CN111931942A

CN111931942A - Method and device for providing machine learning application, electronic equipment and storage medium

Info

Publication number: CN111931942A
Application number: CN202010315660.4A
Authority: CN
Inventors: 徐昀; 唐继正; 李琦; 张世健
Original assignee: 4Paradigm Beijing Technology Co Ltd
Current assignee: 4Paradigm Beijing Technology Co Ltd
Priority date: 2020-04-20
Filing date: 2020-04-20
Publication date: 2020-11-13
Also published as: WO2021213234A1

Abstract

The embodiment of the invention discloses a method and a device for providing machine learning application, electronic equipment and a storage medium, relates to the technical field of artificial intelligence, and is convenient for a user to master the operation of a machine learning product quickly. The method comprises the following steps: displaying a learning circle image at a first display position on a display screen; receiving configuration information which is input by a user through a configuration operation inlet and corresponds to the step; moving the learning circle image from a first display position to a second display position on the display screen, wherein at least part of the learning circle image is displayed in the display screen at the second display position, and identification information of the machine learning step is provided in at least part of the displayed learning circle image; and sequentially executing each step of machine learning based on the configuration information corresponding to the step to acquire and provide the machine learning application. The invention is suitable for machine learning products.

Description

Method and device for providing machine learning application, electronic equipment and storage medium

Technical Field

The invention relates to the technical field of artificial intelligence, in particular to a method and a device for providing machine learning application, electronic equipment and a storage medium.

Background

Machine learning is increasingly applied to various industries, but machine learning is also a field requiring strong professional skills. One machine learning application is from problem definition, modeling and then model online service, and the whole process is very complex.

For users of machine learning products, especially some novice users with limited machine learning knowledge, when using specific machine learning products, because of not knowing the machine learning process, the cognition and operation thresholds of the novice users are increased, and the operation process of the machine learning products is difficult to master quickly.

Disclosure of Invention

In view of this, embodiments of the present invention provide a method and an apparatus for providing a machine learning application, an electronic device, and a storage medium, which are convenient for a user to quickly master operations of a machine learning product.

In a first aspect, an embodiment of the present application provides a method for providing a machine learning application, including: displaying a learning circle image at a first display position on a display screen, wherein the learning circle image provides identification information of a step of machine learning, and a configuration operation inlet corresponding to the step is displayed on the side of the learning circle image; receiving configuration information which is input by a user through the configuration operation inlet and corresponds to the step; if a learning circle starting instruction sent by a user is received, moving the learning circle image from a first display position to a second display position on the display screen, wherein at least part of the learning circle image is displayed in the display screen at the second display position, and the displayed at least part of the learning circle image is provided with identification information of the step of machine learning; and sequentially executing each step of machine learning based on the configuration information corresponding to the step to acquire and provide the machine learning application.

According to a specific implementation manner of the embodiment of the application, the learning circle image at the first display position is further provided with an execution relationship between the steps, and/or the learning circle image at the second display position is further provided with an execution relationship between at least some of the steps.

According to a specific implementation manner of the embodiment of the present application, the step of machine learning includes: the method comprises the steps of collecting behavior data, collecting feedback data, training a machine learning model and applying the machine learning model; the identification information of the machine-learned step includes a step name and/or a step icon.

According to a specific implementation manner of the embodiment of the application, the step name of collecting behavior data, the step name of collecting feedback data, the step name of training the machine learning model, and the step name of applying the machine learning model are behavior, feedback, learning, and application in sequence.

According to a specific implementation manner of the embodiment of the present application, the displaying the learning circle image at the first display position on the display screen includes: displaying identification information of each step of machine learning at a first display position on a display screen, and arranging the identification information of each step of machine learning from beginning to end according to the sequence of execution of each step of machine learning to form a looped image; or displaying the identification information of each step of machine learning at a first display position on a display screen, and correspondingly arranging the identification information of each step of machine learning in the first quadrant to the fourth quadrant according to the sequence of execution of the steps of machine learning to form a four-quadrant image.

According to a specific implementation manner of the embodiment of the present application, the method further includes: and when a user inputs configuration information through a configuration operation entrance of a first step in the steps, highlighting identification information of the first step in the learning circle image and/or highlighting the configuration operation entrance of the first step.

According to a specific implementation manner of the embodiment of the present application, the displaying the image of the learning circle at the first display position on the display screen includes: and if a learning circle establishing instruction sent by a user is received, displaying a learning circle image at a first display position of the display screen.

According to a specific implementation manner of the embodiment of the present application, if a learning circle starting instruction issued by a user is received, moving the learning circle image from a first display position to a second display position on the display screen includes: and if a learning circle starting instruction sent by a user is received, initializing machine learning resources, and after the initialization is completed, moving the learning circle image from a first display position to a second display position on the display screen.

According to a specific implementation manner of the embodiment of the application, at the second display position, a partial image of the learning circle image is displayed on the display screen; wherein the identification information of the step of machine learning is displayed in a partial image of the learning circle image displayed in a display screen.

According to a specific implementation manner of the embodiment of the application, the identification information of the steps of the machine learning is arranged end to end according to the execution sequence of the steps of the machine learning, and is displayed in the partial image of the learning circle image displayed in the display screen.

According to a specific implementation manner of the embodiment of the present application, the sequentially executing each step of the machine learning based on the configuration information corresponding to the step to obtain and provide the machine learning application includes: collecting behavior data based on configuration information corresponding to the step of collecting behavior data; collecting feedback data based on configuration information corresponding to the step of collecting feedback data; performing machine learning training by taking the collected behavior data and the feedback data as training data based on configuration information corresponding to the step of training the machine learning model to obtain the machine learning model; and applying the obtained machine learning model on line.

