A content recommendation method, a terminal device and a readable storage medium

Abstract

Embodiments of the present application provide a content recommendation method, a terminal device and a readable storage medium, and relate to the technical field of terminals. The method is applied to a terminal device and includes: logging in a first user account in a first application; displaying a first interface, the first interface including first recommended content and a first recommendation reason corresponding to the first recommended content; wherein the first recommendation reason is generated by the first application according to learning feedback information of a second user account on the first recommended content, and the learning feedback information includes first learning feedback information, the first learning feedback information being a mastery of a knowledge point corresponding to the first recommended content after the second user account has learned the first recommended content. The method can improve the credibility of the learning content recommended by the terminal device, improve the user experience, improve the trust of the user in the educational application, and thus reduce the loss of user resources.

Description

Technical Field

[0001] This application relates to the field of terminal technology, and in particular to a content recommendation method, a terminal device, and a readable storage medium. Background Technology

[0002] With the rapid development of online education, a large number of educational applications (referred to as educational apps) have emerged. These educational apps can provide users with rich learning content in different learning stages or different professional fields. The learning content includes different types such as documents, videos, slides, and pictures.

[0003] Currently, these educational apps typically use collaborative filtering based on user behavior (such as search and learning activities) to continuously recommend learning content that users are interested in, thereby increasing user dwell time. For example, if an educational app detects that user 1 is interested in a math course taught by teacher 1, and detects that the user searches for math concepts related to "trigonometric functions," it will prioritize recommending learning content A related to "trigonometric functions" taught by teacher 1. However, user 1 needs to spend a considerable amount of time and effort reading or watching the recommended learning content A before they can determine whether it effectively helps them understand the relevant concepts. If the learning content repeatedly recommended by the educational app fails to improve the user's learning outcome, indicating low credibility of the recommended content, it will severely waste the user's time and energy, leading to decreased trust in the educational app and even user attrition. Summary of the Invention

[0004] This application provides a content recommendation method, terminal device, and readable storage medium, which can improve the credibility of learning content recommended by educational applications to users, enhance user experience, increase user trust in the educational application, and thus reduce the loss of user resources.

[0005] To achieve the above objectives, this application adopts the following technical solution:

[0006] In a first aspect, embodiments of this application provide a content recommendation method applied to a terminal device. The method includes: logging into a first user account in a first application; displaying a first interface, the first interface including first recommended content and a first recommendation reason corresponding to the first recommended content; wherein, the first recommendation reason is generated by the first application based on learning feedback information of a second user account on the first recommended content, and the second user account is associated with the first user account; the learning feedback information includes first learning feedback information, which is the degree of mastery and / or change in the degree of mastery of the knowledge points corresponding to the first recommended content by the second user account after learning the first recommended content.

[0007] The method provided in this application allows a terminal device to recommend learning content (such as a first recommended content) based on feedback from other users (e.g., a second user) and display the reasons for the recommendation (such as the first recommendation reason) to the user, enabling the user to prioritize the first recommended content. This method improves the credibility of the learning content recommended by the terminal device, helps reduce the time and effort users spend judging whether the learning content is helpful in improving learning outcomes, enhances user experience, increases user trust in the educational application, and thus reduces user resource loss.

[0008] In some embodiments, the learning feedback information further includes second learning feedback information and / or third learning feedback information; the second learning feedback information is the evaluation result of the second user account or the third user account on the first recommended content; the third learning feedback information is the recommendation status of the second user account or the third user account on the first recommended content, wherein the third user account is associated with the first user account.

[0009] In this embodiment, the terminal device can demonstrate the reasons for recommending the first recommended content to the user from different perspectives, thereby increasing the user's trust in the first application.

[0010] In some embodiments, the first interface includes second recommended content and a second recommendation reason corresponding to the second recommended content. The second recommendation reason is generated by the first application based on the learning feedback information of a second user account or a third user account regarding the second recommended content. The third user account is associated with the first user account; the learning feedback information of the second user account or the third user account regarding the second recommended content includes second learning feedback information and / or third learning feedback information; the second learning feedback information is the evaluation result of the second user account or the third user account regarding the first recommended content, and the third learning feedback information is the recommendation status of the second user account or the third user account regarding the first recommended content. In this embodiment, the terminal device can recommend multiple learning contents to the user based on different learning feedback information, enriching the recommendation format of learning content.

[0011] In some embodiments, the second user account is a second user account in the personal social network corresponding to the first user account in the first application; or, a second user account in the social graph in the first application, which is built based on the basic user information of multiple users in the first application.

[0012] In some embodiments, the third user account is a third user account in the personal social network corresponding to the first user account within the first application; or, a third user account in the social graph within the first application, wherein the social graph is established based on the basic user information of multiple users within the first application.

[0013] In some embodiments, before displaying the first interface, the method further includes: obtaining a search instruction from a first user account and determining keywords based on the search instruction; determining search results based on the keywords, wherein the search results include first recommended content.

[0014] In some embodiments, before displaying the first interface, the method further includes: determining the mastery level of each knowledge point in the first user account; determining the weak knowledge points corresponding to the first user account from each knowledge point based on the mastery level; determining search keywords based on the weak knowledge points; and determining search results based on the keywords, wherein the search results include first recommended content.

[0015] The method provided in this application allows a terminal device to intelligently identify a user's weak knowledge points and recommend reliable learning content based on those points. This method effectively reduces the time and effort users waste learning content with poor teaching results, helps increase user trust in the educational application, and reduces the loss of user resources.

[0016] In some embodiments, the first interface further includes third recommended content, wherein the knowledge points involved in the third recommended content are related to the knowledge points involved in the first recommended content in an inclusive or predecessor relationship. Through this method, the terminal device can progressively recommend learning content to the user based on the relationships between knowledge points, which helps improve the user's academic performance.

[0017] In some embodiments, the search results further include the first learning content; the first interface also includes the first learning content, but the first interface does not include the recommendation reason corresponding to the first learning content. The recommendation reason corresponding to the first learning content is generated by the first application based on the learning feedback information of the second user account regarding the first learning content. That is to say, in this embodiment, the first interface may also display learning content not recommended by the terminal device, but without displaying a recommendation reason for the learning content based on the learning feedback information.

[0018] In some embodiments, displaying a first interface includes: sorting multiple learning contents in the search results according to the learning feedback information; and displaying the search results according to the sorting results.

[0019] In some embodiments, after the first user account has learned the first recommended content, the method further includes: collecting learning feedback information from the first user account regarding the first recommended content.

[0020] In a second aspect, embodiments of this application provide a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method described in the first aspect.

[0021] Thirdly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in the first aspect.

[0022] Fourthly, embodiments of this application provide a computer program product that, when run on a terminal device, enables the terminal device to implement the method described in the first aspect.

[0023] It is understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0024] Figure 1 This is a schematic architecture diagram of the communication system to which the content recommendation method provided in the embodiments of this application is applicable;

[0025] Figure 2 This is a schematic block diagram of a portion of the structure of the terminal device provided in the embodiments of this application;

[0026] Figure 3 This is a schematic diagram of the user basic information acquisition interface provided in the embodiments of this application;

[0027] Figure 4 This is the personal social network provided in the embodiments of this application;

[0028] Figure 5 This is a schematic diagram of the user review interface provided in an embodiment of this application;

[0029] Figure 6 This is a schematic diagram of a knowledge graph provided in one embodiment of this application;

[0030] Figure 7 This is a schematic diagram of a social graph provided in one embodiment of this application;

[0031] Figure 8 This is a flowchart of a content recommendation method provided in one embodiment of this application;

[0032] Figure 9A This is a schematic diagram of a user operation scenario provided in the embodiments of this application. Figure 1 ;

[0033] Figure 9B This is a schematic diagram of a user operation scenario provided in the embodiments of this application. Figure 2 ;

[0034] Figure 9C This is a schematic diagram of a user operation scenario provided in the embodiments of this application. Figure 3 ;

[0035] Figure 10A This is a schematic diagram of the search results display interface provided in the embodiments of this application. Figure 1 ;

[0036] Figure 10B This is a schematic diagram of the search results display interface provided in the embodiments of this application. Figure 2 ;

[0037] Figure 10C This is a schematic diagram of the search results display interface provided in the embodiments of this application. Figure 3 ;

[0038] Figure 11 This is a flowchart of a content recommendation method provided in another embodiment of this application;

[0039] Figure 12 This is a schematic diagram of a user operation scenario provided in the embodiments of this application. Figure 4 ;

[0040] Figure 13 This is a schematic diagram of the chip structure provided in the embodiments of this application. Detailed Implementation

[0041] The technical solutions provided in the embodiments of this application will be described below with reference to the accompanying drawings.

