Micro-course video management method, device, system and storage medium

Abstract

The present invention relates to the field of online education technology, and discloses a video micro-course management method, device, system and storage medium, which are used to improve the interactivity between a smart pen and server content in a micro-course video learning scenario. The method of the present invention comprises: writing the initial text of a target user by a smart pen and performing OCR processing on the initial text to obtain a text image of the initial text; recognizing the text image by a server to determine the text intention of the target user; selecting a target micro-course video in a micro-course video resource library according to the text intention; playing the target micro-course video by a server and determining the type of the target micro-course video; if the type of the target micro-course video is a teaching and research video, calling a preset teaching and research service interface and displaying the teaching and research function logo of the teaching and research service interface in the target micro-course video; if the type of the target micro-course video is a learning video, calling a preset learning service interface and displaying the learning function logo of the learning service interface in the target micro-course video.

Description

Technical Field

[0001] The present invention relates to the field of online education technology, and in particular to a micro-course video management method, device, system and storage medium. Background Art

[0002] With the rapid development of the Internet, the demand for remote work is increasing, especially in the field of online education, such as remote video learning, online teaching, interactive classrooms, etc. The demand has shown explosive growth. With the development of online education, more and more smart devices are involved in online education, among which smart pens are the most widely used smart devices.

[0003] Users can connect the smart pen to the mobile phone APP and upload the content written by the smart pen to the APP to realize content backup and editing. However, current smart pens rely on mobile phone APP or the handwriting board that comes with the smart pen, because the content on the smart pen side is independently saved and calculated, and can only complete simple content recording. When studying online micro-class videos on mobile phones or computers, smart pens can only complete the basic function of writing, and are not very intelligent. They cannot respond to user needs in a timely manner, resulting in low efficiency in the server's management of micro-class videos. Summary of the invention

[0004] The present invention provides a micro-course video management method, device, system and storage medium, which are used to recognize the intention of the writing content of a smart pen, actively select the micro-course video required by the user according to the recognized intention, and provide a functional interface of the corresponding video content, thereby improving the interactivity between the smart pen and the server content in the micro-course video learning scenario and improving the management efficiency of the micro-course video.

[0005] A first aspect of an embodiment of the present invention provides a micro-course video management method, which is applied to a micro-course video service system, wherein the micro-course video service system includes a server, a micro-course video resource library and a smart pen, and is characterized in that it includes: writing the initial text of a target user by means of the smart pen and performing optical character recognition (OCR) processing on the initial text by means of a camera recognition component provided on the smart pen to obtain a text image of the initial text, wherein the smart pen is connected to the server via a communication module; recognizing the text image by means of the server to determine the text intention of the target user; selecting a target micro-course video in the micro-course video resource library according to the text intention, wherein the micro-course video resource library includes teaching and research videos and learning videos, wherein the teaching and research video The videos include online teaching videos, online live broadcast videos, teaching and research conference videos and educational lecture videos, and the learning videos include famous teachers' classroom recording videos, demonstration videos of excellent courses and online micro-class videos; the target micro-class video is played by the server and the type of the target micro-class video is determined; if the type of the target micro-class video is a teaching and research video, a preset teaching and research service interface is called and the teaching and research function logo of the teaching and research service interface is displayed in the target micro-class video, and the teaching and research function logo includes scoring and discussion; if the type of the target micro-class video is a learning video, a preset learning service interface is called and the learning function logo of the learning service interface is displayed in the target micro-class video, and the learning function logo includes likes and collections.

[0006] Optionally, in a first implementation method of the first aspect of the embodiment of the present invention, the text image is recognized by the server to determine the text intent of the target user, including: calling a preset sliding window algorithm to preprocess the text image to obtain a text area, and the text area includes the initial text written by the target user; performing rectangular segmentation on the text area to obtain a plurality of character areas; calling a preset supervised algorithm to recognize each character area to obtain a text sequence, and the text sequence includes a plurality of characters; and inputting the text sequence into a preset intention recognition model to obtain the text intent of the target user.

[0007] Optionally, in a second implementation method of the first aspect of the embodiment of the present invention, the text sequence is input into a preset intent recognition model to obtain the text intent of the target user, including: inputting the text sequence into the encoder layer of the intent recognition model to obtain a hidden state vector, the encoder layer being composed of a BiLSTM; inputting the hidden state vector into a preset word slot filling layer to obtain a domain recognition result; and determining the text intent of the target user based on the hidden state vector and the domain recognition result.

[0008] Optionally, in a third implementation of the first aspect of the embodiment of the present invention, determining the text intention of the target user according to the hidden state vector and the domain recognition result includes: transforming the hidden state vector h i They are input into the intention attention layer and word slot attention layer of the intention recognition model respectively to obtain the intention attention vector c I and the attention vector of the current word slot According to the preset association vector formula, the attention vector c of the intention I and the attention vector of the current word slot The correlation vector g is calculated, and the preset correlation vector formula is: Where W is the weight, v is the preset initialization vector; according to the association vector g and the hidden layer state vector h i Calculate the predicted label of the word slot The textual intention of the target user is determined according to the predicted label of the word slot and the domain recognition result.

[0009] Optionally, in a fourth implementation manner of the first aspect of the embodiment of the present invention, after calling a preset learning service interface and displaying the learning function identifier of the learning service interface in the target micro-class video, and the learning function identifier includes likes and favorites, the method further includes: when the type of the target micro-class video is a learning video, obtaining the like operation and / or favorite operation triggered by the smart pen on the target micro-class video, recording the like operation and / or favorite operation through the server, and updating the number of likes and / or favorites of the target micro-class video.

