Interactive education method, device and system

Abstract

The embodiment of the invention provides an interactive education method, device and system, which can efficiently provide a required explanation video for a user in real time, increase the interestingness of interaction and improve the user experience. The interactive education method comprises the following steps: displaying a first interface, wherein a first explanation video is played in the first interface; receiving first interaction information input in the first interface by a user; in response to the first interaction information, updating a video played in the first interface from the first explanation video to a second explanation video, the second explanation video being generated by the electronic device according to the first interaction information, subtitles displayed by the second explanation video comprise first response information generated according to the first interaction information.

Description

Technical Field

[0001] This application relates to the field of smart terminal technology, and in particular to an interactive education method, device and system. Background Technology

[0002] With the development of technology, modern education is undergoing profound changes, gradually shifting from traditional face-to-face teaching to digital and networked education models. In this process, educational software on electronic devices, providing users with networked educational functions, serves as a crucial bridge connecting teachers and students, and theory and practice. As a popular supplementary teaching tool, it has gradually become an important part of the educational process. In related technologies, this educational software can also be called educational assistant, educational assistant software, etc. However, existing educational software often makes learners feel bored and finds it difficult to maintain attention and interest for extended periods, resulting in a poor user experience. Summary of the Invention

[0003] This application provides an interactive education method, device, and system that can provide users with interactive explanatory videos in real time and efficiently, with high interest and a better user experience.

[0004] Firstly, this application provides an interactive education method applied to an electronic device. The method includes: displaying a first interface on which a first explanatory video is played; receiving first interactive information input by a user on the first interface; and, in response to the first interactive information, updating the video played on the first interface from the first explanatory video to a second explanatory video. The second explanatory video is generated by the electronic device based on the first interactive information, and the subtitles displayed in the second explanatory video include first response information generated based on the first interactive information. The first interface may be, for example, a video explanation interface in a later embodiment; the first explanatory video may be the original explanatory video in a later embodiment or an explanatory video updated based on the user's interactive information. The second explanatory video in this method is generated by the electronic device without interaction with the cloud, thus enabling real-time and efficient intelligent response to the first interactive information input by the user, thereby improving the interaction efficiency between the electronic device and the user. Furthermore, the subtitles displayed in the second explanatory video include first response information generated based on the first interactive information, thereby enabling dialogue with the user through the second explanatory video, providing emotional feedback and encouragement, and learning guidance, thus improving the interactivity and interest of the second explanatory video and enhancing the user experience.

[0005] In one possible implementation, displaying the first interface includes: displaying a second interface; receiving second interactive information input by the user in the second interface; responding to the second interactive information, displaying a list of knowledge points associated with the second interactive information in the second interface; receiving a selection operation for a first knowledge point in the knowledge point list, and displaying the first interface, wherein the first explanatory video played in the first interface is an explanatory video for the first knowledge point. This method provides an implementation for a user to enter the first interface. The aforementioned second interface could, for example, be the main interface of an educational assistant application or the main interface of an educational assistant application in subsequent embodiments.

[0006] In one possible implementation, before displaying the list of knowledge points associated with the second interactive information on the second interface, the method further includes: determining that the user needs resolved based on the second interactive information do not include video explanation requirements. Therefore, this method only displays the list of knowledge points associated with the second interactive information on the second interface when the user needs resolved based on the second interactive information do not include video explanation requirements. This allows the method to be compatible with other interactive educational methods that include video explanation requirements when the user needs resolved based on the second interactive information do, such as the method described below that directly accesses the first interface via the second interactive information.

[0007] In one possible implementation, displaying the first interface further includes: when it is determined that the user's needs, as parsed based on the second interactive information, include a need for video explanation, displaying the first interface, wherein the first explanation video played on the first interface is an explanation video for a second knowledge point, the second knowledge point being a knowledge point determined based on the second interactive information, and the subtitles of the first explanation video including second response information generated based on the second interactive information. This method provides users with an implementation method to directly access the first interface through the second interactive information, thereby realizing the diversity of services provided by electronic devices to users based on the second interactive information, and making the interface services provided by electronic devices to users more closely aligned with user needs.

[0008] In one possible implementation, receiving first interactive information input by the user on the first interface includes: receiving text information input by the user on the first interface as the first interactive information; or, receiving voice information input by the user on the first interface, converting the voice information into text information as the first interactive information; or, receiving image information input by the user on the first interface, recognizing text information in the image information as the first interactive information; or, receiving the user's selection operation on a first control on the first interface, and using the interactive information corresponding to the first control as the first interactive information; the interactive information corresponding to the first control is used to indicate that the first explanatory video does not meet the user's actual needs. The first control mentioned above can be, for example, a "step" control in a subsequent embodiment. This method provides users with multiple possible ways to input interactive information, thereby facilitating user input of interactive information and improving the user experience.

[0009] In one possible implementation, when the target user's needs, as resolved from the first interactive information, include a need to adjust the instructional video, the first response information includes: response information to the first interactive information and guidance information for the teaching content of the second instructional video; and / or, when the target user's needs, as resolved from the first interactive information, include a need to end the video instruction, the first response information includes: response information to the first interactive information. The inclusion of response information to the first interactive information in the first response information allows for dialogue with the user through the second instructional video, providing emotional feedback and encouragement, thereby increasing the video's appeal and interactivity. The inclusion of guidance information for the teaching content of the second instructional video also provides learning guidance and explanations to the user, further enhancing the video's interactivity and improving the user experience.

[0010] In one possible implementation, the second explanatory video is generated by the electronic device based on the first interactive information. This includes: the electronic device parsing the target user's needs based on the first interactive information, obtaining target video material matching the target user's needs from the first video material locally on the electronic device, and generating the second explanatory video based on the target video material. Therefore, the electronic device does not need to interact with the cloud; instead, it generates the second explanatory video based on the local first video material. This makes the generation of the second explanatory video more real-time and efficient, enabling real-time and efficient intelligent responses to the user's input of the first interactive information, improving the interaction efficiency between the electronic device and the user, and enhancing the user experience.

[0011] In one possible implementation, the first video clip locally on the electronic device is obtained from the cloud server's media library based on a list of knowledge points and sent to the electronic device; the media library contains video clips with knowledge points. In this method, the cloud server maintains the media library, obtains the first video clip based on the list of knowledge points, and sends it to the electronic device, thus ensuring that the electronic device can obtain the video clips needed for user interaction in a timely manner without consuming excessive storage resources.

[0012] In one possible implementation, the first video material includes: video material for each knowledge point in the knowledge point list; or, the first video material includes: video material for each knowledge point in the knowledge point list, and video material for knowledge points associated with each knowledge point in the knowledge point list. The inclusion of video material for each knowledge point in the first video material ensures that the electronic device can promptly respond to the user's video viewing needs related to the knowledge points in the knowledge point list; the inclusion of video material for knowledge points associated with each knowledge point in the first video material also ensures that the electronic device can promptly respond to the user's video viewing needs related to the knowledge points associated with the knowledge points in the knowledge point list, allowing for a wider range of timely responses to user needs.

[0013] In one possible implementation, before updating the video played on the first interface from the first explanatory video to the second explanatory video, the method further includes: when the electronic device determines that there is no video material in the first video material that matches the target user's needs, obtaining the second video material from the cloud server based on the first interaction information, obtaining the target video material that matches the target user's needs from the second video material, and generating the second explanatory video based on the target video material. This method ensures that even when there is no video material matching the target user's needs in the first video material locally on the electronic device, it can still respond to and process user needs even when the user's needs vary significantly.

[0014] In one possible implementation, the method for obtaining the second video material from the cloud server includes: sending first interactive information to the cloud server; and receiving the second video material sent by the cloud server. The second video material is obtained by the cloud server from its material library based on the first interactive information, user profile, and historical learning data. The material library contains video materials recording knowledge points. In this method, in addition to the first interactive information, the cloud server also obtains the second video material based on user profile and historical learning data, thereby increasing the probability that the content included in the second video material is closer to the user's needs. This reduces the number of times the electronic device obtains video material from the cloud server and decreases the amount of data transmission between the electronic device and the cloud server.

[0015] In a second aspect, embodiments of this application provide an electronic device, including: a processor and a memory; wherein one or more computer programs are stored in the memory, and the one or more computer programs include instructions that, when executed by the processor, cause the electronic device to perform the method of any one of the first aspects.

[0016] Thirdly, embodiments of this application provide an interactive teaching system, including the electronic device and cloud server described in the third aspect.

[0017] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when run on a computer, causes the computer to perform the method of any one of the first aspects.

[0018] Fifthly, embodiments of this application provide a computer program product comprising a computer program that, when run on a computer, causes the computer to perform the method of any one of the first aspects. Attached Figure Description

[0019] Figure 1 A schematic diagram of the structure of an electronic device provided in an embodiment of this application;

[0020] Figure 2 A schematic diagram of the software structure of an electronic device provided in an embodiment of this application;

[0021] Figure 3 A schematic diagram of an interface for an interactive education method provided in an embodiment of this application;

[0022] Figure 4 A second interface diagram of the interactive education method provided in the embodiments of this application;

[0023] Figure 5A A third interface diagram of the interactive education method provided in the embodiments of this application;

[0024] Figure 5B A fourth interface diagram of the interactive education method provided in the embodiments of this application;

[0025] Figure 6A A schematic diagram of a fifth interface for the interactive education method provided in the embodiments of this application;

[0026] Figure 6B A sixth interface diagram of the interactive education method provided in the embodiments of this application;

[0027] Figure 6C A seventh interface diagram of the interactive education method provided in the embodiments of this application;

[0028] Figure 7 An eighth interface diagram of the interactive education method provided in the embodiments of this application;

[0029] Figure 8 A ninth interface diagram of the interactive education method provided in the embodiments of this application;

[0030] Figure 9 A schematic diagram of the structure of an interactive education system provided in an embodiment of this application;

[0031] Figure 10A flowchart illustrating an interactive education method provided in an embodiment of this application;

[0032] Figure 11 This is a second flowchart illustrating the interactive education method provided in the embodiments of this application;

[0033] Figure 12 A third flowchart illustrating the interactive education method provided in the embodiments of this application;

[0034] Figure 13 This is a schematic diagram of the fourth type of interactive education method provided in the embodiments of this application. Detailed Implementation

[0035] The terminology used in the implementation section of this application is for the purpose of explaining specific embodiments of this application only, and is not intended to limit this application.

[0036] With the development of technology, modern education is undergoing profound changes, gradually shifting from traditional face-to-face teaching to digital and networked education models. In this process, educational software on electronic devices, providing users with networked educational functions, serves as a crucial bridge connecting teachers and students, and theory and practice. As a popular supplementary teaching tool, it has gradually become an important part of the educational process. In related technologies, this educational software can also be called educational assistant, educational assistant software, etc. However, existing educational software often makes learners feel bored and finds it difficult to maintain attention and interest for extended periods, resulting in a poor user experience.

[0037] Analysis revealed that some educational software relies on static text descriptions and image displays to explain knowledge to users. While this provides a certain amount of information, it lacks vividness and interactivity, making users feel bored and unable to maintain their attention and interest for long periods.

