Desk lamp, system and method for assisting learning

Abstract

The embodiments of the present disclosure disclose a desk lamp, system and method for assisting learning. A specific implementation of the desk lamp includes: a lamp holder and a bracket arranged on the lamp holder, wherein a control processor, a communication unit and a power supply unit are arranged in the lamp holder, and a microphone pickup unit, a speaker sound unit, a camera unit and a lighting unit are arranged on the bracket, and the control processor is electrically connected to the communication unit, the microphone pickup unit, the speaker sound unit, the camera unit, the lighting unit and the power supply unit respectively. The desk lamp integrates voice and image recognition capabilities, can assist learning, and has a lighting function, which is very suitable for use in reading and learning scenarios.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the technical field of lighting equipment, and in particular to a desk lamp, system, and method for assisting learning. Background Art

[0002] In addition to tablets and reading machines, the online education industry also uses a number of hardware education products that can interact with voice and image recognition, as intelligent voice technology develops.

[0003] For example, tablet computers have added voice interaction capabilities and image recognition capabilities. When students have questions during study, they can interact with the device through voice. A mirror is added to the camera to capture the contents of the desktop book, and then through voice interaction and image recognition, the cloud processes the content and gives students corresponding question prompts or answers.

[0004] However, tablet computers are generally expensive, and they do not have the lighting function for reading, and a reflector must be added to the device to take photos. When taking photos with a tablet, a reflector must be added to the device, and the image is easily distorted, resulting in poor image recognition. In addition, the photo effect is poor when the light is insufficient, which also affects the image recognition effect. In addition, the tablet itself is multifunctional, which can easily distract children and induce them to use other entertainment apps.

[0005] Simple voice questions and answers and image recognition can also be achieved through the empowerment of other devices. For example, when reading and doing homework, students usually use a desk lamp. A microphone and camera can be added to the desk lamp to realize voice and image recognition capabilities to provide assistance to students.

[0006] Similar products already exist that can add intelligent voice interaction capabilities to lamps to listen to music, ask about the weather, and control the status of lamps, but none of them have image recognition capabilities.

[0007] There is also a camera speaker similar to the alien type. The difference from the educational tablet is that the camera position is designed to be tilted downward in advance, so that it can take pictures of books placed on the table. Because the camera is still tilted at a certain angle, the image will still be distorted, which is not conducive to image recognition. When the light is insufficient, other lighting equipment is still needed. Summary of the invention

[0008] Embodiments of the present disclosure provide a desk lamp, a system, and a method for assisting learning.

[0009] In a first aspect, an embodiment of the present disclosure provides a desk lamp for assisting learning, comprising a lamp holder and a bracket arranged on the lamp holder, wherein a control processor, a communication unit, and a power supply unit are arranged in the lamp holder, and a microphone pickup unit, a speaker sounding unit, a camera unit, and a lighting unit are arranged on the bracket, and the control processor is electrically connected to the communication unit, the microphone pickup unit, the speaker sounding unit, the camera unit, the lighting unit, and the power supply unit, respectively.

[0010] In some embodiments, a display unit is also provided on the bracket and is electrically connected to the control processor.

[0011] In some embodiments, the communication unit includes a wireless communication module and / or a wired communication module.

[0012] In some embodiments, the power supply unit includes a DC power supply unit and / or an AC power supply unit.

[0013] In some embodiments, the lighting unit includes at least one of the following light sources: an incandescent lamp, a halogen lamp, a fluorescent lamp, and an LED lamp.

[0014] In some embodiments, the camera unit is mounted above the lamp holder to take pictures downward.

[0015] In some embodiments, the positions and angles of the lighting unit and the camera unit are adjustable.

[0016] In some embodiments, the microphone pickup unit is a microphone array.

[0017] In some embodiments, the desk lamp is also provided with a key switch and / or a touch switch.

[0018] In a second aspect, an embodiment of the present disclosure provides a system for assisted learning, comprising: a cloud server and a desk lamp as one of the first aspects, wherein the desk lamp is connected to the cloud server by wire and / or wirelessly via a communication unit; the cloud server is configured to receive voice and images sent by the desk lamp, perform voice recognition and image recognition to obtain questions raised by users, search for corresponding answers based on the questions, and send the answers to the desk lamp for output.

