Machine learning teaching method, device, electronic device and storage medium

Abstract

An embodiment of the present invention discloses a machine learning teaching method, device, electronic device, and storage medium. The machine learning teaching method includes: receiving a machine learning teaching instruction input by a user; selecting a target machine learning model from at least two candidate machine learning models according to the machine learning teaching instruction; wherein the at least two candidate machine learning models are pre-configured according to the classification results of standardizing the artificial intelligence teaching scenario; and performing artificial intelligence teaching work based on the target machine learning model. By standardizing the teaching scenario and pre-training the machine learning model, the operation steps of the teaching participants are simplified, the operation difficulty of the teaching participants is reduced, and the timeliness of the machine learning teaching work is improved; and each candidate machine learning model is trained for each type of recognition object, reducing the training complexity and improving the model quality, thereby improving the certainty of the machine learning teaching work and ensuring the teaching effect.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of intelligent education technology, and in particular to a machine learning teaching method, device, electronic device and storage medium. Background Art

[0002] Artificial intelligence education is gaining more and more attention and becoming more and more popular. Currently, AI-related courses have been opened in primary and secondary school classrooms to popularize AI-related knowledge and establish a relevant foundation for primary and secondary school students. Due to the various AI teaching scenarios, the operation process of machine learning teaching in existing AI education is very complicated, requiring four steps: taking sample photos, neural network training, outputting models, and using model recognition. Moreover, all four steps require the teaching participants to operate, which is not conducive to the timeliness of teaching work.

[0003] The quality of the final model is closely related to the appearance style of the sample photos taken by the teaching participants, the number of samples taken, the neural network used for training, and the on-site light environment. In addition, when constructing the neural network used for training, the complexity of the training samples is proportional to the quality of the final model. Therefore, the operations of teachers and students participating in the teaching before recognition are relatively complicated and time-consuming, and the recognition effect is not guaranteed, which is not conducive to the timeliness and certainty of teaching work. Summary of the invention

[0004] The embodiments of the present invention provide a machine learning teaching method, device, electronic device and storage medium to improve the timeliness and certainty of machine learning teaching work, reduce the operation difficulty of teaching participants, and ensure teaching effect.

[0005] In a first aspect, an embodiment of the present invention provides a machine learning teaching method, comprising:

[0006] Receive machine learning teaching instructions input by users;

[0007] Selecting a target machine learning model from at least two candidate machine learning models according to the machine learning teaching instruction; wherein the at least two candidate machine learning models are pre-configured according to the classification results of the standardized artificial intelligence teaching scenario;

[0008] Artificial intelligence teaching is carried out based on the target machine learning model.

[0009] In a second aspect, an embodiment of the present invention further provides a machine learning teaching device, comprising:

[0010] A teaching instruction receiving module, used to receive machine learning teaching instructions input by a user;

[0011] A model selection module, configured to select a target machine learning model from at least two candidate machine learning models according to the machine learning teaching instruction; wherein, the at least two candidate machine learning models are pre-configured according to the classification results of standardizing the artificial intelligence teaching scenario;

[0012] A teaching module, configured to perform artificial intelligence teaching work based on the target machine learning model.

[0013] In a third aspect, an embodiment of the present invention further provides an electronic device, including:

[0014] One or more processors;

[0015] A storage device, configured to store one or more programs,

[0016] When the one or more programs are executed by the one or more processors, the one or more processors implement the machine learning teaching method as described in any embodiment of the present invention.

[0017] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the machine learning teaching method as described in any embodiment of the present invention.

[0018] Embodiments of the present invention are based on receiving a machine learning teaching instruction input by a user; selecting a target machine learning model from at least two candidate machine learning models according to the machine learning teaching instruction; wherein, the at least two candidate machine learning models are pre-configured according to the classification results of standardizing the artificial intelligence teaching scenario; and performing artificial intelligence teaching work based on the target machine learning model. Embodiments of the present invention standardize the teaching scenario, pre-train the machine learning model, simplify the operation steps of teaching participants, reduce the operation difficulty of teaching participants, and improve the timeliness of machine learning teaching work; and each candidate machine learning model is trained for each type of recognition object, reducing the training complexity, improving the model quality, and further improving the certainty of machine learning teaching work and ensuring the teaching effect. Description of the Drawings

