is received;
a generating unit 604, configured to generate, in response to a modeling operation of the first device in the modeling virtual interface for a display control corresponding to the modeling tool, a target model indicated by the modeling operation in the target modeling container;
the output unit 603 is further configured to output the target model in a modeling virtual interface of the first device.
In a possible implementation, the creating unit 602 is further configured to:
acquiring initial display data of the modeling virtual interface;
acquiring modeling tool display data according to the identification information of the modeling tool; the modeling tool display data represents display data of a display control corresponding to the modeling tool;
and determining the initial display data and the modeling tool display data as the display data of the modeling virtual interface, and packaging the display data of the modeling virtual interface in the target modeling container.
In a possible implementation, the output unit 603, when configured to output the modeled virtual interface through the first device, is specifically configured to:
acquiring display data of the modeling virtual interface from the target modeling container;
and generating the modeling virtual interface according to the display data of the modeling virtual interface, and sending the modeling virtual interface to the first equipment so that the first equipment displays the modeling virtual interface.
In a possible implementation, the output unit 603 is further configured to:
responding to a model decision instruction aiming at the target model, and acquiring an adaptive second image file from a decision image library;
and calling the second image file in the target modeling container to execute the model decision operation indicated by the model decision instruction on the target model to obtain a model operation result aiming at the target model.
In a possible implementation manner, if the model decision instruction includes a model encapsulation instruction, the adapted second image file is an image file configured with a model encapsulation function, the model decision operation is a model encapsulation operation, and the model operation result includes identification information of a target interface used for calling the target model.
In a possible implementation, the output unit 603 is further configured to:
when a calling request for the target model sent by second equipment is obtained, obtaining data to be predicted indicated by the calling request and identification information of the target interface;
calling the target interface according to the identification information of the target interface so as to call the target model to process the data to be predicted and obtain a prediction result aiming at the data to be predicted;
and returning the prediction result to the second equipment.
In a possible implementation, the obtaining unit 601 is further configured to:
when a container configuration request sent by the first device is detected, outputting a container configuration interface to the first device, so that the first device performs configuration of a target modeling container according to a plurality of configuration items for configuring the target modeling container, wherein the configuration items are included in the container configuration interface, and generating container configuration data; the plurality of configuration items comprise selection controls corresponding to the modeling tools and selection controls corresponding to the modeling environments.
In the embodiment of the application, when a container creation request sent by a first device is detected, an obtaining unit obtains container configuration data indicated by the container creation request; the creating unit acquires a first image file which is adapted from a modeling image library according to the identification information of the modeling tool and the identification information of the modeling environment, and creates a target modeling container according to the first image file; if receiving a calling instruction aiming at the target modeling container, the output unit outputs a modeling virtual interface through first equipment; the generation unit responds to the modeling operation of the first equipment on a display control corresponding to the modeling tool in the modeling virtual interface, and generates a target model indicated by the modeling operation in a target modeling container; the output unit outputs the target model in a modeling virtual interface of the first device. By implementing the device provided by the embodiment of the application, the target modeling container can be created by configuring the container, the modeling virtual interface matched with the target modeling container is generated, the modeling operation aiming at the modeling tools is unified on the modeling virtual interface, the corresponding target model is generated, the needed resources among the modeling tools are communicated, the modeling operation steps are simplified, the modeling process is simplified, and the modeling efficiency is improved.
Each functional module in the embodiments of the present application may be integrated into one module, or each module may exist alone physically, or two or more modules are integrated into one module. The integrated module may be implemented in a form of hardware, or may be implemented in a form of software functional module, which is not limited in this application.
Referring to fig. 7, fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. As shown in fig. 7, the electronic device 700 includes: at least one processor 701, a memory 702. Optionally, the electronic device may further include a network interface. The processor 701, the memory 702 and the network interface may interact with each other to exchange data, the network interface is controlled by the processor 701 to transmit and receive messages, the memory 702 is used to store a computer program, the computer program includes program instructions, and the processor 701 is used to execute the program instructions stored in the memory 702. Wherein, the processor 701 is configured to call the program instruction to execute the above method.
The memory 702 may include volatile memory (volatile memory), such as random-access memory (RAM); the memory 702 may also include a non-volatile memory (non-volatile memory), such as a flash memory (flash memory), a solid-state drive (SSD), etc.; the memory 702 may also comprise a combination of memories of the above-mentioned kinds.
The processor 701 may be a Central Processing Unit (CPU). In one embodiment, the processor 701 may also be a Graphics Processing Unit (GPU). The processor 701 may also be a combination of a CPU and a GPU.
In one possible embodiment, the memory 702 is used for storing program instructions, and the processor 701 may call the program instructions to perform the following steps:
when a container creation request sent by first equipment is detected, obtaining container configuration data indicated by the container creation request; the container configuration data includes at least identification information of a modeling tool and identification information of a modeling environment;
acquiring a first image file which is adapted from a modeling image library according to the identification information of the modeling tool and the identification information of the modeling environment, and creating a target modeling container according to the first image file; the target modeling container comprises a modeling virtual interface aiming at first equipment, and the modeling virtual interface comprises a display control corresponding to the modeling tool;
if a calling instruction for the target modeling container is received, outputting the modeling virtual interface through the first equipment;
in response to a modeling operation of the first device on a display control corresponding to the modeling tool in the modeling virtual interface, generating a target model indicated by the modeling operation in the target modeling container;
outputting the target model in a modeled virtual interface of the first device.
