Table lamp control method, table lamp, device, equipment and storage medium

Abstract

The embodiment of the invention provides a control method of a table lamp, the table lamp, a device, equipment and a storage medium, and the control method of the table lamp comprises the steps: obtaining a first image collected by a first image collection assembly of the table lamp; based on the first image, identifying an application scene of the table lamp to obtain a current application scene; determining an illumination mode of the table lamp based on the current application scene; and controlling the table lamp to be switched to the illumination mode.

Description

Technical Field

[0001] The present disclosure relates to, but is not limited to, the field of image processing technology, and in particular to a control method for a desk lamp, a desk lamp, a device, equipment, and a storage medium. Background Art

[0002] At present, desk lamps have become a common tool for indoor lighting, and are frequently used in learning, reading, etc. However, desk lamp products in the related art are not smart enough and are difficult to meet the needs of users. Summary of the invention

[0003] In view of this, embodiments of the present disclosure provide a control method for a desk lamp, a desk lamp, a device, a equipment, and a storage medium.

[0004] The technical solution of the embodiment of the present disclosure is implemented as follows:

[0005] In one aspect, an embodiment of the present disclosure provides a method for controlling a desk lamp, the method comprising:

[0006] Acquire a first image captured by a first image acquisition component of the desk lamp;

[0007] Based on the first image, identifying an application scene of the desk lamp to obtain a current application scene;

[0008] Based on the current application scenario, determining a lighting mode of the desk lamp;

[0009] Control the desk lamp to switch to the lighting mode.

[0010] On the other hand, an embodiment of the present disclosure provides a desk lamp, comprising:

[0011] A base, an illumination component, a first image acquisition component, a control component, and a connecting portion connecting the base and the illumination component; wherein,

[0012] The control component is used to: obtain the first image captured by the first image acquisition component; based on the first image, identify the application scene of the desk lamp to obtain the current application scene; based on the current application scene, determine the lighting mode; control the lighting component to switch to the lighting mode.

[0013] On the other hand, an embodiment of the present disclosure provides a control device for a desk lamp, the device comprising:

[0014] A first acquisition module, used to acquire a first image acquired by a first image acquisition component of the desk lamp;

[0015] A first recognition module, configured to recognize an application scenario of the desk lamp based on the first image to obtain a current application scenario;

[0016] A first determination module, configured to determine a lighting mode of the desk lamp based on the current application scenario;

[0017] The first control module is used to control the desk lamp to switch to the lighting mode.

[0018] On the other hand, an embodiment of the present disclosure provides a computer device, including a memory and a processor, wherein the memory stores a computer program executable on the processor, and the processor implements some or all of the steps in the above method when executing the program.

[0019] On the other hand, an embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which implements part or all of the steps in the above method when executed by a processor.

[0020] On the other hand, an embodiment of the present disclosure provides a computer program, including computer-readable codes. When the computer-readable codes are executed in a computer device, a processor in the computer device executes some or all of the steps for implementing the above method.

[0021] On the other hand, an embodiment of the present disclosure provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and when the computer program is read and executed by a computer, it implements some or all of the steps in the above method.

[0022] In the disclosed embodiment, a first image captured by a first image acquisition component of a desk lamp is acquired; based on the first image, an application scenario of the desk lamp is identified to obtain a current application scenario; based on the current application scenario, a lighting mode of the desk lamp is determined; and the desk lamp is controlled to switch to the lighting mode. In this way, the application scenario of the desk lamp can be automatically identified, and the lighting mode of the desk lamp can be better adapted to the current application scenario, thereby better meeting the user's desk lamp usage needs and improving the intelligence of the desk lamp. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A schematic diagram of an implementation flow of a method for controlling a desk lamp provided in an embodiment of the present disclosure;

[0024] Figure 2 A schematic diagram of an implementation flow of a method for controlling a desk lamp provided in an embodiment of the present disclosure;

[0025] Figure 3A A schematic diagram of an implementation flow of a method for controlling a desk lamp provided in an embodiment of the present disclosure;

[0026] Figure 3BA schematic diagram of an implementation of determining the distance between the user's eyes and the desktop in a desk lamp control method provided in an embodiment of the present disclosure;

[0027] Figure 4A A schematic diagram of the structure of a desk lamp provided in an embodiment of the present disclosure;

