CN207851897U - The tutoring system of artificial intelligence based on TensorFlow - Google Patents

Abstract

The utility model discloses an artificial intelligence teaching system based on TensorFlow, comprising a power supply module, an image acquisition device, a processor, several teaching modules and a display module; the power supply module is used to provide working voltage for each component; the processor is connected to each The teaching module is used to receive the image information of the object to be recognized collected by the image acquisition device, perform detection and recognition processing on the image information, and obtain the detection and recognition image information; select the corresponding teaching module according to the detection and recognition image information, and transmit the detection and recognition image information to the corresponding teaching module; the teaching module is used to generate teaching content according to the detection and recognition image information and preset teaching resources; the display module is connected to the processor and is used to display the detection and recognition results and play the teaching content to complete the teaching. The utility model not only lowers the learning threshold, but also can store a large amount of learning resources inside, can reduce the burden of books, improve learning enthusiasm, and enable students to regain interest in learning.

Description

Artificial intelligence teaching system based on TensorFlow

technical field

The utility model relates to the field of education technology, in particular to an artificial intelligence teaching system based on TensorFlow.

Background technique

Artificial intelligence is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. With the development of science and technology, the application field of artificial intelligence has penetrated into every aspect of people's life. Artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a manner similar to human intelligence. Research in this field includes robotics, language recognition, image recognition, natural language processing and expert systems, etc.

In the process of traditional education, the study life is cumbersome and boring. After a long period of study, it is often tiresome, which seriously affects the quality of study. And the traditional book education, students' enthusiasm for learning is also poor.

Utility model content

The purpose of this utility model is to provide an artificial intelligence teaching system based on TensorFlow, which can directly select the corresponding teaching module to carry out relevant teaching according to the image information collected by the image acquisition device, so as to reduce the learning threshold; and a large number of learning resources can be stored inside, It can reduce the burden of books, improve learning enthusiasm, and enable students to regain their interest in learning.

The utility model provides an artificial intelligence teaching system based on TensorFlow, comprising a power supply module, an image acquisition device, a processor, several teaching modules and a display module;

The power supply module is connected to the image acquisition device, processor, teaching module and display module respectively, and is used to provide the working voltage of the image acquisition device, processor, teaching module and display module;

The image acquisition device is connected to the processor, and is used to acquire image information of an object to be identified, and transmit the image information to the processor;

The processor is connected to each of the teaching modules, and is used to receive the image information, perform detection and recognition processing on the image information, and obtain detection and recognition image information; select the corresponding teaching module according to the detection and recognition image information. module, and transmit the detection and recognition image information to the corresponding teaching module;

The teaching module is used to generate teaching content according to detected and recognized image information and preset teaching resources;

The display module, connected to the processor, is used for displaying detection and recognition results and playing teaching content to complete teaching.

As a kind of implementable mode, the artificial intelligence teaching system based on TensorFlow provided by the utility model also includes a communication module;

The communication module is connected to the processor, and is used for exchanging data between the external server and the processor through the communication module, and downloading teaching resources to the corresponding teaching module.

As a possible implementation, the teaching modules are basic teaching modules and advanced teaching modules;

The basic teaching module is connected to the processor, and is used to generate basic teaching content according to detection and recognition image information and preset basic teaching resources;

The high-level teaching module is connected to the processor, and is used to generate high-level teaching content according to detected and recognized image information and preset high-level teaching resources.

As a possible implementation, the basic teaching module includes a support vector machine teaching unit and a Bayesian classifier teaching unit;

The support vector machine teaching unit is used to generate the teaching content of the principle and application of the support vector machine;

The Bayesian classifier teaching unit is used to generate teaching content on the principles and applications of Bayesian classifiers.