In one possible implementation, the processor 701 is further configured to:
acquiring initial display data of the modeling virtual interface;
acquiring modeling tool display data according to the identification information of the modeling tool; the modeling tool display data represents display data of a display control corresponding to the modeling tool;
and determining the initial display data and the modeling tool display data as the display data of the modeling virtual interface, and packaging the display data of the modeling virtual interface in the target modeling container.
In a possible implementation, the processor 701, when configured to output the modeled virtual interface through the first device, is specifically configured to:
acquiring display data of the modeling virtual interface from the target modeling container;
and generating the modeling virtual interface according to the display data of the modeling virtual interface, and sending the modeling virtual interface to the first equipment so that the first equipment displays the modeling virtual interface.
In one possible implementation, the processor 701 is further configured to:
responding to a model decision instruction aiming at the target model, and acquiring an adaptive second image file from a decision image library;
and calling the second image file in the target modeling container to execute the model decision operation indicated by the model decision instruction on the target model to obtain a model operation result aiming at the target model.
In a possible implementation manner, if the model decision instruction includes a model encapsulation instruction, the adapted second image file is an image file configured with a model encapsulation function, the model decision operation is a model encapsulation operation, and the model operation result includes identification information of a target interface used for calling the target model.
In one possible implementation, the processor 701 is further configured to:
when a calling request for the target model sent by second equipment is obtained, obtaining data to be predicted indicated by the calling request and identification information of the target interface;
calling the target interface according to the identification information of the target interface so as to call the target model to process the data to be predicted and obtain a prediction result aiming at the data to be predicted;
and returning the prediction result to the second equipment.
In one possible implementation, the processor 701 is further configured to:
when a container configuration request sent by the first device is detected, outputting a container configuration interface to the first device, so that the first device performs configuration of a target modeling container according to a plurality of configuration items for configuring the target modeling container, wherein the configuration items are included in the container configuration interface, and generating container configuration data; the plurality of configuration items comprise selection controls corresponding to the modeling tools and selection controls corresponding to the modeling environments.
In a specific implementation, the apparatus, the processor 701, the memory 702, and the like described in this embodiment may perform the implementation described in the above method embodiment, and may also perform the implementation described in this embodiment, which is not described herein again.
Also provided in embodiments of the present application is a computer (readable) storage medium storing a computer program comprising program instructions that, when executed by a processor, cause the processor to perform some or all of the steps performed in the above-described method embodiments. Alternatively, the computer storage media may be volatile or nonvolatile. The computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism and an encryption algorithm. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
Embodiments of the present application provide a computer program product, which may include a computer program, and when the computer program is executed by a processor, part or all of the steps in the method may be implemented, which is not described herein again.
Reference herein to "a plurality" means two or more. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.
It will be understood by those skilled in the art that all or part of the processes of the methods of the above embodiments may be implemented by a computer program, which may be stored in a computer storage medium, and the computer storage medium may be a computer readable storage medium, and when executed, the programs may include the processes of the above embodiments of the methods. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
While the present disclosure has been described with reference to particular embodiments, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the present disclosure.
Claims (10)
1. A method of model data processing, the method comprising:
when a container creation request sent by first equipment is detected, obtaining container configuration data indicated by the container creation request; the container configuration data includes at least identification information of a modeling tool and identification information of a modeling environment;
acquiring a first image file which is adapted from a modeling image library according to the identification information of the modeling tool and the identification information of the modeling environment, and creating a target modeling container according to the first image file; the target modeling container comprises a modeling virtual interface aiming at first equipment, and the modeling virtual interface comprises a display control corresponding to the modeling tool;
if a calling instruction for the target modeling container is received, outputting the modeling virtual interface through the first equipment;
in response to a modeling operation of the first device on a display control corresponding to the modeling tool in the modeling virtual interface, generating a target model indicated by the modeling operation in the target modeling container;
outputting the target model in a modeled virtual interface of the first device.
2. The method of claim 1, further comprising:
acquiring initial display data of the modeling virtual interface;
acquiring modeling tool display data according to the identification information of the modeling tool; the modeling tool display data represents display data of a display control corresponding to the modeling tool;
and determining the initial display data and the modeling tool display data as the display data of the modeling virtual interface, and packaging the display data of the modeling virtual interface in the target modeling container.
3. The method of claim 2, wherein said outputting, by said first device, said modeled virtual interface comprises:
acquiring display data of the modeling virtual interface from the target modeling container;
and generating the modeling virtual interface according to the display data of the modeling virtual interface, and sending the modeling virtual interface to the first equipment so that the first equipment displays the modeling virtual interface.