According to a specific implementation manner of the embodiment of the present application, while the steps of machine learning are sequentially executed, the method further includes: and highlighting the identification information of the step corresponding to the currently executed step of machine learning in the learning circle image.

According to a specific implementation manner of the embodiment of the present application, after applying the obtained machine learning model online, the method further includes: collecting new behavior data based on configuration information corresponding to the step of collecting behavior data; collecting new feedback data based on configuration information corresponding to the step of collecting feedback data; and self-learning is carried out based on the new behavior data and the new feedback data, and the obtained machine learning model is updated or replaced.

According to a specific implementation manner of the embodiment of the present application, the method further includes: in a second step of the steps of performing the machine learning, current execution state information of the second step is displayed on a side portion of a partial image of the learning circle image.

According to a specific implementation manner of the embodiment of the present application, the learning circle image at the first display position further provides machine learning status prompt information, and the method further includes: when a user inputs configuration information through the configuration operation entrance and/or after a learning circle starting instruction sent by the user is received, before the learning circle image moves from a first display position to a second display position, machine learning state prompt information is displayed in the learning circle image in a first preset mode; and/or machine learning state prompt information is further provided in the learning circle image of the second display position, and the method further comprises the following steps: and displaying machine learning state prompt information corresponding to the steps in a second preset mode in the learning circle image while sequentially executing the machine learning steps.

In a second aspect, an embodiment of the present application further provides an apparatus for providing a machine learning application, including: the device comprises a first display module, a second display module and a display module, wherein the first display module is used for displaying a learning circle image at a first display position on a display screen, the learning circle image is provided with identification information of a step of machine learning, and a configuration operation inlet corresponding to the step is displayed on the side part of the learning circle image; the configuration module is used for receiving the configuration information which is input by the user through the configuration operation entrance and corresponds to the step; the second display module is used for moving the learning circle image from a first display position to a second display position on the display screen if a learning circle starting instruction sent by a user is received, wherein at least part of the learning circle image is displayed in the display screen at the second display position, and the displayed at least part of the learning circle image is provided with identification information of the step of machine learning; and the execution module is used for sequentially executing each step of machine learning based on the configuration information corresponding to the step so as to obtain and provide the machine learning application.

According to a specific implementation manner of the embodiment of the present application, the first display module is specifically configured to: displaying identification information of each step of machine learning at a first display position on a display screen, and arranging the identification information of each step of machine learning from beginning to end according to the sequence of execution of each step of machine learning to form a looped image; or displaying the identification information of each step of machine learning at a first display position on a display screen, and correspondingly arranging the identification information of each step of machine learning in the first quadrant to the fourth quadrant according to the sequence of execution of the steps of machine learning to form a four-quadrant image.

According to a specific implementation manner of the embodiment of the present application, the first display module includes: and the first highlighting submodule is used for highlighting the identification information of the first step in the learning circle image and/or highlighting the configuration operation entrance of the first step when the user inputs configuration information through the configuration operation entrance of the first step in the steps.

According to a specific implementation manner of the embodiment of the present application, the first display module includes: the first instruction receiving submodule is used for receiving a learning circle creating instruction sent by a user; and the display sub-module is used for displaying the learning circle image at the first display position of the display screen if the instruction receiving sub-module receives a learning circle establishing instruction issued by a user.

According to a specific implementation manner of the embodiment of the present application, the second display module includes: the second instruction receiving submodule is used for receiving a learning circle starting instruction sent by a user; and the initialization sub-module is used for initializing machine learning resources if the second instruction receiving sub-module receives a learning circle starting instruction issued by a user, and moving the learning circle image from a first display position to a second display position on the display screen after the initialization is completed.

According to a specific implementation manner of the embodiment of the present application, the execution module includes: a first execution sub-module for collecting behavior data based on configuration information corresponding to the step of collecting behavior data; a second execution sub-module for collecting the feedback data based on the configuration information corresponding to the step of collecting the feedback data; the third execution submodule is used for performing machine learning training by taking the collected behavior data and the collected feedback data as training data based on configuration information corresponding to the step of training the machine learning model to obtain the machine learning model; and the fourth execution submodule is used for applying the obtained machine learning model on line.

According to a specific implementation manner of the embodiment of the present application, the execution module includes: and the second highlighting submodule is used for highlighting the identification information of the step corresponding to the currently executed machine learning step in the learning circle image while the execution module sequentially executes the machine learning steps.

According to a specific implementation manner of the embodiment of the present application, the apparatus for providing a machine learning application further includes: a self-learning module for collecting new behavior data based on configuration information corresponding to the step of collecting behavior data after the execution module applies the obtained machine learning model online; collecting new feedback data based on configuration information corresponding to the step of collecting feedback data; and self-learning is carried out based on the new behavior data and the new feedback data, and the obtained machine learning model is updated or replaced.

According to a specific implementation manner of the embodiment of the present application, the second display module is further configured to: when the execution module executes a second step of the steps of the machine learning, current execution state information of the second step is displayed on a side portion of a partial image of the learning circle image.

According to a specific implementation manner of the embodiment of the present application, the device for providing a machine learning application further includes a status information prompt module, configured to: when a user inputs configuration information through the configuration operation entrance and/or after a learning circle starting instruction sent by the user is received, before the learning circle image moves from a first display position to a second display position, machine learning state prompt information is displayed in the learning circle image in a first preset mode; and/or displaying machine learning state prompt information corresponding to the steps in a second preset mode in the learning circle image while the execution module sequentially executes the steps of the machine learning.

In a third aspect, an embodiment of the present application further provides an electronic device, where the electronic device includes: the device comprises a shell, a processor, a memory, a circuit board and a power circuit, wherein the circuit board is arranged in a space enclosed by the shell, and the processor and the memory are arranged on the circuit board; a power supply circuit for supplying power to each circuit or device of the electronic apparatus; the memory is used for storing executable program codes; the processor is configured to execute the method for providing the machine learning application according to any of the foregoing embodiments by reading the executable program code stored in the memory.