[0038] In other educational software, pre-made videos are used to explain knowledge to users. While video explanations are more intuitive and offer a richer audiovisual experience than text and images, pre-generated videos lack real-time interaction with users. They cannot be adjusted based on learners' specific needs and feedback, lacking personalization and customization capabilities, which limits their application in personalized learning scenarios. This fixed presentation format also fails to achieve engaging learning for users, easily leading to boredom and difficulty in maintaining attention and interest for extended periods.

[0039] Therefore, this application provides an interactive education method that provides intelligent and interactive explanatory videos in real time and efficiently based on user needs, enabling users to learn in a fun way and providing a better user experience.

[0040] The interactive education method described in this application can be applied to systems including electronic devices and servers. The electronic devices can be mobile phones, tablets (PADs), personal computers (PCs), etc. The server can be a single server or a cluster of multiple servers. In one embodiment, the server can specifically be a cloud server.

[0041] In the following embodiments, the interactive education method of this application is illustrated by taking a cloud server as an example.

[0042] In the following embodiments, the electronic device side is also referred to as the terminal side, and the cloud server side is also referred to as the cloud side.

[0043] Figure 1 A schematic diagram of the structure of the electronic device 100 is shown.

[0044] Electronic device 100 may include processor 110, internal memory 121, antenna 1, antenna 2, mobile communication module 150, wireless communication module 160, speaker 170A, microphone 170C, camera 193, display screen 194, etc.

[0045] It is understood that the structures illustrated in the embodiments of the present invention do not constitute a specific limitation on the electronic device 100. In other embodiments of this application, the electronic device 100 may include more or fewer components than illustrated, or combine certain components, or split certain components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware. For example Figure 1 As shown, the electronic device 100 may further include: an external memory interface 120, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an audio module 170, a receiver 170B, a headphone jack 170D, a sensor module 180, buttons 190, a motor 191, an indicator 192, and a subscriber identification module (SIM) card interface 195, etc. The sensor module 180 may include a pressure sensor 180A, a gyroscope sensor 180B, a barometric pressure sensor 180C, a magnetic sensor 180D, an accelerometer sensor 180E, a proximity sensor 180F, a proximity light sensor 180G, a fingerprint sensor 180H, a temperature sensor 180J, a touch sensor 180K, an ambient light sensor 180L, a bone conduction sensor 180M, etc.

[0046] Processor 110 may include one or more processing units, such as application processors (APs), modem processors, graphics processing units (GPUs), image signal processors (ISPs), controllers, video codecs, digital signal processors (DSPs), baseband processors, and / or neural network processing units (NPUs). These different processing units may be independent devices or integrated into one or more processors.

[0047] The controller can generate operation control signals based on the instruction opcode and timing signals to complete the control of instruction fetching and execution.

[0048] The processor 110 may also include a memory for storing instructions and data. In some embodiments, the memory in the processor 110 is a cache memory. This memory can store instructions or data that the processor 110 has just used or that are used repeatedly. If the processor 110 needs to use the instruction or data again, it can retrieve it directly from the memory. This avoids repeated accesses, reduces the waiting time of the processor 110, and thus improves the efficiency of the system.

[0049] In some embodiments, the processor 110 may include one or more interfaces. Interfaces may include an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a subscriber identity module (SIM) interface, and / or a universal serial bus (USB) interface, etc.

[0050] The wireless communication function of electronic device 100 can be realized through antenna 1, antenna 2, mobile communication module 150, wireless communication module 160, modem processor and baseband processor, etc.

[0051] Antenna 1 and antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna in electronic device 100 can be used to cover one or more communication frequency bands. Different antennas can also be multiplexed to improve antenna utilization. For example, antenna 1 can be multiplexed as a diversity antenna for a wireless local area network. In some other embodiments, the antennas can be used in conjunction with tuning switches.

[0052] The mobile communication module 150 can provide solutions for wireless communication, including 2G / 3G / 4G / 5G, applied to the electronic device 100. The mobile communication module 150 may include at least one filter, switch, power amplifier, low noise amplifier (LNA), etc. The mobile communication module 150 can receive electromagnetic waves via antenna 1, and perform filtering, amplification, and other processing on the received electromagnetic waves before transmitting them to a modem processor for demodulation. The mobile communication module 150 can also amplify the signal modulated by the modem processor and convert it into electromagnetic waves for radiation via antenna 1. In some embodiments, at least some functional modules of the mobile communication module 150 may be housed in the processor 110. In some embodiments, at least some functional modules of the mobile communication module 150 and at least some modules of the processor 110 may be housed in the same device.

[0053] The modem processor may include a modulator and a demodulator. The modulator modulates the low-frequency baseband signal to be transmitted into a mid-to-high frequency signal. The demodulator demodulates the received electromagnetic wave signal into a low-frequency baseband signal. The demodulator then transmits the demodulated low-frequency baseband signal to the baseband processor for processing. After processing by the baseband processor, the low-frequency baseband signal is transmitted to the application processor. The application processor outputs sound signals through an audio device (not limited to speaker 170A, receiver 170B, etc.) or displays images or videos through the display screen 194. In some embodiments, the modem processor may be a separate device. In other embodiments, the modem processor may be independent of the processor 110 and may be housed in the same device as the mobile communication module 150 or other functional modules.

[0054] The wireless communication module 160 can provide solutions for wireless communication applications on the electronic device 100, including wireless local area networks (WLANs) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), and infrared (IR) technologies. The wireless communication module 160 can be one or more devices integrating at least one communication processing module. The wireless communication module 160 receives electromagnetic waves via antenna 2, performs frequency modulation and filtering of the electromagnetic wave signals, and sends the processed signal to processor 110. The wireless communication module 160 can also receive signals to be transmitted from processor 110, perform frequency modulation and amplification, and convert them into electromagnetic waves for radiation via antenna 2.

[0055] In some embodiments, antenna 1 of electronic device 100 is coupled to mobile communication module 150, and antenna 2 is coupled to wireless communication module 160, enabling electronic device 100 to communicate with networks and other devices via wireless communication technology. The wireless communication technology may include Global System for Mobile Communications (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Time Division Code Division Multiple Access (TD-SCDMA), Long Term Evolution (LTE), BT, GNSS, WLAN, NFC, FM, and / or IR technologies, etc. The GNSS may include the Global Positioning System (GPS), the Global Navigation Satellite System (GLONASS), the BeiDou Navigation Satellite System (BDS), the Quasi-Zenith Satellite System (QZSS), and / or satellite-based augmentation systems (SBAS).

[0056] Electronic device 100 implements display functions through a GPU, a display screen 194, and an application processor. The GPU is a microprocessor for image processing, connected to the display screen 194 and the application processor. The GPU is used to perform mathematical and geometric calculations and for graphics rendering. Processor 110 may include one or more GPUs, which execute program instructions to generate or modify display information.

[0057] Display screen 194 is used to display images, videos, etc. Display screen 194 includes a display panel. The display panel may be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), a miniature LED, a microLED, a quantum dot light-emitting diode (QLED), etc. In some embodiments, electronic device 100 may include one or N displays 194, where N is a positive integer greater than 1.

[0058] Electronic device 100 can perform shooting functions through ISP, camera 193, video codec, GPU, display 194 and application processor.

[0059] The ISP (Image Signal Processor) is used to process data fed back from the camera 193. For example, when taking a picture, the shutter is opened, and light is transmitted through the lens to the camera's photosensitive element. The light signal is converted into an electrical signal, and the camera's photosensitive element transmits the electrical signal to the ISP for processing, transforming it into an image visible to the naked eye. The ISP can also perform algorithmic optimization of image noise, brightness, and skin tone. The ISP can also optimize parameters such as exposure and color temperature of the shooting scene. In some embodiments, the ISP can be set in the camera 193.

[0060] Camera 193 is used to capture still images or videos. An object is projected onto a photosensitive element by generating an optical image through the lens. The photosensitive element can be a charge-coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The photosensitive element converts the light signal into an electrical signal, which is then passed to an ISP for conversion into a digital image signal. The ISP outputs the digital image signal to a DSP for processing. The DSP converts the digital image signal into image signals in standard RGB, YUV, or other formats. In some embodiments, the electronic device 100 may include one or N cameras 193, where N is a positive integer greater than 1.

[0061] Digital signal processors (DSPs) are used to process digital signals. Besides digital image signals, they can also process other digital signals. For example, when electronic device 100 selects a frequency, the DSP can perform Fourier transforms on the frequency energy.

[0062] Video codecs are used to compress or decompress digital video. Electronic device 100 may support one or more video codecs. Thus, electronic device 100 can play or record videos in various encoding formats, such as Moving Picture Experts Group (MPEG) 1, MPEG2, MPEG3, MPEG4, etc.

[0063] An NPU (Neural Processing Unit) is a computational processor for neural networks (NNs). By borrowing the structure of biological neural networks, such as the transmission patterns between neurons in the human brain, it can rapidly process input information and continuously learn on its own. NPUs enable intelligent cognitive applications in electronic devices, such as image recognition, facial recognition, speech recognition, and text understanding.

[0064] Internal memory 121 can be used to store computer executable program code, which includes instructions. Internal memory 121 may include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback, image playback, etc.), etc. The data storage area may store data created during the use of electronic device 100 (such as audio data, phonebook, etc.). Furthermore, internal memory 121 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, universal flash storage (UFS), etc. Processor 110 executes various functional applications and data processing of electronic device 100 by running instructions stored in internal memory 121 and / or instructions stored in memory located in the processor.

[0065] Electronic device 100 can implement audio functions, such as music playback and recording, through audio module 170, speaker 170A, receiver 170B, microphone 170C, headphone jack 170D, and application processor.

[0066] The audio module 170 is used to convert digital audio information into analog audio signals for output, and also to convert analog audio input into digital audio signals. The audio module 170 can also be used for encoding and decoding audio signals. In some embodiments, the audio module 170 may be located in the processor 110, or some functional modules of the audio module 170 may be located in the processor 110.

[0067] The speaker 170A, also known as a "loudspeaker," is used to convert audio electrical signals into sound signals. The electronic device 100 can listen to music or make hands-free calls through the speaker 170A.

[0068] Microphone 170C, also known as a "microphone" or "voice transducer," is used to convert sound signals into electrical signals. When making a phone call or sending a voice message, the user can speak by bringing their mouth close to microphone 170C, inputting the sound signal into microphone 170C. Electronic device 100 may have at least one microphone 170C. In some embodiments, electronic device 100 may have two microphones 170C, which, in addition to collecting sound signals, can also perform noise reduction. In other embodiments, electronic device 100 may also have three, four, or more microphones 170C, which can collect sound signals, reduce noise, identify the sound source, and perform directional recording, etc.

[0069] The software system of electronic device 100 can adopt a layered architecture, event-driven architecture, microkernel architecture, microservice architecture, or cloud architecture. This embodiment of the invention uses a layered architecture. Taking the system as an example, the software structure of electronic device 100 is illustrated.

[0070] Figure 2 The diagram shown is a software structure block diagram of an electronic device according to an embodiment of this application. The layered architecture divides the software into several layers, each with a clear role and division of labor. Layers communicate with each other through software interfaces. This embodiment uses the Android system as an example to illustrate the software structure of a first electronic device running the Android system. In some embodiments, the Android system is divided into five layers, from top to bottom: the application layer, the application framework layer, the system library and Android runtime layer, the hardware abstraction layer (HAL), and the kernel layer.

