Learning behavior monitoring method, intelligent table lamp and storage medium

Abstract

The invention discloses a learning behavior monitoring method, an intelligent table lamp and a storage medium, and relates to the technical field of intelligent equipment, the method is applied to the intelligent table lamp, and the intelligent table lamp comprises a camera module and a position detection module; the method comprises the following steps: acquiring a scene video through a camera module, and identifying at least one target object in the scene video; under the condition that the main guardian information corresponding to the target object is obtained, position information corresponding to the target object is obtained through a position detection module; identifying behavior information corresponding to the target object according to the position information and the scene video; and under the condition that the behavior information accords with the preset abnormal information, preset prompt information is output through a prompt module, and the prompt information is sent to the main guardian according to the main guardian information. According to the invention, bad learning habits or abnormal behaviors of students can be detected in real time and prompted, and one or more student objects can be identified and monitored.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent devices, and in particular to a learning behavior monitoring method, an intelligent desk lamp, and a storage medium. Background Art

[0002] When students are studying, it is usually difficult for them to maintain a good sitting posture for a long time. Maintaining a bad sitting posture for a long time and overusing the eyes can easily lead to health problems such as cervical spondylosis and vision loss, which will have an adverse impact on the growth of adolescents.

[0003] Currently, there are some health monitoring devices and apps on the market that can record users' physical activity data, such as step count and sleep duration. However, these devices and apps are mostly aimed at monitoring the health of adults and lack professional monitoring and reminder functions for adolescent learning behavior. Furthermore, while some electronic devices have built-in screen time statistics, these are not integrated with sitting posture monitoring, making it impossible to form a comprehensive learning health management system.

[0004] Therefore, how to monitor teenagers' learning behavior in real time, including sitting posture and eye usage time, so as to provide timely reminders when bad behavior is discovered, thereby ensuring the learning health of teenagers, has become an urgent problem to be solved in this field.

[0005] The above content is only used to assist in understanding the technical solution of this application and does not constitute an admission that the above content is prior art. Summary of the Invention

[0006] The main purpose of this application is to provide a learning behavior monitoring method, a smart desk lamp and a storage medium, aiming to solve the technical problem of how to monitor the learning behavior of teenagers in real time.

[0007] To achieve the above-mentioned purpose, the present application proposes a learning behavior monitoring method, which is applied to a smart desk lamp, wherein the smart desk lamp includes: a camera module and a position detection module;

[0008] The method comprises:

[0009] Acquiring a scene video through the camera module and identifying at least one target object in the scene video;

[0010] When the primary guardian information of the primary guardian corresponding to the target object is obtained, obtaining the location information corresponding to the target object through the location detection module;

[0011] identifying behavior information corresponding to the target object according to the location information and the scene video;

[0012] When the behavior information meets the preset abnormal information, the preset prompt information is output through the prompt module, and the prompt information is sent to the primary guardian according to the primary guardian information.

[0013] In one embodiment, the step of identifying at least one target object in the scene video includes:

[0014] Identifying at least one object to be confirmed in the scene video;

[0015] Obtaining an action video corresponding to the object to be confirmed;

[0016] Input the action video into a preset machine learning model to obtain the target identity type of the object to be confirmed, wherein the machine learning model is trained using the action video as a sample and the identity information as a label, and the target identity types include: a target to be monitored and a general target;

[0017] In the case that there is at least one target to be monitored, the target to be monitored is used as the target object.

[0018] In one embodiment, the target identity type further includes: guardian target; after the step of obtaining the target identity type of the object to be confirmed, the method further includes:

[0019] Sending a query request to the client of the target object connected to the smart desk lamp to determine whether the guardian target is the primary guardian corresponding to the target object;

[0020] Acquiring judgment information returned in response to the query request;

[0021] If it is determined based on the judgment information that the guardian target is the primary guardian corresponding to the target object, then identification of the behavior information corresponding to the target object is stopped.

[0022] In one embodiment, after the step of identifying at least one target object in the scene video, the method further includes:

[0023] Sending an information acquisition request to the client;

[0024] Acquire the primary guardian information of the primary guardian corresponding to the target object returned in response to the information acquisition request.

[0025] In one embodiment, the behavior information includes: a learning posture and a learning duration; and the step of identifying the behavior information corresponding to the target object based on the position information and the scene video includes:

[0026] Obtain key position information of each key point corresponding to the target object in the position information;

[0027] Identify the learning posture corresponding to the target object according to each key position information;

[0028] Determining whether the target object is in a learning state according to the scene video;

[0029] When it is recognized that the target object changes from the resting state to the learning state, starting to count the learning time;

[0030] When it is identified that the target object changes from the learning state to the resting state, the timing of the learning time is stopped to obtain the learning time.

[0031] In one embodiment, when there are multiple target objects, when the behavior information meets the preset abnormal information, the step of outputting the preset prompt information through the prompt module includes:

[0032] When the behavior information of any abnormal object among the target objects conforms to the preset abnormal information, determining the target prompt information corresponding to the abnormal object in the preset prompt information;

[0033] The target prompt information is outputted through the prompt module.

[0034] In one embodiment, after the step of acquiring the position information corresponding to the target object by the position detection module, the method further includes:

[0035] Determining whether the smart desk lamp is moved by the position detection module;

[0036] When the smart desk lamp moves, obtaining motion data of the smart desk lamp through the position detection module;

[0037] Calculating displacement data of the smart desk lamp according to the motion data;

[0038] The position information corresponding to the target object is updated according to the displacement data.