In a fourth aspect, the present application further provides a computer-readable storage medium, where one or more programs are stored, and the one or more programs are executable by one or more processors to implement the method for providing a machine learning application according to any one of the foregoing embodiments.

In a fifth aspect, an embodiment of the present application further provides an application program, where the application program is executed to implement the method provided in any embodiment of the present invention.

The method, the device, the electronic equipment and the storage medium for providing the machine learning application provided by the embodiment of the application divide the machine learning process into different steps based on the Kuber learning circle theory in education, and display different step identifications in the learning circle image. The learning circle image with the identification information of the machine learning step is displayed at a first display position on a display screen, after corresponding configuration is carried out through a configuration operation inlet, if a learning circle starting instruction is received, the learning circle image moves from the first display position to a second display position on the display screen, and the identification information of the machine learning step is still provided in the learning circle image at the second display position; and on the basis of the configuration information corresponding to the steps, sequentially executing the steps of the machine learning, acquiring a machine learning model and applying the acquired machine learning model on line. The learning ring image is always displayed (at least partially displayed) in an interface displayed by a display screen in the change process from the first display position to the second display position, and identification information of the step of machine learning is always provided in the learning ring image, so that a user can know the learning ring and use the learning ring, and the machine learning process can be understood more intuitively through the change process of the learning ring image, and the operation mode of a machine learning product can be mastered more quickly.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

Fig. 1 is a flowchart illustrating a method for providing a machine learning application according to an embodiment of the present disclosure;

FIG. 2 illustrates an interface for displaying a learning circle image for the first time on a display screen in one embodiment;

FIG. 3 shows the process of the learning circle image moving left from the center of the interface after the user finishes the introduction of the guidance information;

FIG. 4 illustrates a learning circle image displayed at a first display position of a display screen in one embodiment;

FIG. 5 illustrates the process of moving the image of the learning circle from the first display position to the second display position on the display screen when the learning circle is activated;

FIG. 6 is a schematic diagram showing the learning circle image after moving from the first display position to the second display position;

FIG. 7 shows the state after the learning loop is on-line, the state of the learning loop is updated to "in-service";

FIG. 8 is a flowchart illustrating a method for providing a machine learning application according to another embodiment of the present disclosure; .

Fig. 9 is a block diagram of a providing apparatus of a machine learning application according to an embodiment of the present application;

fig. 10 is a block diagram of a providing apparatus of a machine learning application according to another embodiment of the present application;

fig. 11 is a schematic structural diagram of an embodiment of an electronic device according to the present application.

Detailed Description

Embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the described embodiments are only some embodiments of the invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

The embodiment of the application provides a method and a device for providing machine learning application, which show the steps of machine learning to a user in the form of learning circles, and are convenient for the user to master the operation of a machine learning product quickly.

The machine learning product provided by the embodiment of the invention can be an artificial intelligence AI application development tool, and a user can construct a machine learning model by using the product, directly provide the constructed machine learning model for the user, and directly deploy the model for online application according to the user requirements.

Fig. 1 is a flowchart illustrating a method for providing a machine learning application according to an embodiment of the present disclosure; referring to fig. 1, the method for providing a machine learning application of the present embodiment includes steps S100 to S106:

and S100, displaying the learning circle image at a first display position on the display screen.

In a learning circle image displayed at a first display position on a display screen, identification information of a step of machine learning is provided, and a configuration operation entry corresponding to the step is displayed on a side portion of the learning circle image.

The learning circle in the application is based on the Kuber learning circle theory in education, the process of machine learning refers to the learning process of people, and is defined as the learning circle, specifically, the process of machine learning, namely training of a machine learning model (also called an artificial intelligence model) is divided into different steps, and the steps are in endless loop machine learning forms or styles.

The learning circle image is an image of a learning circle presented based on the principle of the learning circle, and may also be referred to as a learning circle pattern, a learning graph pattern, or the like. Specifically, the learning circle image may include identification information of each step of machine learning, and may also embody an execution relationship such as a sequence and a cycle between the steps.

The form of the learning circle image may be various. In order to enable a user to understand more intuitively and operate more conveniently, in one example, the form of the learning circle image may be specifically presented as a circle form, and specifically, the identification information of each step of machine learning may be arranged end to end according to the sequential execution order between each step of machine learning to form a circle image (or referred to as a circle form). The step identification information of each step of machine learning may be arranged in a fan shape on the image of the circle.

The form of the learning circle image is not limited to the form of the circle, and in another example, the identification information of each step of machine learning may be correspondingly arranged in the first quadrant to the fourth quadrant according to the sequential execution order among the steps of machine learning to form the image of the four quadrants. In still another example, the identification information of the machine-learned steps may be arranged in a curve or arc shape according to the execution sequence between the machine-learned steps, and so on.

The step of learning machine learning provided in the circle image may include: the method comprises the steps of collecting behavior data, collecting feedback data, training a machine learning model and applying the machine learning model.

The behavior data refers to historical behavior data, and each piece of behavior data corresponds to one historical 'behavior'. For example, in a basketball game, shooting is the "behavior", and a piece of behavior data represents a historical shooting in a past basketball game. Data that may be used to describe the shooting act, such as "shot fighter, pose, position, longitude, latitude, opponent, attack, distance from basket, time remaining, team battle. "department, jump shot, tripartite ball position, 33.7693, -118.1798, pettson (opponent), pelton (attack), 28 feet, 1 second, pioneer (battalion) was.