[0071] The application layer can include several applications (hereinafter referred to as applications), for example Figure 2 The applications shown include music applications, video applications, SMS applications, calling applications, navigation applications, smart assistant applications, and educational assistant applications.

[0072] A smart assistant application can be a smart service integrated into electronic devices. In related technologies, it can also be called the "negative one screen," which can be located on the far left or bottom screen of an electronic device (such as a mobile phone). It can make intelligent recommendations based on the user's usage habits and scenarios, and integrate quick display pages such as smart search, direct access to services, sports data, read later, and news. It can also automatically generate various contextual intelligent reminder cards, including express delivery, travel, and hotel booking reminders, so that users can quickly browse and use it.

[0073] The application framework layer provides application programming interfaces (APIs) and a programming framework for applications in the application layer, including various components and services to support Android development. The application framework layer also includes some predefined functions. For example, the framework layer may include a window manager, a resource manager, etc.

[0074] The system libraries and Android runtime layer comprise the system libraries and the Android Runtime. The system libraries can include multiple functional modules, such as: a surface manager, a 2D graphics engine, a 3D graphics processing library (e.g., OpenGL ES), a media library, and a font library. Specifically, the browser kernel is responsible for interpreting web page syntax (such as HTML and JavaScript, applications of Standard Generalized Markup Language) and rendering (displaying) the web page; the 2D graphics engine is used for 2D graphics drawing, image rendering, compositing, and layer processing; the 3D graphics processing library is used for 3D graphics drawing, image rendering, compositing, and layer processing; the media library is used for inputting different streaming media; and the font library is used for inputting different fonts. The Android runtime is responsible for the scheduling and management of the Android system, specifically including the core libraries and the virtual machine. The core libraries consist of two parts: one part contains the functional functions that Java needs to call, and the other part contains the Android core libraries; the virtual machine is used to run Android applications developed using the Java language.

[0075] The HAL layer is the interface layer located between the operating system kernel and the hardware circuitry. The HAL layer includes, but is not limited to, the camera hardware abstraction layer.

[0076] The hardware abstraction layer includes components such as the Camera Hardware Abstraction Layer (HAL) and the Audio Hardware Abstraction Layer (Audio HAL). The Camera Hardware Abstraction Layer processes the image stream, while the Audio Hardware Abstraction Layer processes the audio data.

[0077] The kernel layer is the layer between hardware and software. The kernel layer can include: camera driver, microphone driver, display driver, etc. Specifically, the camera driver drives the camera, the microphone driver drives the microphone, and the display driver drives the screen.

[0078] The interactive education method of this application will be described in detail in the following embodiments in conjunction with the structure of the above-described electronic device.

[0079] In some embodiments, the educational method provided in this application can be used as a function provided by a smart assistant application. For example... Figure 3 As shown in interface 31, the interface displayed by the smart assistant application may include control 311 corresponding to the education assistant function. When the user clicks control 311, the smart assistant application detects the user's selection operation on control 311, that is, detects the selection operation for the "education assistant" function, and can display the main interface of the education assistant function, as shown in interface 32.

[0080] In some embodiments, the educational method provided in this application can be used as a function provided by an educational assistant application in an electronic device. For example... Figure 3 As shown in interface 33, an application icon 331 for "Education Assistant" can be displayed on the desktop of the electronic device. When the user clicks the application icon 331, the electronic device detects the user's selection operation on the application icon 331, that is, it detects the launch request for the Education Assistant application, launches the Education Assistant application, and displays the main interface of the Education Assistant application, as shown in interface 34.

[0081] In the following embodiments, the interactive education method provided in this application is used as an example of the educational assistant function provided by a smart assistant application to illustrate the interface implementation. It is understood that when the interactive education method provided in this application is used as a function provided by an educational assistant application, its interface implementation can refer to the interface implementation examples provided in the following embodiments of this application. Accordingly, the smart assistant application in the following methods can be replaced with an educational assistant application, and these will not be listed one by one in this application.

[0082] In the interactive education method provided in this application embodiment, users can perform multimodal information input, including but not limited to: image input, voice input, and text input. The interactive education method in this application embodiment can use corresponding recognition methods to recognize the information input by the user, specifically including image recognition, voice recognition, and text recognition. The specific implementation of the above-mentioned image recognition, voice recognition, and text recognition can refer to related technologies, and will not be elaborated in this application embodiment.

[0083] by Figure 3Taking the main interface of the education assistant function shown in interface 32 (hereinafter referred to as the education assistant main interface) as an example, the education assistant main interface may include a text box 320, a text editing control 321, a voice input control 322, an image recognition control 323, etc. The text box 320 is used to display the information input by the user. For the convenience of the description of the embodiments of this application, the information input by the user in the education assistant main interface and the video explanation interface of the education assistant function is collectively referred to as the original input information, and the information recognized based on the original input information is collectively referred to as the interactive information. It can be understood that the interactive information here is to reflect that the information input by the user is used to interact with the smart assistant application, or to interact with the education assistant function of the smart assistant application. It can also be called the user's input information or other names. The embodiments of this application do not limit this.

[0084] Among them, the text editing control 321 is used to support users to trigger text input; the voice input control 322 is used to support users to trigger voice input; and the image recognition control 323 is used to support users to trigger image input.

[0085] When a user needs to input interactive information, they can click the text editing control 321 to enter text in the text box 320, and the smart assistant application can use the text entered by the user as the interactive information. Alternatively, the user can click the voice input control 322 to input voice information, and the smart assistant application can recognize the voice information and use the voice recognition result as the interactive information. Or, the user can click the image recognition control 323 to select an image stored in the electronic device or to take a picture in real time through the camera, and the smart assistant application can recognize the image and use the image recognition result as the interactive information.

[0086] After a user enters interactive information in the main interface of the education assistant, the interactive information can be displayed in text box 320 for easy viewing. Furthermore, the smart assistant application can add response information to the interactive information on the main interface, and also add a list of related knowledge points. For example, the main interface of the education assistant at this time... Figure 4 As shown in interface 35.

[0087] Figure 4 In the example of interface 35 shown, the user can input the following question as interactive information through text input, voice input or image input: What is 1+2+3+4? The question is displayed in the text box 350 of the main interface of the education assistant.

[0088] The main interface of the education assistant shown in interface 35 includes a text box 354, used to display response information for interactive messages. For example... Figure 4The response shown in the image to the interactive message "What is 1+2+3+4?" is as follows:

[0089] Calculate: 1 + 2 + 3 + 4 equals 10.

[0090] The response is divided into two parts: one part is the type of interactive information: calculation; the other part is the answer to the question in the interactive information: 1+2+3+4 equals 10.

[0091] It is understood that the response information generated based on user interaction information is not limited to the examples above. Different response information can generate corresponding response information, and the response information is not limited to the types and answers mentioned above. Specific implementations of generating response information based on user interaction information can refer to relevant technologies, and this application does not impose any limitations. The response information can be generated by the smart assistant application, or it can be generated by a cloud server connected to the smart assistant application and then fed back to the smart assistant application.

[0092] like Figure 4 As shown in the embodiment of this application, the main interface of the educational assistant may further include a knowledge point list display area. The knowledge point list display area is used to display a list of knowledge points, which are knowledge points associated with interactive information. The knowledge point list includes one or more knowledge points, and each knowledge point can correspond to a control used to support users in triggering the playback of the corresponding explanation video.

[0093] For example Figure 4 The knowledge point list displayed in the middle interface 35 includes three knowledge points: arithmetic sequences, four arithmetic operations, and quick calculation.

[0094] If a user wishes to watch a video explanation of a specific knowledge point, they can click the corresponding control on the main interface of the education assistant. The smart assistant application will then display the video explanation interface, where the video explanation of the selected knowledge point can be played. See also... Figure 5A As shown, taking the user clicking the control 355 corresponding to the arithmetic sequence as an example, the video explanation interface displayed by the smart assistant application is as shown in interface 51. The video explanation interface plays an explanation video of the knowledge point "arithmetic sequence".

[0095] Therefore, in the interactive education method of this application embodiment, the main interface of the education assistant helps users to intelligently extract knowledge points based on user interaction information and generate explanation videos, providing users with an interface to watch explanation videos of knowledge points and guiding users to watch explanation videos of knowledge points associated with interactive information.

[0096] like Figure 5AAs shown, the video explanation interface may include a video playback control for playing the explanation video. For example, in the video explanation interface shown in interface 51, control 511 is a video playback control, which is playing an explanation video for the knowledge point of "arithmetic sequences".

[0097] Figure 5A The illustrated embodiment uses the example of a user clicking the control corresponding to a knowledge point in the main interface of the education assistant to enter the video explanation interface. In other embodiments, when the user inputs interactive information in the main interface of the education assistant, the target knowledge point associated with the interactive information is parsed. Instead of displaying the main interface of the education assistant as shown in interface 35, the video explanation interface as shown in interface 51 is directly displayed, and the video explanation video of the target knowledge point is played. Figure 5B As shown, users can input interactive information in the main interface of the education assistant, such as interface 32: "Tell me about arithmetic sequences." The target knowledge point associated with the interactive information is "arithmetic sequences." Accordingly, the smart assistant application can display a video explanation interface, such as interface 51, in which an explanation video of arithmetic sequences is played.

[0098] It should be noted that the smart assistant application can also provide... Figure 5A The method for entering the video tutorial interface shown is as follows: Figure 5B The method shown here for entering the video explanation interface allows the user to input interactive information in the main interface of the education assistant, as shown in interface 32. The smart assistant application can then determine whether the user's needs include a video explanation requirement, i.e., a need to watch video explanations of the knowledge points. If the user's needs do not include a video explanation requirement, the application can... Figure 5A Accessing the video tutorial interface as shown, and confirming that user needs include video tutorial requirements, can be done through... Figure 5B The method shown leads to the video tutorial interface. For example, based on the interactive information "What is 1+2+3+4?", it might be deduced that the user's request does not include a video tutorial. In this case, it can be accessed through... Figure 5A The method shown leads to the video tutorial interface. Based on the interactive message "Tell me about arithmetic sequences," it's possible the user's needs include a video tutorial request, which can be accessed through... Figure 5B Access the video tutorial interface as shown.

[0099] It should be noted that the user needs based on interactive information parsing can be performed by the smart assistant application or by the cloud server and then fed back to the smart assistant application; this application embodiment does not impose any restrictions.

[0100] In this embodiment, the instructional video played when entering the video instruction interface can have its teaching content and style determined based on interactive information, combined with user profiles, user's historical learning data, and user's historical interaction information, so that the video characteristics such as the instructional content and style of the instructional video match the user's actual needs as closely as possible. Specific implementation details can be found in the corresponding descriptions in subsequent embodiments, and will not be elaborated here.

[0101] In the interactive education method provided in this application embodiment, users can input interactive information in the video explanation interface. This interactive information can include user feedback on the explanation video, requests for the explanation video, user emotional expressions, and dialogue between the user and the smart assistant application. The smart assistant application can, based on the user's input, either keep the explanation video unchanged or adjust the video features such as the teaching content and / or teaching style to generate a new explanation video, updating the explanation video playing in the video explanation interface. This allows for intelligent interaction with the user through the explanation video, meeting the user's dynamic and personalized educational needs and improving the user experience. To further enhance interactivity and engagement, this application embodiment can display response information for the user's interactive information in the explanation video updated based on the user's interactive information. This response information is used for dialogue with the user, providing emotional feedback and encouragement, and learning guidance. For example, the response information can include responses to the user's interactive information and guidance information for the teaching content in the explanation video. The following is an example description.