[0039] In one embodiment, the smart desk lamp further comprises: a light emitting module and a visible light detection module;

[0040] The method further comprises:

[0041] detecting ambient light properties of the ambient light by the visible light detection module;

[0042] The output parameters of the light emitting module and the acquisition parameters of the camera module are adjusted according to the ambient light properties.

[0043] In addition, to achieve the above-mentioned purpose, the present application also proposes a learning behavior monitoring device, which is provided in a smart desk lamp, and the smart desk lamp includes: a camera module and a position detection module; the device includes:

[0044] an acquisition module, configured to acquire a scene video through the camera module and identify at least one target object in the scene video;

[0045] a positioning module, configured to obtain the location information corresponding to the target object through the position detection module when the primary guardian information of the primary guardian corresponding to the target object is obtained;

[0046] A behavior recognition module, configured to recognize behavior information corresponding to the target object based on the location information and the scene video;

[0047] The abnormality detection module is used to output preset prompt information through the prompt module when the behavior information meets the preset abnormality information, and send the prompt information to the primary guardian according to the primary guardian information.

[0048] In addition, to achieve the above-mentioned purpose, the present application also proposes a smart desk lamp, which includes: a memory, a processor, and a computer program stored on the memory and runnable on the processor, and the computer program is configured to implement the steps of the learning behavior monitoring method described above.

[0049] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium. A computer program is stored on the storage medium, and when the computer program is executed by the processor, the steps of the learning behavior monitoring method described above are implemented.

[0050] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the learning behavior monitoring method as described above.

[0051] The present application provides a learning behavior monitoring method, which uses a camera module to monitor students' learning scenes in real time, identifies one or more student objects (i.e., target objects) that need to be monitored in the current learning scene, and detects the location information of the target object through a position detection module when the information of the primary guardian of the target object is obtained. The behavior information of the target object is then detected through the position information and the monitored scene video. If the behavior information is consistent with the preset abnormal information, a prompt message is output through a prompt module, thereby reminding students to pay attention when students have abnormal situations such as incorrect posture or long learning time, and sending the prompt message to the primary guardian.

[0052] In summary, this application sets up a camera module to identify whether there are students in the learning scene and how many students there are, then performs position detection on the students, and then identifies the students' behavior information through the location information and the monitored scene video. It can instantly detect students' bad learning habits or abnormal behaviors and remind them. This instant feedback mechanism helps students realize their behavioral problems at the first time and correct them immediately, thereby effectively avoiding health problems or decreased learning efficiency caused by long-term bad habits. In addition, it can identify and monitor one or more student objects, so as to understand each student's specific learning situation more accurately and provide more personalized guidance and support for each student. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0054] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0055] Figure 1 A flowchart of Example 1 of the learning behavior monitoring method of this application is provided;

[0056] Figure 2 A schematic diagram of the single-player mode flow chart provided in Example 1 of the learning behavior monitoring method of this application;

[0057] Figure 3 A multi-person mode flow chart provided in Example 1 of the learning behavior monitoring method of this application;

[0058] Figure 4 This is a schematic diagram of the module structure of the learning behavior monitoring device according to an embodiment of the present application;

[0059] Figure 5 Schematic diagram of the device structure of the hardware operating environment involved in the learning behavior monitoring method in the embodiment of the present application.

[0060] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0061] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0062] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0063] The main solution of the embodiment of the present application is: obtaining a scene video through the camera module and identifying at least one target object in the scene video; when the main guardian information of the main guardian corresponding to the target object is obtained, obtaining the position information corresponding to the target object through the position detection module; identifying the behavior information corresponding to the target object based on the position information and the scene video; when the behavior information meets the preset abnormal information, outputting the preset prompt information through the prompt module.

[0064] When students are studying, it is usually difficult for them to maintain a good sitting posture for a long time. Maintaining a bad sitting posture for a long time and overusing the eyes can easily lead to health problems such as cervical spondylosis and vision loss, which will have an adverse impact on the growth of adolescents.

[0065] Currently, there are some health monitoring devices and apps on the market that can record users' physical activity data, such as step count and sleep duration. However, these devices and apps are mostly aimed at monitoring the health of adults and lack professional monitoring and reminder functions for adolescent learning behavior. Furthermore, while some electronic devices have built-in screen time statistics, these are not integrated with sitting posture monitoring, making it impossible to form a comprehensive learning health management system.

[0066] Therefore, how to monitor teenagers' learning behavior in real time, including sitting posture and eye usage time, so as to provide timely reminders when bad behavior is discovered, thereby ensuring the learning health of teenagers, has become an urgent problem to be solved in this field.

[0067] In response to the above problems, the present application provides a learning behavior monitoring method, which uses a camera module to monitor students' learning scenes in real time, identifies one or more student objects (i.e., target objects) that need to be monitored in the current learning scene, and uses a position detection module to detect the position information of the target object. The behavior information of the target object is then detected through the position information and the monitored scene video. If the behavior information is consistent with the preset abnormal information, a prompt message is output through the prompt module, thereby reminding students to pay attention when students have abnormal situations such as incorrect posture or long learning time.