[0042] It should be understood that in the description of the embodiments of this application, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The "and / or" in this document is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone.

[0043] In this embodiment, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this embodiment, unless otherwise stated, "a plurality of" means two or more.

[0044] With the rapid development of online education, a large number of educational applications (APPs) have emerged, often referred to as educational apps. These apps offer users a wealth of learning content across different learning stages and professional fields, and are increasingly popular. Taking the "Education Center" app as an example, it provides users with learning content for various stages, such as preschool, compulsory education, and vocational skills training; it also offers learning content in fields like the internet, healthcare, professional exams, art and design, architecture, sales, and law. Furthermore, the learning content offered by these apps is diverse, encompassing various formats including videos, audio, documents, slideshows, and images. This content can be provided to users through online live streaming (e.g., online video courses, online audio courses) or as pre-stored learning materials.

[0045] Currently, these educational apps typically use collaborative filtering based on user behavior (such as search behavior, learning behavior, and course purchase behavior) to continuously recommend learning content that users are interested in, thereby increasing user dwell time. For example, if an educational app detects that user 1 is interested in a math course taught by teacher 1, and detects that the user searches for math concepts related to "trigonometric functions," it will prioritize recommending learning content A related to "trigonometric functions" taught by teacher 1. However, learning is a very time-consuming and energy-intensive activity. Therefore, for the learning content A recommended by the educational app, user 1 usually has to invest a considerable amount of time and effort before they can know whether learning content A can effectively help them understand the relevant knowledge points. In other words, for users, the trial-and-error cost of the learning content recommended by educational apps based on user interests is high. If the learning content repeatedly recommended by the educational app fails to improve the user's learning effect (i.e., the credibility of the learning content recommended by the educational app is low), it will seriously waste the user's time and energy, leading to a decrease in user trust in the educational app, and even user churn.

[0046] Therefore, this application provides a content recommendation method that recommends learning content to users based on feedback from other users regarding learning content in educational applications, with the primary goal of improving user learning outcomes. This method helps increase the credibility of content recommended by educational applications, enhances user experience, increases user trust in the educational application, and helps reduce user resource loss.

[0047] Figure 1 This is a schematic architecture diagram of the communication system to which the content recommendation method provided in this application is applicable. See also Figure 1 As shown, the system includes terminal devices and cloud devices. The cloud devices can provide data or services to multiple terminal devices. The terminal devices can be connected via wired connections or wireless connections via communication methods such as wireless local area network (WLAN) or cellular network (CN). The terminal devices and cloud devices are described in detail below.

[0048] (a) Terminal equipment

[0049] In this embodiment, the terminal device can be a mobile phone, tablet computer, computer with wireless transceiver capabilities, smart TV, projector, wearable device (such as a smartwatch), in-vehicle device, augmented reality (AR) / virtual reality (VR) device, ultra-mobile personal computer (UMPC), netbook, personal digital assistant (PDA), etc. This application does not specifically limit the type of terminal device.

[0050] Figure 2 This is a schematic diagram of the structure of a terminal device provided in an embodiment of this application. The terminal device may include a processor 210, an external memory interface 220, an internal memory 221, a universal serial bus (USB) interface 230, a charging management module 240, a power management module 241, a battery 242, an antenna 1, an antenna 2, a mobile communication module 250, a wireless communication module 260, an audio module 270, a speaker 270A, a receiver 270B, a microphone 270C, a headphone jack 270D, a sensor module 280, buttons 290, a motor 291, an indicator 292, a camera 293, a display screen 294, and a subscriber identification module (SIM) card interface 295, etc. The sensor module 280 may include a pressure sensor 280A, a gyroscope sensor 280B, a barometric pressure sensor 280C, a magnetic sensor 280D, an accelerometer sensor 280E, a distance sensor 280F, a proximity sensor 280G, a fingerprint sensor 280H, a temperature sensor 280J, a touch sensor 280K, an ambient light sensor 280L, a bone conduction sensor 280M, etc.

[0051] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the structure of the terminal device. In other embodiments of this application, the terminal device may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0052] For example, when the terminal device is a mobile phone or tablet, it may include all the components shown in the diagram, or it may include only some of the components shown in the diagram. When the terminal device is a large-screen device such as a smart TV or smart screen, it may also include all the components shown in the diagram, or it may include only some of the components shown in the diagram.

[0053] Processor 210 may include one or more processing units, such as application processors (APs), modem processors, graphics processing units (GPUs), image signal processors (ISPs), controllers, memory, video codecs, digital signal processors (DSPs), baseband processors, and / or neural network processing units (NPUs). Different processing units may be independent devices or integrated into one or more processors. The controller may serve as the central nervous system and command center of the terminal device. The controller can generate operation control signals based on instruction opcodes and timing signals to control instruction fetching and execution.

[0054] The processor 210 may also include a memory for storing instructions and data. In some embodiments, the memory in the processor 210 is a cache memory. This memory can store instructions or data that the processor 210 has just used or that are used repeatedly. If the processor 210 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 210, and thus improves the efficiency of the system.

[0055] The charging management module 240 receives charging input from a charger. The charger can be a wireless charger or a wired charger. In some wired charging embodiments, the charging management module 240 receives charging input from the wired charger via a USB interface 230. In some wireless charging embodiments, the charging management module 240 receives wireless charging input via the wireless charging coil of the terminal device. While charging the battery 242, the charging management module 240 can also supply power to the terminal device via the power management module 241.

[0056] The power management module 241 connects the battery 242, the charging management module 240, and the processor 210. The power management module 241 receives input from the battery 242 and / or the charging management module 240, providing power to the processor 210, internal memory 221, external memory, display 294, camera 293, and wireless communication module 260, etc. The power management module 241 can also monitor parameters such as battery capacity, battery cycle count, and battery health status (leakage current, impedance).

[0057] In some other embodiments, the power management module 241 may also be located within the processor 210. In other embodiments, the power management module 241 and the charging management module 240 may also be located in the same device.

[0058] The wireless communication function of the terminal device can be implemented through antenna 1, antenna 2, mobile communication module 250, wireless communication module 260, modem processor, and baseband processor.

[0059] Antenna 1 and antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna in the terminal device can be used to cover one or more communication frequency bands. Different antennas can also be reused to improve antenna utilization. For example, antenna 1 can be reused as a diversity antenna for a wireless local area network. In some other embodiments, the antennas can be used in conjunction with a tuning switch.

[0060] The mobile communication module 250 can provide solutions for wireless communication applications including 2G / 3G / 4G / 5G on terminal devices. The mobile communication module 250 may include at least one filter, switch, power amplifier, low noise amplifier (LNA), etc. The mobile communication module 250 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 250 can also amplify the signal modulated by the modem processor and convert it into electromagnetic waves for radiation via antenna 1.