[0028] Figure 4B A schematic diagram of the structure of a desk lamp provided in an embodiment of the present disclosure;

[0029] Figure 5A A schematic diagram of the structure of a control device for a desk lamp provided in an embodiment of the present disclosure;

[0030] Figure 5B A schematic diagram of an illumination area of ​​a spotlight source of a desk lamp provided in an embodiment of the present disclosure;

[0031] Figure 5C A schematic diagram of an illumination area of ​​a spotlight source of a desk lamp provided in an embodiment of the present disclosure;

[0032] Figure 6 A schematic diagram of the structure of a control device for a desk lamp provided in an embodiment of the present disclosure;

[0033] Figure 7 A hardware entity schematic diagram of a computer device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solutions and advantages of the present disclosure clearer, the technical solutions of the present disclosure are further elaborated in detail below in conjunction with the drawings and embodiments. The described embodiments should not be regarded as limiting the present disclosure. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present disclosure.

[0035] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict. The terms "first / second / third" are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It is understood that "first / second / third" may be interchanged in a specific order or sequential order where permitted, so that the embodiments of the present disclosure described herein can be implemented in an order other than that illustrated or described herein.

[0036] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present disclosure belongs. The terms used herein are only for the purpose of describing the present disclosure and are not intended to limit the present disclosure.

[0037] The present disclosure provides a method for controlling a desk lamp, which can be executed by a processor of a computer device. The computer device may refer to a desk lamp, or a server, a laptop computer, a tablet computer, a desktop computer, a smart TV, a set-top box, a mobile device (such as a mobile phone, a portable video player, a personal digital assistant, a dedicated messaging device, a portable gaming device) and other devices with data processing capabilities that are connected to the desk lamp and used to control the desk lamp. Figure 1 A schematic diagram of the implementation flow of a control method for a desk lamp provided in an embodiment of the present disclosure is shown in FIG. Figure 1 As shown, the method includes the following steps S101 to S104:

[0038] Step S101, obtaining a first image captured by a first image capturing component of the desk lamp.

[0039] Here, the first image acquisition component can be an image acquisition component arranged at any suitable position of the desk lamp. For example, the first image acquisition component can be arranged on the lamp head, the base and / or the connecting rod connecting the lamp head and the base, etc., and the embodiments of the present disclosure are not limited to this.

[0040] The first image acquisition component can be used to acquire an image of the environment in which the desk lamp is currently located to obtain a first image. It is understandable that, when a user uses the desk lamp, the first image can include the user currently using the desk lamp.

[0041] In implementation, the number of the first images may be one or more than two, which is not limited here. When the number of the first images is more than two, the more than two first images may be a sequence of image frames captured by the image capture component.

[0042] In some embodiments, after the first image is acquired, the first image may be corrected and / or subjected to perspective distortion according to actual needs. For example, when the first image acquisition component is a camera, the first image may be corrected and / or subjected to perspective distortion according to the intrinsic parameter coefficients of the camera.

[0043] Step S102: Based on the first image, an application scene of the desk lamp is identified to obtain a current application scene.

[0044] Here, any suitable image recognition algorithm may be used to identify the application scenario of the desk lamp in the first image to obtain the current application scenario of the desk lamp, which is not limited in this regard in the embodiments of the present disclosure.

[0045] In some embodiments, a deep learning image recognition model may be used to recognize at least one object contained in the first image, obtain an object recognition result, and determine the current application scenario of the desk lamp according to the object recognition result. The object to be recognized may include but is not limited to a user's hand, a pen-like object, a book-like object, and / or an electronic device operated by the user. The electronic device operated by the user may be, for example, at least one of a computer, a mobile phone, a tablet computer, a learning machine, and the like.

[0046] For example, when the object recognition result indicates that the user holds a pen-shaped object in his hand, and the frequency of the pen-shaped object being used to write on a book-shaped object (such as a book and / or a workbook, etc.) is higher than a preset frequency threshold and / or the writing time exceeds a preset time threshold, the current application scene can be determined to be a writing scene. For another example, when the object recognition result indicates that the user holds a pen-shaped object in his hand, and the frequency of the pen-shaped object being used to write on a book-shaped object is lower than a preset frequency threshold and / or the writing time is less than a preset time threshold, the current application scene can be determined to be a reading scene. For another example, when the object recognition result indicates that there is no pen-shaped object in the user's hand, and there is an open book-shaped object in the first image, the current application scene can be determined to be a reading scene. For another example, when the object recognition result indicates that the user is sitting in front of a computer and his hand is manipulating a mouse and / or keyboard, or when the object recognition result indicates that the user is operating an electronic device such as a mobile phone and / or a tablet computer, the current application scene can be determined to be an electronic device operation scene. For another example, when the object recognition result indicates that there is no pen-shaped object and no book-shaped object in the first image, the current scene can be determined to be other scenes.