[0068] In summary, this application sets up a camera module to identify whether there are students in the learning scene and how many students there are, then performs position detection on the students, and then identifies the students' behavior information through the location information and the monitored scene video. It can instantly detect students' bad learning habits or abnormal behaviors and remind them. This instant feedback mechanism helps students realize their behavioral problems at the first time and correct them immediately, thereby effectively avoiding health problems or decreased learning efficiency caused by long-term bad habits. In addition, it can identify and monitor one or more student objects, so as to understand each student's specific learning situation more accurately and provide more personalized guidance and support for each student.

[0069] In this embodiment, for ease of description, the following description is made with the smart desk lamp as the execution subject.

[0070] Based on this, the present application embodiment provides a learning behavior monitoring method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the learning behavior monitoring method of this application.

[0071] In this embodiment, the method is applied to a smart desk lamp, which includes a camera module and a position detection module. The learning behavior monitoring method includes steps S10 to S40:

[0072] Step S10, acquiring a scene video through the camera module, and identifying at least one target object in the scene video;

[0073] It should be noted that in this embodiment, the smart desk lamp adds various modules and control systems to the conventional desk lamp design to achieve the technical effect of monitoring students' learning behavior. The smart desk lamp can have multiple modes: pure desk lamp mode, night-time mode, indoor monitoring mode, learning monitoring mode (which can be divided into single-person, multi-person and mixed modes), rehabilitation training monitoring mode (such as eye exercises, etc.), rest mode, etc. The smart desk lamp is connected to the network and can upload monitoring and evaluation data to the cloud in real time or at a scheduled time. Users can obtain relevant data through the mobile phone APP.

[0074] It should be noted that in this embodiment, the smart desk lamp mainly includes an MCU (Microcontroller Unit), a detection module, an interaction module, and a power module. The MCU is the main control part of the entire system and can use mature solutions from mainstream IC manufacturers in the smart wearable product industry.

[0075] The power module is responsible for supplying power to the system, mainly including 5V, 3.3V, 2V8, 1.8V, 1.2V, 0.9V, etc., including but not limited to these, including power management chip and power-on timing control chip.

[0076] The detection module includes the position detection module, which in turn includes the light position detection module and the human position detection module. The light position status detection module is primarily used to locate the position and direction of the light. The human position detection module primarily detects the presence, number, and location of people. The above modules are merely functional categories; some components can be reused in multiple functional categories in different scenarios.

[0077] The interactive module is responsible for human-computer interaction actions, including the camera module. After the camera module collects pictures or video images, they are processed through the SOC (System on a Chip) algorithm to provide a basis for subsequent human-computer interaction.

[0078] It should be noted that when the smart desk lamp is turned on for the first time, the user needs to connect the smart desk lamp to WI FI, and then select the desk lamp number through the APP corresponding to the smart desk lamp, or automatically match the corresponding smart desk lamp through the same WI FI, bind the smart desk lamp with the APP, and then the user can choose to use the smart desk lamp as home or public. Home use means use in a home environment, and public use means use in a study room or other areas with large personnel flow. In home mode, the desk lamp switches to home desk lamp learning and monitoring mode. After the desk lamp is restarted, it will no longer prompt for mode selection. In public mode, the desk lamp switches to public desk lamp learning and monitoring working mode. After the desk lamp is restarted, it needs to be reconnected to WI FI and bound to the APP.

[0079] In this embodiment, based on the aforementioned hardware, when monitoring learning, the camera module is first activated, capturing high-definition video of the surrounding environment. Using a built-in image recognition algorithm, the device analyzes and identifies at least one target object within the scene video. These targets are typically students within the learning space. This recognition process incorporates various techniques, including color recognition, shape matching, and facial recognition, to ensure accurate capture of all key targets.

[0080] In addition, before identifying the target object through the camera module, the infrared sensor in the position detection module can be used to collect the presence, number and approximate location of people, and make a preliminary judgment on whether there are target objects in the current learning scene and how many there are.

[0081] Furthermore, in the above-mentioned step S10, the step of identifying at least one target object in the scene video may include steps S11 to S14:

[0082] Step S11, identifying at least one object to be confirmed in the scene video;

[0083] In this embodiment, when the smart desk lamp is used for public use, due to the high turnover of people, facial recognition cannot effectively identify the target's identity. Therefore, basic image recognition technology is used to identify all possible objects in the scene video captured by the camera module. These objects can be people, animals, or any objects related to learning behavior. At this stage, they are all considered potential monitoring targets.

[0084] Step S12, obtaining an action video corresponding to the object to be confirmed;

[0085] In this embodiment, for each object to be identified, its related action video is extracted. The action video contains key information such as the object's motion trajectory, posture changes, and interaction with other objects, which is crucial for subsequent identity recognition.

[0086] Step S13: Input the action video into a preset machine learning model to obtain the target identity type of the object to be confirmed, wherein the machine learning model is trained using the action video as a sample and the identity information as a label. The target identity types include: a target to be monitored and a general target;

[0087] In this embodiment, the action video of each subject to be identified is then input into a pre-set machine learning model. This machine learning model is trained based on a large number of action video samples and corresponding identity information labels, and can accurately identify the identity type of the object in the action video. In this model, identity types are divided into two categories: monitored targets and general targets. Monitored targets are typically people directly related to learning behavior, such as students; general targets may be people or objects not directly related to learning behavior.

[0088] Step S14: When there is at least one target to be monitored, the target to be monitored is used as the target object.

[0089] In this embodiment, based on the output of the machine learning model, all objects identified as targets to be monitored are screened and used as target objects in subsequent steps. If there are multiple targets to be monitored, the device will track and record their behavior information simultaneously.