[0061] In some embodiments, at least some functional modules of the mobile communication module 250 may be disposed in the processor 210. In some embodiments, at least some functional modules of the mobile communication module 250 and at least some modules of the processor 210 may be disposed in the same device.

[0062] 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 270A, receiver 270B, etc.) or displays images or videos through the display screen 294. In some embodiments, the modem processor may be a separate device. In other embodiments, the modem processor may be independent of the processor 210 and may be housed in the same device as the mobile communication module 250 or other functional modules.

[0063] The wireless communication module 260 can provide solutions for wireless communication applications on terminal devices, 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 260 can be one or more devices integrating at least one communication processing module. The wireless communication module 260 receives electromagnetic waves via antenna 2, performs frequency modulation and filtering of the electromagnetic wave signals, and sends the processed signal to processor 210. The wireless communication module 260 can also receive signals to be transmitted from processor 210, perform frequency modulation and amplification, and convert them into electromagnetic waves for radiation via antenna 2.

[0064] In some embodiments, antenna 1 of the terminal device is coupled to mobile communication module 250, and antenna 2 is coupled to wireless communication module 260, enabling the terminal device to communicate with networks and other devices via wireless communication technology. Wireless communication technologies 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. GNSS can 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).

[0065] The terminal device implements display functions through a GPU, a display screen 294, and an application processor. The GPU is a microprocessor for image processing, connecting the display screen 294 and the application processor. The GPU performs mathematical and geometric calculations and is used for graphics rendering. The processor 210 may include one or more GPUs, which execute program instructions to generate or modify display information.

[0066] The display screen 294 is used to display images, videos, etc. For example, the teaching videos and user action video in this embodiment of the application. The display screen 294 includes a display panel. The display panel can 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 Miniled LED, a MicroLED, a Micro-OLED, a quantum dot light-emitting diode (QLED), etc. In some embodiments, the terminal device may include one or N display screens 294, where N is a positive integer greater than 1.

[0067] Terminal devices can achieve shooting functions through ISP, camera 293, video codec, GPU, display 294 and application processor.

[0068] The ISP (Image Signal Processor) is used to process data fed back from the camera 293. 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 293.

[0069] Camera 293 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 terminal device may include one or N cameras 293, where N is a positive integer greater than 1.

[0070] Digital signal processors (DSPs) are used to process digital signals, including digital image signals and other digital signals. For example, when a terminal device selects a frequency, a DSP can perform a Fourier transform on the frequency energy.

[0071] Video codecs are used to compress or decompress digital video. Terminal devices can support one or more video codecs. This allows the terminal device to play or record video in various encoding formats, such as Moving Picture Experts Group (MPEG) 1, MPEG2, MPEG3, MPEG4, etc.

[0072] 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 terminal devices, such as image recognition, facial recognition, speech recognition, and text understanding.

[0073] In the embodiments of this application, the NPU or other processor can be used to perform operations such as analysis and processing of images in videos stored in the terminal device.

[0074] The external storage interface 220 can be used to connect an external storage card, such as a Micro SD card, to expand the storage capacity of the terminal device. The external storage card communicates with the processor 210 through the external storage interface 220 to perform data storage functions. For example, music, video, and other files can be saved on the external storage card.

[0075] Internal memory 221 can be used to store executable program code, including instructions. Processor 210 executes various functional applications and data processing of the terminal device by running the instructions stored in internal memory 221. Internal memory 221 may include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a given function (such as sound playback, image playback, etc.). The data storage area may store data created during the use of the terminal device (such as audio data, phonebook, etc.).

[0076] In addition, the internal memory 221 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.

[0077] The terminal device can implement audio functions through audio module 270, speaker 270A, receiver 270B, microphone 270C, headphone jack 270D, and application processor.

[0078] The audio module 270 is used to convert digital audio signals into analog audio signals for output, and also to convert analog audio inputs into digital audio signals. The audio module 270 can also be used for encoding and decoding audio signals. In some embodiments, the audio module 270 may be located in the processor 210, or some functional modules of the audio module 270 may be located in the processor 210.

[0079] The speaker 270A, also known as a "loudspeaker," is used to convert audio electrical signals into sound signals. Terminal devices can listen to music or hands-free calls through the speaker 270A. For example, the speaker can play the comparison analysis results provided in the embodiments of this application.

[0080] The receiver 270B, also known as the "earpiece," is used to convert audio electrical signals into sound signals. When a terminal device answers a phone call or voice message, the receiver 270B can be brought close to the user's ear to hear the voice.

[0081] Microphone 270C, 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 270C, inputting the sound signal into microphone 270C. A terminal device can be equipped with at least one microphone 270C. In some embodiments, the terminal device can be equipped with two microphones 270C, which, in addition to collecting sound signals, can also perform noise reduction. In other embodiments, the terminal device can be equipped with three, four, or more microphones 270C, enabling sound signal collection, noise reduction, sound source identification, and directional recording functions, etc.

[0082] The headphone jack 270D is used to connect wired headphones. The headphone jack 270D can be a USB 230 interface or a 3.5mm Open Mobile Terminal Platform (OMTP) standard interface, a CTIA (Cellular Telecommunications Industry Association of the USA) standard interface.

[0083] Buttons 290 include a power button, volume buttons, etc. Buttons 290 can be mechanical buttons or touch-sensitive buttons. The terminal device can receive button input and generate key signal inputs related to user settings and function control of the terminal device.

[0084] Motor 291 can generate vibration alerts. Motor 291 can be used for incoming call vibration alerts or for touch vibration feedback. For example, different vibration feedback effects can be corresponding to touch operations applied to different applications (such as taking photos, playing audio, etc.). Motor 291 can also correspond to different vibration feedback effects for touch operations applied to different areas of the display screen 294. Different application scenarios (such as time reminders, receiving messages, alarm clocks, games, etc.) can also correspond to different vibration feedback effects. The touch vibration feedback effect can also be customized.

[0085] Indicator 292 can be an indicator light, which can be used to indicate charging status, power changes, messages, missed calls, notifications, etc.

[0086] The SIM card interface 295 is used to connect a SIM card. The SIM card can be inserted into or removed from the SIM card interface 295 to achieve contact and separation with the terminal device. The terminal device can support one or N SIM card interfaces, where N is a positive integer greater than 1. The SIM card interface 295 can support Nano SIM cards, Micro SIM cards, SIM cards, etc. Multiple cards can be inserted into the same SIM card interface 295 simultaneously. The multiple cards can be of the same or different types. The SIM card interface 295 is also compatible with different types of SIM cards. The SIM card interface 295 is also compatible with external memory cards. The terminal device interacts with the network through the SIM card to achieve functions such as calls and data communication. In some embodiments, the terminal device uses an eSIM, i.e., an embedded SIM card. The eSIM card can be embedded in the terminal device and cannot be separated from the terminal device.

[0087] In this embodiment, the terminal device can install or call an educational application (also referred to as the first application). The educational application can be an application carried in an Android software installation package (APK), a program running on a webpage, or an applet embedded in some application platforms. This embodiment does not impose any restrictions on this.

[0088] Users log in to the educational application using their user accounts. For example, a first user logs in to the educational application using a first user account, a second user logs in using a second user account, and a third user logs in using a third user account.

[0089] During the user registration process for an educational application, or after the user logs into the application, the terminal device can display a user information retrieval interface to obtain the user's basic information. After obtaining the user's basic information, the terminal device sends it to the cloud device for storage and processing.