[0019] In a third aspect, an embodiment of the present disclosure provides a method for assisted learning, which is applied to a desk lamp, comprising: in response to detecting that a user has input a wake-up word, receiving a voice command input by the user; capturing an image specified by the user according to the voice command; uploading the voice command and the image to a cloud server, wherein the cloud server determines the question raised by the user through voice recognition and image recognition, searches for the answer, and then returns it to the desk lamp; in response to receiving the answer returned by the cloud server, outputting the answer in audio or video format.

[0020] In a fourth aspect, an embodiment of the present disclosure provides a method for assisted learning, which is applied to a cloud server, including: receiving voice commands and images from a desk lamp; identifying the user's intention based on the voice commands; capturing a segment of the location pointed to by the user from the image according to the intention; performing text recognition on the segment to obtain a question; searching for the answer to the question and returning it to the desk lamp.

[0021] The desk lamp, system and method for assisting learning proposed in the embodiments of the present application integrate voice and image recognition capabilities and have lighting functions, which are very suitable for use in reading and learning scenarios. Currently, competitors mostly implement this in the form of tablets or special-shaped speakers with cameras. Different from the way we empower the lighting equipment that is already commonly used for learning, and optimize the user experience through combination and improvement, 1. The camera is structurally facing vertically downward, and the imaging is not prone to distortion due to angle problems; 2. The lighting effect during imaging can be ensured through lighting to ensure clearer imaging, which is conducive to image recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Other features, objects and advantages of the present disclosure will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0023] Figure 1 is an exemplary system architecture diagram of a system for assisting learning;

[0024] Figure 2 is a structural schematic diagram of an embodiment of a desk lamp for assisting learning according to the present application;

[0025] Figure 3 is a flow chart of one embodiment of a method for outputting information according to the present disclosure.

[0026] Figure 4 is a flow chart of yet another embodiment of a method for outputting information according to the present disclosure. DETAILED DESCRIPTION

[0027] The present disclosure is further described in detail below in conjunction with the accompanying drawings and embodiments. It is understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the relevant invention are shown in the accompanying drawings.

[0028] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0029] Figure 1 FIG. 1 shows an architecture diagram of a system for assisting learning. Figure 1As shown, the system for assisting learning includes a desk lamp 10 and a cloud server 20. The desk lamp includes a lamp holder and a bracket arranged on the lamp holder, wherein a control processor 104, a communication unit 103, and a power supply unit 102 are arranged in the lamp holder, and a microphone pickup unit 105, a speaker sound unit 108, a camera unit 106, and a lighting unit 101 are arranged on the bracket, and the control processor 104 is electrically connected to the communication unit 103, the microphone pickup unit 105, the speaker sound unit 108, the camera unit 106, the lighting unit 101, and the power supply unit 102 respectively. The power supply unit 102 supplies power to other components. For simplicity, the connection relationship between the power supply unit and other components is not drawn.

[0030] When a user has questions about a target text or graphic and needs an image recognition answer, the user can wake up the lamp through voice and let the lamp execute the command, take a picture of the text or image pointed by the finger, upload it to the cloud server for image recognition, and then the speaker sound unit obtains the voice feedback result processed by the server cloud to assist in guiding the user's required learning content. Optionally, the lamp can include a display unit for displaying video answers.

[0031] Continue to refer Figure 2 , showing a structural diagram of a desk lamp for assisting learning. The desk lamp includes a lamp holder and a bracket arranged on the lamp holder, wherein a control processor, a communication unit, and a power supply unit are arranged in the lamp holder, and a microphone pickup unit, a speaker sound unit, a camera unit, and a lighting unit are arranged on the bracket, and the control processor is electrically connected to the communication unit, the microphone pickup unit, the speaker sound unit, the camera unit, the lighting unit, and the power supply unit, respectively.

[0032] In this embodiment, the base is placed on the desktop and can be round or square, without limitation. All parts that do not need to be exposed can be installed in the base. A power button and a brightness adjustment button can be set on the base. The button can be a physical button or a touch button. Optionally, the brightness of the lighting can also be controlled by voice control without button control.

[0033] In this embodiment, the bracket includes a horizontal bar and a vertical bar. The lighting unit and the camera unit are located on the horizontal bar. The height of the horizontal bar from the desktop is adjustable. It can be adjusted manually or by voice control. A microphone pickup unit and a speaker sound unit are installed on the vertical bar. Optionally, a display unit can also be installed on the vertical bar.