[0019] Figure 1 is a flowchart of the machine learning teaching method in Embodiment 1 of the present invention;

[0020] Figure 2 is a flowchart of the configuration method of the candidate machine learning model in Embodiment 2 of the present invention;

[0021] Figure 3 is a schematic structural diagram of the machine learning teaching device in Embodiment 3 of the present invention;

[0022] Figure 4It is a schematic structural diagram of the electronic device in the fourth embodiment of the present invention. Detailed implementation manners

[0023] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the present invention, rather than limiting the present invention. In addition, it should be noted that for the convenience of description, only parts related to the present invention rather than all structures are shown in the drawings. Embodiment 1

[0024] Figure 1 It is a flowchart of the machine learning teaching method in the first embodiment of the present invention. This embodiment is applicable to the situation of teaching artificial intelligence courses to primary and middle school students. This method can be executed by a machine learning teaching device, which can be implemented in software and / or hardware and can be configured in an electronic device. For example, the electronic device can be an intelligent camera or other devices with image acquisition and computing capabilities. As Figure 1 shown, the method specifically includes:

[0025] Step 101, receive a machine learning teaching instruction input by a user.

[0026] Due to the popularization of artificial intelligence, artificial intelligence-related courses have gradually begun to be offered in primary and middle school classrooms. However, due to the age limit of the teaching objects, the teaching of artificial intelligence needs to simplify the operation steps while ensuring the teaching quality so that primary and middle school students can understand. In existing artificial intelligence teaching courses, teachers or students need to take photos of sample photos on site in the classroom, perform neural network training, and finally obtain a model. However, since taking sample photos on site will cause the quality of the finally obtained model to be affected by the appearance style of the sample photos, the number of sample photos, and the on-site light environment, it is difficult to ensure the final teaching quality; and due to the complex and time-consuming operation steps, the timeliness of on-site teaching is difficult to ensure, and it is difficult for students to understand artificial intelligence in a timely manner.

[0027] Among them, the user can be a teacher or a student in the teaching classroom. The machine learning teaching instruction input by the user is used to determine the function of the artificial intelligence for teaching. Since there are many artificial intelligence teaching scenarios and there are too many interference factors in the teaching scenarios, the teaching quality will decline. Exemplarily, in existing teaching scenarios, the same model is used to implement the recognition of various items to achieve the display effect for students. However, in the actual scenario, each image to be recognized will include multiple types of items, making it difficult to accurately display the recognized items that meet the real needs for users during teaching, which has a certain adverse impact on teaching.

[0028] In an embodiment of the present invention, a machine learning teaching instruction input by a user is first received, and the object type that the user needs to identify in this teaching is clearly obtained from the teaching instruction, so as to achieve a clear positioning of the teaching scene. Exemplarily, different types of buttons for identifying object types are provided to the user, and the user can select according to actual needs. A machine learning teaching instruction is generated according to the button selected by the user, and the object type to be identified is obtained from the teaching instruction.

[0029] Step 102: Select a target machine learning model from at least two candidate machine learning models according to the machine learning teaching instructions; wherein, at least two candidate machine learning models are pre-configured based on the classification results of standardized artificial intelligence teaching scenarios.

[0030] Among them, the candidate machine learning model is generated by analyzing and refining the artificial intelligence teaching scenario in advance to obtain standardized classification results based on each category of objects to be identified in the classification results.

[0031] Specifically, since the machine learning teaching instructions include the object type that the user needs to identify, a target machine learning model associated with the object model can be selected from the candidate machine learning models according to the object type. Specifically, the association relationship between the candidate machine learning model and the identification object type is pre-configured, and the relationship between the candidate machine learning model with the association relationship and the object type to be identified is: the candidate machine learning model is obtained by personalized training based on the object type to be identified, so that each candidate machine learning model is only trained on any one class in the standardized classification results, simplifying the complexity of identifying the object type, thereby improving the quality of the corresponding generated candidate machine learning model.

[0032] Step 103: Perform artificial intelligence teaching based on the target machine learning model.