[0090] In some embodiments, see Figure 3 As shown, basic user information includes at least one of the following: user type, user address, and user education / employment information. For example, user type may include "preschool child," "student" (e.g., primary school student, junior high school student, senior high school student), and "adult" (e.g., university student, graduate student, and employed person). User address may be the address automatically identified by the terminal device (e.g., the city it is in), or it may be a user-specified address (e.g., the city specified by the user). If the user type is "student," the terminal device also needs to obtain the user's education information, including the user's school, grade, and class. If the user type is "adult," the terminal device also needs to obtain the user's employment information, including the user's occupation type and employer. Occupation type may include teacher, engineer, civil servant, lawyer, actor, designer, etc.

[0091] In this embodiment, user 1 is taken as an example, see Figure 3 As shown, User 1's basic information may include: student, city A, school B, ninth grade, class 1. For User 2, the basic information may include: adult, city A, school B, teacher. For User 3, the basic information may include: student, city A, school B, ninth grade, class 3. For User 4, the basic information may include: student, city A, school B, ninth grade, class 1. It can be seen that User 1 and User 2 are students and teachers at the same school, User 1 and User 3 are classmates at the same school and in the same grade, and User 1 and User 4 are classmates.

[0092] Optionally, users can also verify their identity to enhance its credibility. For example, a user with the occupation type "teacher" can further verify their teacher status in the educational application by submitting information such as a teacher's certificate or proof of employment at a school. Similarly, a user with the occupation type "lawyer" can further verify their lawyer status by submitting information such as a lawyer's license or proof of employment at a law firm. After verifying their identity, the credibility of the learning content that the user provides to other users in the educational application, as well as the evaluation information given regarding that content, will be higher. For example, if a verified teacher recommends learning content 2 about "trigonometric functions" in the educational application, or believes that learning content 2 is helpful for students to learn the knowledge points of "trigonometric functions," then the credibility of that user's recommendation or evaluation of learning content 2 will be higher.

[0093] After logging into the educational application, the terminal device can also add friends and build a personal social network according to user instructions. For example, the terminal device can add friends by searching for phone numbers, usernames, scanning QR codes, searching phone contacts, searching for nearby users, or searching for alumni; this embodiment does not limit this. Taking user 1 adding user 3 as a friend as an example, user 1 can add user 3 by searching for user 3's phone number or username; can add user 3 by scanning user 3's QR code in the educational application; or can search for all users in city A, school B, and ninth grade in the educational application and select user 3 to add as a friend.

[0094] In this embodiment, a user's personal social network can be as follows: Figure 4 As shown, this includes the user and the multiple friends added by that user, such as friend 1 to friend N. It should be understood that each user can have an independent personal social network.

[0095] After logging into the educational application, the terminal device can upload learning content according to user instructions. The uploaded content is stored in a cloud device, and the terminal device can retrieve the required content from the cloud device based on user commands. In some embodiments, only authorized users (e.g., schools, teachers, educational institutions) can upload learning content to the application, ensuring the effectiveness and suitability of the content and thus enabling standardized management. In other embodiments, all users have the right to upload learning content, which helps to improve the richness and diversity of the learning content.

[0096] After detecting that a user is searching for target learning content in an educational application, the terminal device can interact with the cloud device and display the corresponding learning content based on the search. For example, after detecting the user's keyword "quadratic equation", the terminal device can display learning content such as "solving quadratic equations", "applications of quadratic equations", and "specialized breakthroughs in quadratic equations".

[0097] During the user's use of the educational application, the terminal device also records the user's behavior and reports it to the cloud device for storage and processing. In this embodiment, the user behavior includes at least one of the following: search behavior, learning behavior, course purchase behavior, and evaluation behavior. Search behavior may include the keywords the user searches for, the search frequency of each keyword, and the search time. Learning behavior may include the user's learning content, learning duration, and learning effectiveness (e.g., scores and accuracy of practice exercises). Course purchase behavior includes the name of the course purchased, the purchase time, and the purchase cost. Evaluation behavior includes whether the user recommends the learning content to other users, and the user's rating and / or comments on the learning content.

[0098] The terminal device can assess a user's mastery of a knowledge point based on the user's practice results of exercises. In some embodiments, the terminal device can quantify the user's mastery of the knowledge point as a numerical range of 1 to 5, where a higher value indicates greater proficiency and a lower value indicates less proficiency. For example, after a user completes exercises related to "solving quadratic equations," the terminal device can determine the user's mastery of the knowledge point "solving quadratic equations" based on the score. Taking a full score of 100 as an example, if the score is between 0 and 30, the terminal device assigns a mastery level of 1; if the score is between 31 and 60, it assigns a mastery level of 2; if the score is between 61 and 75, it assigns a mastery level of 3; if the score is between 76 and 85, it assigns a mastery level of 4; and if the score is between 86 and 100, it assigns a mastery level of 5.

[0099] Furthermore, cloud-based devices can also assess the effectiveness of courses on users by providing them with complementary learning content that includes both lessons and exercises. For example, before User 1 learns the content related to the keyword "quadratic equation," the cloud-based device detects that User 1's mastery level of the knowledge point "quadratic equation" is 2. After User 1 learns the content, the cloud-based device detects that User 1's mastery level of the knowledge point "quadratic equation" becomes 5. Therefore, the cloud-based device considers that the content significantly helped in learning "quadratic equation," improving the mastery level by 3, an improvement of 3 ÷ 5 = 60%.

[0100] After a terminal device detects that a user has finished learning content (e.g., after completing a course), it can display a user evaluation interface to obtain the user's evaluation information of the learning content, and / or whether the user will recommend the learning content to other users.

[0101] For example, taking a course called "In-Depth Analysis of Trigonometric Functions" as an example, after the terminal device detects that the user has completed the course, it can display, for example... Figure 5 The user rating interface shown asks the user, "Would you like to recommend this course to other users?" and displays a "Yes" recommendation control and a "No" rejection control. After detecting the user's interaction with the recommendation control, the terminal device determines that the user agrees to recommend the course to other users. Furthermore, the terminal device can guide the user to rate the course and fill in comments.

[0102] In some embodiments, educational applications can include student clients and teacher clients. Student users use the student client to perform operations such as user registration, login, filling in basic user information, uploading learning content, taking courses, and taking quizzes on their terminal devices. Teacher users use the teacher client to upload learning content, build knowledge graphs for various subjects, recommend and evaluate learning content, and view the learning results of individual student users. For example, teachers at School A can view the learning results of all students at School A.

[0103] (II) Cloud Devices

[0104] Cloud-based devices are primarily used for storing learning content, building knowledge graphs, constructing social graphs, and distributing learning content to users based on their needs, combining knowledge graphs and social graphs. These will be explained in detail below.

[0105] When storing learning content, cloud devices can identify and filter the content, delete unhealthy content, and standardize the management of learning content.

[0106] Cloud-based devices can construct a knowledge graph for an educational application based on instructions from designated users (such as specific teachers). This knowledge graph includes the relationships between various knowledge points. It can encompass knowledge graphs from different subjects, grade levels, and fields. For example, authorized teacher users can construct a knowledge graph about ninth-grade mathematics; see [link to relevant documentation]. Figure 6 As shown, this knowledge graph includes the relationships between various knowledge points in Grade 9 mathematics (e.g., graphs and geometry, numbers and algebra, probability and statistics, formulas and equations, quadratic equations, solving quadratic equations, applications of quadratic equations, quadratic functions, applications of quadratic functions, etc.). Alternatively, a user can construct a knowledge graph about Grade 11 physics, which includes the relationships between various knowledge points in Grade 11 physics (e.g., description of motion, mechanical motion, reference frame, instant and time, displacement and distance, velocity, acceleration, interaction, force, friction, composition and decomposition of forces, etc.). Based on the knowledge graph, the cloud device can determine multiple other knowledge points 2 related to knowledge point 1, as well as the inclusion and predecessor relationships between knowledge point 1 and these multiple knowledge points 2. Here, knowledge point 1 includes knowledge point 2, meaning that knowledge point 2 is a sub-knowledge point of knowledge point 1; for example, knowledge point 1 "description of motion" includes knowledge point 2 "mechanical motion". Knowledge point 1 is a precursor to knowledge point 2. Knowledge point 1 means that knowledge point 1 is the foundation for learning knowledge point 2. For example, knowledge point 1 "distance" is the foundation for learning knowledge point 2 "speed".