As a possible implementation, the advanced teaching module includes a picture classification teaching unit, a Chinese character recognition teaching unit, a fake teaching unit, an object detection teaching unit, an artistic style transfer teaching unit, a speech recognition teaching unit, a picture-speaking teaching unit, Facial recognition teaching unit, robot humanoid game teaching unit and chat robot teaching unit;

The picture classification teaching unit is used to generate the teaching content of the principle and application of picture classification;

The Chinese character recognition teaching unit is used to generate the teaching content of the principle and application of Chinese character recognition;

The teaching unit of confusing the real with the fake is used to generate the teaching content of the principle and application of the fake for the real;

The target detection teaching unit is used to generate the teaching content of the principle and application of target detection;

The artistic style transfer teaching unit is used to generate the teaching content of the artistic style transfer principle and application;

The speech recognition teaching unit is used to generate the teaching content of the principles and applications of speech recognition;

The talking-by-pictures teaching unit is used to generate teaching content on the principle and application of talking by pictures;

The face recognition teaching unit is used to generate teaching content on principles and applications of face recognition;

The teaching unit for playing humanoid games with machines is used to generate teaching content on the principle and application of humanoid machines for playing games;

The chat robot teaching unit is used to generate the teaching content of the principles and applications of the chat robot.

As a kind of implementable mode, the artificial intelligence teaching system based on TensorFlow provided by the utility model also includes an input module;

The input module is connected to the processor and used for providing instruction data input.

As a possible implementation manner, the input module is a keyboard input module and/or a human-computer interaction interface.

As a possible implementation, the image acquisition device includes a light source and several cameras;

The light source is connected to the processor, and when the camera collects image information, the supplementary light is performed according to the supplementary light signal of the processor;

Each of the cameras is set according to a preset angle, and is used to collect image information from different angles of the object to be identified.

As a kind of implementable mode, the artificial intelligence teaching system based on TensorFlow provided by the utility model also includes a voice module;

The voice module is connected to the processor and is used for playing teaching content by voice.

As a kind of implementable mode, the artificial intelligence teaching system based on TensorFlow provided by the utility model also includes a storage module;

The storage module is connected to the processor and used for storing historical data.

Compared with the prior art, the utility model has the following advantages:

The artificial intelligence teaching system based on TensorFlow provided by the utility model includes a power supply module, an image acquisition device, a processor, several teaching modules and a display module; the power supply module is used to provide working voltage for each component; the processor is connected to each teaching module , used to receive the image information of the object to be recognized collected by the image acquisition device, perform detection and recognition processing on the image information, and obtain the detection and recognition image information; select the corresponding teaching module according to the detection and recognition image information, and transmit the detection and recognition image information to the corresponding The teaching module; the teaching module is used to generate teaching content according to the detection and recognition image information and preset teaching resources; the display module is connected to the processor to display the detection and recognition results and play the teaching content to complete the teaching. The utility model can directly select the corresponding teaching module to carry out relevant teaching according to the image information collected by the image acquisition device, and lower the learning threshold; moreover, a large amount of learning resources can be stored inside, which can reduce the burden of books, improve learning enthusiasm, and enable students to find interest in learning.

Description of drawings

FIG. 1 is a schematic structural diagram of a TensorFlow-based artificial intelligence teaching system provided by Embodiment 1 of the present invention.

In the figure: 1. Power supply module; 2. Image acquisition device; 3. Processor; 4. Teaching module; 5. Display module; 6. Communication module; 7. Input module; 8. Voice module; 9. Storage module.

Detailed ways

The above and other technical features and advantages of the utility model are clearly and completely described below in conjunction with the accompanying drawings. Apparently, the described embodiments are only some embodiments of the utility model, rather than all embodiments.

Please refer to Fig. 1, the artificial intelligence teaching system based on TensorFlow provided by the first embodiment of the utility model includes a power supply module 1, an image acquisition device 2, a processor 3, several teaching modules 4 and a display module 5;

The power supply module 1 is connected with the image acquisition device 2, the processor 3, the teaching module 4 and the display module 5 respectively, and is used to provide the working voltage of the image acquisition device 2, the processor 3, the teaching module 4 and the display module 5; the image acquisition device 2 Connected to the processor 3 for collecting the image information of the object to be recognized and transmitting the image information to the processor 3; the processor 3 is connected to each teaching module 4 for receiving the image information and performing detection and recognition processing on the image information, Obtain the detection and recognition image information; select the corresponding teaching module 4 according to the detection and recognition image information, and transmit the detection and recognition image information to the corresponding teaching module 4; the teaching module 4 is used to generate teaching content according to the detection and recognition image information and preset teaching resources ; The display module 5 is connected to the processor 3 for displaying the detection and recognition results and playing the teaching content to complete the teaching.