[0033] After determining the target machine learning model, the object types required to be identified in the machine learning teaching instructions can be accurately identified. For users, when conducting artificial intelligence teaching, the only operation required is to determine the object type that the teaching is aimed at identifying. After entering the object type, the items of the object type can be identified to achieve the development of artificial intelligence teaching. While ensuring the quality of teaching, the user's operation is simplified. The user does not need to take sample photos, perform neural network training, and obtain the model. These operations have been preset when the product integrated by this method leaves the factory. The user only needs to use the model for identification teaching, which improves the timeliness of classroom teaching.

[0034] Exemplarily, if the user inputs that the recognition object to be displayed in this teaching is a human face, then the machine learning model corresponding to face recognition is determined inside the method integration teaching product according to the instruction input by the user, and this machine learning model is provided for the user to use. The user can then use the product to perform intelligent face recognition, serving a teaching purpose.

[0035] In the embodiment of the present invention, by standardizing the teaching scenario, pre-training the machine learning model, simplifying the operation steps of the teaching participants, reducing the operation difficulty of the teaching participants, and improving the timeliness of the machine learning teaching work; and each candidate machine learning model is trained for each type of recognition object, reducing the training complexity, improving the model quality, and further improving the certainty of the machine learning teaching work and ensuring the teaching effect.

[0036] Embodiment 2

[0037] Figure 2 It is a flowchart of the configuration method of the candidate machine learning model in Embodiment 2 of the present invention. Embodiment 2 is further optimized on the basis of Embodiment 1. As Figure 2 shown, the method includes:

[0038] Step 201: Standardize the artificial intelligence teaching scenario to obtain the classification results of at least two types of recognition objects in the teaching scenario.

[0039] Among them, standardizing means analyzing and refining the artificial intelligence teaching scenario, classifying and summarizing the recognition objects in the teaching scenario, and finally obtaining the classification results of at least two types of recognition objects in the teaching scenario. Exemplarily, recognition objects with common recognition features are determined as the same category to simplify user operations.

[0040] In a feasible embodiment, Step 201 includes:

[0041] Determine all recognition objects in the artificial intelligence teaching scenario;

[0042] Perform standardized classification on the recognition objects to obtain the classification results of at least two types of recognition objects in the teaching scenario.

[0043] Among them, all recognition objects are determined according to the actual teaching needs. Due to the limitations of the artificial intelligence teaching scenario and the educational objects, all recognition objects can be listed. Optionally, standardizing means setting customized recognition object types for the user according to the teaching needs. That is, providing specific recognition objects for the user to achieve the standardization of the artificial intelligence teaching scenario.

[0044] Analyze the characteristics of each recognized object, perform standardized classification on all recognized objects, divide the recognized objects with common recognition characteristics into the same category, and obtain the classification results of at least two types of recognized objects in the teaching scenario.

[0045] In a feasible embodiment, the classification results include at least one of the following: face recognition object, card recognition object, line segment recognition object, color recognition object, and feature learning object.

[0046] Among them, the face recognition object refers to an object of the face category; the card recognition object includes objects such as digital cards, letter cards, and traffic symbol cards that display specific items on paper; the line segment recognition object refers to the finite part between two points; the feature learning object is a general object provided for users to learn and expand. Exemplarily, the feature learning object refers to the recognized object to be learned that is not included in the classification results. In the embodiments of the present invention, the examples of the recognized object types in the classification results do not constitute a limitation on the protection scope of the present invention, and the recognized objects in the classification results can be increased according to actual teaching needs.

[0047] Step 202: Perform model training for each type of recognized object in the classification results to obtain the machine learning model for each type of recognized object.

[0048] Sample pictures of each type of recognition object are collected respectively as the training sample set for each type of recognition object. Each training sample set for each type of recognition object is trained respectively to obtain a machine learning model for each type of recognition object. Exemplarily, when the classification results include face recognition objects, card recognition objects, line segment recognition objects, color recognition objects, and feature learning objects, model training is performed for each type of recognition object respectively to obtain a face recognition model, a card recognition model, a line segment recognition model, a color recognition model, and a feature learning model respectively. Among them, the face recognition model is used to respond to the machine learning teaching instruction input by the user for face recognition teaching; the card recognition model is used to respond to the machine learning teaching instruction input by the user for card recognition teaching; the line segment recognition model is used to respond to the machine learning teaching instruction input by the user for line segment recognition teaching, and the line segment recognition model can adopt a binary traditional model; the color recognition model is used to respond to the machine learning teaching instruction input by the user for color recognition teaching, and the color recognition model can adopt a basic color recognition model plus a classification model; the feature learning model is used to respond to the machine learning teaching instruction input by the user for extended teaching, and the feature learning model can adopt a feature extraction model. When performing artificial intelligence teaching work based on the feature learning model, the user can identify objects for classification. Exemplarily, the user inputs a picture of item A not included in the classification results into the feature learning model. The feature learning model can learn the features of item A and thus achieve the recognition of item A in the image to be recognized. The setting of the feature learning model realizes the expansion of artificial intelligence teaching, which is more conducive to improving the quality of artificial teaching and avoiding teaching omissions.