[0102] by Figure 5A Taking the video tutorial interface shown in interface 51 as an example, the video tutorial interface may also include: a text box 512, a text editing control 513, a voice input control 514, an image recognition control 515, and other controls, to support users in inputting interactive information. The implementation of users inputting interactive information in the video tutorial interface through the above controls can be referred to the corresponding explanation of inputting interactive information in the main interface of the education assistant, which will not be repeated here.

[0103] See Figure 6ASuppose the smart assistant application displays a video explanation interface as shown in interface 51, playing an explanation video of an arithmetic sequence. To distinguish it from subsequent explanation videos, this explanation video is referred to as the original explanation video, which is the explanation video displayed in the video explanation interface when the user enters. When the original explanation video is playing in the video explanation interface shown in interface 51, if the user clicks the text editing control 513 in interface 51 and enters the following interactive information 1 in the interactive text box 512: "This knowledge is too simple, is there an advanced version? I prefer a more serious teacher style," the smart assistant application receives the above interactive information 1. Based on this information, it can parse the target user's needs, including the requirement to adjust the content of the original explanation video, obtain the explanation video 1 corresponding to interactive information 1, and update the video explanation interface. In the updated video explanation interface, the video playback control 511 plays the explanation video 1 corresponding to interactive information 1. In other words, the video playback control 511 in the video explanation interface stops playing the original explanation video and starts playing the explanation video 1 corresponding to interactive information 1. The updated video explanation interface is as follows: Figure 6A As shown in interface 52, based on the target user needs analyzed from interactive information 1, explanation video 1, compared to the original explanation video, still explains the knowledge point of "arithmetic sequences," but the difficulty level is relatively higher: it changes from the derivation of the formula for the sum of an arithmetic sequence to a college entrance examination question on arithmetic sequences, and the teaching style is relatively more serious: it changes from a friendly female teacher to a serious male teacher, and the knowledge is explained in the mode of a school teacher explaining examples on a blackboard. See also Figure 6A The updated video tutorial interface 52 can also add a text box 521 compared to interface 51 to display the interactive information 1 entered by the user, so that the user can easily view the interactive information 1 entered by the user.

[0104] Optionally, the explanation video 1 corresponding to interactive information 1 may also display response information 1 for interactive information 1. This response information can be implemented through subtitles or video frame images, thereby improving the interactivity between the explanation video and the user. For example, the first frame subtitle of the explanation video 1 played in the video playback control 511 of interface 52 displays response information 1 for interactive information 1, responding to the user's interactive information about "simple" and guiding the content to be explained in the explanation video 1: Since you think it's simple, then let's experience the college entrance examination questions about arithmetic sequences together.

[0105] If the user enters interactive information again in the updated video tutorial interface, the smart assistant application can respond to the new input and update the tutorial video playing in the interface again. This process continues, enabling the educational assistant function within the smart assistant application to dynamically adjust the tutorial video based on user interaction, supporting personalized learning. An example is shown below.

[0106] See Figure 6A As the explanatory video 1 corresponding to interactive information 1 plays, the smart assistant application displays a video explanation interface, such as interface 53, where explanatory video 1 is playing. If the user clicks the text editing control 513 in interface 53 and enters the following interactive information 2 in the interactive text box 512: "I don't understand the derivation, it feels very complicated." Accordingly, the smart assistant application receives the above interactive information 2, parses the user's needs based on interactive information 2, including: the need to adjust the content of explanatory video 1, obtains the corresponding explanatory video 2 based on the above interactive information 2, updates the video explanation interface, and the video playback control 511 in the updated video explanation interface plays the video corresponding to interactive information 2. In other words, the video playback control 511 stops playing the explanatory video 1 corresponding to interactive information 1 and starts playing the explanatory video 2 corresponding to interactive information 2. The updated video explanation interface is as follows: Figure 6A As shown in interface 54, the smart assistant application, based on the target user needs analyzed from interactive information 2, explains that while the teaching style of video 2 remains the same as that of video 1, the teaching content has changed: from arithmetic sequence college entrance examination questions to a collection of incorrect arithmetic sequence questions. Furthermore, the first frame of video 2 corresponding to interactive information 2 also displays response information 2, addressing the user's feelings of "not understanding the derivation and finding it very complicated": You are already very good! The questions are beyond the scope of first-year high school knowledge; and it guides the user towards the upcoming content, the "collection of incorrect questions": Let's review the collection of incorrect questions first? Optionally, interface 54 can also add a text box 522 compared to interfaces 52 and 53 to display the user-input interactive information 2.

[0107] Understandably, users can continue to input interactive information in the updated video tutorial interface. As long as the user's needs for adjusting the content of the tutorial video are analyzed based on the interactive information, the smart assistant application can respond to the user's newly input interactive information, update the tutorial video playing in the video tutorial interface, and the updated tutorial video can be obtained by adjusting the video features of the tutorial video according to the target user needs analyzed from the interactive information.

[0108] In other embodiments, the interactive information entered by the user in the video explanation interface may not include information on adjusting the content of the explanation video, but only visual feedback, emotional expression, etc. In this case, the smart assistant application can display an explanation video that does not include teaching content based on the parsed target user needs, as illustrated below.

[0109] See Figure 6BAs the explanation video 2 corresponding to interactive information 2 plays, the smart assistant application displays a video explanation interface, such as shown in interface 55. If the user clicks the text editing control 513 in interface 55 and enters the following interactive information 3 in the text box 512: "Thank you, Xiaoyi, you explained it so well!", the electronic device receives the above interactive information 3 and can parse it to determine that the user's request is to stop watching the video. The smart assistant application can obtain the explanation video 3 corresponding to interactive information 3, update the video explanation interface, and the video playback control 511 in the updated video explanation interface plays the explanation video 3 corresponding to interactive information 3. The updated video explanation interface is shown in the image below. Figure 6B As shown in interface 56, since user interaction information 3 only contains the user's evaluative language regarding the instructional video and does not include any content requirements for the video, the parsed user requirement is to end watching the video. Therefore, the video displayed in interface 56 only shows the corresponding response information 3 in response to interaction information 3, without any teaching content about the knowledge points. Response information 3 includes the response to interaction information 3: You're great too! Thumbs up!

[0110] It should be noted that for interactive information like Message 3, which only contains emotional language and does not include interactive information related to the need for explanatory videos, the content displayed by electronic devices to users is not limited to videos; it can also include images or text. For example... Figure 6C As shown in the interface, the response image corresponding to interactive information 3 is displayed at the location of the video playback control 511, instead of the explanatory video. This image includes the response information for interactive information 3.

[0111] exist Figure 6A and Figure 6B In the method described, the video features of the instructional video (such as teaching content and / or teaching style) can be updated in real time based on the interactive information input by the user, thereby greatly satisfying the user's dynamically changing learning needs. Furthermore, the instructional video includes response information to the interactive information, thus tracking, encouraging, and guiding the user's emotions, making the updates of the instructional video more interesting and interactive, increasing user viewing interest, and enhancing the user's learning experience.

[0112] Optionally, with Figure 5ATaking the video explanation interface shown in interface 51 as an example, the video explanation interface may also include controls such as a "like" control 516 and a "dislike" control 517, which allow users to directly select and directly reflect their viewing feedback on the explanation video. In this embodiment, such controls are referred to as viewing feedback controls. Users can click on the above-mentioned viewing feedback controls to express their viewing feedback or evaluation of the played explanation video. Correspondingly, the smart assistant application can use the interactive information corresponding to the viewing feedback controls as the interactive information input by the user. Among them, the interactive information input by the user to the electronic device by clicking on the viewing feedback controls can be displayed in the interactive text box 512, or it can not be displayed in the interactive text box 512. Among them, the interactive information corresponding to the above-mentioned "like" control 516 can be used to indicate that the explanation video meets the user's actual needs, and the interactive information corresponding to the "dislike" control 517 can be used to indicate that the explanation video does not meet the user's actual needs.

[0113] See Figure 7 As shown, an exemplary description is provided of the interface implementation when the video explanation interface includes opinion expression controls such as the "like" control 516 and the "dislike" control 517.

[0114] See Figure 7 Taking the video explanation interface shown in interface 55 as an example, if a user clicks the "Like" control 516 while watching the explanation video 2 corresponding to interactive information 2, the smart assistant application can obtain the interactive information 4 corresponding to the "Like" control 516, such as: liking the explanation video. Based on this interactive information, if the target user's need is to keep the explanation video playing, the smart assistant application can continue playing the explanation video corresponding to interactive information 2. In other embodiments, if a user clicks the "Like" control 516 while watching the explanation video 2 corresponding to interactive information 2, the smart assistant application can also directly determine that the target user's need is to keep the explanation video playing, and the smart assistant application can continue playing the explanation video corresponding to interactive information 2.

[0115] See Figure 7 If a user clicks the "dislike" control 517 while watching the explanation video 2 corresponding to interactive information 2, the smart assistant application can obtain the interactive information 5 corresponding to the "dislike" control 517, such as: dislike of the explanation video. The smart assistant application can parse the target user's needs based on the interactive information 5 corresponding to the "dislike" control 517, including the user's need to adjust the explanation video, obtain the explanation video 4 corresponding to interactive information 5, and update the video playing in the video playback control 511 to the explanation video 4 corresponding to interactive information 5. The updated video explanation interface will look like this: Figure 7As shown in interface 57, the smart assistant application, based on the target user needs analyzed from interaction information 5, changes the teaching content of explanation video 4 compared to explanation video 2, maintaining the same teaching style: from a collection of incorrect problems in arithmetic sequences to a summary of difficult points. Furthermore, explanation video 4 corresponding to interaction information 5 also displays response information 3 in the first frame, addressing the user's feelings of "not liking the explanation video": "If you don't like reviewing the collection of incorrect problems…"; and guides the user towards the upcoming teaching content, "summary of difficult points": "Let's take a look at the summary of difficult points."

[0116] This method provides users with other possible ways to interact besides inputting information, thereby increasing the diversity and fun of user interaction.

[0117] See Figure 8 As shown, if the user needs parsed from the user's input interaction information differ too much from the user needs corresponding to the currently playing explanation video, the smart assistant application may be unable to obtain the explanation video corresponding to the interaction information from the local device in a timely manner. In other words, the smart assistant application may need a relatively long time to obtain the explanation video corresponding to the interaction information. An example of the interface implementation in this case is provided.