[0034] In some optional implementations of this embodiment, the display unit may be a normal screen or a touch screen. It may be used to output the answer returned by the cloud server, which may be an image or a video. The display unit may also display the camera shooting result in real time, and then the user may further confirm whether a reshoot is needed.

[0035] In this embodiment, the lighting unit provides normal lighting required for reading, which can ensure the lighting effect during reading, make the text on the paper more clearly visible, and assist the visual senses and camera imaging effects.

[0036] In some optional implementations of this embodiment, the lighting unit may include at least one of the following light sources: an incandescent lamp, a halogen lamp, a fluorescent lamp, and an LED lamp.

[0037] In this embodiment, the camera unit is set above the product to take pictures downward. The shooting effect is not prone to distortion caused by the shooting angle. It can take photos or videos, and the user can identify the pointed position content when pointing to text or image content with a finger. The camera unit captures images or videos and then sends them to the control processor. The control processor can perform simple processing on the image, such as cropping, or directly send the original image or video to the cloud server through the communication unit. The user can control the camera zoom by voice, the display unit can display the camera's shooting content, the user can adjust the focal length through the buttons on the display screen, and can also control the camera to enlarge the image by voice. The angle of the camera can be adjusted by sliding on the display screen.

[0038] In some optional implementations of this embodiment, the camera unit can also adjust the angle and position. For example, the position can be adjusted by sliding on the crossbar of the bracket, and the angle can be adjusted by flipping. In addition, the height of the bracket can be adjusted to adjust the distance between the camera unit and the desktop. The position and angle of the camera unit can be adjusted manually, and the adjustment of the camera unit can also be controlled by voice commands. For example, the user can say "adjust the camera higher". The control processor can perform voice recognition and semantic understanding, and then execute the command. Voice recognition and semantic understanding can be performed locally, or the voice command can be sent to a cloud server for voice recognition and semantic understanding.

[0039] In some optional implementations of this embodiment, at least one camera may be provided. In addition to the camera for photographing the desktop, a camera for photographing the user may also be provided to facilitate the user's video course learning.

[0040] In this embodiment, the microphone pickup unit is used to collect the user's voice. Then it is sent to the control processor for processing. The position and angle of the microphone pickup unit are adjustable. It can be adjusted manually or by voice command. Optionally, the microphone pickup unit detects the user's voice, determines the direction of the sound source, and then points the microphone pickup unit toward the user.

[0041] In some optional implementations of this embodiment, the microphone pickup unit may be in the form of a microphone array, which can suppress environmental noise, suppress its own echo, pick up the user's voice information more clearly, and better achieve voice recognition and wake-up.

[0042] In this embodiment, the speaker sound unit enables the user to obtain audio information more conveniently. The position and angle of the speaker sound unit are adjustable. It can be adjusted manually or by voice command. The microphone pickup unit detects the user's voice, determines the direction of the sound source, and then points the microphone pickup unit and the speaker sound unit toward the user.

[0043] In this embodiment, the control processor, mainly as a unit for processing images and audio, can execute relevant algorithms and control the functions of the device, and process the data information obtained by itself and the data information transmitted by the server cloud. The control processor can perform voice recognition processing on the voice collected by the microphone pickup unit, for example, detect whether the voice is a wake-up word, and if so, execute the command according to the user's next voice instruction. Basic lighting commands can be executed, such as "turn on the light", "turn off the light", and "brighten the light". Common commands can be parsed locally by the control processor, and voice commands that cannot be parsed locally are sent to the cloud server for parsing through the communication unit. When the intention to take a photo is parsed, take a photo. For example, the user points out "how to read this word" with a finger or a pen. The control processor parses the user's question as a question, and calls the camera unit to take a photo. The entire page will be photographed, and then the photo and voice instruction will be sent to the cloud server through the communication unit, and the cloud server will process and return the answer. After receiving the answer, the communication unit will be handed over to the control processor for processing. The control processor can select the device to play according to the format of the answer. For example, if a voice answer is received, it is played using the speaker pronunciation unit. If an image or video answer is received, it can be played through the display unit.