[0047] In some embodiments, before identifying the application scenario of the desk lamp based on the first image, the user's gesture in the first image may be identified first, and when the second preset gesture is identified, the application scenario of the desk lamp is identified; when the third preset gesture is identified, the application scenario of the desk lamp is stopped. During implementation, the second preset gesture and the third preset gesture may be set by those skilled in the art according to actual conditions, or may be set by the user according to personal needs. For example, the second preset gesture may include but is not limited to at least one of an OK gesture, a palm-up gesture, etc., and the third preset gesture may include but is not limited to at least one of a V-sign gesture, a fist gesture, etc.

[0048] In some embodiments, a switch for turning on or off the scene recognition function can be set on the desk lamp. When it is detected that the switch is turned on, the application scene of the desk lamp is identified based on the first image; when it is detected that the switch is turned off, the application scene of the desk lamp is not identified.

[0049] Step S103: determining the lighting mode of the desk lamp based on the current application scenario.

[0050] Here, at least one usable lighting mode can be set in advance for the desk lamp, and the lighting mode currently to be used by the desk lamp can be determined from the at least one usable lighting mode based on the current application scenario. For example, the lighting mode that the desk lamp can use can include but is not limited to at least one of a floodlight mode, a spotlight mode, a mixed mode, etc., wherein the mixed mode can be a floodlight plus spotlight mode.

[0051] During implementation, those skilled in the art may determine the lighting mode of the desk lamp based on the current application scenario in any suitable manner according to actual needs, and the embodiments of the present disclosure are not limited to this.

[0052] In some embodiments, the correspondence between at least one application scenario of the desk lamp and at least one available lighting mode can be preset, and the corresponding relationship can be queried based on the current application scenario to determine the lighting mode currently to be used by the desk lamp. During implementation, the correspondence between the at least one application scenario and the at least one available lighting mode can be a factory default configuration, or it can be configured by the user according to actual conditions, which is not limited here. For example, the user can configure the correspondence through an application (Application, APP) running on the mobile phone, and can also modify the correspondence configured by the user and / or the factory default configuration through the APP.

[0053] Step S104, controlling the desk lamp to switch to the lighting mode.

[0054] During implementation, those skilled in the art may implement each lighting mode in any suitable manner according to actual conditions, and the embodiments of the present disclosure are not limited thereto.

[0055] In some embodiments, the desk lamp may have multiple light sources, and each lighting mode may correspond to a different on state of each light source. For example, the light source of the desk lamp may include but is not limited to at least one of a spotlight light source and a floodlight light source. By turning on the spotlight light source and turning off the floodlight light source, the desk lamp can be switched to the spotlight mode; by turning on the floodlight light source and turning off the spotlight light source, the desk lamp can be switched to the floodlight mode; by turning on the spotlight light source and the floodlight light source, the desk lamp can be switched to the mixed mode.

[0056] In some embodiments, the desk lamp may have a light source with an adjustable illumination range, and each illumination mode may correspond to a different illumination range of the light source. For example, the illumination range of the light source may be reduced to achieve spotlight illumination, thereby switching the desk lamp to spotlight mode. For another example, the illumination range of the light source may be increased to achieve floodlight illumination, thereby switching the desk lamp to floodlight mode.

[0057] In the disclosed embodiment, a first image captured by a first image acquisition component of a desk lamp is acquired; based on the first image, an application scenario of the desk lamp is identified to obtain a current application scenario; based on the current application scenario, a lighting mode of the desk lamp is determined; and the desk lamp is controlled to switch to the lighting mode. In this way, the application scenario of the desk lamp can be automatically identified, and the lighting mode of the desk lamp can be better adapted to the current application scenario, thereby better meeting the user's desk lamp usage needs and improving the intelligence of the desk lamp.