[0118] See Figure 8 Taking the video explanation interface shown in interface 53 as an example, if a user is watching the explanation video 1 corresponding to interactive information 1, and the user clicks the text editing control 513 in interface 53 and enters the following interactive information 6 in the text box 512: "Tell me about Li Bai's poems." Correspondingly, the smart assistant application receives the above interactive information 6 and determines that it cannot obtain the explanation video 5 corresponding to interactive information 6 in a timely manner. It can then display the video explanation interface shown in interface 58, and display a waiting prompt image 518 at the video playback control 511 to prompt the user to wait. After obtaining the explanation video 5 corresponding to interactive information 6, the smart assistant application displays the video explanation interface shown in interface 59, and plays the explanation video 5 corresponding to interactive information 6 in the video playback control 511. As shown in interface 59, according to the target user needs obtained from the analysis of interactive information 6, the teaching style of explanation video 5 remains unchanged compared to explanation video 1, but the teaching content has changed: from the derivation of the summation formula of an arithmetic sequence to Li Bai's "The Road to Shu is Hard." As shown in interface 59, the first frame of the explanatory video 5 corresponding to interactive information 6 displays the response information for the user's waiting and interactive information 6, as well as the guidance information for the upcoming teaching content: Sorry to keep you waiting, now let's talk about Li Bai's "The Road to Shu is Hard"!

[0119] It should be noted that the above interface implementation is only an example. In other embodiments, the type, number, position of the controls in the interface and the information displayed in the interface can be changed and adjusted, as long as the interactive education method of this application embodiment can be achieved.

[0120] See Figure 9 The implementation structure of the electronic device and the cloud server is described exemplarily when the interactive education method of the present application is applied to a system including an electronic device and a cloud server.

[0121] See Figure 9 The electronic device may include: a terminal data parsing module, an interface display module, an interactive video generation module, and a terminal requirement understanding module; among which,

[0122] The edge data parsing module is used to parse data, specifically including: recognizing interactive information under multimodal input, determining preceding behavioral information, and generating edge-specific user notes. The user's original input information can be multimodal, such as text, voice, and images. The edge data parsing module can recognize the raw input information of various modalities to obtain the user's interactive information. The user-specific notes can be used to record the user's historical interaction information, as well as the video features of previously played explanation videos and the user's feedback on those videos. Each time user interaction information is received, the edge data parsing module can determine the preceding behavioral information for this interaction. Specifically, it can obtain the user's historical interaction information from the user-specific notes, form a behavioral sequence according to the chronological order of the interaction information, and use this behavioral sequence as the preceding behavioral information.

[0123] The interface display module is used for displaying the interface.

[0124] The interactive video generation module is used to generate explanatory videos;

[0125] The client-side demand understanding module is used to respond to user input and interactive information, determine the target user's needs and video features, and also manage secondary creation materials sent from the cloud side and locally preset video materials.

[0126] The modules included in the electronic device may be modules in applications that execute the interactive education methods of the embodiments of this application, such as smart assistant applications or education assistant applications.

[0127] The cloud server may include: a cloud-side data parsing module, a cloud-side raw video generation module, and a cloud-side scene discrimination module; among which,

[0128] The cloud-side data parsing module can include a cloud-side profile, cloud-side memory, and a resource library. The cloud-side profile manages user profiles, which are generated by the cloud-side data parsing module based on user-inputted personal information and historical learning data. The cloud-side memory stores users' historical learning data, such as historical interaction information, video characteristics of previously played instructional videos, and user feedback on those videos. This historical learning data can include user-specific notes synchronized from the client to the cloud, as well as information recorded by the cloud-side data parsing module itself. The resource library stores video materials for knowledge points, including video templates with different teaching styles and various teaching content. Each teaching content can be used as subtitles in a video template to create an instructional video. In some embodiments, the cloud-side data parsing module can also review incorrect answers and summarize difficult points based on users' historical learning data and interaction information, storing this information in the resource library to include user-specific information and facilitate effective learning.

[0129] The cloud-based original video generation module is used for generating original explanatory videos;

[0130] The cloud-based scene discrimination module is used to determine the user's learning scenario.

[0131] It is understood that the above implementation of the terminal and cloud side structures is only an example. In other embodiments, the terminal side and / or cloud side may include more or fewer modules, and the functions of some modules may be split or merged, etc. The embodiments of this application do not impose any limitations.

[0132] The following combination Figure 9 ,pass Figures 10-13 The implementation process of the interactive education method in the embodiments of this application will be described by way of example.

[0133] Figure 10 This is a flowchart illustrating an interactive education method provided in an embodiment of this application. This method can support smart assistant applications to implement, for example... Figure 5A The interface shown is implemented as follows. Figure 10 As shown, the method may include:

[0134] Step 1001: Display the main interface of the Education Assistant.

[0135] The interface display module of the smart assistant application displays the main interface of the education assistant, for example... Figure 3 As shown in interface 32.

[0136] The main interface of the education assistant may include controls such as text editing controls, voice input controls, and image recognition controls to support users in triggering multimodal information input.

[0137] Step 1002: Receive the user's original input information

[0138] In the main interface of the education assistant, the user clicks the text editing control, enters text information in the text box, and the corresponding interface display module receives the user's original input information; or...

[0139] When a user clicks the voice input control on the main interface of the education assistant, the interface display module can instruct the microphone driver to control the microphone to collect the user's voice signal, using the user's voice signal as the user's raw input information; or...

[0140] When a user clicks the image recognition control on the main interface of the education assistant, the interface display module can access the photo application to display a photo selection interface to the user. Based on the user's image selection operation, the selected image is obtained as the user's original input information. Alternatively, when a user clicks the image recognition control on the main interface of the education assistant, the first application can instruct the camera driver to control the camera to capture images. Based on the user's photo-taking operation, the image captured by the camera is obtained as the user's original input information.

[0141] In this step, the interface display module receives the user's original input information and can send it to the terminal data parsing module.

[0142] Step 1003: Determine the user's interaction information based on the user's original input information; and obtain the user's prior behavior information.

[0143] See Figure 10 As shown, this step can be specifically executed by the edge data parsing module.

[0144] In this embodiment, taking text-based user interaction information as an example, if the user's original input information is text, the edge data parsing module can directly use the user's original input information as the user's interaction information; if the user's original input information is an image, the edge data parsing module can recognize the text information in the image as the user's interaction information; if the user's original input information is speech, the edge data parsing module can perform speech recognition, and the recognized text information can be used as the user's interaction information.

[0145] It is understood that the above implementation is only an example. In some embodiments, the cloud side can also identify the user's original input information to obtain the input information in text form. In this case, the terminal data parsing module in step 1003 can directly use the user's original input information as the user's interaction information without needing to process it in different modalities.

[0146] In some embodiments, the edge data parsing module can store the interactive information entered by the user during the use of the education assistant function, as the user's historical interaction information, and store it in the user's personal notes. In this step, the user's historical interaction information within a certain period of time before the current interaction information is received can be obtained from the user's personal notes. The specific duration of this period of time is not limited in this embodiment of the application, for example, it can be 12 hours, a day, a week, or a month, etc. For example, if the above period of time is a week, and the user has entered interactive information such as "summary of arithmetic sequence formulas" and "advanced arithmetic sequence questions" in the main interface of the education assistant within the week before the current input of "What is 1+2+3+4?", then the historical interaction information within the week can be obtained from the user's personal notes, including "summary of arithmetic sequence formulas" and "advanced arithmetic sequence questions". Correspondingly, the user's prior behavior information obtained this time includes "summary of arithmetic sequence formulas" and "advanced arithmetic sequence questions". In some embodiments, the user's prior behavior information can be sorted according to the input time of the interactive information to form a behavior sequence, so that the cloud side can use it as a reference when performing subsequent processing based on the prior behavior information.

[0147] In some embodiments, the edge data parsing module can upload user-specific notes to the cloud server at certain intervals. In other words, the cloud server can also store user-specific notes. Therefore, in this step, when the edge data parsing module obtains the user's prior behavior information, it can obtain historical interaction information from the user's specific notes that has not been synchronized to the cloud server, as prior behavior information. This reduces the amount of data transmitted by the edge data parsing module to the cloud server in the current interaction, thereby improving the speed and efficiency of the smart assistant application's feedback to the user and enhancing the user experience. For example, the edge data parsing module can synchronize user-specific notes to the cloud server at 5:00 PM every day. In this step, if the edge data parsing module obtains the user's interaction information at 6:00 PM, it can obtain historical interaction information from the user's specific notes for the hour from 5:00 PM to 6:00 PM as prior behavior information.

[0148] In some embodiments, the client-side data parsing module may also omit obtaining the user's prior behavior information. For example, if the client-side data parsing module synchronizes the user's personal notes to the cloud server in a short period of time and can synchronize the user's personal notes to the cloud server in a relatively timely manner, then omitting the step of obtaining the user's prior behavior information will have a small impact on subsequent processing, and therefore the step of obtaining the user's prior behavior information can be omitted.

[0149] Understandably, the edge data parsing module can also store the user's interaction information received this time into the user's personal notes as the user's historical interaction information, and use it as part of the user's previous behavior information when the user's interaction information is received again in the future.

[0150] Step 1004: Send the user's interaction information and prior behavior information to the cloud server.

[0151] See Figure 10 Specifically, the edge data parsing module can send the user's interaction information and preceding behavior information to the cloud-side scene discrimination module on the cloud server.

[0152] Step 1005: Obtain user profiles and historical learning data.

[0153] See Figure 10 The cloud-side scene discrimination module receives user interaction information and prior behavior information, and sends a data request to the cloud-side data parsing module to request user profile and historical learning data. In response to the data request, the cloud-side data parsing module sends the user profile and historical learning data to the cloud-side scene discrimination module.

[0154] The cloud-side data parsing module can store user profiles. These profiles are generated based on personal information provided by the user on the client side, their historical learning data, etc. The specific generation method can be implemented using relevant technologies, and this application embodiment does not impose any limitations. User profiles may include, but are not limited to: username, user type, knowledge stage, knowledge level, difficulty level, key knowledge points, preferred teaching style, etc. User type can include: student, parent, teacher, etc. Knowledge stage can include: elementary school, junior high school, high school, university, etc. For each knowledge stage, the knowledge level can be further subdivided according to grade level. Elementary school stage can include: first grade, second grade, ..., sixth grade; junior high school stage can include: first year, second year, third year; high school stage can include: first year, second year, third year, etc. Difficulty level can include: easy, moderate, complex, etc. It is understood that, theoretically, the more detailed the division of knowledge stage, knowledge level, and difficulty level, the higher the matching degree between the subsequent instructional videos provided to the user and the user's needs.

[0155] A user's historical learning data may include, but is not limited to: the user's historical interaction information, the video characteristics of the historical explanation videos played, and the user's feedback on the historical explanation videos.

[0156] Step 1006: Identify the user scenario and determine the list of knowledge points associated with the interactive information.

[0157] The cloud-side scene discrimination module can identify user scenarios based on user interaction information and prior behavior information received from the terminal side, user profiles obtained from the cloud-side data parsing module and historical learning data, determine the list of knowledge points associated with the interaction information, and send the user scenario and knowledge point list to the cloud-side raw video generation module.

[0158] The user scenario can specifically include parameters such as user type, knowledge stage, knowledge level, difficulty level, and teaching style.

[0159] In some embodiments, a user scene recognition model can be pre-trained. The input to the model can be user interaction information, prior behavior information, user profiles, historical learning data, etc., and the output can be a user scene. The structure and training methods of the above model are not limited in this application embodiment and can be implemented based on relevant model training methods. The trained user scene recognition model can be pre-stored in the cloud-side scene discrimination module.

[0160] The implementation of the cloud-side scene discrimination module in determining the list of knowledge points associated with interactive information can refer to relevant technologies, and this application embodiment does not impose any limitations.