[0107] Cloud-based devices can build social graphs based on the basic user information uploaded by each user. See [link / reference] Figure 7As shown, this social graph includes the relationships between various users. Optionally, the cloud device can construct a general social graph based on the basic user information of all users, or it can construct a social graph for different regions (e.g., different cities). This embodiment does not impose any restrictions on this.

[0108] Understandably, the more basic user information a user has, the larger the social graph becomes, and the richer the relationships between users. Based on the social graph, cloud devices can identify multiple other users related to User 1 (e.g., User 2, User 3, User 4, User 8, and User 9), as well as the relationships between User 1 and these users. For example, if User 1's basic information includes "student," "city A," "school B," and "grade 9, class 1," then, assuming User 1 is a student in City A, school B, and grade 9, the cloud device can identify other users related to User 1 based on the social graph. For instance, according to preset identification rules, these other users could be other students in grade 9 in City A, or other students in City A, school B, and grade 9, or other students in City A, school B, and grade 9, class 1. Furthermore, if the social graph of City A includes teachers, the cloud device can also identify teachers in City A, or teachers in City A and school B, based on that social graph.

[0109] Cloud-based devices can also send search results to terminal devices based on their search requests. For example, after receiving a request from a terminal device to search for "quadratic equation," the cloud-based device can recommend search results related to "quadratic equation," such as "applications of quadratic equation" and "solving quadratic equations." Users can then select their target learning content based on these search results.

[0110] In this embodiment, the cloud device can recommend learning content to the user based on a knowledge graph, thereby providing more reasonable learning suggestions. For example, when recommending learning content about "quadratic equations," the cloud device prioritizes recommending content about the basic concepts of quadratic equations, followed by content about solving quadratic equations. Alternatively, during quadratic equation practice, the device first prompts the user to practice problems about the basic concepts of quadratic equations, and after detecting that the user has reached the required level, it continues to prompt the user to practice problems about solving quadratic equations. In this embodiment, the user is considered to have passed the training once their score on the practice problems reaches a preset score (e.g., 80 points).

[0111] Furthermore, in some embodiments, the cloud device can also recommend learning content to users based on social graphs and other users' learning feedback on the learning content, and display the reasons for the recommendation. For example, when the cloud device detects that user 1 is searching for learning content about "quadratic equations", if multiple other users in the same school and grade as user 1 have significantly improved their mastery of the knowledge point of "quadratic equations" after studying learning content C, then learning content C will be recommended to user 1 first.

[0112] In other embodiments, the cloud device can also recommend learning content to users based on social graphs and other users' evaluations of the learning content. For example, when the cloud device detects that user 1 is searching for learning content about "quadratic equations," if user 2, who is a teacher, has recommended learning content C within the educational application, then learning content C will be recommended to user 1 first.

[0113] In summary, through the communication system provided in this application embodiment, the terminal device can recommend highly credible learning content to the user based on the user's learning results, thereby improving user experience, increasing user trust in educational applications, and reducing the loss of user resources.

[0114] Based on the communication system provided in the embodiments of this application, the terminal device can recommend learning content to the user according to the user's search instructions, or intelligently recommend learning content to the user based on the user's mastery of each knowledge point. These will be described in detail below.

[0115] Figure 8 This is a flowchart of a content recommendation method provided in one embodiment of this application, involving a terminal device recommending learning content to a user based on the user's search instructions and other users' learning feedback information. Specifically, it includes the following steps S801 to S813.

[0116] S801, the terminal device obtains the user's search command.

[0117] In this embodiment, the user can input a search command to the terminal device through a first user operation. This search command instructs the terminal device to search for relevant learning content. For example, see [link to example]. Figure 9A As shown, this first user action can be a selection operation on the search control after the user enters keywords (e.g., "quadratic equation") in the search interface. Alternatively, see [link to relevant documentation]. Figure 9B As shown, this first user action can be a user's selection of recommended popular search terms (such as "quadratic equation") in the search interface. Alternatively, see... Figure 9CAs shown, the first user operation can be a user's selection of recommended historical search terms (e.g., "quadratic equation") from the search interface. Alternatively, the first user operation can be a user-input voice search control operation, etc. This embodiment does not limit the specific form of the first user operation.

[0118] S802, the terminal device sends a search request to the cloud device based on the first user's operation.

[0119] In this embodiment, the search request carries keywords to retrieve search results related to those keywords from the cloud device. For example, if the keyword is "quadratic equation," the search request would retrieve search results related to "quadratic equation" from the cloud device.

[0120] S803, cloud-based devices determine search results based on keywords.

[0121] The search results include information related to multiple learning resources associated with the keywords, such as basic introductions, user reviews, and reasons for recommendation. However, the search results typically do not directly include specific learning content (such as instructional videos or practice exercises). The basic introductions include the learning resource's name, description, category, cost, and the number of users currently participating in the learning process.

[0122] If the search request contains the keyword "quadratic equation," the cloud device can recommend learning content A through E based on "quadratic equation." For example, learning content A is "equations and inequalities," learning content B is "solving quadratic equations," learning content C is "applications of quadratic equations," learning content D is "specialized breakthroughs in quadratic equations," and learning content E is "quadratic functions."

[0123] S804: The cloud device determines recommended content and generates recommendation reasons based on other users' learning feedback on the learning content in the search results.

[0124] As described above, feedback from other users on the learning content includes at least one of the following:

[0125] First-level learning feedback: This reflects how other users have grasped the knowledge points related to the learning content, or how their grasp has changed, in response to the learning content. This first-level learning feedback needs to be determined by the cloud device according to preset rules.

[0126] Secondary learning feedback: Evaluation results from other users regarding the learning content (e.g., comments and ratings). For information on obtaining secondary learning feedback, please refer to [link to relevant documentation]. Figure 5 As shown in items 2 and 3.

[0127] Third learning feedback information: Recommendations from other users regarding this learning content. For information on obtaining second learning feedback information, please refer to [link to relevant documentation]. Figure 5 As shown in the first item.

[0128] The following sections will illustrate, using examples of the different learning feedback information mentioned above, the process by which cloud devices determine recommended content and corresponding reasons for recommendation.

[0129] (1) Regarding the first feedback information: the degree of mastery or changes in the degree of mastery of the knowledge points corresponding to the learning content by other users under the influence of the learning content.

[0130] In this embodiment, the cloud device can determine recommended content and reasons for recommendations based on the user's different social groups. For example, the social group can be all users within the educational application, users within the user's personal social network, or all users in the social graph.

[0131] A. Determine recommended content based on all users of educational applications.

[0132] After receiving a search request, the cloud device first searches for relevant learning content in its database based on the keywords in the search request (i.e., determines the search results). Then, it determines the initial learning feedback from all other users within the educational application regarding each learning content in the search results. Finally, based on the initial learning feedback, it determines recommended content from this learning content and generates corresponding recommendation reasons. In this embodiment, the other users can be one or more users, including the second user.

[0133] Taking a search request containing the keyword "quadratic equation," the cloud device can retrieve search results including learning content A through learning content E. The cloud device can first determine the average effect of learning content A through E on other users' mastery of the knowledge points. This average effect includes at least one of two indicators. The first indicator refers to the average level of mastery of the corresponding knowledge point by other users after learning a particular learning content. The second indicator refers to the average percentage increase in mastery of the corresponding knowledge point by other users after learning a particular learning content.