[0090] In the above steps, the application of machine learning models enables the device to automatically distinguish between monitored targets and general targets, thereby reducing the possibility of false positives and missed negatives. This not only improves the accuracy of the monitoring system but also allows the system to focus more on objects directly related to the learning behavior, providing more reliable data support for subsequent behavioral analysis and anomaly detection. Furthermore, this approach is also versatile and scalable, adapting to the needs of different learning scenarios and subjects.

[0091] Step S20: When the primary guardian information of the primary guardian corresponding to the target object is obtained, the location information corresponding to the target object is obtained through the location detection module;

[0092] In this embodiment, after identifying one or more target objects, it is necessary to obtain the information of the primary guardian corresponding to the target object so as to send the detection result of the target object to the primary guardian. If the primary guardian information is not detected, no subsequent detection is performed. Then, the depth camera in the position detection module is used to collect depth information to further obtain the specific location information of each identified target object. The position detection module can be implemented by infrared sensors, depth camera detection, RFID (Radio Frequency Identification, wireless radio frequency identification technology) tag readers or computer vision technology. These technologies can track the movement trajectory of target objects in real time and accurately calculate their specific positions in space, providing key data for subsequent behavioral analysis.

[0093] Furthermore, in a feasible implementation manner, the target identity type further includes: guardian target. Before the above step S20, the method may further include steps S101 to S103:

[0094] Step S101, sending a query request to the client of the target object connected to the smart desk lamp to determine whether the guardian target is the primary guardian corresponding to the target object;

[0095] In this embodiment, the smart desk lamp establishes a connection with the client (e.g., a smartphone, tablet, etc.) used by the target subject through its built-in communication module (e.g., Wi-Fi, Bluetooth, etc.). The smart desk lamp then sends a query request to the client. The purpose of this request is to confirm whether the guardian (i.e., guardian target) currently interacting with the smart desk lamp or within the smart desk lamp's monitoring range is the registered or designated primary guardian of the target subject.

[0096] Step S102, obtaining judgment information returned in response to the query request;

[0097] In this embodiment, after sending the query request, the smart desk lamp waits for the judgment information returned by the client used by the target object. This judgment information can be a simple confirmation or denial, indicating whether the guardian target is the primary guardian corresponding to the target object.

[0098] Step S103: If it is determined based on the judgment information that the guardian target is the primary guardian corresponding to the target object, then the identification of the behavior information corresponding to the target object is stopped.

[0099] In this embodiment, after receiving the judgment information, the smart desk lamp will analyze and judge it. If the judgment information indicates that the guardian target is indeed the primary guardian of the target object, the smart desk lamp will stop further identifying or monitoring the target object's behavior information. This means that after confirming the identity of the primary guardian, the smart desk lamp will no longer record or analyze the target object's daily behavior, thereby reducing unnecessary monitoring and data processing.

[0100] Furthermore, after the above step S10, the method may further include steps S104 to S105:

[0101] Step S104: sending an information acquisition request to the client;

[0102] In this embodiment, after confirming that the guardian target is the primary guardian of the target object, the smart desk lamp sends an information acquisition request to the client it previously communicated with. This request aims to obtain more detailed information about the primary guardian, including but not limited to basic information such as the primary guardian's name and contact information, as well as any special permissions or settings.

[0103] Step S105: Acquire the primary guardian information of the primary guardian corresponding to the target object returned in response to the information acquisition request.

[0104] In this embodiment, after sending the information acquisition request, the smart desk lamp will wait for the client's response. The target object can enter the primary guardian's information in the client and send it to the smart desk lamp, which will receive and store this information for subsequent use.

[0105] Step S30, identifying behavior information corresponding to the target object based on the location information and the scene video;

[0106] In this embodiment, a behavior recognition algorithm is used to analyze the behavior information of the target object in combination with location information and scene video. Behavioral information may include posture during learning, learning duration, monitoring of learning content, etc. When analyzing learning behavior, it is necessary to analyze the video frames frame by frame, and extract and compare the characteristics of the target object's posture, movement, speed, etc. By comparing the preset behavior pattern library, the device can identify whether the target object is engaged in normal learning activities, such as reading, writing, or group discussion, or is engaged in behaviors that may be considered abnormal, such as leaving the seat, playing with the phone, or dozing off. It is also possible to remind students that they need to take a break by recording the time they spend studying.

[0107] Furthermore, in a feasible implementation, the behavior information includes: learning posture and learning duration; the above-mentioned step S30 may include steps S31 to S35:

[0108] Step S31, obtaining key position information of each key point corresponding to the target object in the position information;

[0109] In this embodiment, the key position information of each key point corresponding to the target object in the position information is first obtained. These key points include the head, shoulders, hands, feet, etc. Their position information can reflect the overall posture of the target object. Using high-precision human posture recognition technology, the device can capture and record the position changes of these key points in real time.

[0110] Step S32, identifying the learning posture corresponding to the target object according to each key position information;

[0111] In this embodiment, a preset posture recognition algorithm is used to identify the target subject's learning posture based on the positional information of each key point. This involves analyzing the positional relationships of key points, extracting posture features, and comparing them with a learning posture database. By recognizing the learning posture, the device can determine whether the target subject maintains the correct sitting, standing, or writing posture.