[0010] Optionally, in a fifth implementation manner of the first aspect of the embodiment of the present invention, after calling a preset learning service interface and displaying the learning function identifier of the learning service interface in the target micro-class video, wherein the learning function identifier includes likes and favorites, the method further includes: when the type of the target micro-class video is a learning video and it is a paid video, sending a play request instruction to the server through the smart pen, and receiving the fee information fed back by the server, and making online payment according to the fee information through the billing component in the smart pen, wherein the billing component of the smart pen is pre-bound to a payment channel.

[0011] Optionally, in a sixth implementation manner of the first aspect of the embodiment of the present invention, after calling a preset learning service interface and displaying the learning function identifier of the learning service interface in the target micro-class video, wherein the learning function identifier includes likes and favorites, the method further includes: when the smart pen is lost, tracking and locating the smart pen through a server, wherein the smart pen and the server have been bound and authorized, and a positioning component is provided on the smart pen.

[0012] The second aspect of the embodiment of the present invention provides a micro-course video management device, including: a processing module, used to write the initial text of the target user through a smart pen and perform optical character recognition (OCR) processing on the initial text through a camera recognition component provided on the smart pen to obtain a text image of the initial text, wherein the smart pen is connected to the server through a communication module; an intention recognition module, used to recognize the text image through the server to determine the text intention of the target user; a video selection module, used to select a target micro-course video in the micro-course video resource library according to the text intention, wherein the micro-course video resource library includes teaching and research videos and learning videos, wherein the teaching and research videos include online teaching videos, online live broadcast videos, teaching and research conference videos and Educational lecture videos, the learning videos include famous teachers' classroom recording videos, demonstration videos of excellent courses and online micro-class videos; a playback determination module, used to play the target micro-class video through the server and determine the type of the target micro-class video; a first calling display module, if the type of the target micro-class video is a teaching and research video, it is used to call a preset teaching and research service interface and display the teaching and research function logo of the teaching and research service interface in the target micro-class video, and the teaching and research function logo includes scoring and discussion; a second calling display module, if the type of the target micro-class video is a learning video, it is used to call a preset learning service interface and display the learning function logo of the learning service interface in the target micro-class video, and the learning function logo includes likes and collections.

[0013] Optionally, in a first implementation method of the second aspect of the embodiment of the present invention, the intention recognition module includes: a preprocessing unit, used to call a preset sliding window algorithm to preprocess the text image to obtain a text area, and the text area includes the initial text written by the target user; a segmentation unit, used to perform rectangular segmentation on the text area to obtain multiple character areas; a character recognition unit, used to call a preset supervised algorithm to recognize each character area to obtain a text sequence, and the text sequence includes multiple characters; an intention recognition unit, used to input the text sequence into a preset intention recognition model to obtain the text intention of the target user.

[0014] Optionally, in a second implementation manner of the second aspect of the embodiment of the present invention, the intention recognition unit includes: a first input subunit, used to input the text sequence into the encoder layer of the intention recognition model to obtain a hidden state vector, the encoder layer being composed of a BiLSTM; a second input subunit, used to input the hidden state vector into a preset word slot filling layer to obtain a domain recognition result; and a determination subunit, used to determine the text intention of the target user based on the hidden state vector and the domain recognition result.

[0015] Optionally, in a third implementation of the second aspect of the embodiment of the present invention, the determination subunit is specifically configured to: transform the hidden layer state vector h i They are input into the intention attention layer and word slot attention layer of the intention recognition model respectively to obtain the intention attention vector c I and the attention vector of the current word slot According to the preset association vector formula, the attention vector c of the intention I and the attention vector of the current word slot The correlation vector g is calculated, and the preset correlation vector formula is: Where W is the weight, v is the preset initialization vector; according to the association vector g and the hidden layer state vector h i Calculate the predicted label of the word slot The textual intention of the target user is determined according to the predicted label of the word slot and the domain recognition result.

[0016] Optionally, in a fourth implementation method of the second aspect of the embodiment of the present invention, the micro-course video management device also includes: a record update module, which is used to obtain the like operation and / or collection operation triggered by the smart pen on the target micro-course video when the type of the target micro-course video is a learning video, record the like operation and / or collection operation through the server, and update the number of likes and / or collections of the target micro-course video.

[0017] Optionally, in a fifth implementation method of the second aspect of the embodiment of the present invention, the micro-course video management device also includes: a payment module, which is used to send a play request instruction to the server through a smart pen when the type of the target micro-course video is a learning video and it is a paid video, and receive fee information fed back by the server, and make online payment according to the fee information through the billing component in the smart pen, wherein the billing component of the smart pen is pre-bound with a payment channel.

[0018] Optionally, in a sixth implementation method of the second aspect of the embodiment of the present invention, the micro-class video management device also includes: a tracking and positioning module, which is used to track and locate the smart pen through a server when the smart pen is lost, wherein the smart pen and the server have been bound and authorized, and a positioning component is provided on the smart pen.

[0019] A third aspect of an embodiment of the present invention provides a micro-course video management system, comprising: a server, a micro-course video resource library and a smart pen; the server is connected to the micro-course video resource library and the smart pen through a network; the server comprises a processing module, a playback component, an interface calling component and a communication module, wherein the processing module is used to process the data transmitted by the smart pen and the data generated in the micro-course video resource library, the playback component is used to play the teaching and research video or the learning video, the interface calling component is used to call the learning service interface or the teaching and research service interface, and the communication module is used to connect the smart pen; the micro-course video resource library comprises a video storage module and an interface library component, wherein the video storage module is used to store the teaching and research video and the learning video, The teaching and research videos include online teaching videos, online live broadcast videos, teaching and research conference videos and educational lecture videos; the learning videos include real-time videos of famous teachers' classes, demonstration videos of excellent courses and online micro-class videos; the interface library component is used to connect the video storage component to the learning service interface or the teaching and research service interface; the smart pen includes a communication module, a writing component, a camera recognition component, a billing component and a tracking component, wherein the communication module is used to connect to the server, the writing component is used to write text on paper, the camera recognition component is used to take pictures and recognize the text written by the smart pen, the billing component is used to make online payments, the billing component includes a quick payment button set on the smart pen, and the tracking component is used to provide a positioning function.