[0044] In this embodiment, the communication unit may include a wireless communication module and / or a wired communication module. Usually, a wireless communication module is sufficient. The wireless communication module has wireless communication functions such as Bluetooth and Wi-Fi, and can directly communicate data with the cloud server or obtain communication data with the help of mobile phones and other devices. The communication unit of the desk lamp can be configured through a mobile phone to connect it to the home wireless router. The communication unit can send voice commands and images to the cloud server, and then receive the answer from the cloud server and hand it over to the control processor to distribute the output device.

[0045] In this embodiment, the power supply unit includes power supplying each of the above parts respectively. The power supply unit includes a DC power supply unit and / or an AC power supply unit. The desk lamp can be portable, so it is necessary to configure a DC power supply unit, for example, using battery power or USB power supply. The battery can be an ordinary dry cell battery or a rechargeable battery.

[0046] When a user has questions about a target text or graphic that require image recognition answers, he or she can wake up the device through voice and let the device execute instructions, take a picture of the finger pointing at the text or image, upload it to the server cloud for image recognition, and then the speaker sound unit obtains the voice feedback results processed by the server cloud to assist in guiding the user's required learning content.

[0047] Continue to refer Figure 3 , shows a process 300 of an embodiment of a method for assisting learning according to the present disclosure. The method for assisting learning comprises the following steps:

[0048] Step 301, in response to detecting that a user has input a wake-up word, receiving a voice command input by the user.

[0049] In this embodiment, the execution subject of the method for assisting learning (for example Figure 1 The desk lamp shown in the figure) listens to the voice input by the user for voice recognition. The voice recognition human-computer interaction scheme requires a keyword (wake-up word) to be said first to wake up. After confirming that the user has a clear intention, the secondary human-computer dialogue system for voice recognition is turned on. This method uses an offline keyword recognition in advance. After waking up, the voice command input by the user is received for intention recognition. It is divided into two stages, voice recognition and semantic understanding. These two stages can be performed offline or online. Two servers are required: a voice recognition server and a semantic understanding server. The voice recognition server and the semantic understanding server can also be combined into one server and shared with the cloud server of the auxiliary learning system.

[0050] The speech recognition server is used to receive the speech sent by the desk lamp and convert the vocabulary content in the speech into computer-readable input, such as keystrokes, binary codes or character sequences. This is different from speaker recognition and speaker confirmation, which attempt to identify or confirm the speaker who made the speech rather than the vocabulary content contained therein. A speech recognition system is installed on the speech recognition server. The speech recognition system is generally divided into two stages: training and decoding. Training is to train the acoustic model through a large amount of annotated speech data. Decoding is to recognize the speech data outside the training set into text through the acoustic model and language model. The quality of the trained acoustic model directly affects the recognition accuracy.

[0051] The semantic understanding server is used to receive the text results sent by the desk lamp or speech recognition server, and perform semantic analysis based on the text results. Semantic analysis refers to the use of various methods to learn and understand the semantic content represented by a text. Any understanding of language can be classified as semantic analysis. A text is usually composed of words, sentences and paragraphs. According to the different language units of the object of understanding, semantic analysis can be further decomposed into lexical level semantic analysis, sentence level semantic analysis and chapter level semantic analysis. Generally speaking, lexical level semantic analysis focuses on how to obtain or distinguish the semantics of words, sentence level semantic analysis attempts to analyze the semantics expressed by the entire sentence, and chapter semantic analysis aims to study the internal structure of natural language text and understand the semantic relationship between text units (which can be sentence clauses or paragraphs). Simply put, the goal of semantic analysis is to achieve automatic semantic analysis in each language unit (including words, sentences and chapters, etc.) by establishing an effective model and system, so as to understand the true semantics expressed by the entire text.

[0052] Step 302: photograph an image specified by the user according to the voice command.

[0053] In this embodiment, after recognizing that the user's instruction includes the intention to take a photo (for example, how to solve this problem? Score this page of questions, etc.), the camera is called to take a photo. You can take a panoramic photo directly. After recognizing the voice command, the camera can automatically take a photo and display it on the screen. If the user has no doubts, it will be sent directly to the cloud server together with the voice command. You can also take partial photos as needed. For example, if a user says "how do you read this word", his hand or pen will point to the word, the position where the hand or pen points can be detected, and then a photo of the area within a predetermined range of the position is taken. The user can see the camera's framing results through the display screen, and then focus manually or by voice. The shooting range can be determined based on keywords. For example, if the user says "how do you read this word", a smaller range can be set. If the user asks "how do you solve this problem", a larger range is required.