[0134] For example, if the first indicators corresponding to learning content A through learning content E are as shown in Table 1-1, then the cloud device can recommend the learning content that ranks in the top N of the search results based on the first indicator, i.e., the content that the user is encouraged to choose first. Here, N is an integer, such as 1, 2, 3, etc. Taking N=1 as an example, for the search results shown in Table 1-1, the cloud device can recommend learning content C.

[0135] For recommended content, cloud-based devices can also generate recommendation reasons. These reasons are used to inform users about the effectiveness of the learning content on other users. For example, they could suggest that other users' understanding of the knowledge points has significantly improved after learning the content. Taking learning content C as an example, the corresponding recommendation reason could be: Users who learned learning content C have the best average understanding of the knowledge point "quadratic equations".

[0136] Table 1-1 Search Results

[0137]

[0138] Optionally, the cloud device can also sort the learning content in the search results in descending order according to the first metric. In one example, for the search results shown in Table 1-1, after the cloud device sorts them in descending order according to the first metric, the sorting results shown in Table 1-2 can be obtained. The cloud device can control the terminal device to display the search results to the user according to this sorting result.

[0139] Table 1-2 Sorting Results

[0140]

[0141] For example, if the second indicators corresponding to learning content A through learning content E are as shown in Table 2, then the cloud device can recommend the learning content whose second indicator ranks in the top N of the search results, i.e., the content that the user is encouraged to choose first. Here, N is an integer, such as 1, 2, 3, etc. Taking N=1 as an example, for the search results shown in Table 1-1, the cloud device can recommend learning content C.

[0142] Cloud-based devices can also generate recommendation reasons for recommended content. Taking learning content C as an example, the corresponding recommendation reason could be: After learning this course, the user's mastery of the knowledge point "quadratic equation in one variable" has greatly improved.

[0143] Table 2-1 Search Results

[0144]

[0145] Optionally, the cloud device can also sort the learning content in the search results from highest to lowest according to the second metric. In one example, for the search results shown in Table 2-1, after the cloud device sorts them from highest to lowest according to the second metric, the sorting results shown in Table 2-2 can be obtained. The cloud device can then control the terminal device to display the search results to the user according to this sorting result.

[0146] Table 2-2 Sorting Results

[0147]

[0148] Furthermore, cloud-based devices can also combine the first and second indicators with other information (such as course fees, number of online learners, etc.) to comprehensively determine the ranking results, and this embodiment does not impose any restrictions on this. Additionally, after displaying the search results, the terminal device can also locally readjust the sorting of the learning content as needed, such as sorting by relevance from high to low, by the course's effectiveness in improving the user experience from high to low, by course fees from low to high, or by the number of online learners from high to low, etc., and this embodiment does not impose any restrictions on this.

[0149] B. Determine recommended content based on personal social networks.

[0150] After receiving a search request, the cloud device first searches for relevant learning content in its database based on the keywords in the request (i.e., determines the search results). Then, it considers the user's personal social network (see [link to relevant documentation]). Figure 4 (As shown) Identify the user's friends and their initial learning feedback on each learning content in the search results. Finally, based on the initial learning feedback, determine recommended content from this learning content and generate corresponding recommendation reasons.

[0151] Taking a search request containing the keyword "quadratic equation," the cloud device can find recommended content including learning content A through learning content E based on "quadratic equation." If the cloud device detects that after learning content C, the user's friend 1's mastery of the knowledge point improved from 2 to 5, meaning a significant improvement in mastery, then the cloud device can identify learning content C as recommended content and generate a recommendation reason. For example, this recommendation could be "Your friend 1 significantly improved their mastery of the knowledge point after learning this content," or "Your friend 1 improved their mastery of the knowledge point from 2 to 5 after learning this content."

[0152] B. Determine recommended content based on social graphs

[0153] After receiving a search request, the cloud device first searches for relevant learning content in its database based on the keywords in the request (i.e., determines the search results). Then, based on the user's social graph (see [link to relevant documentation]), it further analyzes the results. Figure 7 (As shown) The system identifies the user's social network and their initial learning feedback on each learning content item in the search results. Finally, based on the initial learning feedback from their social network, recommended content is determined from this learning content, and corresponding recommendation reasons are generated.

[0154] Taking a student in Class 1, Grade 9 at School B in City A as an example, the cloud device can identify other Grade 9 users at School B in City A (e.g., User 2, User 3, User 4, User 8, and User 9) as this user's social network. Based on this, for learning content A to learning content E searched by the cloud device, if the cloud device detects that user 3, this user's social network member, improved their understanding of the knowledge point from 3 to 5 after learning learning content C (i.e., a significant improvement in understanding), then the cloud device can identify learning content C as recommended content and generate a recommendation reason. For example, the recommended content could be "Your classmate User 3 significantly improved their understanding of the knowledge point after learning this content," or "Your classmate User 3 improved their understanding of the knowledge point from 3 to 5 after learning this content."

[0155] (2) Second learning feedback information: Evaluation results of other users on the learning content (such as comments and ratings).

[0156] In this embodiment, the cloud device can also determine recommended content and reasons for recommendations based on the user's different social groups. For example, the social group can be all users within the educational application, users within the user's personal social network, or all users in the social graph.

[0157] After receiving a search request, the cloud device first searches for relevant learning content in its database based on the keywords in the request (i.e., determining the search results). Then, it determines secondary learning feedback information (e.g., average ratings) from other users within the educational application / user's personal social network / social graph regarding each learning content in the search results. Finally, it determines recommended content from this learning content based on the average ratings and generates corresponding recommendation reasons.

[0158] Taking a search request containing the keyword "quadratic equation," the cloud device can find recommended content including learning content A through learning content E based on "quadratic equation." For example, based on a social graph (see [link to social graph]),... Figure 7 User 1's social contacts (e.g., at least one of users 2, 3, 4, 8, and 9) after learning content A through E, will receive feedback on the user evaluation interface (see [link]). Figure 5The system inputs second learning feedback information for each learning content, and the average ratings of these users for learning content A through E are shown in Table 3-1. Therefore, the learning content with the highest average rating in the search results (ranked Nth highest) can be recommended as the content that users are encouraged to choose first. Here, N is an integer, such as 1, 2, 3, etc. Taking N=1 as an example, for the search results shown in Table 3-1, the cloud device can recommend learning content C.

[0159] Table 3-1 Search Results

[0160]

[0161] For recommended content, cloud-based devices can also generate recommendation reasons. Taking learning content C as an example, the corresponding recommendation reason could be: This course has the highest rating from users around you.

[0162] Optionally, the cloud device can also sort the learning content in the search results from highest to lowest average rating. In one example, for the search results shown in Table 3-1, after the cloud device sorts them from highest to lowest average rating, the sorting results shown in Table 3-2 can be obtained. The cloud device can then control the terminal device to display the search results to the user according to this sorting result.

[0163] Table 3-2 Sorting Results

[0164]

[0165] (3) Third learning feedback information: Recommendations from other users regarding the learning content.

[0166] In this embodiment, the cloud device can also determine recommended content and reasons for recommendations based on the user's different social groups. For example, the social group can be all users within the educational application, users within the user's personal social network, or all users in the social graph.

[0167] In some embodiments, after receiving a search request, the cloud device first searches for relevant learning content in all learning content in the database based on the keywords carried in the request (i.e., determines the search results). Then, it determines third-party learning feedback information (e.g., total number of recommendations) from other users within the educational application / user's personal social network / social graph regarding each learning content in the search results. Finally, it determines recommended content from this learning content based on the total number of recommendations and generates corresponding recommendation reasons.

[0168] Optionally, for both certified users (e.g., teachers) and non-certified users (e.g., students), the cloud device can assign the number of recommendations for certified users as A1 and the number of recommendations for non-certified users as A2 for a single recommendation, where A1 is greater than A2, for example, A1 = 50 and A2 = 1. This method can increase the credibility of the recommended learning content.