[0020] A fourth aspect of an embodiment of the present invention provides a computer-readable storage medium, which stores instructions. When the instructions are executed by a processor, the steps of the micro-course video management method described in any of the above embodiments are implemented.

[0021] In the technical solution provided by the embodiment of the present invention, the initial text of the target user is written by a smart pen, and the initial text is subjected to optical character recognition (OCR) processing by a camera recognition component provided on the smart pen to obtain a text image of the initial text, and the smart pen is connected to a server through a communication module; the text image is recognized by the server to determine the text intention of the target user; a target micro-class video is selected from a micro-class video resource library according to the text intention, and the micro-class video resource library includes teaching and research videos and learning videos, wherein the teaching and research videos include online teaching videos, online live broadcast videos, teaching and research conference videos and educational lecture videos, and the learning videos include famous teachers' classroom recording videos, demonstration excellent course videos and online micro-class videos; the target micro-class video is played by the server and the type of the target micro-class video is determined; if the type of the target micro-class video is a teaching and research video, a preset teaching and research service interface is called and a teaching and research function identifier of the teaching and research service interface is displayed in the target micro-class video, and the teaching and research function identifier includes scoring and discussion; if the type of the target micro-class video is a learning video, a preset learning service interface is called and a learning function identifier of the learning service interface is displayed in the target micro-class video, and the learning function identifier includes likes and collections. The embodiment of the present invention recognizes the intention of the writing content of the smart pen, actively selects the micro-course video required by the user according to the recognized intention, and provides a functional interface of the corresponding video content, thereby improving the interactivity between the smart pen and the server content in the micro-course video learning scenario and improving the management efficiency of the micro-course videos. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A schematic diagram of an embodiment of a micro-course video management method in an embodiment of the present invention;

[0023] Figure 2 A schematic diagram of another embodiment of the micro-course video management method in an embodiment of the present invention;

[0024] Figure 3 A schematic diagram of an embodiment of a micro-course video management device in an embodiment of the present invention;

[0025] Figure 4 It is another embodiment schematic diagram of the micro-course video management device in the embodiment of the present invention;

[0026] Figure 5 Schematic diagram of an embodiment of a micro-course video management system in an embodiment of the present invention. DETAILED DESCRIPTION

[0027] The present invention provides a micro-course video management method, device, system and storage medium, which are used to recognize the intention of the writing content of a smart pen, actively select the micro-course video required by the user according to the recognized intention, and provide a functional interface of the corresponding video content, thereby improving the interactivity between the smart pen and the server content in the micro-course video learning scenario and improving the management efficiency of the micro-course video.

[0028] In order to enable those skilled in the art to better understand the solutions of the present invention, the embodiments of the present invention will be described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0029] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] See also Figure 1 , a flow chart of the micro-course video management method provided by an embodiment of the present invention specifically includes:

[0031] 101. Write the target user's initial text with a smart pen and perform optical character recognition (OCR) on the initial text through a camera recognition component provided on the smart pen to obtain a text image of the initial text. The smart pen is connected to a server through a communication module.

[0032] The micro-course video management system uses a smart pen to write the target user's initial text and performs OCR processing on the initial text through the camera recognition component set on the smart pen to obtain a text image of the initial text. The smart pen is connected to the server through a communication module. For example, the initial text can be "High School Mathematics Video", "Primary School Chinese Classroom Explanation", "Primary School English Classroom Recording Video of Famous Teachers", etc. The details are not repeated here.

[0033] It should be noted that the present embodiment is applied to a micro-course video management system, including: a server, a micro-course video resource library and a smart pen; the server is connected to the micro-course video resource library and the smart pen through a network; the server includes a processing module, a playback component, an interface calling component and a communication module, wherein the processing module is used to process data transmitted by the smart pen and data generated in the micro-course video resource library, the playback component is used to play teaching and research videos or learning videos, the interface calling component is used to call a learning service interface or a teaching and research service interface, and the communication module is used to connect to the smart pen; the micro-course video resource library includes a video storage module and an interface library component, wherein the video storage module is used to store teaching and research videos and learning videos, and the teaching and research service interface is used to call the learning service interface or the teaching and research service interface. Research videos include online teaching videos, online live broadcast videos, teaching and research meeting videos and educational lecture videos. Learning videos include famous teachers' classroom recordings, demonstration videos of excellent courses and online micro-class videos. The interface library component is used to connect the video storage component to the learning service interface or the teaching and research service interface; the smart pen includes a communication module, a writing component, a camera recognition component, a billing component and a tracking component. Among them, the communication module is used to connect to the server, the writing component is used to write text on paper, the camera recognition component is used to take pictures and recognize the text written by the smart pen, the billing component is used to make online payments, the billing component includes a quick payment button set on the smart pen, and the tracking component is used to provide positioning function.

[0034] It is understandable that the execution subject of the present invention may be a micro-course video management device or a micro-course video management system, which is not specifically limited herein. The embodiment of the present invention is described by taking the micro-course video management system as the execution subject.

[0035] 102. The text image is recognized by the server to determine the text intention of the target user.

[0036] The micro-course video management system recognizes text images through the server to determine the text intent of the target user.