Feedback data, which is "feedback" on historical behavior, represents the results produced by the behavior data. In the game of basketball, the result of a pitch is a hit or a miss. When the ball is thrown, the feedback data is a "hit".

The machine learning model is trained by taking a large amount of collected behavior data and feedback quantity as training data and performing supervised machine learning to obtain the machine learning model.

And the application of the machine learning model is to apply the trained machine learning model to a business system for prediction to obtain a prediction result.

In the learning circle image, the identification information can be presented in various ways such as graphics and characters. The identification information of the step of machine learning may specifically include a step name and/or a step icon. In one example, the identification information is a machine learning step name, such as a chinese name or an english name; in another example, the identification information is a step icon for machine learning, such as an arrow, a symbol, etc., and different steps can be distinguished and represented by icons of different shapes or different colors; in yet another example, the identifying information is a combination of a machine-learned step name and a step icon.

As for the step name of machine learning, in one example, the step name of collecting behavior data is "behavior", the step name of collecting feedback data is "feedback", the step name of training a machine learning model is "learning", and the step name of applying a machine learning model is "application".

The display screen for displaying the learning circle image can be a display screen of a desktop computer (commonly known as a desktop computer), a notebook computer or a tablet computer, can also be a display screen of a server, and can also be a display screen of industry-specific computing equipment. The display screen may be a touch screen or a non-touch screen.

The first display position on the display screen may be a central display area of the display screen or may be another display area which is offset from the central display area by a certain distance.

The display of the learning circle image at the first display position on the display screen may be triggered by a user. In one example, the user may create the learning circle image by clicking a "create learning circle" button in an operation interface displayed on the display screen, i.e., initiate display of the learning circle image at a first display position on the display screen. Specifically, the displaying the learning circle image at the first display position on the display screen may include: if the user issues (for example, by clicking a "create learning circle" button) a learning circle creation instruction, the electronic device displays a learning circle image at a first display position of a display screen of the electronic device after receiving the learning circle creation instruction issued by the user.

When the learning circle image is displayed on the display screen of the electronic equipment for the first time (when a user enters the display interface for the first time), the guide information related to the learning circle can be automatically played in the interface displayed on the display screen, and the guide information can comprise information such as the flow and basic concept of the learning circle, so that the user can understand and master the operation method of the learning circle quickly.

When the learning circle image is displayed on the display screen of the electronic equipment for the first time, the learning circle image is preferentially displayed in the central display area on the display screen, so that the learning circle image can be used as a core focus in an interface, and a user can understand and remember the learning circle image better. Fig. 2 illustrates an interface for displaying the learning circle image for the first time on the display screen in an embodiment.

After the guiding message is automatically played, the learning circle image can be moved to a predetermined direction (such as left) from the first display position until the learning circle image is moved to the first display position of the display screen. Fig. 3 shows the process of moving the learning circle image from the center of the interface to the left after the user finishes the introduction of the guidance information.

Fig. 4 shows a learning circle image displayed at the first display position of the display screen in an embodiment, and referring to fig. 4, in addition to providing identification information of the steps of machine learning, the learning circle image at the first display position may also be provided with an execution relation between the steps of machine learning, so that a user can clearly understand the execution sequence and the cycle manner between the steps. In one example, the sequential execution relationship between adjacent steps can be indicated in a manner of pointing by an arrow, and a step at the starting point of the arrow is executed before a step at the ending point of the arrow.

In another example, the execution relationship between the steps can be represented by a numerical size, and the step corresponding to a small number is executed before the step corresponding to a large number, for example, the step of collecting behavior data corresponding to a number "1" is executed before the step of collecting feedback data corresponding to a number "2".

And S102, receiving configuration information which is input by a user through the configuration operation entrance and corresponds to the step.

Referring to fig. 4, the side of the learning circle image is displayed with a configuration operation entry corresponding to the machine learning step. By configuring the operation entry, data or parameters required for performing the steps can be configured.

The operation entry is configured with behavior data corresponding to the step of collecting behavior data, and it is selectable which behavior data is collected.

The collection of the results produced by the behavioral data (i.e., the feedback data) may be configured by a feedback data configuration operation portal corresponding to the step of collecting the feedback data. Because the feedback data corresponds to the behavior data, the feedback data can be automatically configured while the behavior data is configured through the behavior data configuration operation entry, that is, the feedback data configuration operation entry does not need to be separately set.

Through the learning configuration operation entry corresponding to the step of training the machine learning model, the frequency of machine learning, the time range of training data used by the machine learning, the splitting ratio of the training data and the test data, the accuracy rate of the machine learning, the time of the machine learning and the like can be configured.

Whether the machine learning model is automatically on-line or whether the self-learning of the machine learning model is automatically started or not can be configured through an application configuration operation inlet corresponding to the step of applying the machine learning model.

In order to facilitate providing guidance to the user regarding configuration operations, in one example, when the user inputs configuration information through the configuration operation entry of a first step of the steps, identification information of the first step in the learning circle image may be highlighted and/or the configuration operation entry of the first step may be highlighted. The highlighting may be highlighting, underlining, increasing font size, etc. The highlighting manner of the identification information in the first step may be the same as or different from the highlighting manner of the configuration operation entry in the first step. The first step herein is broadly directed to any of the multiple steps of the machine learning model. The identification information of the step of collecting behavioural data in figure 4 is highlighted in a highlighted manner.

In order to make the user know the current state of the learning circle, in one example, the learning circle image at the first display position is further provided with machine learning state prompt information, and specifically, when the user inputs configuration information through the configuration operation inlet, the machine learning state prompt information is displayed in a first preset mode in the learning circle image. In a specific example, the first preset manner may be to display a word "in configuration" in a central area of the learning circle, and further, a bar-shaped or annular pattern with a scrolling effect may be displayed on a side portion or a periphery of the word "in configuration" to increase a dynamic effect of the status prompt information and enhance a user experience.