[0049] In the embodiment of the present invention, recognition objects with common features are classified into the same category, and personalized machine learning models are customized for each category respectively, so that each machine learning model only needs to focus on one category of recognition objects, reducing the training complexity. Correspondingly, the quality of the machine learning model is improved, thereby ensuring the teaching accuracy when conducting artificial intelligence teaching in the classroom.

[0050] Optionally, when performing model training for each type of recognition object in the classification results, a pre-set standardized sample picture is provided as the training sample set, and at the same time, the standard recognition object in the standardized sample picture is provided to the user for recognition to ensure the accuracy of the recognition result and thus ensure the teaching effect.

[0051] Step 203: Configure the machine learning model for each type of recognition object as a candidate machine learning model.

[0052] All types of machine learning models for recognition objects are used as candidate machine learning models to select a target machine learning model according to the actual teaching needs of users. Exemplarily, machine learning models for all recognition objects are configured in the device firmware integrated in the method of the embodiment of the present invention. For example, the candidate machine learning model is built into an intelligent camera to collect pictures using the intelligent camera and recognize the collected pictures using the built-in machine learning model.

[0053] In the embodiment of the present invention, by standardizing the teaching scenario, pre-training the machine learning model, simplifying the operation steps of teaching participants, reducing the operation difficulty of teaching participants, and improving the timeliness of machine learning teaching work; and each candidate machine learning model is trained for each type of recognition object, reducing the training complexity, improving the model quality, and further improving the certainty of machine learning teaching work and ensuring the teaching effect.

[0054] The embodiment of the present invention provides a feasible machine learning teaching method, and the specific steps include:

[0055] Analyze and refine the artificial intelligence teaching scenario, and classify common recognition objects. Customize personalized machine learning models for each type of common recognition object. Build each customized machine learning model into the firmware of the machine learning teaching device. When the user uses the machine learning teaching device, the user independently selects the required recognition type, and the machine learning teaching device calls the associated pre-trained machine learning model according to the recognition type selected by the user to carry out the teaching work of artificial intelligence education.

[0056] In the embodiment of the present invention, the objects to be recognized in the artificial intelligence teaching scenario are standardized and refined into face recognition, card recognition, line segment recognition, color recognition, and feature learning. Analyze the characteristics of each type of object, customize models and scripts for different recognition object types in a personalized manner, and build the script models into the firmware of the machine learning teaching device, reducing the operation threshold of users and improving the classroom efficiency.

[0057] Embodiment III

[0058] Figure 3 It is a schematic structural diagram of a machine learning teaching device in Embodiment III of the present invention. This embodiment is applicable to the situation of teaching artificial intelligence courses to primary and secondary school students. As Figure 3 shown, the device includes:

[0059] A teaching instruction receiving module 310, configured to receive a machine learning teaching instruction input by a user;

[0060] A model selection module 320, configured to select a target machine learning model from at least two candidate machine learning models according to a machine learning teaching instruction; wherein, the at least two candidate machine learning models are pre-configured according to a classification result of standardizing an artificial intelligence teaching scenario;

[0061] A teaching module 330, configured to perform artificial intelligence teaching work based on the target machine learning model.

[0062] In the embodiment of the present invention, by standardizing the teaching scenario and pre-training the machine learning model, the operation steps of the teaching participating users are simplified, the operation difficulty of the teaching participants is reduced, and the timeliness of the machine learning teaching work is improved; and each candidate machine learning model is trained for each type of recognition object, reducing the training complexity, improving the model quality, and further improving the certainty of the machine learning teaching work and ensuring the teaching effect.