[0161] It should be noted that, in some embodiments, the above knowledge points may include knowledge points in related technologies, educational topics, educational themes, error collections, exercise summaries, exercise breakdowns, error analysis, etc.

[0162] It should be noted that, in this embodiment of the application, the cloud-side data parsing module can classify and manage knowledge points layer by layer according to disciplines, fields, educational themes, etc., so that the above-mentioned knowledge point list can further include: the discipline, field, educational theme, etc. corresponding to each knowledge point, so that users can better understand the knowledge system to which the knowledge point belongs.

[0163] Step 1007: Obtain the secondary creation materials for each knowledge point in the knowledge point list, and generate the original explanation video corresponding to each knowledge point.

[0164] refer to Figure 10 The cloud-side original video generation module sends a data request to the cloud-side data parsing module based on the user scenario and the knowledge point list, requesting the secondary creation materials corresponding to each knowledge point in the knowledge point list. The cloud-side data parsing module responds to the data request, obtains the secondary creation materials corresponding to each knowledge point in the knowledge point list, and sends them to the cloud-side original video generation module. The cloud-side original video generation module then generates the original explanation video for each knowledge point.

[0165] In some embodiments, the cloud-side data parsing module's media library may store video materials for each knowledge point. The cloud-side data parsing module can then obtain secondary creation materials for each knowledge point from the video materials of each knowledge point in the knowledge point list based on the user scenario. The following provides exemplary descriptions of possible specific implementations.

[0166] The video materials stored in the cloud-based data parsing module's resource library for each knowledge point can include, but are not limited to: video templates for different user types, knowledge stages, knowledge levels, and styles; and teaching content for different user types, knowledge stages, knowledge levels, and difficulty levels. For example, for the knowledge point "arithmetic sequence," its video materials could include:

[0167] Several video templates for different student types, elementary school levels, first grade, and serious teaching styles; several video templates for different student types, elementary school levels, first grade, and lively teaching styles; ...; etc.

[0168] Several video templates for different parent types, elementary school level, first grade, and serious teaching style; several video templates for different parent types, elementary school level, first grade, and lively teaching style; ...; etc.

[0169] Several video templates for different teacher types, elementary school level, first grade, and serious teaching style; several video templates for different teacher types, elementary school level, first grade, and lively teaching style; ...; etc.

[0170] Several teaching contents of varying difficulty levels, categorized by student type, elementary school stage, first grade, and general difficulty; ...; etc.

[0171] Several teaching contents at different levels (easiest and simple) for different parent types, elementary school stage, first grade; several general teaching contents for different parent types, elementary school stage, first grade; ...; etc.

[0172] Teacher type, primary school stage, first grade, several simple (difficulty level) teaching contents; teacher type, primary school stage, first grade, several general teaching contents; ...; etc.

[0173] In some embodiments, for each knowledge point in the knowledge point list, the cloud-side data parsing module can obtain secondary creation materials for the knowledge point from the video materials of the knowledge point based on some or all parameters in the user scenario. The following is an example.

[0174] Example 1: The cloud-based data parsing module can obtain secondary creation materials for knowledge points based on user type and knowledge stage in the user scenario. Continuing the previous example, assuming the user type is a student and the stage is primary school, the following can be obtained from the video materials for the "arithmetic sequence" knowledge point: all video templates for the student type and primary school stage, and all teaching content for the student type and primary school stage; the above information can be used as secondary creation materials for the "arithmetic sequence" knowledge point.

[0175] Example 2: The cloud-based data parsing module can obtain secondary creation materials for knowledge points based on user type, knowledge stage, and knowledge level within a user scenario. Continuing the previous example, assuming the user type is a student, the stage is elementary school, and the level is third grade, then the following can be obtained from the video materials for the "arithmetic sequence" knowledge point: all video templates for the student type, elementary school stage, and third grade, and all teaching content for the student type, elementary school stage, and third grade; the above information can be used as secondary creation materials for the "arithmetic sequence" knowledge point.

[0176] It is understood that in practical applications, secondary creative materials for knowledge points can be obtained based on more or fewer parameters than in Example 1 and Example 2. These will not be listed one by one in the embodiments of this application.

[0177] Regarding Examples 1 and 2 above, under the same knowledge point material library, for the same knowledge point, Example 2 obtains less secondary creation material than Example 1, that is, the data volume is smaller, so the subsequent transmission from the cloud server to the electronic device is faster, and the electronic device responds to the user faster on the first time; while Example 1 obtains more secondary creation material than Example 2, so when interacting with users, it can respond to a wider range of user needs in a timely manner.

[0178] In some embodiments, to enable the electronic device to respond more promptly to a wider range of user needs during interaction, secondary creation materials from other knowledge points with high relevance to the knowledge points in the knowledge point list can also be obtained and sent to the electronic device as secondary creation materials for the knowledge points in the knowledge point list. This allows the electronic device to generate explanatory videos corresponding to the interactive information in a timely and efficient manner. The relevance between knowledge points can be pre-calculated and stored in a knowledge point material library. In this step, the aforementioned other knowledge points can be determined based on preset conditions, such as the number of other knowledge points with high relevance to the knowledge points or a relevance threshold. Then, secondary creation materials for the aforementioned other knowledge points can be obtained using a similar method as described above, which will not be elaborated here.

[0179] In some embodiments, the cloud-side original video generation module can determine the video features of the original explanation video for each knowledge point in the knowledge point list based on information such as user scenarios, user interaction information and prior behavior information received from the client side, and user profiles and historical learning data obtained from the cloud-side data parsing module. The video features may include: teaching content and teaching style. For each knowledge point, a video template for the teaching content and teaching style is obtained from the corresponding secondary creation materials to generate the original explanation video. Specific methods for generating explanation videos based on video templates and teaching content can be found in related technologies, and this application embodiment does not impose limitations.

[0180] In some embodiments, the resource library can also pre-set original explanation videos for each knowledge point according to user type, knowledge stage, knowledge level, difficulty, teaching style, etc. In this step, the original explanation video corresponding to each knowledge point in the knowledge point list can be directly obtained from the resource library according to the user scenario, without the need for the cloud-side original video generation module to generate it in real time. This improves the efficiency of the cloud-side original video generation module in obtaining the original explanation video, thereby shortening the time for the terminal to display the knowledge point list and play the original explanation video to the user.

[0181] Step 1008: Send the list of knowledge points, the secondary creation materials for each knowledge point in the list, and the original explanation video.

[0182] See Figure 10 Specifically, the cloud-side original video generation module can send the knowledge point list, the secondary creation materials for each knowledge point in the knowledge point list, and the original explanation video to the client-side requirement understanding module.

[0183] In some embodiments, user scenarios and other information can also be sent to the edge-side requirement understanding module, so that when the edge-side requirement understanding module receives user interaction information in the future, it can combine the user scenario to analyze user requirements and improve the accuracy of analyzing user requirements.

[0184] In some embodiments, in order to improve the efficiency of displaying the knowledge point list to the user on the client side, this step can also first send the knowledge point list to the client side, and then send the secondary creation materials and original explanation videos for each knowledge point in the knowledge point list to the client side.

[0185] Step 1009: Display a list of knowledge points associated with the interactive information on the main interface of the education assistant.

[0186] See Figure 10 The client-side requirements understanding module can send the knowledge point list to the interface display module, which then displays the knowledge point list in the main interface of the education assistant. The main interface of the education assistant displaying the knowledge point list with interactive information in this step is shown in, for example, interface 35.

[0187] Optionally, the main interface of the education assistant can also display response information for the interactive information. For example, text box 354 in interface 35 displays the response information "Calculate, 1+2+3+4 equals 10". In this case, after the smart assistant application determines the user's interactive information in step 1005, it also needs to obtain the response information for the interactive information, thus displaying the response information for the interactive information in the main interface of the education assistant in this step. This application embodiment does not limit how the smart assistant application obtains the response information for the interactive information. For example, the smart assistant application can generate the response information based on the interactive information, or the cloud server can generate the response information based on the interactive information and send it to the smart assistant application on the client side. This application embodiment does not limit the method for generating response information based on the interactive information.

[0188] Step 1010: Upon receiving the user's selection of the first knowledge point in the knowledge point list, the video explanation interface is displayed, and the original explanation video of the first knowledge point is played in the video explanation interface.

[0189] The interface display module receives the user's selection of the first knowledge point in the main interface of the education assistant, and sends the information of the first knowledge point to the client-side demand understanding module. The client-side demand understanding module obtains the original explanation video corresponding to the first knowledge point and sends it to the interface display module. The interface display module displays the video explanation interface and plays the original explanation video corresponding to the first knowledge point in the video explanation interface.

[0190] The user's selection of the first knowledge point in the main interface of the education assistant can be, for example, by clicking on the control 355 corresponding to the arithmetic sequence (the first knowledge point) in the main interface of the education assistant, as shown in interface 35. The video explanation interface is shown in interface 51.

[0191] In other embodiments, the original explanation video corresponding to each knowledge point in the knowledge point list may not be sent from the cloud side to the edge side. Instead, the edge-side demand understanding module instructs the edge-side interactive video generation module to generate the original explanation video corresponding to each knowledge point based on the received secondary creation materials for each knowledge point. In this case, in step 1009, the interface display module receives the user's selection of the first knowledge point in the main interface of the education assistant and sends the information of the first knowledge point to the edge-side demand understanding module. The edge-side demand understanding module can then instruct the edge-side interactive video generation module to generate the original explanation video for the first knowledge point and send it to the interface display module. Specifically, the edge-side demand understanding module can determine the video characteristics of the original explanation video corresponding to the first knowledge point based on user scenarios, interaction information, and prior behavior information. It then obtains a video template and teaching content matching the video characteristics from the secondary creation materials corresponding to the first knowledge point and sends the matching video template and teaching content to the edge-side interactive video generation module, which generates the original explanation video.

[0192] In this method, a list of knowledge points associated with the user's interactive information is automatically displayed on the main interface of the education assistant. Furthermore, the user can select a knowledge point from the list and watch the corresponding explanation video, thereby enabling the user to enter the intelligent interactive video explanation interface and watch the explanation video for the knowledge point.

[0193] Figure 11 This application provides another flowchart illustrating the interactive education method according to its embodiments. This method can support smart assistant applications to implement, for example... Figure 5B The interface shown is implemented as follows. Figure 11 As shown, the method may include:

[0194] For the implementation of steps 1101 to 1105, please refer to steps 1001 to 1005, which will not be repeated here.

[0195] Step 1106: Identify user scenarios and determine target knowledge points.

[0196] The method for the cloud-side scene discrimination module to identify user scenes can be found in step 1006, and will not be elaborated here.

[0197] In some embodiments, the cloud-side scene discrimination module can determine the target knowledge point based on the user's interaction information, or it can further combine the user's prior behavior information, user profile, and / or historical learning data to determine the target knowledge point. This application embodiment does not impose any limitations. For example, if the interaction information "Tell me about arithmetic sequences" explicitly indicates that arithmetic sequences are the target knowledge point, then the target knowledge point can be determined directly based on the user's interaction information. If the interaction information does not explicitly indicate the target knowledge point, the cloud-side scene discrimination module can further combine the user's prior behavior information, user profile, and / or historical learning data to select the knowledge point with the highest historical attention and access frequency from the user's historical data as the target knowledge point. The specific implementation of the cloud-side scene discrimination module in determining the target knowledge point is not limited in this application embodiment.