FIG. 4 illustrates a configuration page for a learning circle, showing the current state of the learning circle- -in the configuration at the center of the circle. Meanwhile, the navigation bar above prompts the user for the name of the current learning circle and the button of global operation. The user can start or delete the current learning circle; the four-step card shown on the right allows the user to adjust the specific parameters of the four steps of the learning circle. After the user determines the configuration, the user can click a button for starting the learning circle for navigation at the upper right corner, so that the learning circle starts the process of machine learning.

And S104, moving the learning circle image from the first display position to the second display position on the display screen.

After configuration through the configuration operation portal, a learning loop may be initiated to perform the step of machine learning.

In one example, if a learning circle starting instruction sent by a user is received, the learning circle image can be moved from a first display position to a second display position on the display screen, and the state of the learning circle after starting is displayed at the second display position. Specifically, if a learning circle starting instruction sent by a user is received, machine learning resources are initialized, and after the initialization is completed, a learning circle image is moved from a first display position to a second display position on a display screen, so that the current state of machine learning is represented through the change of the position of the learning circle.

In order to enable the user to know the current state of the learning ring, in one example, after a learning ring starting instruction issued by the user is received, before the learning ring image moves from the first display position to the second display position, state prompt information of machine learning is displayed in the learning ring image in a first preset mode. In a specific example, the first preset manner may be to display a word "in the middle of the learning circle, and further, a bar-shaped or annular pattern with a scrolling effect may be displayed on a side portion or a periphery of the word" in the middle of the learning circle, so as to increase a dynamic effect of the status prompt information and enhance user experience.

Fig. 5 shows the process of moving the image of the learning circle from the first display position to the second display position on the display screen after the learning circle is started. Fig. 6 shows a schematic diagram of the learning circle image after moving from the first display position to the second display position.

After the learning circle image moves from the first display position to the second display position on the display screen, the learning circle image can be completely displayed in the display screen at the second display position, and the displayed learning circle image is provided with the identification information of the machine learning step. In some examples, only a portion (e.g., 1/3, 1/2, 2/3, etc.) of the learning circle image is displayed on the display screen in the second display position, and in the embodiment shown in fig. 6, about 2/3 of the learning circle image is displayed on the display screen. And displaying identification information of the step of machine learning in a partial image of the learning circle image displayed in a display screen. Specifically, the identification information of each step of machine learning is arranged end to end according to the execution sequence of each step of machine learning, and is displayed in the partial image of the learning circle image displayed in the display screen.

In the learning circle image of the second display position, an execution relationship between at least a part of the steps may be further provided. The execution relation between the steps may be a display manner in the learning circle image at the second display position, which is coincident with a display manner in the learning circle image at the first display position.

And S106, sequentially executing each machine learning step based on the configuration information corresponding to the step to acquire and provide the machine learning application.

After the learning circle image is moved from the first display position to the second display position on the display screen, the steps of machine learning can be sequentially executed based on the configuration information corresponding to the steps, so as to obtain and provide the machine learning application. Specifically, the sequentially executing the steps of machine learning based on the configuration information corresponding to the steps to acquire and provide the machine learning application may include: collecting behavior data based on configuration information corresponding to the step of collecting behavior data; collecting feedback data based on configuration information corresponding to the step of collecting feedback data; performing machine learning training by taking the collected behavior data and the feedback data as training data based on configuration information corresponding to the step of training the machine learning model to obtain the machine learning model; and applying the obtained machine learning model on line.

In fig. 6, after the learning circle image moves from the first display position to the second display position, the state of the learning circle is updated to "learning", and at the same time, the global operation button of the learning circle is changed at the top; at the moment, the user can select to apply for the on-line learning of the machine learning model to be learned or stop the learning of the learning ring; on the right side, the state of the learning circle learning step at this time is shown. The user can click on the four steps at the periphery of the learning circle to switch to view the state of the four steps. When the learning circle has a learning result and a machine learning model is generated, the user can click the application on-line button at the upper right corner to apply the machine learning model of the learning circle to the on-line service. At this time, the user can still switch back to the configuration page through the bottom button to view the configuration of the learning circle.

Fig. 7 shows the state after the learning circle is on-line, and the state of the learning circle is updated to "in service". And meanwhile, the online performance of the machine learning model is shown. On the top of the display interface, the global operation buttons of the learning circle are changed; at this time, the user can select to apply for the machine learning model to be learned to be offline or manually online to obtain a new machine learning model.

In the embodiment of the application, based on the Kuber learning circle theory in education, the training process of the machine learning model is divided into different steps, and the different steps are displayed in the learning circle image. Displaying a learning circle image with identification information of a machine learning step at a first display position on a display screen; after corresponding configuration is carried out through the configuration operation entrance, if a learning circle starting instruction is received, the learning circle image moves from a first display position to a second display position on the display screen, and identification information of the machine learning step is still provided in the learning circle image at the second display position; and on the basis of the configuration information corresponding to the steps, sequentially executing the steps of the machine learning, acquiring a machine learning model and applying the acquired machine learning model on line. The learning ring image is always displayed (at least partially displayed) in an interface displayed by a display screen in the change process from the first display position to the second display position, and identification information of the step of machine learning is always provided in the learning ring image, so that a user can know the learning ring and use the learning ring, and the machine learning process can be understood more intuitively through the change process of the learning ring image, and the operation mode of a machine learning product can be mastered more quickly.