[0169] Taking a search request containing the keyword "quadratic equation" as an example, the cloud device can find recommended content including learning content A to learning content E based on "quadratic equation". For instance, if the total number of recommendations for learning content A to learning content E within the social graph is as shown in Table 4-1, then the learning content with the highest total recommendation count in the search results can be used as the recommended content, i.e., the content that users are encouraged to choose first. Here, N is an integer, such as 1, 2, 3, etc. Taking N=1 as an example, for the search results shown in Table 4-1, the cloud device can use learning content C as the recommended content.

[0170] Table 4-1 Search Results

[0171]

[0172] For recommended content, cloud-based devices can also generate recommendation reasons. Taking learning content C as an example, the corresponding recommendation reason could be: other users have recommended this course the most times in total.

[0173] Optionally, the cloud device can also sort the learning content in the search results in descending order of total recommendation frequency. In one example, for the search results shown in Table 4-1, after the cloud device sorts them in descending order of total recommendation frequency, the sorting results shown in Table 4-2 can be obtained. The cloud device can then control the terminal device to display the search results to the user according to this sorting result.

[0174] Table 4-2 Sorting Results

[0175]

[0176] In other embodiments, when determining the effect of learning content on knowledge points, the cloud device can rely on social graphs (see [reference needed]). Figure 7 (As shown) The system identifies verified individuals within the user's social network, such as "teachers." Based on these verified individuals' recommendations of learning content, it recommends relevant learning materials to the user. For example, if user 1 is a ninth-grade student at school B in city A, the cloud device, based on the social graph, identifies user 2 as a teacher at the same school as user 1. After user 2 completes learning material C, the system will recommend learning content to the user on the user evaluation interface (see [link]). Figure 5When evaluating learning content C, the user selected the "Yes" control for the third learning feedback information to recommend the learning content to other users. Therefore, for learning content A through E found by the user, the cloud device can identify learning content C as the recommended content and generate a recommendation reason. For example, this recommendation reason could be, "Your teacher, user 2, recommended this course."

[0177] In addition, the cloud device can also determine the recommended content by combining at least two of the first learning feedback information, the second learning feedback information and the third learning feedback information, and generate corresponding recommendation reasons. This embodiment does not limit this.

[0178] It should be noted that, optionally, in this embodiment, the recommended content determined based on the first learning feedback information can be referred to as the first recommended content, and the recommendation reason corresponding to the first recommended content can be referred to as the first recommendation reason. The recommended content generated based on the second learning feedback information and / or the second learning feedback information can be determined as the second recommended content, and the recommendation reason corresponding to the second recommended content can be referred to as the second recommendation reason.

[0179] S805: The cloud device sends recommended content and reasons for the recommendation to the terminal device.

[0180] In one example, for the search results corresponding to the keyword "quadratic equation," which includes learning content A through E, if the cloud device determines that learning content C is the recommended content, with the reason "Your classmate user 3 significantly improved their understanding of the knowledge points after learning this content," then the cloud device can send the terminal device basic information about learning content A through E (such as the name, description, category, cost, and number of users currently participating in the learning), as well as the instruction to recommend learning content C, and the reason "Your classmate user 3 significantly improved their understanding of the knowledge points after learning this content."

[0181] S806, the terminal device displays a first interface, which includes recommended content and reasons for recommendation.

[0182] The following examples illustrate the search results displayed on terminal devices in different scenarios.

[0183] (1) Regarding the first learning feedback information

[0184] In this embodiment, taking the search results including learning content A to learning content E, the recommended content being learning content C, and the recommendation reason being "Your classmate user 3 significantly improved their mastery of the knowledge points after learning this content," and the search results being sorted as learning content C, learning content B, learning content A, learning content D, and learning content E, the search results displayed on the terminal device can be as follows: Figure 10A As shown.

[0185] (2) Regarding the second learning feedback information

[0186] In this embodiment, taking the search results including learning content A to learning content E, the recommended content being learning content C, and the recommendation reason being "users around you have given this course the highest rating," as an example, the search results are sorted as learning content C, learning content B, learning content A, learning content D, and learning content E. The search results displayed on the terminal device can be as follows: Figure 10B As shown.

[0187] (3) Regarding the third learning feedback information

[0188] In this embodiment, taking an example where the search results include learning content A through E, the recommended content is learning content C, and the recommendation reason is "Your teacher, user 2, recommended this course," the search results are sorted as follows: learning content C, learning content B, learning content A, learning content D, and learning content E. The search results displayed on the terminal device can be as follows: Figure 10C As shown.

[0189] S807, the terminal device obtains the second user's operation.

[0190] In this embodiment, the second user action is the user's action of selecting target learning content in the search results. For example, this second user action is the user's action of selecting learning content C.

[0191] S808, the terminal device sends a target learning content retrieval request to the cloud device. This target learning content retrieval request is used to retrieve the target learning content.

[0192] Taking learning content C as an example, the target learning content retrieval request is used to obtain specific course information for learning content C, such as course videos.

[0193] S809: The cloud device sends the target learning content to the terminal device.

[0194] S810: The terminal device displays the target learning content. For example, the terminal device plays a course video.

[0195] S811, the terminal device obtains the user's learning feedback information on the target learning content.

[0196] As described above, learning feedback information includes: First, the change in the user's mastery of the knowledge points under the influence of the learning content. Second, the user's evaluation of the learning content (e.g., comments and ratings). Third, recommendations from other users regarding the learning content.

[0197] Taking the target learning content C, "Application of Quadratic Equations," as an example, the terminal device can prompt the user to perform related exercises after completing the learning of content C, in order to test the effect of learning content C on the user. See the previous description for details; this embodiment will not repeat them here. Alternatively, the device can prompt the user to rate the learning content and fill in comments. Or, it can ask the user if they want to recommend the learning content to other users.

[0198] S812, the terminal device sends the user's learning feedback information on the target learning content to the cloud device.

[0199] S813, cloud-based devices store learning feedback information.

[0200] Through the steps S801 to S813 described above, the terminal device can recommend highly credible learning content to the user based on the user's search instructions. This can effectively reduce the time and energy users waste learning content with poor teaching results, increase users' trust in the educational application, and reduce the loss of user resources.

[0201] Figure 11 This is a flowchart of a content recommendation method provided in another embodiment of this application. It involves a process in which a terminal device intelligently recommends learning content to a user based on the user's mastery of each knowledge point and feedback from other users. Specifically, it includes the following steps S1101 to S1105.

[0202] S1101, the cloud device determines the user's level of mastery of each knowledge point in a specified subject.

[0203] In this embodiment, for users whose user type is student, the designated subjects include the main subjects of their grade level. For example, for a user in the ninth grade, the designated subjects include the main subjects of the ninth grade, such as Chinese, mathematics, and English. Furthermore, regardless of the user type, the designated subjects can also include subjects that the user is particularly interested in, such as spoken English, writing, and the bar exam. Taking user 1 as an example, if user 1 is a ninth-grade student, for the designated subject of mathematics, the cloud device analyzes user 1's past practice scores or accuracy rates to determine user 1's mastery of each knowledge point in ninth-grade mathematics, as shown in Table 5.

[0204] Table 5

[0205]

[0206] S1102, the cloud device determines the user's weak knowledge points based on the user's mastery of each knowledge point.

[0207] In some embodiments, the cloud device can identify knowledge points where the user's mastery level is lower than a preset mastery level (e.g., 3) as weak knowledge points. Based on this, for the data table shown in Table 5, the cloud device can determine that among the various knowledge points in the ninth grade, the user's weak knowledge points include "application of quadratic equations".