[0112] Step S33, judging whether the target object is in a learning state according to the scene video;

[0113] In this embodiment, while recognizing the learning posture, the device also determines whether the target subject is in a learning state based on the scene video. For example, the device analyzes the target subject's activities, such as whether they are reading, writing, or using an electronic device to learn. By combining video content and posture information, the device can more accurately determine the target subject's learning state.

[0114] Step S34, when it is recognized that the target object changes from the resting state to the learning state, starting to count the learning time;

[0115] In this embodiment, once the device recognizes the target object's transition from a resting state to a learning state, it immediately begins timing the learning duration. This step is triggered based on the learning state recognition result and the determination of the stability and duration of the target object's posture. The start of the timing process marks the official start of the learning activity.

[0116] Step S35 , when it is identified that the target object changes from the learning state to the resting state, the timing of the learning time is stopped to obtain the learning time.

[0117] In this embodiment, when the device recognizes that the target subject has transitioned from a learning state to a resting state, it stops counting the learning duration and records the final learning duration. This step also relies on the results of learning state recognition and changes in the target subject's posture and activity. By stopping the timing, the device can accurately calculate the total time the target subject has spent in the learning activity.

[0118] Through the above steps, this application becomes more precise and comprehensive in identifying and analyzing the target subject's learning posture and study time. This method not only improves the monitoring system's ability to identify learning behavior, but also provides richer data support for subsequent behavior analysis and anomaly detection. At the same time, by accurately recording study time, the device can provide learners with valuable feedback on their learning efficiency and habits, helping them better adjust and optimize their learning behavior.

[0119] Step S40: When the behavior information meets the preset abnormal information, the preset prompt information is output through the prompt module.

[0120] It should be noted that, in this embodiment, the prompt module may include a speaker, which is used not only to play prompt sound information but also to play system audio files and remote voice calls.

[0121] In addition, the device also includes a microphone, which can be used to collect user information in order to complete the voice signal collection work when completing remote voice calls or voice control of the console lamp.

[0122] In this embodiment, once the device detects that the target subject's behavior matches pre-set abnormal information, indicating that the subject may be sitting incorrectly or studying for too long, the device will immediately output a pre-set prompt message through the prompt module. These prompt messages may be presented in the form of sound, flashing lights, screen displays, etc., to promptly remind the target subject to adjust their behavior, and also provide a basis for monitoring and intervention by teaching administrators.

[0123] Furthermore, in a feasible implementation manner, when there are multiple target objects, the above step S40 may include steps S41 to S42:

[0124] Step S41, when the behavior information of any abnormal object among the target objects meets the preset abnormal information, determining the target prompt information corresponding to the abnormal object in the preset prompt information;

[0125] Step S42: outputting the target prompt information through the prompt module.

[0126] In this embodiment, when there are multiple target objects, the system monitors each target object separately and stores the corresponding behavior information of each target object. When performing anomaly detection, the system also performs detection based on the behavior information of each target object. If the behavior information of an abnormal object among the target objects meets the preset abnormality information, the device determines the target prompt information corresponding to the abnormal object and then outputs the corresponding target prompt information through the prompt module.

[0127] As an example, when there are three students A, B, and C, the device monitors and records the behavioral information of A, B, and C respectively, and stores them as (A, x), (B, y), and (C, z), where x, y, and z are the behavioral information of A, B, and C respectively. When it is detected that C's study time exceeds the preset time, a prompt tone is output: "Please take a break, student C."

[0128] Specifically, when there are multiple students and students are to be identified, in one example, the step of identifying at least one target object in the scene video in step S10 may further include:

[0129] Obtaining facial information of each target object;

[0130] Searching for identity information corresponding to the facial information in a preset identity information database;

[0131] Each piece of identity information is associated with the corresponding face information and stored.

[0132] For example, when students register, their identity information can be pre-registered and associated with their facial information. When multiple students are identified, facial recognition can be used to identify each student's identity, and the identified behavior information can be associated with the identity information of the corresponding target object. When the behavior information of a target object matches abnormal information, a prompt message can be output based on the target object's corresponding identity information. For example, if facial recognition identifies two students as "Wang Yi" and "Wang Er", and if "Wang Yi" is detected to have an incorrect posture, the speaker can output "Please correct your sitting posture, Wang Yi."

[0133] In another example, each target object can also be labeled using the acquired position information, and each target object can be labeled in a preset direction order (e.g., from left to right, from front to back). When the behavior information of a target object matches the abnormal information, a prompt message is output based on the position label corresponding to the target object. For example, if there are three students from left to right through position recognition, and if the posture of the leftmost student is detected to be incorrect, the speaker outputs "Please correct the sitting posture of the student on the leftmost." Or if there are multiple students and the study time of the second student from the left has exceeded, the speaker outputs "Please take a break, the second student from the left."

[0134] In another example, the step of identifying at least one target object in the scene video in the above step S10 may further include:

[0135] Respectively identifying the external features of each of the target objects using an image recognition algorithm;

[0136] Each of the external features is associated with each of the target objects and stored.

[0137] For example, each target object can also be labeled by external features, which may include: clothing features (wearing red clothes), appearance features (whether wearing glasses), body features (long hair), etc., and the features of each target object need to be unique features, that is, other target objects do not have the same features. After completing the feature labeling of each target object, the detected behavior information is stored accordingly. When the behavior information of a target object is identified to match the abnormal information, a prompt message is output according to the feature labeling corresponding to the target object. For example, three students are wearing blue, red and black tops respectively. When it is detected that the student wearing the blue top is sitting incorrectly, the speaker outputs "Please correct your sitting posture, students wearing blue tops."