[0058] In some embodiments, the above step S103 may include at least one of the following steps S111 to S113:

[0059] Step S111, when the current application scene is a writing scene, determining that the lighting mode of the desk lamp is a spotlight mode; wherein the spotlight mode represents turning on at least a spotlight light source of the desk lamp.

[0060] Here, the desk lamp may have a spotlight source for spotlighting the user's activity area. Since users usually need to concentrate highly when writing, when the current application scenario is a writing scenario, the lighting mode of the desk lamp can be determined to be a spotlight mode. In the spotlight mode, at least the spotlight source of the desk lamp is turned on, which can provide an immersive writing atmosphere for the user.

[0061] In some embodiments, in the spotlight mode, only the spotlight source of the desk lamp may be turned on, so that the user can better concentrate during writing.

[0062] In some embodiments, the desk lamp may also have a fill light source for providing appropriate fill light to the environment outside the spotlight irradiation area, and / or a floodlight source for floodlighting the user's activity area. In the spotlight mode, the spotlight source of the desk lamp can be turned on, and the fill light source and / or the floodlight source can be turned on to provide appropriate fill light to the environment outside the irradiation area of ​​the spotlight source. In this way, on the one hand, the user's concentration during writing can be improved through the irradiation of the spotlight source, and on the other hand, the fill light source and / or the floodlight source can reduce the damage to the eyes caused by the excessive difference in light intensity inside and outside the irradiation area of ​​the spotlight source, thereby protecting the user's eyesight.

[0063] Step S112, when the current application scenario is a reading scenario, determining that the lighting mode of the desk lamp is a floodlight mode; wherein the floodlight mode represents turning on at least the floodlight source of the desk lamp.

[0064] Here, the desk lamp may have a floodlight source for floodlighting the user's activity area. Since users usually need a more relaxed atmosphere during reading, when the current application scenario is a reading scenario, the lighting mode of the desk lamp may be determined to be a floodlight mode. In the floodlight mode, at least the floodlight source of the desk lamp is turned on, which can better provide a more relaxed reading atmosphere for the user.

[0065] In some embodiments, only the flood light source may be turned on in the flood mode.

[0066] In some embodiments, in the floodlight mode, the floodlight source can be turned on, and at the same time, a fill-in light source for providing appropriate fill-in light to the environment outside the illumination area of ​​the floodlight source can be turned on, so as to further improve the user experience.

[0067] Step S113, when the current application scenario is an electronic device operation scenario, determining that the lighting mode of the desk lamp is the floodlight mode.

[0068] Here, since the screen of the electronic device itself usually has a certain brightness when the user is using the electronic device for entertainment or learning, in this case, the lighting mode of the desk lamp can be determined as a floodlight mode, so that floodlighting can be provided for the area outside the screen of the electronic device, making it easier for the user to operate the electronic device.

[0069] In some embodiments, the method may further include one of the following: in response to receiving a voice light-on command, turning on at least one light source of the desk lamp; in response to receiving a voice light-off command, turning off the light source of the desk lamp. In this way, the light switch control can be conveniently performed.

[0070] In some embodiments, the desk lamp further includes a wireless charging component, and the method may further include: in response to detecting that a mobile phone is placed on the wireless charging component of the desk lamp, controlling the wireless charging component to charge the mobile phone.

[0071] In some embodiments, the method further includes: when it is detected that the current ambient light intensity is less than the first light intensity threshold or the current ambient light intensity is greater than the second light intensity threshold, outputting fifth prompt information for prompting the user to adjust the light intensity. The first light intensity threshold and the second light intensity threshold can be set by those skilled in the art according to actual conditions and are not limited here.

[0072] The first light intensity threshold is smaller than the second light intensity threshold.

[0073] In some embodiments, the desk lamp can be bound to the user's terminal device, and the method may include one of the following: collecting a video of the user's activities in front of the desk lamp; in response to receiving a real-time data viewing request sent by the terminal device, sending the currently collected first image frame sequence of the user's activities in front of the desk lamp to the terminal device; in response to receiving a data playback request sent by the terminal device, sending the historically collected second image frame sequence of the user's activities in front of the desk lamp to the terminal device. The terminal device may include but is not limited to at least one of a mobile phone, a tablet computer, a smart watch, a laptop computer, a desktop computer, etc. In this way, the user's activities in front of the desk lamp can be viewed in real time or traced back through the terminal device, thereby better meeting the user's usage needs. For example, the desk lamp can be bound to the mobile phone of the student's parents, and the parents can remotely watch in real time or remotely view the child's sitting posture, eye use and / or other learning conditions in front of the desk lamp afterwards.