[0037] Specifically, the micro-course video management system calls a preset sliding window algorithm to pre-process the text image to obtain a text area, which includes the initial text written by the target user; the micro-course video management system performs rectangular segmentation on the text area to obtain multiple character areas; the micro-course video management system calls a preset supervision algorithm to identify each character area to obtain a text sequence, which includes multiple characters; the micro-course video management system inputs the text sequence into a preset intent recognition model to obtain the text intent of the target user.

[0038] It should be noted that other algorithms (for example, CTPN algorithm, SegLink algorithm, etc.) can also be used to determine the text area. The text area is the content range written by the target user through the smart pen. According to the different writing habits of the target user, the range of the corresponding text area is also different. This embodiment uses the minimum range surrounding all the written content as the text area, and calls the preset supervision algorithm for character recognition. The details will not be repeated here.

[0039] 103. Select the target micro-course video in the micro-course video resource library according to the textual intent. The micro-course video resource library includes teaching and research videos and learning videos. Teaching and research videos include online teaching videos, online live broadcast videos, teaching and research meeting videos and educational lecture videos. Learning videos include famous teachers’ classroom recording videos, demonstration videos of excellent courses and online micro-course videos.

[0040] The micro-course video management system selects the target micro-course video from the micro-course video resource library according to the text intent. The micro-course video resource library includes teaching and research videos and learning videos. Among them, teaching and research videos include online teaching videos, online live broadcast videos, teaching and research meeting videos and educational lecture videos. Learning videos include famous teachers' classroom recordings, demonstration videos of excellent courses and online micro-course videos.

[0041] 104. Play the target micro-course video through the server and determine the type of the target micro-course video.

[0042] The micro-course video management system plays the target micro-course video through the server and determines the type of the target micro-course video.

[0043] Among them, the types of target micro-class videos include teaching and research videos and learning videos. Teaching and research videos are videos with themes of popular science knowledge, common sense of production and life, or production skills knowledge, and learning videos are videos with themes of teaching materials. The teaching themes of teaching and research videos and learning videos are different.

[0044] 105. If the type of the target micro-class video is a teaching and research video, the preset teaching and research service interface is called and the teaching and research function logo of the teaching and research service interface is displayed in the target micro-class video. The teaching and research function logo includes scoring and discussion.

[0045] If the type of the target micro-course video is a teaching and research video, the micro-course video management system calls the preset teaching and research service interface and displays the teaching and research function logo of the teaching and research service interface in the target micro-course video. The teaching and research function logo includes scoring and discussion.

[0046] In this embodiment, the corresponding functional interface is selected according to the different themes of the videos, thereby improving efficiency and saving unnecessary resource expenditures.

[0047] 106. If the type of the target micro-course video is a learning video, a preset learning service interface is called and a learning function identifier of the learning service interface is displayed in the target micro-course video. The learning function identifier includes likes and collections.

[0048] If the type of the target micro-course video is a learning video, the micro-course video management system calls a preset learning service interface and displays the learning function identifier of the learning service interface in the target micro-course video. The learning function identifier includes likes and collections.

[0049] The embodiment of the present invention recognizes the intention of the writing content of the smart pen, actively selects the micro-course video required by the user according to the recognized intention, and provides the functional interface of the corresponding video content, thereby improving the interactivity between the smart pen and the server content in the micro-course video learning scene and improving the management efficiency of the micro-course video. In addition, this solution can be applied to the field of smart education, thereby promoting the construction of smart cities.

[0050] See also Figure 2 , another flow chart of the micro-course video management method provided by an embodiment of the present invention specifically includes:

[0051] 201. Write the target user's initial text with a smart pen and perform optical character recognition (OCR) on the initial text through a camera recognition component provided on the smart pen to obtain a text image of the initial text. The smart pen is connected to a server through a communication module.

[0052] The micro-course video management system uses a smart pen to write the target user's initial text and performs OCR processing on the initial text through the camera recognition component set on the smart pen to obtain a text image of the initial text. The smart pen is connected to the server through a communication module. For example, the initial text can be "High School Mathematics Video", "Primary School Chinese Classroom Explanation", "Primary School English Classroom Recording Video of Famous Teachers", etc. The details are not repeated here.

[0053] It should be noted that the present embodiment is applied to a micro-course video management system, including: a server, a micro-course video resource library and a smart pen; the server is connected to the micro-course video resource library and the smart pen through a network; the server includes a processing module, a playback component and an interface calling component, wherein the processing component is used to process data transmitted by the smart pen and data generated in the micro-course video resource library, the interface calling component is used to call a learning service interface or a teaching and research service interface, and the playback component is used to play teaching and research videos or learning videos; the micro-course video resource library includes a video storage module and an interface library component, wherein the video storage module is used to store teaching and research videos and learning videos, and the teaching and research service interface is used to call a learning service interface or a teaching and research service interface, and the playback component is used to play teaching and research videos or learning videos. Research videos include online teaching videos, online live broadcast videos, teaching and research meeting videos and educational lecture videos. Learning videos include famous teachers' classroom recordings, demonstration videos of excellent courses and online micro-class videos. The interface library component is used to connect the video storage component to the learning service interface or the teaching and research service interface; the smart pen includes a writing component, a camera recognition component, a billing component and a tracking component. Among them, the writing component is used to write text on paper, the camera recognition component is used to take pictures and recognize the text written by the smart pen, the billing component is used to make online payments, the billing component includes a quick payment button set on the smart pen, and the tracking component is used to provide positioning function.

[0054] It is understandable that the execution subject of the present invention may be a micro-course video management device or a micro-course video management system, which is not specifically limited herein. The embodiment of the present invention is described by taking the micro-course video management system as the execution subject.

[0055] 202. The text image is recognized by the server to determine the text intention of the target user.

[0056] The micro-course video management system recognizes text images through the server to determine the text intent of the target user.