It should be noted that the power supply module 1 is connected to each component that needs power supply, and provides working voltage for each component to ensure normal operation of each component. The power supply module 1 may be a built-in power supply, or an external power supply interface connected to an external power supply. The image information collected by the image acquisition device 2 of the object to be identified includes, but is not limited to, picture information, text information, and video information. For each object to be identified, its image information can be obtained from different angles and time nodes, and the image information can be collected in all directions to improve the integrity of the collection, thereby improving the accuracy of subsequent detection and recognition.

Detection and recognition image information includes, but is not limited to, position information, category information, environment information, action information, name information, and item feature information; for example, the obtained detection and recognition image information includes male, indoor, sitting on a seat, vector machine and Style and other data, select the corresponding teaching module 4 according to the above-mentioned detection and recognition image information. In the teaching module 4, the corresponding teaching content is generated according to the above-mentioned detected and recognized image information and the preset teaching resources. Teaching module 4 is constructed by artificial intelligence construction based on TensorFlow framework through machine learning. Different teaching modules 4 are constructed according to different preset teaching resources, and each teaching module 4 can generate teaching content according to detected and recognized image information and preset teaching resources. For example, the basic teaching resources are preset in the basic teaching module, and the basic teaching resources include teaching resources not limited to Chinese, mathematics, music and science; when using the basic teaching module to generate teaching content, you can generate Chinese, mathematics, music and science teaching content of other subjects. The teaching resources of artistic style transfer principles and applications are preset in the artistic style transfer teaching unit. The burden of books can be reduced, only the image information collected by the image collection device 2 can be used to carry out appropriate teaching, the enthusiasm for learning is improved, and learning is no longer boring. In other embodiments, during the teaching process, the teaching process can be controlled according to the motion information in the detected and recognized image information. For example, gestures such as pause, fast forward, and skip can be used to control the teaching content through the processor 3 . In other embodiments, the teaching module 4 can be constructed based on artificial intelligence of other frameworks, which is not limited here.

The display module 5 can display the detection and recognition results and play the teaching content to complete the teaching; the display module 5 can also display the playing process of the teaching content, which is convenient for the user to control the playback through the action information. Further, the preferred model of the display screen is VX2039-SAW.

The artificial intelligence teaching system based on TensorFlow provided by the utility model includes a power supply module 1, an image acquisition device 2, a processor 3, several teaching modules 4 and a display module 5; the power supply module 1 is used to provide working voltage for each component; The device 3 is connected to each teaching module 4, and is used to receive the image information of the object to be recognized collected by the image acquisition device 2, and perform detection and recognition processing on the image information to obtain detection and recognition image information; select the corresponding teaching module 4 according to the detection and recognition image information , and transmit the detection and recognition image information to the corresponding teaching module 4; the teaching module 4 is used to generate teaching content according to the detection and recognition image information and preset teaching resources; the display module 5 is connected to the processor 3 for displaying the detection and recognition results and playing The teaching content completes the teaching. The utility model can directly select the corresponding teaching module 4 to carry out relevant teaching according to the image information collected by the image acquisition device 2, and lower the learning threshold; moreover, a large amount of learning resources can be stored inside, which can reduce the burden of books, improve learning enthusiasm, and make students Get back your interest in learning.

Further, the artificial intelligence teaching system based on TensorFlow provided by Embodiment 2 of the utility model also includes a communication module 6 compared with Embodiment 1; the communication module 6 is connected to the processor 3, and is used to make the external server communicate with Processor 3 performs data interaction, and downloads teaching resources to corresponding teaching modules 4 .

The communication module 6 can be a wired communication module or a wireless communication module; different communication modules 6 are selected according to different application scenarios to complete the data interaction between the external server and the processor 3, which is convenient for users. Avoid the use restrictions in some places without wireless communication.