In order to enhance the user's understanding of the execution sequence of the steps of machine learning, and facilitate the user to know which step the machine learning is currently in, in one example, while each of the steps of machine learning is sequentially executed, identification information of a step corresponding to the currently executed step of machine learning in the learning circle image may be highlighted. The highlighting may be highlighting, underlining, increasing font size, etc. The identification information of the step of training the machine learning model in fig. 6 and the identification information of the step of online application of the machine learning model in fig. 7 are highlighted in a highlighted manner, respectively.

In the process of executing the steps of machine learning in sequence, the identification information of the steps corresponding to the steps of machine learning is correspondingly and sequentially highlighted, so that a user can more easily understand and master the learning circle.

In order to enable the user to know the current state of the learning circle, in one example, the learning circle image at the second display position is further provided with machine learning state prompt information, and specifically, while each step of machine learning is sequentially executed, the machine learning state prompt information corresponding to the step is displayed in a second preset manner in the learning circle image. In a specific example, when the step of collecting behavior data is performed, the step of collecting feedback data is performed, and the step of training the machine learning model is performed, the second preset manner may be to display a word "learning" in a central region of the learning circle, as shown in fig. 6; when the machine learning model is applied online, the second preset mode may be to display the word "in application" in the central area of the learning circle, as shown in fig. 7. Further, bar-shaped or annular patterns with a scrolling effect can be displayed on the side part or the periphery of the characters in learning and application to increase the dynamic effect of the state prompt information and enhance the user experience.

In order to allow the user to intuitively know some execution state information of the currently executed step, in one example, the current execution state information of the second step may be displayed at a side portion of a partial image of the learning circle image while the second step of the steps of the machine learning is executed. The second step herein is broadly directed to any of the steps of the machine learning model.

For example, as shown in fig. 6, when the step of training the machine learning model is performed, that is, when the learning circle is in the "learning state", the learning state information may be displayed on the side portion of the partial image of the learning circle image. The learning state information can comprise information such as a state prompt that the current learning circle is in learning, the optimal effect of the current learning, the running time, the estimated remaining time, the running number of rounds, the trend relationship between the running effect and the behavior data and the like.

For another example, as shown in fig. 7, when the step of applying the machine learning model is executed, that is, when the learning circle is in the "application state", the application state information may be displayed on the side portion of the partial image of the learning circle image. The application state information can include information such as accumulated prediction accuracy, prediction failure rate, 7-day prediction quantity, total prediction quantity, failure prediction quantity, application online time, trend relation between prediction accuracy and behavior data and the like.

Fig. 8 is a flowchart illustrating a method for providing a machine learning application according to another embodiment of the present disclosure.

After the obtained machine learning model is applied online, the self-learning of the machine learning model can be started, and the machine learning model applied currently can be optimized or replaced through the self-learning. Specifically, referring to fig. 8, on the basis of the embodiment shown in fig. 1, further, after applying the obtained machine learning model online, the method may further include the steps of:

and S108, collecting new behavior data based on the configuration information corresponding to the step of collecting behavior data.

And S110, collecting new feedback data based on the configuration information corresponding to the step of collecting the feedback data.

And S112, self-learning is carried out based on the new behavior data and the new feedback data, and the obtained machine learning model is updated or replaced.

In this embodiment, based on the kueber learning circle theory in education, the process of machine learning is divided into four steps of behavior, feedback, learning, and application. The four steps are continuously circulated, and the machine learning model becomes better and better in the process of continuously repeating the four steps in sequence.

Fig. 9 is a block diagram of a device for providing a machine learning application according to an embodiment of the present application, and referring to fig. 9, the device for providing a machine learning application according to the present embodiment includes: a first display module 10, a configuration module 20, a second display module 30 and an execution module 40; the first display module 10 is configured to display a learning circle image at a first display position on a display screen, where the learning circle image provides identification information of a step of machine learning, and a side of the learning circle image displays a configuration operation entry corresponding to the step.

In this embodiment, the identification information of the learning circle, the learning circle image, the step of machine learning, and the step of machine learning can refer to the related explanation of the embodiment of the method shown in fig. 1, and is not repeated herein.

A configuration module 20, configured to receive configuration information corresponding to the step, which is input by the user through the configuration operation entry.

The second display module 30 is configured to, if a learning circle starting instruction issued by a user is received, move the learning circle image from a first display position to a second display position on the display screen, where at least part of the learning circle image is displayed in the display screen at the second display position, and the displayed at least part of the learning circle image is provided with identification information of the step of machine learning.

And the execution module 40 is configured to sequentially execute each step of the machine learning based on the configuration information corresponding to the step to obtain and provide the machine learning application.

After the learning circle image is moved from the first display position to the second display position on the display screen, the steps of machine learning can be sequentially executed based on the configuration information corresponding to the steps, so as to obtain and provide the machine learning application.

The apparatus of this embodiment may be used to implement the technical solution of the method embodiment shown in fig. 1, and the implementation principle and the technical effect are similar, which are not described herein again.

In an embodiment, the learning circle image of the first display position is further provided with an execution relation among the steps, so that a user can clearly understand the execution sequence among the steps. In one example, the sequential execution relationship between adjacent steps can be indicated in a manner of pointing by an arrow, and a step at the starting point of the arrow is executed before a step at the ending point of the arrow. In another example, the execution relationship between the steps can be represented by a numerical size, and the step corresponding to a small number is executed before the step corresponding to a large number, for example, the step of collecting behavior data corresponding to a number "1" is executed before the step of collecting feedback data corresponding to a number "2".

In an embodiment, the first display module 10 is specifically configured to: displaying identification information of each step of machine learning at a first display position on a display screen, and arranging the identification information of each step of machine learning from beginning to end according to the sequence of execution of each step of machine learning to form a looped image; or displaying the identification information of each step of machine learning at a first display position on a display screen, and correspondingly arranging the identification information of each step of machine learning in the first quadrant to the fourth quadrant according to the sequence of execution of the steps of machine learning to form a four-quadrant image.