[0057] Specifically, the micro-course video management system calls a preset sliding window algorithm to pre-process the text image to obtain a text area, which includes the initial text written by the target user; the micro-course video management system performs rectangular segmentation on the text area to obtain multiple character areas; the micro-course video management system calls a preset supervision algorithm to identify each character area to obtain a text sequence, which includes multiple characters; the micro-course video management system inputs the text sequence into a preset intent recognition model to obtain the text intent of the target user.

[0058] It should be noted that other algorithms (for example, CTPN algorithm, SegLink algorithm, etc.) can also be used to determine the text area. The text area is the content range written by the target user through the smart pen. According to the different writing habits of the target user, the range of the corresponding text area is also different. This embodiment uses the minimum range surrounding all the written content as the text area, and calls the preset supervision algorithm for character recognition. The details will not be repeated here.

[0059] Optionally, the micro-course video management system inputs the text sequence into a preset intent recognition model to obtain the text intent of the target user, including:

[0060] The micro-course video management system inputs the text sequence into the encoder layer of the intent recognition model to obtain a hidden state vector, and the encoder layer is composed of BiLSTM; the micro-course video management system inputs the hidden state vector into the preset word slot filling layer to obtain a domain recognition result; the micro-course video management system determines the text intent of the target user based on the hidden state vector and the domain recognition result.

[0061] Optionally, the micro-course video management system determines the textual intent of the target user based on the hidden state vector and the domain recognition result, specifically including:

[0062] The micro-course video management system converts the hidden state vector h i They are input into the intention attention layer and word slot attention layer of the intention recognition model respectively to obtain the intention attention vector c I and the attention vector of the current word slot The micro-course video management system uses the preset association vector formula and the attention vector c of the intention I and the attention vector of the current word slot The correlation vector g is calculated, and the preset correlation vector formula is Where W is the weight, v is the preset initialization vector; the micro-course video management system is based on the association vector g and the hidden state vector h i Calculate the predicted label of the word slot The micro-course video management system determines the target user's textual intent based on the predicted labels of the word slots and the domain recognition results. It should be noted that,

[0063] This embodiment adds the task of domain identification. After the domain identification, the scope of intent that needs to be identified will be further narrowed, which enhances the correlation and hierarchy between the tasks and improves the performance of the model.

[0064] 203. Select the target micro-class video in the micro-class video resource library according to the textual intent. The micro-class video resource library includes teaching and research videos and learning videos. The teaching and research videos include online teaching videos, online live broadcast videos, teaching and research conference videos and educational lecture videos. The learning videos include famous teachers’ classroom recording videos, demonstration videos of excellent courses and online micro-class videos.

[0065] The micro-course video management system selects the target micro-course video from the micro-course video resource library according to the text intent. The micro-course video resource library includes teaching and research videos and learning videos. Among them, teaching and research videos include online teaching videos, online live broadcast videos, teaching and research meeting videos and educational lecture videos. Learning videos include famous teachers' classroom recordings, demonstration videos of excellent courses and online micro-course videos.

[0066] 204. Play the target micro-course video through the server and determine the type of the target micro-course video.

[0067] The micro-course video management system plays the target micro-course video through the server and determines the type of the target micro-course video.

[0068] Among them, the types of target micro-class videos include teaching and research videos and learning videos. Teaching and research videos are videos with themes of popular science knowledge, common sense of production and life, or production skills knowledge, and learning videos are videos with themes of teaching materials. The teaching themes of teaching and research videos and learning videos are different.

[0069] 205. If the type of the target micro-class video is a teaching and research video, the preset teaching and research service interface is called and the teaching and research function logo of the teaching and research service interface is displayed in the target micro-class video. The teaching and research function logo includes scoring and discussion.

[0070] If the target micro-course video type is a teaching and research video, the micro-course video management system calls the preset teaching and research service interface and displays the teaching and research function logo of the teaching and research service interface in the target micro-course video. The teaching and research function logo includes scoring and discussion. The teaching and research function logo can also add other logos for the specific type of video. For example, for live webcast videos, a shopping cart logo can be added. The details are not repeated here.

[0071] In this embodiment, the corresponding functional interface is selected according to the different themes of the videos, thereby improving efficiency and saving unnecessary resource expenditures.

[0072] 206. If the type of the target micro-course video is a learning video, a preset learning service interface is called and a learning function identifier of the learning service interface is displayed in the target micro-course video. The learning function identifier includes likes and collections.

[0073] If the type of the target micro-course video is a learning video, the micro-course video management system calls the preset learning service interface and displays the learning function identification of the learning service interface in the target micro-course video. The learning function identification includes likes and collections. The learning function identification can also add other identifications for the specific type of video. For example, for the demonstration of excellent course videos, a parsing identification can be added. By clicking on the parsing identification, the evaluation criteria for the demonstration of excellent courses can be obtained. The details will not be repeated here.

[0074] 207. When the type of the target micro-course video is a learning video, obtain the like operation and / or favorite operation triggered by the smart pen on the target micro-course video, record the like operation and / or favorite operation through the server, and update the number of likes and / or favorites of the target micro-course video.

[0075] When the type of the target micro-class video is a learning video, the micro-class video management system obtains the like operation and / or favorite operation triggered by the smart pen on the target micro-class video, records the like operation and / or favorite operation through the server, and updates the number of likes and / or favorites of the target micro-class video.

[0076] Optionally, this embodiment may further include:

[0077] When the target micro-course video type is a learning video and is a paid video, the micro-course video management system sends a play request instruction to the server through the smart pen, and receives the fee information fed back by the server, and makes online payment based on the fee information through the billing component in the smart pen, wherein the billing component of the smart pen is pre-bound with a payment channel.