Each part of the utility model is described in detail below:

The teaching module 4 is a basic teaching module and an advanced teaching module; the basic teaching module is connected to the processor 3, and is used to generate basic teaching content according to the detected and recognized image information and preset basic teaching resources; the advanced teaching module is connected to the processor 3, used to Generate high-level teaching content based on detection and recognition image information and preset high-level teaching resources. The utility model has abundant teaching modules 4, which not only reduces the burden of books and waste of resources, but also can meet the learning needs of users in various aspects.

Among them, the basic teaching module includes the teaching unit of support vector machine and the teaching unit of Bayesian classifier; the teaching unit of support vector machine is used to generate the teaching content of the principle and application of support vector machine; the teaching unit of Bayesian classifier is used Generate teaching content on the principles and applications of Bayesian classifiers.

Among them, the advanced teaching module includes picture classification teaching unit, Chinese character recognition teaching unit, fake teaching unit, target detection teaching unit, artistic style transfer teaching unit, speech recognition teaching unit, picture-speaking teaching unit, face recognition teaching unit, machine The humanoid game teaching unit and the chat robot teaching unit; the picture classification teaching unit is used to generate the teaching content of the principle and application of picture classification; the Chinese character recognition teaching unit is used to generate the teaching content of the principle and application of Chinese character recognition; The target detection teaching unit is used to generate the teaching content of the principle and application of target detection; the artistic style transfer teaching unit is used to generate the teaching content of the artistic style transfer principle and application; the speech recognition teaching unit It is used to generate the teaching content of the principle and application of speech recognition; the teaching unit of talking through pictures is used to generate the teaching content of the principle and application of speaking through pictures; the teaching unit of face recognition is used to generate the teaching content of the principle and application of face recognition ; The teaching unit of robot humanoid game playing is used to generate the teaching content of the principle and application of the robot humanoid game playing; the chat robot teaching unit is used to generate the teaching content of the principle and application of the chat robot.

Further, the image acquisition device 2 includes a light source and a plurality of cameras; the light source is connected to the processor 3, and when the camera collects image information, it performs supplementary light according to the supplementary light signal of the processor 3; Identify image information from different angles of an object.

The light source can be one or more of LED lamps, incandescent lamps and fluorescent lamps. It can be set separately or in the camera. When the camera collects image information, supplementary light is performed according to the supplementary light signal of the processor 3, which avoids unclear image information caused by insufficient light. The preferred model of the camera is IMX214, which can cooperate with the amcap in the processor 3 to set and adjust the camera to improve the quality of the collected image information.

Compared with Embodiment 1, the artificial intelligence teaching system based on TensorFlow provided by Embodiment 3 of the utility model also includes an input module 7 and a voice module 8; the input module 7 is connected to the processor 3 for providing instruction data input. The input module 7 is a keyboard input module and/or a human-computer interaction interface. The voice module 8 is connected to the processor 3 and is used for voice playing teaching content.

In addition to realizing the control of the teaching content according to the action information, it can also be realized according to the instruction data input of the input module 7 . When the input module 7 is a keyboard input module, the corresponding command data is directly generated through the keyboard input module, and the command data is transmitted to the processor 3 for corresponding control. When the input module 7 is a human-computer interaction interface, the corresponding command data is directly generated through the human-computer interaction interface, and the command data is transmitted to the processor 3 for corresponding control. When teaching according to the teaching content, the voice module 8 can also be used to play teaching, so as to realize the diversity of teaching and improve the teaching effect.

Compared with Embodiment 1, the TensorFlow-based artificial intelligence teaching system provided by Embodiment 4 of the present utility model also includes a storage module 9; the storage module 9 is connected to the processor 3 for storing historical data. The stored historical data can be used as reference data, and a database can be established based on historical data, which is convenient for data traceability and subsequent analysis and research on historical data.

Although the utility model has been disclosed as above with preferred embodiments, it is not intended to limit the utility model, and any person skilled in the art can utilize the method and technology disclosed above without departing from the spirit and scope of the utility model The content makes possible changes and modifications to the technical solution of the utility model. Therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the utility model without departing from the content of the technical solution of the utility model shall be It belongs to the protection scope of the technical solution of the utility model.