[0138] For example, in order to help understand the implementation process of the learning behavior monitoring method obtained by combining this embodiment with the above embodiment 1, please refer to Figure 2 , Figure 2 A brief single-player mode flow chart of a learning behavior monitoring method is provided. Specifically:

[0139] When a shared smart desk lamp begins operating in learning monitoring mode, it first detects the number of people using a human infrared sensor (Sensor) and then uses a camera (RGBCAM) to capture real-time footage. If multiple people are detected in the image, the system directly switches to multi-person mode. If only one person is in the image, the system uses the camera and depth camera (TOFCAM) ​​to capture real-time footage and monitor the student's behavior. If a student's posture is incorrect, the system provides voice prompts to correct the posture. This prompt and a live image are sent to the student's primary guardian to ensure they understand the student's progress. If the student's posture is correct, the system determines whether the student's study time has expired. If so, the system switches to rehabilitation training monitoring mode. Once rehabilitation training monitoring mode begins, a voice prompt announcing the upcoming eye exercises is followed by eye exercise music. Simultaneously, the system captures footage to determine if the student is performing the exercises. If not, the system provides a voice prompt to perform the exercises. After the exercises are completed, the system switches to rest mode. After starting work in rest mode, a voice prompt will be given to inform the student that rest mode is about to begin, and then a set audio file will be played to soothe the student's mood. After the scheduled rest time is reached, a voice prompt will be given to inform the student that rest mode is about to end, and then the camera will be used to identify whether the student is ready to study. If so, the system will switch to study monitoring mode. If the student is not ready to study and there is ambient light in the room, it means the student needs to rest, and a voice prompt will be given and the desk lamp will be turned off. If there is no ambient light in the room and it is time for a night rest, the system will switch to night waking mode, and the desk lamp will be turned on when the student's movement is detected, otherwise it will switch directly to pure desk lamp mode.

[0140] For example, please refer to Figure 3 , Figure 3 A brief multiplayer mode flow chart of a learning behavior monitoring method is provided, specifically:

[0141] After the multi-person mode starts working, the camera is used to shoot. If multiple people are detected learning, the camera and depth camera will be used to detect the sitting posture and learning time of each target. If the sitting posture is incorrect, voice prompts will be given to correct the sitting posture. When someone's learning time exceeds the limit, a voice prompt will be given to the person who has exceeded the limit to take a rest.

[0142] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above embodiment 1 can be referred to the above introduction and will not be repeated hereafter. On this basis, after the above step S20, the method may further include steps A10 to A40:

[0143] Step A10, determining whether the smart desk lamp has moved by the position detection module;

[0144] It should be noted that, in this embodiment, the position detection module may also include an inertial sensor and a geomagnetic sensor to collect the motion data of the device, and then use a machine learning model to estimate the current and past motion speeds.

[0145] In this embodiment, the device first determines whether it has moved using a position detection module, and then analyzes the data output by the position detection module to detect any significant position changes or signs of movement.

[0146] Step A20: When the smart desk lamp moves, obtaining motion data of the smart desk lamp through the position detection module;

[0147] In this embodiment, after confirming the movement of the device, the device further obtains its own motion data through the position detection module. This motion data includes the device's speed, acceleration, direction, etc., which can describe the device's movement trajectory and status in detail.

[0148] Step A30, calculating displacement data of the smart desk lamp according to the motion data;

[0149] In this embodiment, the acquired motion data is used to calculate the displacement data of the device. The displacement data reflects the linear distance and direction change from the initial position to the current position of the device.

[0150] Step A40: updating the position information corresponding to the target object according to the displacement data.

[0151] In this embodiment, the target object's position information is updated based on the calculated displacement data. Because device movement can cause the scene captured by the camera module to change, updating position information is crucial for maintaining the accuracy and continuity of monitoring data. The device recalculates the target object's information relative to its new position to ensure that subsequent behavior analysis and anomaly detection are based on accurate data.

[0152] Through the above steps, this application can more accurately handle the impact of its own movement on monitoring data. This approach not only improves the stability and reliability of the monitoring system, but also ensures that accurate target object location information can be continuously provided even when the device is moving. This is crucial for maintaining the continuity and consistency of monitoring data, and contributes to the accuracy of subsequent behavior analysis and anomaly detection.

[0153] Based on the first and / or second embodiments of the present application, in the third embodiment of the present application, the same or similar contents as those of the first and / or second embodiments can be referred to above and will not be described in detail. On this basis, the smart desk lamp further includes: a light emitting module and a visible light detection module;

[0154] The method may further include steps B10 to B20:

[0155] Step B10, detecting the ambient light properties of the ambient light by the visible light detection module;

[0156] In this embodiment, a visible light detection module is used to detect the current ambient light properties. These light properties include light intensity, color temperature, and illumination uniformity. The visible light detection module can capture and analyze changes in ambient light in real time, providing accurate data support for subsequent parameter adjustments.

[0157] Step B20: adjusting the output parameters of the light emitting module and the acquisition parameters of the camera module according to the ambient light properties.

[0158] In this embodiment, after obtaining the ambient light properties, the device adjusts the output parameters of the light module and the camera module's acquisition parameters based on this data. For the light module, the device adjusts the brightness or color temperature of the LED light according to the ambient light intensity to ensure that the camera module can capture clear and bright images. Furthermore, to prevent damage to the camera module or poor acquisition quality caused by excessive or insufficient light, the device also adjusts acquisition parameters such as exposure time and gain based on the ambient light properties.