[0078] Optionally, this embodiment may further include:

[0079] When the smart pen is lost, the micro-course video management system tracks and locates the smart pen through the server, wherein the smart pen and the server have been bound and authorized, and a positioning component is set on the smart pen.

[0080] The micro-course video management system is built on the basis of the regional basic education curriculum standards. It can fully support regional education and teaching research, curriculum learning, and provide a service platform for the district's teaching and research, live course resources, and results display. It also supports online on-demand previews for users across the district, and can participate in scoring, liking, commenting, and discussions. According to the type of video micro-courses, the resource library mainly includes: teaching and research videos (for example, online teaching videos, online live videos, teaching and research meeting videos, educational lecture videos, etc.), learning videos (for example, famous teachers' classroom records, demonstration of excellent courses, online micro-course videos, etc.), which are convenient for providing classified retrieval for users with different identities. This embodiment shares and disseminates high-quality educational resources, which is conducive to promoting the improvement of teachers' comprehensive quality, innovation of education and teaching methods, and expanding students' interest in learning and cultivating the formation of independent inquiry learning habits.

[0081] The embodiment of the present invention recognizes the intention of the writing content of the smart pen, actively selects the micro-course video required by the user according to the recognized intention, and provides the functional interface of the corresponding video content, thereby improving the interactivity between the smart pen and the server content in the micro-course video learning scene and improving the management efficiency of the micro-course video. In addition, this solution can be applied to the field of smart education, thereby promoting the construction of smart cities.

[0082] The above describes the micro-course video management method in the embodiment of the present invention. The following describes the micro-course video management device in the embodiment of the present invention. Figure 3 , an embodiment of the micro-course video management device in the embodiment of the present invention includes:

[0083] The processing module 301 is used to write the initial text of the target user through the smart pen and perform optical character recognition (OCR) processing on the initial text through the camera recognition component provided on the smart pen to obtain a text image of the initial text, and the smart pen is connected to the server through the communication module;

[0084] The intention recognition module 302 is used to recognize the text image through the server to determine the text intention of the target user;

[0085] The video selection module 303 is used to select a target micro-course video in the micro-course video resource library according to the text intention, wherein the micro-course video resource library includes teaching and research videos and learning videos, wherein the teaching and research videos include online teaching videos, online live broadcast videos, teaching and research conference videos and educational lecture videos, and the learning videos include famous teachers' classroom recording videos, demonstration videos of excellent courses and online micro-course videos;

[0086] A play determination module 304 is used to play the target micro-course video through the server and determine the type of the target micro-course video;

[0087] The first calling display module 305 is used to call a preset teaching and research service interface and display the teaching and research function identification of the teaching and research service interface in the target micro-class video if the type of the target micro-class video is a teaching and research video, wherein the teaching and research function identification includes scoring and discussion;

[0088] The second calling display module 306 is used to call a preset learning service interface and display the learning function identifier of the learning service interface in the target micro-class video if the type of the target micro-class video is a learning video. The learning function identifier includes likes and collections.

[0089] The embodiment of the present invention recognizes the intention of the writing content of the smart pen, actively selects the micro-course video required by the user according to the recognized intention, and provides the functional interface of the corresponding video content, thereby improving the interactivity between the smart pen and the server content in the micro-course video learning scene and improving the management efficiency of the micro-course video. In addition, this solution can be applied to the field of smart education, thereby promoting the construction of smart cities.

[0090] See also Figure 4 Another embodiment of the micro-course video management device in the embodiment of the present invention includes:

[0091] The processing module 301 is used to write the initial text of the target user through the smart pen and perform optical character recognition (OCR) processing on the initial text through the camera recognition component provided on the smart pen to obtain a text image of the initial text, and the smart pen is connected to the server through the communication module;

[0092] The intention recognition module 302 is used to recognize the text image through the server to determine the text intention of the target user;

[0093] The video selection module 303 is used to select a target micro-course video in the micro-course video resource library according to the text intention, wherein the micro-course video resource library includes teaching and research videos and learning videos, wherein the teaching and research videos include online teaching videos, online live broadcast videos, teaching and research conference videos and educational lecture videos, and the learning videos include famous teachers' classroom recording videos, demonstration videos of excellent courses and online micro-course videos;

[0094] A play determination module 304 is used to play the target micro-course video through the server and determine the type of the target micro-course video;

[0095] The first calling display module 305 is used to call a preset teaching and research service interface and display the teaching and research function identification of the teaching and research service interface in the target micro-class video if the type of the target micro-class video is a teaching and research video, wherein the teaching and research function identification includes scoring and discussion;

[0096] The second calling display module 306 is used to call a preset learning service interface and display the learning function identifier of the learning service interface in the target micro-class video if the type of the target micro-class video is a learning video. The learning function identifier includes likes and collections.

[0097] Optionally, the intention recognition module 302 includes:

[0098] A preprocessing unit 3021 is used to call a preset sliding window algorithm to preprocess the text image to obtain a text area, wherein the text area includes the initial text written by the target user;

[0099] A segmentation unit 3022, configured to perform rectangular segmentation on the text region to obtain a plurality of character regions;

[0100] A character recognition unit 3023 is used to call a preset supervision algorithm to recognize each character region to obtain a text sequence, wherein the text sequence includes a plurality of characters;

[0101] The intention recognition unit 3024 is used to input the text sequence into a preset intention recognition model to obtain the text intention of the target user.

[0102] Optionally, the intention recognition unit 3024 includes:

[0103] A first input subunit 30241 is used to input the text sequence into an encoder layer of an intent recognition model to obtain a hidden layer state vector, wherein the encoder layer is composed of a BiLSTM;

[0104] The second input subunit 30242 is used to input the hidden layer state vector into a preset word slot filling layer to obtain a domain recognition result;

[0105] The determination subunit 30243 is used to determine the text intention of the target user according to the hidden layer state vector and the domain recognition result.