Claims (9)

1. a kind of tutoring system of the artificial intelligence based on TensorFlow, which is characterized in that including power module, Image Acquisition Device, processor, several Teaching Modules and display module；

The power module connect with described image harvester, processor, Teaching Module and display module, is used for respectively The operating voltage of described image harvester, processor, Teaching Module and display module is provided；

Described image harvester, is connected to the processor, the image information for acquiring object to be identified, and by the figure As information is transmitted to the processor；

Described image harvester includes light source and several cameras；

The light source connects the processor, in camera collection image information, is mended according to the light filling signal of processor Light；

Each camera is arranged according to predetermined angle, the image information of the different angle for acquiring object to be identified；

The processor connects each Teaching Module and is examined to described image information for receiving described image information Identifying processing is surveyed, detection identification image information is obtained；Identify that image information selects the corresponding teaching mould according to the detection Block, and detection identification image information is transmitted to the corresponding Teaching Module；

The Teaching Module, for generating the content of courses according to detection identification image information and preset teaching resource；

The display module connects the processor, and teaching is completed for showing detection recognition result and playing the content of courses.

2. the tutoring system of the artificial intelligence based on TensorFlow as described in claim 1, which is characterized in that further include leading to Interrogate module；

The communication module connects the processor, so that external server is carried out data with processor for passing through communication module Interaction, and teaching resource is downloaded in corresponding Teaching Module.

3. the tutoring system of the artificial intelligence based on TensorFlow as described in claim 1, which is characterized in that the teaching Module is basic Teaching Module and high-order Teaching Module；

The elementary teaching module, connects the processor, for being provided according to detection identification image information and preset elementary teaching Source generates elementary teaching content；

The high-order Teaching Module, connects the processor, for according to detection identification image information and preset high-order teaching money Source generates the high-order content of courses.

4. the tutoring system of the artificial intelligence based on TensorFlow as claimed in claim 3, which is characterized in that the basis Teaching Module includes support vector machines teaching unit and Bayes classifier teaching unit；

The support vector machines teaching unit, the content of courses of principle and application for generating support vector machines；

The Bayes classifier teaching unit, the content of courses for generating Bayes classifier principle and application.

5. the tutoring system of the artificial intelligence based on TensorFlow as claimed in claim 3, which is characterized in that the high-order Teaching Module includes picture classification teaching unit, Chinese Character Recognition teaching unit, teaching unit of mixing the spurious with the genuine, target detection teaching list Member, artistic style migration teaching unit, speech recognition tutorial unit, picture talk teaching unit, recognition of face teaching unit, machine Device apery plays play instruction unit and chat robots teaching unit；

The picture classification teaching unit, the content of courses of principle and application for generating picture classification；

The Chinese Character Recognition teaching unit, the content of courses of principle and application for generating Chinese Character Recognition；

The teaching unit of mixing the spurious with the genuine, the content of courses for generating the principle and application mixed the spurious with the genuine；

The target detection teaching unit, the content of courses of principle and application for generating target detection；

The artistic style migrates teaching unit, is used for the content of courses of Generative Art Style Transfer principle and application；

The speech recognition tutorial unit, the content of courses of principle and application for generating speech recognition；

The picture talk teaching unit, the content of courses of principle and application for generating picture talk；

The recognition of face teaching unit, the content of courses of principle and application for generating recognition of face；

The machine apery plays play instruction unit, the content of courses for playing the principle and application of game for generating machine apery；

The chat robots teaching unit, the content of courses of principle and application for generating chat robots.

6. the tutoring system of the artificial intelligence based on TensorFlow as described in claim 1, which is characterized in that further include defeated Enter module；

The input module connects the processor, for providing director data input.

7. the tutoring system of the artificial intelligence based on TensorFlow as claimed in claim 6, which is characterized in that the input Module is keyboard input module and/or human-computer interaction interface.

8. the tutoring system of the artificial intelligence based on TensorFlow as described in claim 1, which is characterized in that further include language Sound module；

The voice module connects the processor, is used for the speech play content of courses.

9. the tutoring system of the artificial intelligence based on TensorFlow as described in claim 1, which is characterized in that further include depositing Store up module；

The memory module connects the processor, is used for store historical data.