[0159] In addition, the light emitting module also includes a prompt light that can display multiple colors. Different colors will be displayed for different operating modes, making it easier for users to identify the current operating mode of the device.

[0160] It should be noted that the above examples are only used to understand this application and do not constitute a limitation on the learning behavior monitoring method of this application. More simple transformations based on this technical concept are all within the scope of protection of this application.

[0161] This application also provides a learning behavior monitoring device, please refer to Figure 4 The device is provided in a smart desk lamp, and the smart desk lamp includes: a camera module and a position detection module; the learning behavior monitoring device includes:

[0162] The acquisition module 10 is configured to acquire a scene video through the camera module and identify at least one target object in the scene video;

[0163] The positioning module 20 is configured to obtain the location information corresponding to the target object through the position detection module when the primary guardian information of the primary guardian corresponding to the target object is obtained;

[0164] A behavior recognition module 30 is configured to recognize behavior information corresponding to the target object based on the location information and the scene video;

[0165] The abnormality detection module 40 is configured to output preset prompt information through the prompt module when the behavior information meets preset abnormality information, and send the prompt information to the primary guardian according to the primary guardian information.

[0166] Optionally, the acquisition module 10 is further configured to:

[0167] Identifying at least one object to be confirmed in the scene video;

[0168] Obtaining an action video corresponding to the object to be confirmed;

[0169] Input the action video into a preset machine learning model to obtain the target identity type of the object to be confirmed, wherein the machine learning model is trained using the action video as a sample and the identity information as a label, and the target identity types include: a target to be monitored and a general target;

[0170] In the case that there is at least one target to be monitored, the target to be monitored is used as the target object.

[0171] Optionally, the target identity type further includes: guardian target; the learning behavior monitoring device is further used to:

[0172] Sending a query request to the client of the target object connected to the smart desk lamp to determine whether the guardian target is the primary guardian corresponding to the target object;

[0173] Acquiring judgment information returned in response to the query request;

[0174] If it is determined based on the judgment information that the guardian target is the primary guardian corresponding to the target object, then identification of the behavior information corresponding to the target object is stopped.

[0175] Optionally, the learning behavior monitoring device is further used to:

[0176] Sending an information acquisition request to the client;

[0177] Acquire the primary guardian information of the primary guardian corresponding to the target object returned in response to the information acquisition request.

[0178] Optionally, the behavior information includes: learning posture and learning duration; the behavior recognition module 30 is further used to:

[0179] Obtain key position information of each key point corresponding to the target object in the position information;

[0180] Identify the learning posture corresponding to the target object according to each key position information;

[0181] Determining whether the target object is in a learning state according to the scene video;

[0182] When it is recognized that the target object changes from the resting state to the learning state, starting to count the learning time;

[0183] When it is identified that the target object changes from the learning state to the resting state, the timing of the learning time is stopped to obtain the learning time.

[0184] Optionally, when there are multiple target objects, the anomaly detection module 40 is further configured to:

[0185] When the behavior information of any abnormal object among the target objects conforms to the preset abnormal information, determining the target prompt information corresponding to the abnormal object in the preset prompt information;

[0186] The target prompt information is outputted through the prompt module.

[0187] Optionally, the learning behavior monitoring device is further used to:

[0188] Determining whether the smart desk lamp is moved by the position detection module;

[0189] When the smart desk lamp moves, obtaining motion data of the smart desk lamp through the position detection module;

[0190] Calculating displacement data of the smart desk lamp according to the motion data;

[0191] The position information corresponding to the target object is updated according to the displacement data.

[0192] Optionally, the smart desk lamp further includes: a light emitting module and a visible light detection module; the learning behavior monitoring device is further used to:

[0193] detecting ambient light properties of the ambient light by the visible light detection module;

[0194] The output parameters of the light emitting module and the acquisition parameters of the camera module are adjusted according to the ambient light properties.

[0195] The learning behavior monitoring device provided in this application, employing the learning behavior monitoring method of the aforementioned embodiment, can solve the technical problem of how to monitor adolescents' learning behavior in real time. Compared to the prior art, the beneficial effects of the learning behavior monitoring device provided in this application are the same as those of the learning behavior monitoring method provided in the aforementioned embodiment, and the other technical features of the learning behavior monitoring device are the same as those disclosed in the aforementioned embodiment method, and are not further described here.

[0196] The present application provides a smart desk lamp, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the learning behavior monitoring method in the above-mentioned embodiment one.

[0197] Reference below Figure 5 , which shows a schematic diagram of the structure of a smart desk lamp suitable for implementing the embodiments of the present application. The smart desk lamp in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), smart desk lamps, etc., as well as fixed terminals such as digital TVs and desktop computers. Figure 5 The smart desk lamp shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0198] like Figure 5 As shown, the smart desk lamp may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 1002 or the program loaded from the storage device 1003 to the random access memory (RAM) 1004. Various programs and data required for the operation of the smart desk lamp are also stored in the RAM 1004. The processing device 1001, ROM 1002 and RAM 1004 are connected to each other through a bus 1005. The input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the smart desk lamp to communicate with other devices wirelessly or wired to exchange data. Although the figure shows a smart desk lamp with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have instead.