[0063] Optionally, the device further includes a candidate model configuration module, including:

[0064] A teaching scenario classification unit, configured to standardize an artificial intelligence teaching scenario to obtain a classification result of at least two types of recognition objects in the teaching scenario;

[0065] A classification training unit, configured to perform model training for each type of recognition object in the classification result to obtain a machine learning model for each type of recognition object;

[0066] A model configuration unit, configured to configure the machine learning model for each type of recognition object as a candidate machine learning model.

[0067] Optionally, the teaching scenario classification unit is specifically configured to:

[0068] Determine all recognition objects in the artificial intelligence teaching scenario;

[0069] Perform standardized classification on the recognition objects to obtain a classification result of at least two types of recognition objects in the teaching scenario.

[0070] Optionally, the classification result includes at least one of the following: a face recognition object, a card recognition object, a line segment recognition object, a color recognition object, and a feature learning object.

[0071] The machine learning teaching device provided in the embodiment of the present invention can execute the machine learning teaching method provided in any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the machine learning teaching method.

[0072] Embodiment 4

[0073] Figure 4 It is a schematic structural diagram of an electronic device provided in Embodiment 4 of the present invention.Figure 4 FIG. shows a block diagram of an exemplary electronic device 12 suitable for implementing embodiments of the present invention. Figure 4 The illustrated electronic device 12 is merely an example and should not impose any limitation on the functions and scope of use of the embodiments of the present invention.

[0074] As Figure 4 shown, the electronic device 12 is presented in the form of a general-purpose computing device. The components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system storage device 28, and a bus 18 connecting different system components (including the system storage device 28 and the processing unit 16).

[0075] The bus 18 represents one or more of several types of bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

[0076] The electronic device 12 typically includes a variety of computer system-readable media. These media can be any available media accessible by the electronic device 12, including volatile and non-volatile media, removable and non-removable media.

[0077] The system storage device 28 may include computer system-readable media in the form of volatile storage devices, such as random access memory (RAM) 30 and / or cache storage device 32. The electronic device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, a storage system 34 may be used for reading and writing on non-removable, non-volatile magnetic media ( Figure 4 not shown, commonly referred to as a "hard disk drive"). Although Figure 4 not shown in, a disk drive for reading and writing on removable non-volatile disks (such as "floppy disks") and an optical disk drive for reading and writing on removable non-volatile optical disks (such as CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 through one or more data media interfaces. The storage device 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0078] A program / utilities 40 having a set (at least one) of program modules 42 can be stored, for example, in a storage device 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment. The program modules 42 generally execute the functions and / or methods in the embodiments described in the present invention.

[0079] The electronic device 12 can also communicate with one or more external devices 14 (such as a keyboard, a pointing device, a display 24, etc.), and can also communicate with one or more devices that enable a user to interact with the device 12, and / or communicate with any device that enables the device 12 to communicate with one or more other computing devices (such as a network card, a modem, etc.). Such communication can be carried out through an input / output (I / O) interface 22. Moreover, the electronic device 12 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 20. As Figure 4 shown, the network adapter 20 communicates with other modules of the electronic device 12 through a bus 18. It should be understood that although Figure 4 not shown in the figure, other hardware and / or software modules can be used in combination with the electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0080] The processing unit 16 executes various functional applications and data processing by running programs stored in the system storage device 28, for example, implementing the machine learning teaching method provided in the embodiments of the present invention, including:

[0081] Receiving a machine learning teaching instruction input by a user;

[0082] Selecting a target machine learning model from at least two candidate machine learning models according to the machine learning teaching instruction; wherein, the at least two candidate machine learning models are pre-configured according to the classification results of standardizing the artificial intelligence teaching scenarios;

[0083] Carrying out artificial intelligence teaching work based on the target machine learning model.

[0084] Embodiment Five

[0085] Embodiment Five of the present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the machine learning teaching method provided in the embodiments of the present invention, including:

[0086] Receiving a machine learning teaching instruction input by a user;

[0087] Select a target machine learning model from at least two candidate machine learning models according to the machine learning teaching instruction; wherein, the at least two candidate machine learning models are pre-configured according to the classification results of standardizing the artificial intelligence teaching scenario.

[0088] Carry out artificial intelligence teaching work based on the target machine learning model.