[0054] Step 303, uploading the voice command and the image to the cloud server.

[0055] In this embodiment, voice instructions and panoramic images or partial images are uploaded to a cloud server. The cloud server determines the question raised by the user through voice recognition and image recognition, searches for the answer, and returns it to the desk lamp. The cloud server first recognizes the user's intention through voice, and then crops the image according to the intention. Then perform image recognition, such as OCR to recognize the text. Enter the text into the search engine to search for matching answers. The answer can be an audio file or a video file, or it can be a picture. For example, if the question is how to solve the problem, the answer is a video of the problem-solving process. If the question is about grading, the answer is a picture of the marked answer sheet.

[0056] Step 304, in response to receiving the answer returned by the cloud server, output the answer in audio or video form.

[0057] In this embodiment, if it is an audio file, it is played directly by the speaker. If it is a video file or a picture, it is played by the display screen.

[0058] Users can turn on the device for lighting while reading. If they encounter questions and need assistance during the reading process, they can point their fingers at the text or image in question and wake up the device with a wake-up word. They can use voice commands to ask the device to recognize the content they are pointing to. The device takes a photo with the camera and uploads the image information to the server cloud for corresponding recognition and processing, and then transmits it downstream to the device to provide corresponding feedback on the problem in the form of sound or image.

[0059] In sufficient light conditions, it can also assist learning without turning on the lighting.

[0060] Continue to refer Figure 4 , shows a process 400 of another embodiment of a method for assisting learning according to the present disclosure. The method for assisting learning comprises the following steps:

[0061] Step 401, receiving voice instructions and images from the desk lamp.

[0062] In this embodiment, the execution subject of the method for assisting learning (for example Figure 1 The cloud server shown in the figure can receive voice commands and images from the desk lamp through wired or wireless communication. The image can be a panoramic image or an image cropped by the desk lamp.

[0063] Step 402, identifying the user's intention according to the voice instruction.

[0064] In this embodiment, the vocabulary content in the speech is converted into computer-readable input, such as a key, binary code or character sequence. This is different from speaker recognition and speaker verification, which attempt to identify or confirm the speaker who made the speech rather than the vocabulary content contained therein. A speech recognition system is installed on the speech recognition server. The speech recognition system is generally divided into two stages: training and decoding. Training is to train the acoustic model through a large amount of annotated speech data. Decoding is to recognize the speech data outside the training set into text through the acoustic model and language model. The quality of the trained acoustic model directly affects the recognition accuracy.

[0065] Semantic analysis is performed based on the text results. Semantic analysis refers to the use of various methods to learn and understand the semantic content expressed by a text. Any understanding of language can be classified as semantic analysis. A text is usually composed of words, sentences and paragraphs. According to the different language units of the object of understanding, semantic analysis can be further decomposed into lexical level semantic analysis, sentence level semantic analysis and text level semantic analysis. Generally speaking, lexical level semantic analysis focuses on how to obtain or distinguish the semantics of words, sentence level semantic analysis attempts to analyze the semantics expressed by the entire sentence, and text semantic analysis aims to study the internal structure of natural language text and understand the semantic relationship between text units (which can be sentence clauses or paragraphs). Simply put, the goal of semantic analysis is to achieve automatic semantic analysis in various language units (including words, sentences and texts, etc.) by establishing effective models and systems, so as to understand the true semantics expressed by the entire text. For example, although a panoramic photo is taken, the user's intention is to identify the word he is pointing to.

[0066] Step 403: capture a segment of the position pointed to by the user from the image according to the intention.

[0067] In this embodiment, the cropping operation is performed according to the recognized intention. The workload of image recognition is reduced. For example, if the user asks "how to read a word", the part including the text in the area he points to can be cropped. Specifically, the image can be converted into a binary image, edge detection can be performed, and the cropping position can be determined. The segment where the word is located can be cropped.

[0068] Step 404: Perform text recognition on the segment to obtain a question.

[0069] In this embodiment, the problem can be identified by using text recognition technology such as OCR.

[0070] Step 405, search for the answer to the question and return it to the desk lamp.

[0071] In this embodiment, the text recognition result is combined with the voice to search for answers in the search engine. Various neural network models can be pre-trained to answer learning questions, such as mathematical models, English models, etc.