Referring to fig. 10, in an embodiment, the first display module 10 may include: the first instruction receiving submodule 100 is configured to receive a learning circle creation instruction issued by a user; the display sub-module 102 is configured to display a learning circle image at a first display position of the display screen if the instruction receiving sub-module receives a learning circle creation instruction issued by a user.

In order to make the user know the current state of the learning circle, in one example, the learning circle image at the first display position is further provided with machine learning state prompt information, and in particular, the providing device of the machine learning application may further include a state information prompt module 50 configured to: and when a user inputs configuration information through the configuration operation entrance, displaying machine learning state prompt information in the learning circle image in a first preset mode. In a specific example, the first preset manner may be to display a word "in configuration" in a central area of the learning circle, and further, a bar-shaped or annular pattern with a scrolling effect may be displayed on a side portion or a periphery of the word "in configuration" to increase a dynamic effect of the status prompt information and enhance a user experience.

In order to provide guidance to a user regarding configuration operations, in one example, the first display module 10 may further include: a first highlighting submodule 104, configured to highlight the identification information of the first step in the learning circle image and/or highlight the configuration operation entry of the first step when the user inputs configuration information through the configuration operation entry of the first step of the steps. The identification information of the first step and/or the highlighting manner of the configuration operation entry of the first step can refer to the related description in the embodiment of the method shown in fig. 1, and will not be described herein again.

Referring to fig. 10, in an embodiment, the second display module 30 may include: the second instruction receiving submodule 300 is configured to receive a learning circle starting instruction issued by a user; the initialization sub-module 302 is configured to initialize the machine learning resource if the second instruction receiving sub-module 300 receives a learning circle starting instruction issued by a user, and move the learning circle image from the first display position to the second display position on the display screen after the initialization is completed, so as to represent the current state of machine learning through the change of the position of the learning circle.

The user is enabled to know the current state of the learning ring, and in one example, after a learning ring starting instruction issued by the user is received and before the learning ring image moves from the first display position to the second display position, state prompt information of machine learning is displayed in the learning ring image in a first preset mode. In a specific example, the first preset manner may be to display a word "in the middle of the learning circle, and further, a bar-shaped or annular pattern with a scrolling effect may be displayed on a side portion or a periphery of the word" in the middle of the learning circle, so as to increase a dynamic effect of the status prompt information and enhance user experience.

After the learning circle image moves from the first display position to the second display position on the display screen, the learning circle image can be completely displayed in the display screen at the second display position, and the displayed learning circle image is provided with the identification information of the machine learning step. In some examples, in the second display position, only a portion (e.g., 1/3, 1/2, 2/3, etc.) of the learning circle image is displayed on the display screen, and in fig. 6, about 2/3 of the learning circle image is displayed on the display screen. And displaying identification information of the step of machine learning in a partial image of the learning circle image displayed in a display screen. Specifically, the identification information of each step of machine learning is arranged end to end according to the execution sequence of each step of machine learning, and is displayed in the partial image of the learning circle image displayed in the display screen.

In order to make the user intuitively know some execution status information of the currently executed step, in one example, the second display module 30 may further be configured to: when the execution module 40 executes the second step of the steps of the machine learning, current execution state information of the second step is displayed on a side portion of a partial image of the learning circle image. The second step herein is broadly directed to any of the steps of the machine learning model.

In one example, the execution module 40 may include: a first execution sub-module 400 for collecting behavior data based on configuration information corresponding to the step of collecting behavior data; a second execution sub-module 402 for collecting feedback data based on configuration information corresponding to the step of collecting feedback data; a third execution sub-module 404, configured to perform machine learning training with the collected behavior data and the feedback data as training data based on configuration information corresponding to a step of training a machine learning model, so as to obtain a machine learning model; and a fourth execution submodule 406, configured to apply the obtained machine learning model online.

In an example, the status information prompting module 50 is further configured to display the status prompting information of the machine learning corresponding to each step in a second preset manner in the learning circle image while the executing module 40 sequentially executes the step of the machine learning. In a specific example, when the step of collecting behavior data is performed, the step of collecting feedback data is performed, and the step of training the machine learning model is performed, the second preset manner may be to display a word "learning" in a central region of the learning circle, as shown in fig. 6; when the machine learning model is applied online, the second preset mode may be to display the word "in application" in the central area of the learning circle, as shown in fig. 7. Further, bar-shaped or annular patterns with a scrolling effect can be displayed on the side part or the periphery of the characters in learning and application to increase the dynamic effect of the state prompt information and enhance the user experience.

Referring to fig. 10, to enhance the user's understanding of the execution sequence of the steps of machine learning, so as to facilitate understanding which step the machine learning is currently in, in one example, the execution module 40 may further include: a second highlighting submodule 406, configured to highlight, while the execution module 40 sequentially executes each step of the machine learning, identification information of a step corresponding to a currently executed step of the machine learning in the learning circle image. The highlighting may be highlighting, underlining, increasing font size, etc. The identification information of the step of training the machine learning model in fig. 6 and the identification information of the step of online application of the machine learning model in fig. 7 are highlighted in a highlighted manner, respectively.

After the obtained machine learning model is applied online, the self-learning of the machine learning model can be started, and the machine learning model applied currently can be optimized or replaced through the self-learning. Specifically, referring to fig. 10, on the basis of the embodiment shown in fig. 9, the apparatus for providing a machine learning application may further include: a self-learning module 60 for collecting new behavior data based on configuration information corresponding to the step of collecting behavior data after the execution module 40 applies the obtained machine learning model online; collecting new feedback data based on configuration information corresponding to the step of collecting feedback data; and self-learning is carried out based on the new behavior data and the new feedback data, and the obtained machine learning model is updated or replaced.