[0074] In some embodiments, the method may further include: in response to receiving a homework upload operation by the user, using the first image acquisition component and / or the second image acquisition component to acquire a fifth image containing the user's homework content, and uploading the fifth image to a terminal device bound to the desk lamp and / or the cloud. In this way, it is convenient for parents and / or teachers to check the student's homework status.

[0075] The present disclosure provides a method for controlling a desk lamp, which can be executed by a processor of a computer device. Figure 2 As shown, the method includes the following steps S201 to S207:

[0076] Step S201, obtaining a first image captured by a first image capturing component of the desk lamp.

[0077] Step S202: Based on the first image, an application scene of the desk lamp is identified to obtain a current application scene.

[0078] Step S203: determining the lighting mode of the desk lamp based on the current application scenario.

[0079] Step S204, controlling the desk lamp to switch to the lighting mode.

[0080] Here, the above steps S201 to S204 correspond to steps S101 to S104 in the above embodiments respectively, and the implementation of the above steps S101 to S104 may be referred to during implementation.

[0081] Step S205, when the spotlight source of the desk lamp is turned on, obtaining the second image captured by the first image acquisition component.

[0082] Here, the second image may be the same as the first image or may be different from the first image, which is not limited in the embodiment of the present disclosure.

[0083] In some embodiments, after acquiring the second image, the second image may be corrected and / or perspective-distorted according to actual needs. For example, when the first image acquisition component is a camera, the second image may be corrected and / or perspective-distorted according to the intrinsic parameter coefficient of the camera.

[0084] Step S206: determining a first illumination area to be irradiated based on the second image.

[0085] Here, the first illumination area is the area to be illuminated by the spotlight source. During implementation, those skilled in the art may determine the first illumination area to be illuminated in any suitable manner based on the second image, and the embodiments of the present disclosure are not limited to this. For example, the user's line of sight direction, the position of the hand and / or the position of the book in the second image may be identified, and the first illumination area to be illuminated may be determined based on the identified line of sight direction, the position of the hand and / or the position of the book.

[0086] Step S207: adjusting the illumination direction of the spotlight source based on the first illumination area.

[0087] Here, the irradiation direction of the spotlight source may be adjusted based on the first irradiation area so that the spotlight source irradiates the first irradiation area.

[0088] In some embodiments, a motor and / or servo for controlling the direction of the spotlight source may be provided in the desk lamp. The irradiation direction of the spotlight source may be adjusted by adjusting the rotation angle of the motor and / or servo for controlling the direction of the spotlight source.

[0089] It is understandable that, when the user is using the desk lamp, the above steps S205 to S207 may be executed in a loop, thereby achieving continuous dynamic adjustment of the irradiation direction of the spotlight source.

[0090] In the disclosed embodiment, when the spotlight source of the desk lamp is turned on, the second image captured by the first image acquisition component is acquired; based on the second image, the first illumination area to be illuminated is determined; based on the first illumination area, the illumination direction of the spotlight source is adjusted. In this way, when the spotlight source is turned on, the illumination direction of the spotlight source can be dynamically adjusted according to the second image captured by the first image acquisition component, thereby better meeting the user's usage needs.

[0091] In some embodiments, the above method further includes the following step S211:

[0092] Step S211, identifying the gesture corresponding to the target hand in the second image to obtain the current gesture of the target hand.

[0093] Here, the target hand may be the hand of the current user identified from the second image. In implementation, any appropriate method may be used to identify the gesture corresponding to the target hand in the second image to obtain the current gesture of the target hand.

[0094] In some implementations, when only one hand is recognized in the second image, the hand can be directly determined as the target hand, and the gesture corresponding to the target hand can be recognized.

[0095] In some embodiments, when at least two hands are identified in the second image, the target hand belonging to the current user can be determined from the at least two hands according to the preset first configuration information and / or the correspondence between the hands and the target face in the second image. The first configuration information may include but is not limited to at least one of the dominant hand (such as the left hand or the right hand) of the current user, hand features, and facial features. The target face may be the face of the current user identified from the second image.