[0106] Optionally, the determination subunit 30243 is specifically used for:

[0107] The hidden layer state vector h i They are input into the intention attention layer and word slot attention layer of the intention recognition model respectively to obtain the intention attention vector c I and the attention vector of the current word slot According to the preset association vector formula, the attention vector c of the intention I and the attention vector of the current word slot The correlation vector g is calculated, and the preset correlation vector formula is: Where W is the weight, v is the preset initialization vector; according to the association vector g and the hidden layer state vector h i The predicted label of the word slot is calculated; and the text intention of the target user is determined according to the predicted label of the word slot and the domain recognition result.

[0108] Optionally, the micro-course video management device further includes:

[0109] The record update module 307 is used to obtain the like operation and / or collection operation triggered by the smart pen on the target micro-class video when the type of the target micro-class video is a learning video, record the like operation and / or collection operation through the server, and update the number of likes and / or collections of the target micro-class video.

[0110] Optionally, the micro-course video management device further includes:

[0111] The payment module 308 is used to send a play request instruction to the server through the smart pen when the type of the target micro-class video is a learning video and it is a paid video, and receive the fee information fed back by the server, and make online payment according to the fee information through the billing component in the smart pen, wherein the billing component of the smart pen is pre-bound with a payment channel.

[0112] Optionally, the micro-course video management device further includes:

[0113] The tracking and positioning module 309 is used to track and position the smart pen through the server when the smart pen is lost, wherein the smart pen and the server have been bound and authorized, and a positioning component is provided on the smart pen.

[0114] The embodiment of the present invention recognizes the intention of the writing content of the smart pen, actively selects the micro-course video required by the user according to the recognized intention, and provides the functional interface of the corresponding video content, thereby improving the interactivity between the smart pen and the server content in the micro-course video learning scene and improving the management efficiency of the micro-course video. In addition, this solution can be applied to the field of smart education, thereby promoting the construction of smart cities.

[0115] above Figure 3 to Figure 4 The micro-course video management device in the embodiment of the present invention is described in detail from the perspective of modular functional entities. The micro-course video management device in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0116] Figure 5 1 is a schematic diagram of the structure of a micro-course video management system 500 provided by an embodiment of the present invention, including a server 501, a micro-course video resource library 502 and a smart pen 503;

[0117] The server 501 is connected to the micro-course video resource library 502 and the smart pen 503 through a network;

[0118] The server 501 includes a processing module 5011, a playback component 5012, an interface calling component 5013 and a communication module 5014, wherein the processing module 5011 is used to process the data transmitted by the smart pen 503 and the data generated in the micro-course video resource library 502, the playback component 5012 is used to play the teaching and research video or the learning video, the interface calling component 5013 is used to call the learning service interface or the teaching and research service interface, and the communication module 5014 is used to connect the smart pen;

[0119] The micro-course video resource library 502 includes a video storage module 5021 and an interface library component 5022, wherein the video storage module 5021 is used to store teaching and research videos and learning videos, the teaching and research videos include online teaching videos, online live broadcast videos, teaching and research conference videos and educational lecture videos, and the learning videos include famous teachers' classroom recording videos, demonstration of excellent courses and online micro-course videos, and the interface library component 5022 is used to connect the video storage component to the learning service interface or the teaching and research service interface;

[0120] The smart pen 503 includes a communication module 5031, a writing component 5032, a camera recognition component 5033, a billing component 5034 and a tracking component 5035, wherein the communication module 5031 is used to connect to the server 501, the writing component 5032 is used to write text on paper, the camera recognition component 5033 is used to take a picture of and recognize the text written by the smart pen, the billing component 5034 is used to make online payments, and the billing component 5034 includes a quick payment button set on the smart pen, and the tracking component 5035 is used to provide a positioning function.

[0121] Those skilled in the art will understand that Figure 5 The illustrated micro-course video management system structure does not constitute a limitation on the micro-course video management system, and may include more or fewer components than illustrated, or a combination of certain components, or a different arrangement of components.

[0122] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are executed on a computer, the computer executes the steps of the micro-course video management method.

[0123] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0124] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program codes.

[0125] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A micro-course video management method, applied to a micro-course video service system, wherein the micro-course video service system comprises a server, a micro-course video resource library and a smart pen, characterized in that: include: Writing the target user's initial text with a smart pen and performing optical character recognition (OCR) processing on the initial text through a camera recognition component provided on the smart pen to obtain a text image of the initial text, wherein the smart pen is connected to the server through a communication module; Recognizing the text image by the server to determine the text intention of the target user; According to the text intention, a target micro-course video is selected from the micro-course video resource library, wherein the micro-course video resource library includes teaching and research videos and learning videos, wherein the teaching and research videos include online teaching videos, online live broadcast videos, teaching and research conference videos, and educational lecture videos, and the learning videos include famous teachers’ classroom recording videos, demonstration videos of excellent courses, and online micro-course videos; Play the target micro-course video through the server and determine the type of the target micro-course video; If the type of the target micro-class video is a teaching and research video, a preset teaching and research service interface is called and a teaching and research function identifier of the teaching and research service interface is displayed in the target micro-class video, wherein the teaching and research function identifier includes scoring and discussion; If the type of the target micro-course video is a learning video, a preset learning service interface is called and a learning function identifier of the learning service interface is displayed in the target micro-course video, wherein the learning function identifier includes like and favorite; When the type of the target micro-class video is a learning video, obtaining a like operation and / or a favorite operation triggered by the smart pen on the target micro-class video, recording the like operation and / or the favorite operation through the server, and updating the number of likes and / or the number of favorites of the target micro-class video; When the type of the target micro-course video is a learning video and a paid video, a play request instruction is sent to the server through the smart pen, and fee information fed back by the server is received, and online payment is made according to the fee information through the billing component in the smart pen, wherein the billing component of the smart pen is pre-bound with a payment channel; The method of identifying the text image by the server to determine the text intention of the target user includes: calling a preset sliding window algorithm to pre-process the text image to obtain a text area, wherein the text area includes the initial text written by the target user; performing rectangular segmentation on the text area to obtain a plurality of character areas; calling a preset supervision algorithm to identify each character area to obtain a text sequence, wherein the text sequence includes a plurality of characters; and inputting the text sequence into a preset intention recognition model to obtain the text intention of the target user.