An embodiment of the present invention further provides an electronic device, fig. 11 is a schematic structural diagram of an embodiment of the electronic device, and a flow of the embodiments shown in fig. 1 and fig. 8 of the present invention can be implemented, as shown in fig. 11, where the electronic device may include: the device comprises a shell 41, a processor 42, a memory 43, a circuit board 44 and a power circuit 45, wherein the circuit board 44 is arranged inside a space enclosed by the shell 41, and the processor 42 and the memory 43 are configured on the circuit board 44; a power supply circuit 45 for supplying power to each circuit or device of the electronic apparatus; the memory 43 is used for storing executable program code; the processor 42 is configured to execute the method for providing the machine learning application according to any of the foregoing embodiments by reading the executable program code stored in the memory 43.

For the specific execution process of the above steps by the processor 42 and the steps further executed by the processor 42 by running the executable program code, reference may be made to the description of the embodiments shown in fig. 1 and fig. 8 of the present invention, which is not described herein again.

The electronic device exists in a variety of forms, including but not limited to: a desktop computer (commonly referred to as a desktop computer), a notebook computer, or a tablet computer, and may also be a server, or may also be an industry-specific computing device, etc. .

Embodiments of the present application also provide a computer-readable storage medium, which stores one or more programs, where the one or more programs are executable by one or more processors to implement the method for providing a machine learning application according to any of the foregoing embodiments.

Embodiments of the present application also provide an application program, which is executed to implement the method for providing a machine learning application described in any one of the foregoing embodiments.

It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus 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 apparatus. The term "comprising", without further limitation, means that the element so defined is not excluded from the group consisting of additional identical elements in the process, method, article, or apparatus that comprises the element.

All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments.

In particular, as for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

For convenience of description, the above devices are described separately in terms of functional division into various units/modules. Of course, the functionality of the units/modules may be implemented in one or more software and/or hardware implementations of the invention.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.

The above description is only for the specific embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for providing a machine learning application, comprising:

displaying a learning circle image at a first display position on a display screen, wherein the learning circle image provides identification information of a step of machine learning, and a configuration operation inlet corresponding to the step is displayed on the side of the learning circle image;

receiving configuration information which is input by a user through the configuration operation inlet and corresponds to the step;

if a learning circle starting instruction sent by a user is received, moving the learning circle image from a first display position to a second display position on the display screen, wherein at least part of the learning circle image is displayed in the display screen at the second display position, and the displayed at least part of the learning circle image is provided with identification information of the step of machine learning;

and sequentially executing each step of machine learning based on the configuration information corresponding to the step to acquire and provide the machine learning application.

2. The method for providing a machine learning application according to claim 1,

the learning circle image of the first display position is also provided with the execution relation among the steps, and/or the learning circle image of the second display position is also provided with the execution relation among at least part of the steps.

3. The method for providing a machine learning application according to claim 1,

the step of machine learning includes: the method comprises the steps of collecting behavior data, collecting feedback data, training a machine learning model and applying the machine learning model;

the identification information of the machine-learned step includes a step name and/or a step icon.

4. The method for providing a machine learning application according to claim 3, wherein the step name of collecting behavior data, the step name of collecting feedback data, the step name of training a machine learning model, and the step name of applying a machine learning model are behavior, feedback, learning, and application in sequence.

5. The method for providing a machine learning application according to claim 1, wherein the displaying a learning circle image at a first display position on a display screen includes:

displaying identification information of each step of machine learning at a first display position on a display screen, and arranging the identification information of each step of machine learning from beginning to end according to the sequence of execution of each step of machine learning to form a looped image; alternatively, the first and second electrodes may be,

and displaying identification information of each step of machine learning at a first display position on a display screen, and correspondingly arranging the identification information of each step of machine learning in the first quadrant to the fourth quadrant according to the sequence of execution of the steps of machine learning to form a four-quadrant image.

6. The method for providing a machine learning application according to claim 1,

at the second display position, a partial image of the learning circle image is displayed in the display screen; wherein the identification information of the step of machine learning is displayed in a partial image of the learning circle image displayed in a display screen.

7. The method for providing a machine learning application according to claim 6, wherein the identification information of the steps of machine learning is displayed in the partial image of the learning circle image displayed on the display screen in an order of execution of the steps of machine learning from beginning to end.

8. An apparatus for providing a machine learning application, comprising:

the device comprises a first display module, a second display module and a display module, wherein the first display module is used for displaying a learning circle image at a first display position on a display screen, the learning circle image is provided with identification information of a step of machine learning, and a configuration operation inlet corresponding to the step is displayed on the side part of the learning circle image;

the configuration module is used for receiving the configuration information which is input by the user through the configuration operation entrance and corresponds to the step;

the second display module is used for moving the learning circle image from a first display position to a second display position on the display screen if a learning circle starting instruction sent by a user is received, wherein at least part of the learning circle image is displayed in the display screen at the second display position, and the displayed at least part of the learning circle image is provided with identification information of the step of machine learning;

and the execution module is used for sequentially executing each step of machine learning based on the configuration information corresponding to the step so as to obtain and provide the machine learning application.

9. An electronic device, characterized in that the electronic device comprises: the device comprises a shell, a processor, a memory, a circuit board and a power circuit, wherein the circuit board is arranged in a space enclosed by the shell, and the processor and the memory are arranged on the circuit board; a power supply circuit for supplying power to each circuit or device of the electronic apparatus; the memory is used for storing executable program codes; the processor is configured to execute the method for providing a machine learning application according to any one of the preceding claims 1 to 7 by reading executable program code stored in the memory.

10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores one or more programs which are executable by one or more processors to implement the method for providing a machine learning application of any one of the preceding claims 1 to 7.