[0096] The above step S207 may include the following step S212:

[0097] Step S212: when the current gesture is the first preset gesture, adjusting the illumination direction of the spotlight source based on the first illumination area.

[0098] Here, the first preset gesture may be set by a person skilled in the art according to actual conditions, or may be set by a user according to personal needs. For example, the first preset gesture may include but is not limited to at least one of an OK gesture, a palm-up gesture, and the like.

[0099] In the above embodiment, the gesture corresponding to the target hand in the second image is recognized to obtain the current gesture of the target hand, and when the current gesture is the first preset gesture, the irradiation direction of the spotlight source is adjusted based on the first illumination area. In this way, the irradiation direction of the spotlight source can be adjusted by identifying the gesture of the target hand, thereby better meeting the user's usage needs.

[0100] In some embodiments, when the current gesture is not the first preset gesture, the irradiation direction of the spotlight source may be kept unchanged.

[0101] In some embodiments, before the above step S211, the above method further includes the following steps S221 to S223:

[0102] Step S221, detecting the human face in the second image to obtain at least one candidate human face, at least one first candidate hand, and the imaging size of each candidate human face in the second image.

[0103] Here, any suitable face detection algorithm may be used to detect the face in the second image, and the embodiments of the present disclosure are not limited to this.

[0104] The imaging size of the candidate face in the second image may include, but is not limited to, at least one of the area occupied by the candidate face in the second image, the number of pixels occupied, the size of the face detection frame corresponding to the candidate face, and the like.

[0105] Step S222: determining a target human face from the at least one candidate human face based on the imaging size.

[0106] Here, the target face may be determined from at least one candidate face in any suitable manner based on the imaging size, and the embodiments of the present disclosure are not limited to this.

[0107] In some implementations, the candidate human face with the largest imaging size among the at least one candidate human face may be determined as the target human face.

[0108] In some implementations, a candidate human face whose imaging size among at least one candidate human face is within a preset size range may be determined as a target human face.

[0109] The preset size range may be preset by those skilled in the art according to actual conditions. By comparing whether the image sizes of the candidate human faces are within the preset size range, a target human face may be determined from at least one candidate human face.

[0110] In some embodiments, the preset size range can be obtained by pre-calibrating the size of the human face in the image captured by the first image acquisition component during the normal use of the desk lamp by the user. For example, before the desk lamp leaves the factory, a suitable distance range from the human face to the first image acquisition component can be determined based on experience; within this distance range, the imaging size range of the human face in the imaging area of ​​the first image acquisition component is calculated, and the preset size range is determined based on the imaging size range.

[0111] In some embodiments, the preset size range may include at least one of an area range greater than a first preset area, a pixel number range greater than a preset number, a face detection frame size range greater than a second preset area, and the like.

[0112] In some embodiments, when there are multiple candidate human faces with imaging sizes within a preset size range among at least one candidate human face, the candidate human face with the largest pixel area among the multiple candidate human faces with imaging sizes within the preset size range can be determined as the target face.

[0113] In some embodiments, when there are multiple candidate human faces with imaging sizes within a preset size range among at least one candidate human face, the sum of the pixel areas occupied by the human head, torso, and hands corresponding to each candidate human face among the multiple candidate human faces with imaging sizes within the preset size range can be identified, and the candidate human face with the largest sum of pixel areas can be determined as the target face.

[0114] Step S223: Determine, from the at least one first candidate hand, a target hand that belongs to the same person as the target face.

[0115] Here, any appropriate method may be used to determine whether each first candidate hand and the target face belong to the same person, thereby determining the target hand, and the embodiments of the present disclosure are not limited to this.

[0116] In some implementations, the target hand that belongs to the same person as the target face can be determined by identifying the connection relationship between each first candidate hand and the target face.

[0117] In some implementations, a plurality of first matching relationships between faces and hands may be preset, and by querying the first matching relationship, a target hand that belongs to the same person as the target face may be determined.

[0118] In some embodiments, a second matching relationship between multiple facial features and hand features can be pre-set; by performing feature extraction on the target face, the facial features of the target face can be obtained; the second matching relationship can be queried using the facial features of the target face to obtain the target hand features that match the facial features of the target face, and the first candidate hand whose hand features match the target hand features is determined as the target hand that belongs to the same person as the target face.