[0198] In some embodiments, in order to enable the smart assistant application to simultaneously support Figure 5A and Figure 5B The interface shown can be further implemented as follows: determine whether the user's needs include video explanation requirements; if not, execute step 1006 and subsequent steps; if the user's needs include video explanation requirements, execute step 1106 and subsequent steps in this embodiment.

[0199] In some embodiments, the cloud-side scene discrimination module can parse user needs based on user interaction information and determine whether the user needs are for video explanations. In other embodiments, the cloud-side scene discrimination module can also parse user needs based on user interaction information, combined with the user's prior behavior information, user profile, and / or historical learning data, and determine whether the user needs are for video explanations of knowledge points.

[0200] In some embodiments, when parsing user needs based on user interaction information, a model for user needs parsing can be pre-trained. The input to the model can be user interaction information, and the output can be user needs. Specific implementations are not limited in this application. It is understood that if user needs are parsed based on prior behavioral information, user profiles, and / or historical learning data, then the input to the above model can be user interaction information, prior behavioral information, user profiles, and / or historical learning data, etc., which will not be elaborated here. The training method for the above model can be implemented using related technologies, and is not limited in this application.

[0201] The cloud-side scene discrimination module can send user scenarios and target knowledge points to the cloud-side raw video generation module. Once the cloud-side scene discrimination module parses and obtains the user requirements, it can also send those requirements to the cloud-side raw video generation module.

[0202] Step 1107: Obtain secondary creation materials for the target knowledge point and generate the original explanation video for the target knowledge point.

[0203] The cloud-side original video generation module receives the user scenario, user requirements (video explanation requirements for knowledge points), and target knowledge points. It can send a data request to the cloud-side data parsing module to request secondary creation materials for the target knowledge points. The cloud-side data parsing module responds to the data request, obtains the secondary creation materials for the target knowledge points, and sends them to the cloud-side original video generation module. The cloud-side original video generation module then generates the original explanation video for the target knowledge points.

[0204] The implementation of this step can refer to the corresponding description in step 1007. The difference is that this step is the target knowledge point, while step 1007 is each knowledge point in the knowledge point list.

[0205] It is understood that the secondary creation materials for the target knowledge point obtained in this step may include only the secondary creation materials for the target knowledge point itself, or it may include the secondary creation materials for the target knowledge point itself, as well as the secondary creation materials for several other knowledge points that are highly related to the target knowledge point.

[0206] Step 1108: Send the user's requirements, secondary creation materials for the target knowledge points, and the original explanation video.

[0207] The cloud-side original video generation module can send the target knowledge points, secondary creation materials for the target knowledge points, and the original explanation videos to the client-side requirements understanding module.

[0208] Step 1109: Display the video tutorial interface, where the original tutorial video will play.

[0209] The client-side requirement understanding module determines that the user's requirement is a video explanation requirement for a knowledge point based on the user's requirements. It then sends the original explanation video of the target knowledge point to the interface display module, which displays the video explanation interface and plays the original explanation video of the target knowledge point.

[0210] It should be noted that the original explanation video of the target knowledge point can also be generated by the client. For specific implementation details, please refer to the relevant instructions in step 1010, which will not be elaborated here.

[0211] Figure 11 This provides users with an alternative way to access the video explanation interface from the main interface of the education assistant, eliminating the need for users to select the corresponding control for each knowledge point, thus simplifying user operation and improving user experience.

[0212] It should be noted that, in order to make Figure 10 The interactive educational methods shown are compatible with Figure 11 In the interactive education method shown, in step 1006, the cloud-side scene discrimination module can also parse the user's needs and, when it determines that the user's needs are not video explanations of knowledge points, determine the list of knowledge points. Correspondingly, in step 1006, the cloud-side scene discrimination module can also send the parsed user needs to the cloud-side original video generation module. In step 1008, the cloud-side original video generation module sends the user needs to the end-side needs understanding module, so that the end-side needs understanding module can send the list of knowledge points to the interface display module based on the user's needs, thereby adding the display of the knowledge point list to the main interface of the education assistant.

[0213] It should be noted that, in another embodiment, in step 1006, the cloud-side scene discrimination module may not send the parsed user requirements to the cloud-side original video generation module, but instead send a requirement indicator to indicate whether the user requirement is a video explanation requirement. Correspondingly, in step 1008, the cloud-side original video generation module can send the requirement indicator to the end-side requirement understanding module. The end-side requirement understanding module can also obtain the user requirements parsed by the cloud side, and then send the knowledge point list or the original explanation video of the target knowledge point to the interface display module according to the user requirements.

[0214] Figure 12This application provides another flowchart illustrating the interactive education method according to its embodiments. This method can support the implementation of smart assistant applications. Figures 6A-7 The interface shown is implemented as follows. Figure 12 As shown, the method may include:

[0215] Step 1201: Display the video tutorial interface.

[0216] The video explanation interface in this step can be the video explanation interface displayed in step 1010 in response to the user's selection of the first knowledge point, such as interface 51.

[0217] Alternatively, the video tutorial interface in this step can be executed. Figure 12 Following the method shown, an updated video tutorial interface was created for playing the video. Examples include interfaces 52, 53, 54, 55, 56, and 57.

[0218] This step can be specifically executed by the interface display module.

[0219] Step 1202: Obtain user interaction information.

[0220] The interface display module receives raw input messages from the user via text, voice, images, etc., on the video tutorial interface and sends the raw input information to the client-side data parsing module. The client-side data parsing module can determine the user's interaction information based on the raw input information. For specific implementation details, please refer to the corresponding explanations in steps 1002 and 1003; they will not be elaborated here. For interface implementation, please refer to... Figures 6A-6B The interactive information input by the user is, for example, the interactive information 1 to 3 mentioned above.

[0221] In other embodiments, the user can also click, for example... Figure 7 The "like" or "dislike" controls shown in the figure can be used to express opinions. Correspondingly, the interface display module can also receive the interactive information corresponding to the opinion expression control clicked by the user. The interactive information corresponding to the opinion expression control can be preset, and the specific implementation of the interactive information is not limited in this application embodiment.

[0222] Step 1203: Determine the key information of the interactive message.

[0223] In some embodiments, the client-side data parsing module can extract keywords from interactive messages and send the extracted keywords as key information to the client-side requirement understanding module.

[0224] In other embodiments, the client-side data parsing module can obtain the user's historical interaction information, extract keywords from both the historical and current interaction information (i.e., the interaction information obtained in step 1202), and send the extracted keywords as key information to the client-side requirement understanding module. Since this embodiment incorporates the user's historical interaction information, theoretically, compared to embodiments that only extract keywords from interaction information as key information, this embodiment can improve the client-side requirement understanding module's understanding and matching accuracy of the user's needs in the current interaction.

[0225] Step 1204: Determine the needs of the target users.

[0226] In this step, the client-side requirement understanding module can determine the target user requirements for this interaction based on the received key information. In other words, it determines the target user requirements corresponding to the interaction information in step 1202.

[0227] In some embodiments, the edge-side demand understanding module can determine the target user demand for this interaction based on key information, user scenarios, etc. In some embodiments, a target user demand identification model can be preset, and the input of the model can be the aforementioned key information and user scenario information, and the output can be the target user demand. The training method of the above model is not limited in the embodiments of this application.

[0228] The target user's needs can include: continue watching the explanation video, stop watching the explanation video, and adjust the explanation video. "Continue watching the explanation video" means the smart assistant application doesn't need to change the currently playing explanation video in the video explanation interface; in other words, it maintains the playback of the currently playing explanation video. For example, if explanation video A is playing in the video explanation interface, and the user inputs interactive information, the parsing reveals that the target user's need is to continue watching the explanation video. Therefore, explanation video A will continue playing in the video explanation interface. From the interface implementation perspective, the user has input interactive information, but explanation video A remains in playback. "Stop watching the explanation video" means stopping the currently playing explanation video in the video explanation interface. From the interface implementation perspective, for example... Figure 6B As shown, if the user enters "Thank you, Xiaoyi, you explained it so well" in interface 55, the explanation video playing in the video explanation interface will update from the explanation video in interface 55 to the explanation video in interface 56, and the explanation video playing in interface 55 will stop playing. Adjusting the explanation video refers to adjusting the video characteristics of the explanation video provided to the user and regenerating the explanation video. From the perspective of interface implementation, the interface implementation is as follows: Figure 6AAs shown in interfaces 51-54, after the user inputs interactive information, the explanation video played in the video explanation interface is updated, and the updated explanation video adjusts its video features based on the user's interactive information, which may be adjustments to the teaching content and / or teaching style, etc.

[0229] When adjusting instructional videos, the target user needs can be further specified as: requirements for teaching content, and / or requirements for teaching style. The requirements for teaching content can be further refined into: requirements for knowledge points, knowledge stages, knowledge levels, and difficulty levels; the requirements for teaching style can also be further refined into: requirements for knowledge stages, knowledge levels, and style types.

[0230] For example, if a user's interaction message is "Thank you, Xiaoyi, that's all for today," then the target user's need might be: to stop watching the explanation video. If a user's interaction message is "This knowledge is too simple, is there an advanced version? I prefer a more serious teaching style," then the target user's need might be: to adjust the explanation video, and could further include: more difficult teaching content and a more serious teaching style. If a user's interaction message is "Xiaoyi, this is exactly what I want to see," then the target user's need might be: to continue watching the explanation video.

[0231] Step 1205: When the target user's need is not to continue watching the tutorial video, obtain the target video material based on the target user's needs.

[0232] See Figure 10 This step can be performed by the client-side requirements understanding module, which will then send the target video material to the interactive video generation module.

[0233] In some embodiments, when the target user's requirement is to adjust the explanatory video, the edge-side requirement understanding module determines the target video features based on the target user's requirements and obtains secondary creation materials that match the target video features from the secondary creation materials; furthermore, the edge-side requirement understanding module can generate response information corresponding to the interactive information based on the target video features and interactive information, and use the response information and the secondary creation materials that match the target video features as the target video materials.

[0234] When determining target video features based on the needs of the target users, the video features of the current instructional video can be adjusted according to those needs to obtain the target video features. Specifically, which features do the target users require, and which parameters of the instructional features can be adjusted?

[0235] For example, the current teaching characteristics of instructional videos include: arithmetic sequences (knowledge points), primary school stage (knowledge stage), third grade (knowledge level), lively style (teaching style type), and moderate difficulty level (difficulty level).

[0236] For example, if the target user needs include: increasing the knowledge level, then the "third grade" in the teaching characteristics of the current instructional video can be adjusted to "fourth grade"; if the target user needs include: a more serious teaching style, then the lively type in the teaching characteristics of the current instructional video can be adjusted to a serious type; and so on.

[0237] It should be noted that when adjusting a specific teaching feature, the needs of the target users may be somewhat vague. For example, if the knowledge level is raised, the adjustment can be made according to the preset adjustment strategy. The adjustment strategies for different teaching features can be the same or different. Alternatively, if the needs of the target users may be clear, for example, if the knowledge level is adjusted to the fourth grade, the knowledge level can be adjusted directly according to the fourth grade in the needs of the target users.