[0208] S1103, the cloud device determines the search results by combining the keywords corresponding to the weak knowledge point.

[0209] Taking a user's weak knowledge point as "applications of quadratic equations" as an example, the cloud device can determine the keywords "quadratic equations" and "applications". After determining the keywords, it searches the database for relevant learning content based on those keywords.

[0210] S1104, the cloud device determines recommended content and generates recommendation reasons based on other users' learning feedback on various learning contents in the search results.

[0211] In this embodiment, for example, after determining the search results for the weak knowledge point, the cloud device can first identify the user's friends / social contacts based on the user's personal social network / social graph. Then, it determines whether any of the user's friends / social contacts have significantly improved their mastery of the weak knowledge point after studying it in an educational application, for example, with an improvement rate exceeding 20%. If user 3's mastery of the weak knowledge point significantly improves after studying learning content M, then the cloud device will identify learning content M as recommended content.

[0212] It should be understood that a user may have one or more weak knowledge points. If a user has multiple weak knowledge points, the cloud device can determine recommended content for each of those weak knowledge points separately. Furthermore, for the same weak knowledge point, the cloud device can determine one or more recommended content points and generate corresponding recommendation reasons.

[0213] S1105, the cloud device sends the search results to the terminal device, which carries the basic information of the recommended content and the reasons for the recommendation.

[0214] The basic information of the recommended content includes its name, description, category, cost, and the number of users currently participating in the learning. Additionally, based on the example in S1103, taking learning content M as the recommended content, the recommendation reason is: "Your knowledge of 'Applications of Quadratic Equations' is weak; your classmate, user 3, has significantly improved their understanding of this knowledge point after learning this course."

[0215] It should be noted that, in this embodiment, the operations S1101 to S1104 performed by the cloud device can be performed by the cloud device itself, or they can be performed by the cloud device according to the instructions of the terminal device. For example, after the terminal device detects the user's operation on the first control (e.g., the "Precision Practice" control in Huawei Education Center) and determines the specified subject (e.g., mathematics), the terminal device sends search instruction information to the cloud device to instruct the cloud device to perform S1101 to S1104 to recommend suitable learning content to the user.

[0216] S1106, The terminal device displays the search results, which include basic information about the recommended content and the reasons for the recommendation.

[0217] For example, see Figure 12 As shown, the terminal device can display basic information about multiple recommended content items. The displayed recommended content is learning material related to the user's weak knowledge points. The user can select a target learning item based on their needs and view its detailed information. The terminal device can also display the reasons for recommending the target learning item on the interface containing this detailed information.

[0218] Through steps S1101 to S1106, the terminal device can intelligently recommend highly reliable learning content to the user, based on the user's weak knowledge points and incorporating feedback from other users. This method effectively reduces the time and effort users waste learning on ineffective content, increases user trust in the educational application, and minimizes user resource loss.

[0219] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0220] Based on the content recommendation method provided in this embodiment, this application also provides the following technical solutions.

[0221] This application provides a terminal device that includes an educational application, and the terminal device is configured to execute the content recommendation method executed by the terminal device in the above embodiments.

[0222] This application provides a cloud device configured to execute the content recommendation method performed by the cloud device in the above embodiments.

[0223] This application also provides a chip, see [link to example]. Figure 13 As shown, the chip includes a processor and a memory, in which a computer program is stored. When the computer program is executed by the processor, it implements the content recommendation method executed by the terminal device or cloud device in the above embodiments.

[0224] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the content recommendation method executed by the terminal device or cloud device in the above embodiments.

[0225] This application also provides a computer program product, which includes a computer program that, when run by a terminal device, enables the terminal device to implement the content recommendation method executed by the terminal device or cloud device in the above embodiments.

[0226] It should be understood that the processor mentioned in the embodiments of this application can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0227] It should also be understood that the memory mentioned in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0228] In the embodiments provided in this application, the division of each framework or module is only a logical functional division. In actual implementation, there may be other division methods. For example, multiple frameworks or modules may be combined or integrated into another system, or some features may be ignored or not executed.

[0229] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0230] 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.

[0231] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0232] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A content recommendation method, characterized in that, Applied to a terminal device, the method includes: Log in to the first user account in the first application; The system displays a first interface, which includes first recommended content and a first recommendation reason corresponding to the first recommended content. The first recommendation reason is generated by the first application based on learning feedback information from a second user account regarding the first recommended content, and the second user account is associated with the first user account. The learning feedback information includes first learning feedback information, which reflects the second user account's mastery level and / or changes in mastery level of the knowledge points corresponding to the first recommended content after learning it. Furthermore, the first learning feedback information is obtained by the first application through training exercises related to the first recommended content after the second user account has learned it. The first application also includes other learning content corresponding to the knowledge point, and the degree of mastery and / or change in the degree of mastery of the knowledge point by the second user account corresponding to the first recommended content is better than the degree of mastery and / or change in the degree of mastery of the knowledge point by the user account corresponding to the other learning content. Before displaying the first interface, the method further includes: determining keywords, and determining search results based on the keywords, the search results including the first recommended content.

2. The method according to claim 1, characterized in that, The learning feedback information also includes second learning feedback information and / or third learning feedback information; The second learning feedback information is the evaluation result of the second user account or the third user account on the first recommended content; The third learning feedback information is the recommendation status of the second user account or the third user account for the first recommended content, wherein the third user account is associated with the first user account.

3. The method according to claim 1, characterized in that, The first interface includes second recommended content and a second recommendation reason corresponding to the second recommended content. The second recommendation reason is generated by the first application based on the learning feedback information of the second user account or the third user account regarding the second recommended content. The third user account is associated with the first user account; The learning feedback information of the second user account or the third user account on the second recommended content includes second learning feedback information and / or third learning feedback information; The second learning feedback information is the evaluation result of the second user account or the third user account on the first recommended content. The third learning feedback information is the recommendation status of the second user account or the third user account for the first recommended content.

4. The method according to any one of claims 1 to 3, characterized in that, The second user account is, The second user account within the personal social network corresponding to the first user account in the first application; or... The second user account in the social graph within the first application, wherein the social graph is established based on the basic user information of multiple users within the first application.

5. The method according to claim 2 or 3, characterized in that, The third user account is... A third user account within the personal social network corresponding to the first user account in the first application; or... The third user account in the social graph within the first application, wherein the social graph is built based on the basic user information of multiple users within the first application.

6. The method according to claim 1, characterized in that, The determination of keywords includes: Obtain the search instructions of the first user account, and determine the keywords based on the search instructions.

7. The method according to claim 1, characterized in that, The determination of keywords includes: Determine the level of mastery of each knowledge point in the first user account; Based on the level of mastery, the weak knowledge points corresponding to the first user account are determined from each of the knowledge points; The keywords are determined based on the identified weak knowledge points.

8. The method according to any one of claims 1 to 3, 6 and 7, characterized in that, The first interface also includes third recommended content, and the knowledge points involved in the third recommended content are related to the knowledge points involved in the first recommended content in an inclusive or predecessor relationship.

9. The method according to claim 6 or 7, characterized in that, The search results also include the first learning content; the first interface also includes the first learning content, and the first interface does not include the recommendation reason corresponding to the first learning content. The recommendation reason corresponding to the first learning content is generated by the first application based on the learning feedback information of the second user account on the first learning content.

10. The method according to claim 6 or 7, characterized in that, The first interface for display includes: The learning content in the search results is sorted according to the learning feedback information. The search results are displayed based on the sorting order.

11. The method according to any one of claims 1 to 3, 6 and 7, characterized in that, After the first user account has learned the first recommended content, the method further includes: Collect learning feedback information from the first user account regarding the first recommended content.

12. A terminal device, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method as described in any one of claims 1 to 11.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method as described in any one of claims 1 to 11.

Images