[0119] In some embodiments, a neural network model for recognizing the relationship between faces and hands may be pre-trained, and a second image with first candidate hand information and a target face may be input into the neural network model to obtain a target hand belonging to the target face.

[0120] In the above embodiment, the face in the second image is detected to obtain at least one candidate face, at least one first candidate hand, and the imaging size of each candidate face in the second image; from the at least one candidate face, a target face whose imaging size is within a preset size range is determined; from the at least one first candidate hand, a target hand belonging to the same person as the target face is determined. In this way, the target hand of the current user can be determined quickly and accurately, thereby better meeting the user's usage needs and improving the intelligence of adjusting the irradiation direction of the spotlight source.

[0121] In some embodiments, the above step S221 may include the following step S231:

[0122] Step S231, performing human body semantic segmentation on the second image to obtain at least one candidate face, at least one first candidate hand, at least one human body trunk, and the imaging size of each candidate face in the second image.

[0123] Here, the human body trunk may include but is not limited to at least one of the arms, elbows, shoulders, chest, neck and the like.

[0124] In some embodiments, a deep learning model may be used to perform semantic segmentation of the human body in the second image to obtain at least one candidate face, at least one first candidate hand, at least one human torso, and the imaging size of each candidate face in the second image.

[0125] The above step S223 may include the following steps S232 to S233:

[0126] Step S232: Determine, from the at least one first candidate hand, at least one second candidate hand that is connected to the target face by a human body trunk.

[0127] Here, any appropriate method may be used to analyze the connection relationship between each first candidate hand and the target face, and the embodiments of the present disclosure are not limited to this.

[0128] In some implementations, a pixel connectivity analysis may be performed on each first candidate hand and the target face to determine whether there is a human body trunk connection between each first candidate hand and the target face.

[0129] Step S233: When the second candidate hand includes a left hand and a right hand, determine the target hand from the left hand and the right hand based on the preset first configuration information.

[0130] Here, when there is only one second candidate hand connected to the target face by a human body trunk, this second candidate hand can be determined as the target hand.

[0131] In the case where there are multiple second candidate hands connected to the target face by a human body trunk, including a left hand and a right hand, the target hand can be determined from the left hand and the right hand based on the preset first configuration information. The first configuration information can be preset by the user. In some embodiments, the first configuration information can include the user's dominant hand, and the left hand or the right hand can be determined as the target hand based on the user's dominant hand in the first configuration information. In some embodiments, the first configuration information can include the hand features of the user's dominant hand, and the one of the left hand and the right hand that matches the hand features of the dominant hand can be determined as the target hand.

[0132] In some embodiments, the first configuration information may include at least one correspondence between an application scenario and a hand, and based on the correspondence, one of the left hand or the right hand in the second candidate hand that matches the current application scenario may be determined as the target hand. For example, in the correspondence in the first configuration information, the writing scenario may correspond to the right hand, that is, the right hand in the second candidate hand may be determined as the target hand in the writing scenario, and the reading scenario may correspond to the right hand and the left hand, that is, any one of the left hand and the right hand in the second candidate hand may be determined as the target hand in the reading scenario.

[0133] In some implementations, the first configuration information may include a second target object, and the left hand or the right hand of the second candidate hand holding the second target object may be determined as the target hand. For example, the second target object may include but is not limited to at least one of a pen, a book, a mobile phone, etc.

[0134] In the above embodiment, the second image is subjected to semantic segmentation of the human body to obtain at least one candidate face, at least one first candidate hand, at least one human torso, and the imaging size of each candidate face in the second image; at least one second candidate hand connected to the target face by the human torso is determined from the at least one first candidate hand; when the second candidate hand includes a left hand and a right hand, the target hand is determined from the left hand and the right hand based on the preset first configuration information. In this way, the target hand of the current user can be determined quickly and accurately.

[0135] In some embodiments, the above step S206 may include the following steps S241 to S243:

[0136] Step S241, determining a first target object to be identified.

[0137] Here, the first target object may include but is not limited to at least one of an intersection between the user's line of sight and a desktop currently used by the user, a book, a pen, an electronic device, and the like.

[0138] During implementation, the first target object to be identified may be determined according to the current application scenario, or may be determined according to preset second configuration information, which is not limited in the embodiments of the present disclosure.

[0139] Step S242: Identify the first target object in the second image to obtain first position information of the first target object.

[0140] Step S243: determining the first illumination area based on the first position information of the first target object.