[0238] When generating response information corresponding to interactive information, response information can be generated based on the interactive information, and guidance information can be generated based on the teaching content in the target video features. The response information and guidance information are then combined to obtain the response information. The specific methods for generating the response information and guidance information can be implemented using relevant technologies, and this application does not impose any limitations on these methods.

[0239] In some embodiments, when the target user's requirement is to stop watching the tutorial video, the client-side requirement understanding module can obtain the video material corresponding to the request to stop watching the tutorial video, generate response information corresponding to the interaction information based on the interaction information, and use the video material and response information as the target video material. The video material corresponding to the target user's requirement to stop watching the tutorial video can be preset in the client-side requirement understanding module, or it can be sent to the client-side requirement understanding module in secondary creation materials; this application embodiment does not impose any limitations. The video material corresponding to the request to stop watching the tutorial video may include a video template, which may or may not include preset subtitles.

[0240] In some embodiments, when the target user's requirement is to stop watching the instructional video, if the client-side requirement understanding module displays the following to the user: Figure 6C The response image shown can be obtained by the client-side requirement understanding module, which can then send the response image to the interface display module for display. Alternatively, the client-side requirement understanding module can generate response information corresponding to the interaction information, generate a response image based on the response information, and then send it to the interface display module for display.

[0241] In some embodiments, when the target user's requirement is to continue watching the tutorial video, the endpoint demand understanding module can directly send an instruction message to the interface display module to instruct the interface display module to continue playing the current tutorial video, that is, to keep playing the current tutorial video unchanged. The processing flow of this embodiment is not shown. Figure 12 middle.

[0242] Step 1205: Generate the explanatory video corresponding to the interactive information.

[0243] The interactive video generation module can generate an explanatory video based on the received target video material, and then send the generated explanatory video to the interface display module.

[0244] In some embodiments, if the target video material includes: interactive response information and secondary creation material, the response information can be used as subtitles for the explanatory video, such as the first frame subtitle, and the teaching content in the secondary creation material can be used as subtitles for the second and subsequent frames. Combined with a video template, an explanatory video is generated. By using response information as subtitles for the explanatory video, such as the first frame subtitle, the explanatory video becomes more interactive with the user, increasing the user's viewing interest and improving the user experience.

[0245] It is understood that in other embodiments, the response information can also be used as part of the first frame subtitle, and part of the teaching content in the secondary creation material can also be used as the first frame subtitle, with the others serving as subtitles for the second and subsequent frames, combined with the video template to generate the explanatory video. Alternatively, in other embodiments, the aforementioned response information can also be used as subtitles for other frames, such as the second frame subtitle, etc., and this application embodiment does not impose any limitations.

[0246] In some embodiments, if the target video material includes: response information for interactive information, and video material corresponding to stopping watching the explanatory video, an explanatory video can be generated based on the response information and the video material. For example, if the video material includes a video template, the response information can be used as subtitles for the explanatory video, such as the first frame subtitle, and combined with the video template to generate the explanatory video.

[0247] Step 1206: Update the tutorial videos in the video tutorial interface.

[0248] The interface display module updates the video playing in the video explanation interface to the received explanation video, which is the explanation video generated in step 1205.

[0249] In some embodiments, the interface display module may also add text boxes to the video explanation interface to display user interaction information. This allows users to clearly understand the interactive information corresponding to the currently playing explanation video, improving the user experience. Examples include text box 521 in interface 52 and text box 522 in interface 54.

[0250] This method can generate explanatory videos corresponding to user interaction information in real time based on secondary creation materials sent from the cloud and pre-stored video materials locally, without interacting with the cloud. This allows for real-time and efficient intelligent response to user interaction information, with strong user perception, high level of intelligence, and improved interaction efficiency between the smart assistant application and the user.

[0251] exist Figure 12 In the method shown, after determining the target user's needs in step 1204, the client-side needs understanding module may be unable to obtain the target video materials from the local storage based on the target user's needs. In other words, the locally stored video materials and the secondary creation materials sent from the cloud cannot meet the target user's needs. To solve the above problem, this application embodiment also provides... Figure 13 The interactive education method shown can support the implementation of smart assistant applications. Figure 8 The interface shown is implemented as follows. Figure 13 As shown, this method is relative to Figure 12 The method shown may include steps 1301 to 1309 after step 1204.

[0252] Step 1301: Send request information.

[0253] Once the client-side demand understanding module determines that it cannot obtain the target video material corresponding to the target user's demand from the local machine, it sends a request to the client-side data parsing module to request the client-side data parsing module to obtain the secondary creation material of this interaction information from the cloud side.

[0254] In some embodiments, the client-side demand understanding module can also send a waiting prompt image to the interface display module. The interface display module can replace the video playing on the video explanation interface with the aforementioned waiting prompt image. This waiting prompt image is used to remind the user to wait for the video to update, thereby alleviating user anxiety caused by slow video updates. The video explanation interface displayed by the interface display module, including the waiting prompt image, is as follows: Figure 8 The interface shown in image 58 shows a waiting prompt image, such as image 518.

[0255] The implementation of steps 1302 to 1306 can refer to steps 1104 to 1108; the main difference is:

[0256] In step 1302, the edge data parsing module can also send the video features of the current explanation video (the explanation video playing in the video explanation interface when inputting interactive information) and the target user needs determined by the edge requirement understanding module to the cloud-side scene discrimination module, so that the cloud-side scene discrimination module can better determine the user scenario and target knowledge points.

[0257] Step 1307: Update the video tutorial playing on the video tutorial interface to the original video tutorial.

[0258] In this step, the edge-side requirement understanding module can send the received original explanation video to the interface display module, and the interface display module will update the video playing in the video explanation interface to the original explanation video.

[0259] In other embodiments provided in this application, the cloud-side original video generation module in step 1305 may not generate an original explanatory video. Instead, it sends the secondary creation materials to the end-side demand understanding module. The end-side demand understanding module can obtain target video materials based on the target user's needs and send the target video materials to the interactive video generation module to generate an explanatory video. The interactive video generation module then sends the generated explanatory video to the interface display module, which updates the video playing in the video explanation interface to the generated explanatory video. This embodiment is different from... Figure 13 The illustrated embodiment can reduce the amount of data processing on the cloud server, as well as the amount of data transmission between the endpoint and the cloud.

[0260] This application provides an electronic device, including a processor and a memory, wherein the processor is used to execute the method provided in this application.

[0261] This application also provides a computer-readable storage medium storing a computer program that, when run on a computer, causes the computer to execute the method provided in this application.

[0262] This application also provides a computer program product, which includes a computer program that, when run on a computer, causes the computer to perform the method provided in this application.

[0263] In this application embodiment, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent the existence of A alone, A and B simultaneously, or B alone. A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of singular or plural items. For example, at least one of a, b, and c can represent: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, and c can be single or multiple.

[0264] Those skilled in the art will recognize that the units and algorithm steps described in the embodiments disclosed herein can be implemented using electronic hardware, computer software, or a combination of electronic hardware and software. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0265] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0266] In the several embodiments provided in this application, any function, if implemented as a software functional unit and sold or used as an independent product, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0267] The above description is merely a specific embodiment of this application. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the protection scope of this application. The protection scope of this application should be determined by the protection scope of the claims.

Claims

1. An interactive education method, characterized by, The method is applied to an electronic device, and the method comprises: displaying a first interface in which a first explanation video is played; receiving first interaction information input by a user in the first interface; in response to the first interaction information, updating the video played in the first interface from the first explanation video to a second explanation video, the second explanation video being generated by the electronic device according to the first interaction information, and subtitles displayed in the second explanation video including first response information generated according to the first interaction information.

2. The method of claim 1, wherein, The first interface is displayed, comprising: displaying a second interface; receiving second interaction information input by a user in the second interface; in response to the second interaction information, displaying a knowledge point list associated with the second interaction information in the second interface; receiving a selection operation on a first knowledge point in the knowledge point list, and displaying the first interface, the first explanation video played in the first interface being an explanation video of the first knowledge point.

3. The method of claim 2, wherein, Before displaying the knowledge point list associated with the second interaction information in the second interface, the method further comprises: determining that a user demand analyzed based on the second interaction information does not include a video explanation demand.

4. The method of claim 3, wherein, The first interface is displayed, further comprising: when it is determined that the user demand analyzed based on the second interaction information includes a video explanation demand, displaying the first interface, the first explanation video played in the first interface being an explanation video of a second knowledge point, the second knowledge point being a knowledge point determined based on the second interaction information, and the subtitles of the first explanation video including second response information generated according to the second interaction information.

5. The method according to any one of claims 1 to 4, characterized in that, The first interaction information input by the user in the first interface is received, comprising: receiving text information input by the user in the first interface as the first interaction information; or receiving voice information input by the user in the first interface, converting the voice information into text information, and taking the text information as the first interaction information; or receiving picture information input by the user in the first interface, identifying text information in the picture information, and taking the text information as the first interaction information; or receiving a selection operation of a first control in the first interface by the user, and taking interaction information corresponding to the first control as the first interaction information, the interaction information corresponding to the first control being used to indicate that the first explanation video does not meet actual demands of the user.

6. The method according to any one of claims 1 to 5, characterized in that, When an adjustment demand for the explanation video is included in a target user demand analyzed based on the first interaction information, the first response information includes: response information for the first interaction information, and guidance information for teaching content of the second explanation video; and / or When a demand for ending the video explanation is included in the target user demand analyzed based on the first interaction information, the first response information includes: response information for the first interaction information.

7. The method according to any one of claims 2 to 4, characterized in that, The second explanation video is generated by the electronic device according to the first interaction information, comprising: The second explanation video is generated by the electronic device based on the first interaction information, target user demand, target video material matching the target user demand obtained from the first video material in the local electronic device, and the target video material.

8. The method of claim 7, wherein, The first video material in the local electronic device is obtained from the material library of the cloud server based on the knowledge point list and sent to the electronic device; the material library records the video material of the knowledge point.

9. The method of claim 8, wherein, The first video material includes the video material of each knowledge point in the knowledge point list; or, The first video material includes the video material of each knowledge point in the knowledge point list and the video material of the knowledge point associated with each knowledge point in the knowledge point list.

10. The method of claim 7, wherein, Before updating the video played in the first interface from the first explanation video to the second explanation video, it further includes: When the electronic device determines that there is no video material matching the target user demand in the first video material, it obtains the second video material from the cloud server based on the first interaction information, obtains the target video material matching the target user demand from the second video material, and generates the second explanation video according to the target video material.

11. The method of claim 10, wherein, The method for obtaining the second video material from the cloud server includes: Sending the first interaction information to the cloud server; Receiving the second video material sent by the cloud server, which is obtained by the cloud server from the material library of the cloud server according to the first interaction information, user portrait, and historical learning data, and records the video material of the knowledge point in the material library.

12. An electronic device, comprising: It includes: Processor, memory; One or more computer programs are stored in the memory, and the one or more computer programs include instructions that, when executed by the processor, cause the electronic device to perform the method of any one of claims 1 to 11.

13. An interactive teaching system characterized by It includes the electronic device and the cloud server of claim 12.

14. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program which, when running on a computer, causes the computer to execute the method of any one of claims 1 to 11.

15. A computer program product, characterised in that, The computer program product includes a computer program which, when running on a computer, causes the computer to execute the method of any one of claims 1 to 11.

Images