[0089] The computer storage medium of the embodiments of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (non-exhaustive list) of the computer-readable storage medium include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0090] The computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries the computer-readable program code. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0091] The program code contained on the computer-readable medium may be transmitted by any appropriate medium, including but not limited to wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0092] Computer program code for performing the operations of the present invention may be written in one or more programming languages or combinations thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network including a local area network (LAN) or a wide area network (WAN), or, may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0093] Note that the above is only the preferred embodiment of the present invention and the technical principles applied. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, re-adjustments and substitutions can be made by those skilled in the art without departing from the protection scope of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments only. Without departing from the concept of the present invention, more other equivalent embodiments may be included, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A machine learning teaching method, characterized in that, It includes: Receiving a machine learning teaching instruction input by a user; Selecting a target machine learning model from at least two candidate machine learning models according to the machine learning teaching instruction; Among them, the at least two candidate machine learning models are pre-configured according to the classification results of standardizing the artificial intelligence teaching scenario; Among them, the candidate machine learning models are obtained by pre-analyzing and refining the artificial intelligence teaching scenario to obtain standardized classification results, and generating for each type of object to be recognized in the classification results; Carrying out artificial intelligence teaching work based on the target machine learning model; The configuration process of the candidate machine learning models is as follows: Standardizing the artificial intelligence teaching scenario to obtain the classification results of at least two types of recognized objects in the teaching scenario; Training a machine learning model for each type of recognized object to obtain the machine learning model of each type of recognized object; Configuring the machine learning model of each type of recognized object as a candidate machine learning model; Among them, the candidate machine model is obtained by personalized training according to the type of object to be recognized; Standardizing the artificial intelligence teaching scenario to obtain the classification results of at least two types of recognized objects in the teaching scenario, including: Determining all recognized objects in the artificial intelligence teaching scenario; Carrying out standardized classification on the recognized objects to obtain the classification results of at least two types of recognized objects in the teaching scenario; The classification results include at least one of the following: face recognition object, card recognition object, line segment recognition object, color recognition object, and feature learning object; Providing buttons of different types of recognized object types for the user, the user makes a selection according to actual needs, generating a machine learning teaching instruction according to the selected button, and obtaining the type of object to be recognized from the teaching instruction; The machine learning teaching instruction includes the type of object that the user needs to recognize, and a target machine learning model associated with the object model is selected from the candidate machine learning models according to the type of object; Pre-configuring the association relationship between the candidate machine learning models and the types of recognized objects, and the relationship between the candidate machine learning models and the types of objects to be recognized with the association relationship is: the candidate machine learning model is obtained by personalized training according to the type of object to be recognized, so that each candidate machine learning model only trains for any one category in the standardized classification results.

2. A machine learning teaching device, characterized in that, It includes: A teaching instruction receiving module, which is used to receive a machine learning teaching instruction input by a user; A model selection module, which is used to select a target machine learning model from at least two candidate machine learning models according to the machine learning teaching instruction; Among them, the at least two candidate machine learning models are pre-configured according to the classification results of standardizing the artificial intelligence teaching scenario; A teaching module, which is used to carry out artificial intelligence teaching work based on the target machine learning model; The device further includes a candidate model configuration module, including: A teaching scenario classification unit, which is used to standardize the artificial intelligence teaching scenario to obtain the classification results of at least two types of recognized objects in the teaching scenario; A classification training unit for training a model for each type of recognition object in the classification result to obtain a machine learning model for each type of recognition object; A model configuration unit for configuring the machine learning model for each type of recognition object as a candidate machine learning model; wherein the candidate machine learning model is obtained by personalized training according to the type of object to be recognized.

3. The device according to claim 2, characterized in that, The teaching scenario classification unit is specifically used for: Determining all recognition objects in the artificial intelligence teaching scenario; Performing standardized classification on the recognition objects to obtain a classification result of at least two types of recognition objects in the teaching scenario.

4. The device according to any one of claims 2-3, characterized in that, The classification result includes at least one of the following: a face recognition object, a card recognition object, a line segment recognition object, a color recognition object, and a feature learning object.

5. An electronic device, characterized in that, Including: One or more processors; A storage device for storing one or more programs, which when executed by the one or more processors cause the one or more processors to implement the machine learning teaching method as claimed in claim 1.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the machine learning teaching method as claimed in claim 1.

Images