4. The method of claim 1, further comprising:
responding to a model decision instruction aiming at the target model, and acquiring an adaptive second image file from a decision image library;
and calling the second image file in the target modeling container to execute the model decision operation indicated by the model decision instruction on the target model to obtain a model operation result aiming at the target model.
5. The method according to claim 4, wherein if the model decision instruction includes a model encapsulation instruction, the adapted second image file is an image file configured with a model encapsulation function, the model decision operation is a model encapsulation operation, and the result of the model operation includes identification information of a target interface for calling the target model.
6. The method of claim 5, further comprising:
when a calling request for the target model sent by second equipment is obtained, obtaining data to be predicted indicated by the calling request and identification information of the target interface;
calling the target interface according to the identification information of the target interface so as to call the target model to process the data to be predicted and obtain a prediction result aiming at the data to be predicted;
and returning the prediction result to the second equipment.
7. The method of claim 1, further comprising:
when a container configuration request sent by the first device is detected, outputting a container configuration interface to the first device, so that the first device performs configuration of a target modeling container according to a plurality of configuration items for configuring the target modeling container, wherein the configuration items are included in the container configuration interface, and generating container configuration data; the plurality of configuration items comprise selection controls corresponding to the modeling tools and selection controls corresponding to the modeling environments.
8. A model data processing apparatus, characterized in that the apparatus comprises:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring container configuration data indicated by a container creation request when the container creation request sent by first equipment is detected; the container configuration data includes at least identification information of a modeling tool and identification information of a modeling environment;
the creating unit is used for acquiring a first image file which is adapted from a modeling image library according to the identification information of the modeling tool and the identification information of the modeling environment, and creating a target modeling container according to the first image file; the target modeling container comprises a modeling virtual interface aiming at first equipment, and the modeling virtual interface comprises a display control corresponding to the modeling tool;
the output unit is used for outputting the modeling virtual interface through the first equipment if a calling instruction aiming at the target modeling container is received;
a generating unit, configured to generate, in response to a modeling operation of the first device in the modeling virtual interface for a display control corresponding to the modeling tool, a target model indicated by the modeling operation in the target modeling container;
the output unit is further configured to output the target model in a modeling virtual interface of the first device.
9. An electronic device comprising a processor and a memory, wherein the memory is configured to store a computer program comprising program instructions, and wherein the processor is configured to invoke the program instructions to perform the method of any of claims 1-7.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program comprising program instructions that, when executed by a processor, cause the processor to carry out the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111197113.1A CN113946406A (en) | 2021-10-14 | 2021-10-14 | Model data processing method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111197113.1A CN113946406A (en) | 2021-10-14 | 2021-10-14 | Model data processing method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113946406A true CN113946406A (en) | 2022-01-18 |
Family
ID=79330428
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111197113.1A Pending CN113946406A (en) | 2021-10-14 | 2021-10-14 | Model data processing method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113946406A (en) |
-
2021
- 2021-10-14 CN CN202111197113.1A patent/CN113946406A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TWI757743B (en) | Mini program generation method and device | |
| CN109104467B (en) | Development environment construction method and device, platform system and storage medium | |
| CN110249307A (en) | System and method for executing primary contract on block chain | |
| CN111901294A (en) | Method for constructing online machine learning project and machine learning system | |
| US11422785B2 (en) | Container orchestration framework | |
| US20170048331A1 (en) | Platform runtime abstraction | |
| US9210098B2 (en) | Enhanced command selection in a networked computing environment | |
| CN112634047A (en) | Foreign exchange transaction simulation test method and device, computer equipment and storage medium | |
| US20180316572A1 (en) | Cloud lifecycle managment | |
| US7428486B1 (en) | System and method for generating process simulation parameters | |
| CN113535335B (en) | Virtual resource allocation method and device based on block chain and electronic equipment | |
| CN112991064B (en) | Service processing method, device, computer equipment and storage medium | |
| CN113946406A (en) | Model data processing method and device, electronic equipment and storage medium | |
| CN116204307A (en) | Federal learning method and federal learning system compatible with different computing frameworks | |
| Um et al. | Virtualized oneM2M system architecture in smart factory environments | |
| CN115328611A (en) | Virtual machine management method, device, server and readable storage medium | |
| CN114327941A (en) | Service providing method and device | |
| CN114090188A (en) | Method for realizing independent multi-user system based on android system virtualization and application | |
| CN113704120A (en) | Data transmission method, device, equipment and storage medium | |
| US20200034119A1 (en) | Translating User Inputs Into Discretely Functional Styled Standalone Web and Mobile Software Features | |
| CN117056028B (en) | Robot simulation platform building method and device, computer equipment and storage medium | |
| CN115242658B (en) | Open system access method, device, computer equipment and storage medium | |
| Gharehchopogh et al. | A new approach for inter process communication with hybrid of message passing mechanism and event based software architecture | |
| US20220270122A1 (en) | Information delivery method, apparatus, and device, and computer-readable storage medium | |
| CN110321335B (en) | Modeling data downloading method and device, electronic equipment and computer storage medium |
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 |