[0072] This product is an intelligent educational auxiliary product that integrates voice and image recognition capabilities and has lighting functions. It is very suitable for reading and learning scenarios. Currently, most competitors implement it in the form of tablets or special-shaped speakers with cameras. Different from us, we have given new empowerment to the lighting equipment that is already commonly used for learning, and optimized the user experience through combination and improvement. 1. The camera is structurally facing vertically downward, and the imaging is not prone to distortion due to angle problems; 2. The lighting effect during imaging can be ensured to ensure clearer imaging, which is conducive to image recognition.

Claims

1. A desk lamp for assisting learning, comprising a lamp holder and a bracket arranged on the lamp holder, wherein: The bracket includes a horizontal bar and a vertical bar, and the lighting unit and the camera unit are located on the horizontal bar. The height of the horizontal bar from the desktop is adjusted manually or by voice control. A microphone pickup unit and a speaker sounding unit are installed on the vertical bar. A control processor, a communication unit, and a power supply unit are arranged in the lamp holder. The control processor is electrically connected to the communication unit, the microphone pickup unit, the speaker sounding unit, the camera unit, the lighting unit, and the power supply unit respectively. The camera unit includes two cameras, one camera is used to shoot the desktop, and the other camera shoots the user. The microphone pickup unit detects the user's voice, determines the direction of the sound source, and then points the microphone pickup unit toward the user. The control processor performs voice recognition processing on the voice collected by the microphone pickup unit. For voice commands that cannot be parsed locally, they are sent to the cloud server through the communication unit for intention recognition. If it is recognized that the user instruction includes the intention to take a photo, the camera unit is called to take a photo, and the photo range is determined according to the keyword; Among them, the camera unit identifies the pointing position content when the user points to the text or image content with a finger, controls the processor to crop the image, the focal length of the camera is adjusted by voice control or button control, the angle and height of the camera are adjusted by the display screen and voice respectively, and the position of the camera unit is adjusted by sliding on the crossbar of the bracket; The bracket is also provided with a display unit, which is electrically connected to the control processor and is used to display the answer and the shooting result of the camera.

2. The desk lamp according to claim 1, wherein: The communication unit includes a wireless communication module and / or a wired communication module.

3. The desk lamp according to claim 1, wherein: The power supply unit includes a DC power supply unit and / or an AC power supply unit.

4. The desk lamp according to claim 1, wherein: The lighting unit includes at least one of the following light sources: an incandescent lamp, a halogen lamp, a fluorescent lamp, and an LED lamp.

5. The desk lamp according to claim 1, wherein: The camera unit is installed above the lamp holder to take photos downward.

6. The table lamp according to claim 1, wherein: The positions and angles of the lighting unit and the camera unit are adjustable.

7. The desk lamp according to claim 1, wherein: The microphone pickup unit is a microphone array.

8. The desk lamp according to any one of claims 1 to 7, wherein: The desk lamp is also provided with a key switch and / or a touch switch.

9. A system for assisting learning, comprising: A cloud server and a desk lamp as claimed in any one of claims 1 to 8, wherein: The desk lamp is connected to the cloud server by wire and / or wirelessly via the communication unit; The cloud server is configured to receive the voice and image sent by the desk lamp, perform voice recognition and image recognition to obtain the question raised by the user, search for the corresponding answer according to the question, and send the answer to the desk lamp for output.

10. A method for assisting learning, applied to the desk lamp according to any one of claims 1 to 8, comprising: In response to detecting that a user inputs a wake-up word, receiving a voice command input by the user; According to the voice command, the image specified by the user is photographed, and the text or image content pointed at by the user with a finger is recognized for cropping, wherein the user adjusts the focal length by pressing buttons on the display screen, or controls the camera to zoom in the image by voice, and adjusts the angle of the camera by sliding on the display screen; Uploading the voice command and the cropped image to a cloud server, wherein the cloud server determines the question raised by the user through voice recognition and image recognition, searches for the answer, and returns it to the desk lamp; In response to receiving the answer returned by the cloud server, the answer is output in audio or video form.

11. A method for assisting learning, applied to a cloud server, comprising: Receiving the voice command and the image uploaded by the desk lamp according to the method of claim 10; recognizing the user's intention according to the voice command; capturing a segment of the position pointed to by the user from the image according to the intention; Performing text recognition on the fragment to obtain a question; The answer to the question is searched and returned to the lamp.

Images