2. The micro-course video management method according to claim 1, characterized in that: The step of inputting the text sequence into a preset intention recognition model to obtain the text intention of the target user includes: Input the text sequence into an encoder layer of an intent recognition model to obtain a hidden state vector, wherein the encoder layer is composed of a BiLSTM; Inputting the hidden layer state vector into a preset word slot filling layer to obtain a domain recognition result; The text intention of the target user is determined according to the hidden layer state vector and the domain recognition result.

3. The micro-course video management method according to claim 2, characterized in that: The determining the text intention of the target user according to the hidden layer state vector and the domain recognition result includes: The hidden layer state vector h i They are input into the intention attention layer and word slot attention layer of the intention recognition model respectively to obtain the intention attention vector c I and the attention vector of the current word slot According to the preset association vector formula, the attention vector c of the intention I and the attention vector of the current word slot The correlation vector g is calculated, and the preset correlation vector formula is: Where W is the weight and v is the preset initialization vector; According to the association vector g and the hidden layer state vector h i Calculate the predicted label of the word slot According to the predicted label of the word slot and determining the textual intention of the target user with the domain recognition result.

4. The micro-course video management method according to any one of claims 1-3, characterized in that: After calling the preset learning service interface and displaying the learning function identifier of the learning service interface in the target micro-class video, wherein the learning function identifier includes like and favorite, the method further includes: When the smart pen is lost, the smart pen is tracked and located through the server, wherein the smart pen and the server have been bound and authorized, and a positioning component is provided on the smart pen.

5. A micro-course video management device, characterized in that: include: A processing module, used for writing the initial text of the target user through the smart pen and performing optical character recognition (OCR) processing on the initial text through the camera recognition component provided on the smart pen to obtain a text image of the initial text, wherein the smart pen is connected to the server through the communication module; An intention recognition module, used to recognize the text image through the server to determine the text intention of the target user; A video selection module is used to select a target micro-course video in the micro-course video resource library according to the text intention, wherein the micro-course video resource library includes teaching and research videos and learning videos, wherein the teaching and research videos include online teaching videos, online live broadcast videos, teaching and research conference videos and educational lecture videos, and the learning videos include famous teachers' classroom recording videos, demonstration videos of excellent courses and online micro-course videos; A play determination module, used to play the target micro-course video through the server and determine the type of the target micro-course video; The first calling display module is used to call a preset teaching and research service interface and display the teaching and research function identification of the teaching and research service interface in the target micro-class video if the type of the target micro-class video is a teaching and research video, wherein the teaching and research function identification includes scoring and discussion; The second calling display module is used to call a preset learning service interface and display a learning function identifier of the learning service interface in the target micro-class video if the type of the target micro-class video is a learning video, wherein the learning function identifier includes a like and a favorite; When the type of the target micro-class video is a learning video, obtaining a like operation and / or a favorite operation triggered by the smart pen on the target micro-class video, recording the like operation and / or the favorite operation through the server, and updating the number of likes and / or the number of favorites of the target micro-class video; When the type of the target micro-course video is a learning video and a paid video, a play request instruction is sent to the server through the smart pen, and fee information fed back by the server is received, and online payment is made according to the fee information through the billing component in the smart pen, wherein the billing component of the smart pen is pre-bound with a payment channel; The intention recognition module includes: a preprocessing unit, which is used to call a preset sliding window algorithm to preprocess the text image to obtain a text area, and the text area includes the initial text written by the target user; a segmentation unit, which is used to perform rectangular segmentation on the text area to obtain multiple character areas; a character recognition unit, which is used to call a preset supervised algorithm to recognize each character area to obtain a text sequence, and the text sequence includes multiple characters; an intention recognition unit, which is used to input the text sequence into a preset intention recognition model to obtain the text intention of the target user.

6. A micro-course video management system, characterized in that: include: Server, micro-course video resource library and smart pen; The server is connected to the micro-course video resource library and the smart pen network; The server includes a processing module, a playback component, an interface calling component and a communication module, wherein the processing module is used to process the data transmitted by the smart pen and the data generated in the micro-course video resource library, the playback component is used to play the teaching and research video or the learning video, the interface calling component is used to call the learning service interface or the teaching and research service interface, and the communication module is used to connect the smart pen; The micro-course video resource library includes a video storage module and an interface library component, wherein the video storage module is used to store teaching and research videos and learning videos, the teaching and research videos include online teaching videos, online live broadcast videos, teaching and research conference videos and educational lecture videos, the learning videos include famous teachers' classroom recording videos, demonstration of excellent courses and online micro-course videos, and the interface library component is used to connect the video storage component to the learning service interface or the teaching and research service interface; The smart pen includes a communication module, a writing component, a camera recognition component, a billing component and a tracking component, wherein the communication module is used to connect to a server, the writing component is used to write text on paper, the camera recognition component is used to take a picture of and recognize the text written by the smart pen, the billing component is used to make online payments, the billing component includes a quick payment button set on the smart pen, and the tracking component is used to provide a positioning function.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed by the processor, the micro-course video management method as described in any one of claims 1 to 4 is implemented.

Images