[0199] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0200] The smart desk lamp provided in this application, employing the learning behavior monitoring method of the aforementioned embodiment, can solve the technical problem of how to monitor adolescents' learning behavior in real time. Compared to the prior art, the beneficial effects of the smart desk lamp provided in this application are the same as those of the learning behavior monitoring method provided in the aforementioned embodiment, and the other technical features of this smart desk lamp are the same as those disclosed in the aforementioned embodiment, and are not further described here.

[0201] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0202] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0203] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer program) stored thereon, and the computer-readable program instructions are used to execute the learning behavior monitoring method in the above-mentioned embodiment.

[0204] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0205] The computer-readable storage medium may be included in the smart desk lamp, or may exist independently without being assembled into the smart desk lamp.

[0206] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the smart desk lamp, the smart desk lamp: obtains the scene video through the camera module and identifies at least one target object in the scene video; when the main guardian information of the main guardian corresponding to the target object is obtained, obtains the position information corresponding to the target object through the position detection module; identifies the behavior information corresponding to the target object based on the position information and the scene video; when the behavior information meets the preset abnormal information, outputs the preset prompt information through the prompt module.

[0207] The computer program code for performing the operations of the present application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0208] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0209] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0210] The computer-readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned learning behavior monitoring method. This computer-readable storage medium can solve the technical problem of how to monitor adolescents' learning behavior in real time. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the learning behavior monitoring method provided in the aforementioned embodiment, and are not further elaborated here.

[0211] The present application also provides a computer program product, comprising a computer program, which implements the steps of the above-mentioned learning behavior monitoring method when executed by a processor.

[0212] The computer program product provided in this application can solve the technical problem of how to monitor the learning behavior of teenagers in real time. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the learning behavior monitoring method provided in the above embodiment, and will not be repeated here.

[0213] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A learning behavior monitoring method, characterized in that: The method is applied to a smart desk lamp, which includes: a camera module and a position detection module; The method comprises: Acquire a scene video through the camera module, and identify at least one target object in the scene video; When the primary guardian information of the primary guardian corresponding to the target object is obtained, obtaining the location information corresponding to the target object through the location detection module; Identify behavior information corresponding to the target object according to the location information and the scene video; When the behavior information conforms to the preset abnormal information, the preset prompt information is outputted through the prompt module, and the prompt information is sent to the primary guardian according to the primary guardian information.

2. The learning behavior monitoring method according to claim 1, characterized in that: The step of identifying at least one target object in the scene video comprises: Identifying at least one object to be confirmed in the scene video; Obtaining an action video corresponding to the object to be confirmed; Input the action video into a preset machine learning model to obtain the target identity type of the object to be confirmed, wherein the machine learning model is trained with the action video as a sample and the identity information as a label, and the target identity type includes: a target to be monitored and a general target; In the case that there is at least one target to be monitored, the target to be monitored is used as the target object.

3. The learning behavior monitoring method according to claim 2, characterized in that: The target identity type also includes: guardian target; after the step of obtaining the target identity type of the object to be confirmed, the method further includes: Sending a query request to a client connected to the target object with the smart desk lamp to determine whether the guardian target is the primary guardian corresponding to the target object; Acquire the judgment information returned in response to the query request; If it is determined based on the judgment information that the guardian target is the primary guardian corresponding to the target object, then identification of the behavior information corresponding to the target object is stopped.

4. The learning behavior monitoring method according to claim 3, characterized in that: After the step of identifying at least one target object in the scene video, the method further comprises: Sending an information acquisition request to the client; Acquire the primary guardian information of the primary guardian corresponding to the target object returned in response to the information acquisition request.

5. The learning behavior monitoring method according to claim 1, characterized in that: The behavior information includes: learning posture and learning duration; the step of identifying the behavior information corresponding to the target object according to the position information and the scene video includes: Acquire key position information of each key point corresponding to the target object in the position information; Identify the learning posture corresponding to the target object according to each of the key position information; Determining whether the target object is in a learning state according to the scene video; When it is recognized that the target object is switched from the resting state to the learning state, the timing of the learning time is started; When it is identified that the target object is converted from the learning state to the resting state, the timing of the learning time is stopped to obtain the learning time.

6. The learning behavior monitoring method according to claim 1, characterized in that: In the case where there are multiple target objects, when the behavior information meets the preset abnormal information, the step of outputting the preset prompt information through the prompt module includes: In the case where the behavior information of any abnormal object among the target objects conforms to the preset abnormal information, determining the target prompt information corresponding to the abnormal object in the preset prompt information; The target prompt information is outputted through the prompt module.

7. The learning behavior monitoring method according to claim 1, characterized in that: After the step of acquiring the position information corresponding to the target object through the position detection module, the method further includes: Determining whether the smart desk lamp is moved by the position detection module; When the smart desk lamp moves, obtaining motion data of the smart desk lamp through the position detection module; Calculating displacement data of the smart desk lamp according to the motion data; The position information corresponding to the target object is updated according to the displacement data.

8. The learning behavior monitoring method according to any one of claims 1 to 7, characterized in that: The smart desk lamp also includes: a light emitting module and a visible light detection module; The method further comprises: Detecting the ambient light properties of the ambient light by means of the visible light detection module; The output parameters of the light emitting module and the acquisition parameters of the camera module are adjusted according to the ambient light properties.

9. A smart desk lamp, characterized in that: The smart desk lamp comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the learning behavior monitoring method as described in any one of claims 1 to 8.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the learning behavior monitoring method according to any one of claims 1 to 8 are implemented.

Images