[0141] In some embodiments, the area where the first target object is located can be determined based on the first position information of the first target object, and the area, or the area and the adjacent area of ​​the area can be determined as the first illumination area. For example, when the first target object is the intersection between the user's line of sight and the user's currently used desktop, a book and / or a pen, the intersection between the user's line of sight and the user's currently used desktop, the area where the book and / or the pen are located can be determined as the first illumination area, and the intersection between the user's line of sight and the user's currently used desktop, the area where the book and / or the pen are located, and the adjacent area of ​​the area can also be determined as the first illumination area.

[0142] In some embodiments, the area where the first target object is located can be determined according to the first position information of the first target object, and the adjacent area of ​​the area can be determined as the first illumination area. For example, when the first target object is an electronic device, since the display screen of the electronic device usually has its own backlight, the adjacent area of ​​the area where the electronic device is located can be determined as the first illumination area.

[0143] It can be understood that the above steps S242 to S243 and step S207 can be executed in a loop, so as to realize the process of the spotlight source of the desk lamp following the first target object for illumination.

[0144] In the above embodiment, a first target object to be identified is determined; the first target object in the second image is identified to obtain first position information of the first target object; and the first illumination area is determined based on the first position information of the first target object. In this way, the illumination direction of the spotlight source of the desk lamp can be intelligently adjusted according to the position information of the first target object, thereby better meeting the lighting needs of the user and improving the intelligence of the desk lamp lighting.

[0145] In some embodiments, the above step S241 may include the following step S251 or step S252:

[0146] Step S251: determine the first target object based on the current application scenario and / or preset second configuration information.

[0147] In some implementations, the first target object may be determined based on the current application scenario. For example, when the current application scenario is a writing scenario, the first target object may be determined to be a pen or the intersection between the user's sight line and the desktop currently used by the user; when the current application scenario is a reading scenario, the first target object may be determined to be a book; when the current application scenario is an electronic device operation scenario, the first target object may be determined to be an electronic device. In this way, the lighting requirements in different application scenarios may be better adapted.

[0148] In some embodiments, the first target object may be determined based on preset second configuration information. The second configuration information may be default configuration information or configuration information configured according to user needs. For example, the user may configure the first object to be identified in the second configuration information in advance, and the first object may be obtained by reading the second configuration information, and the first object may be determined as the first target object.

[0149] In some implementations, the first target object may be determined in combination with the current application scenario and the second configuration information. For example, the user may configure the first object to be identified corresponding to at least one application scenario in the second configuration information in advance, and query the second configuration information using the current application scenario to obtain the first object matching the current application scenario, and determine the first object as the first target object.

[0150] In this way, based on the current application scenario and / or the preset second configuration information, the first target object can be determined conveniently and quickly, thereby further improving the intelligence of the desk lamp lighting.

[0151] Step S252: recognize the gesture corresponding to the target hand in the second image to obtain the current gesture of the target hand, and determine the first target object based on the current gesture.

[0152] In some implementations, a correspondence between at least one gesture and a first object to be identified may be preset, and the correspondence may be queried using the current gesture to determine a first object matching the current gesture, and the first object may be determined as the first target object.

[0153] In some embodiments, the gesture corresponding to the target hand may be a gesture for pointing to an object, and the first target object may be determined according to the object pointed to by the current gesture in the second image. For example, when the current gesture of the target hand points to a book, the book may be determined as the first target object; when the current gesture of the target hand points to the user's eyes, the intersection between the user's sight line and the desktop currently used by the user may be determined as the first target object.

[0154] In this way, the user can flexibly and conveniently indicate the first target object through gestures, thereby further improving the intelligence of the desk lamp lighting.

[0155] In some embodiments, the above step S251 may include the following step S261, step S262 or step S263:

[0156] Step S261, when the current application scene is a writing scene, determining that the first target object is the intersection between the user's line of sight and the desktop currently used by the user.

[0157] In this way, when the user uses the desk lamp to write, the irradiation direction of the spotlight source of the desk lamp can follow the intersection between the user's line of sight and the desktop currently used by the user, thereby better meeting the user's lighting needs during the writing process.

[0158] Step S262: when the current application scenario is a reading scenario, determining that the first target object is a book.

[0159] In this way, when the user uses the desk lamp to read, the irradiation direction of the spotlight source of the desk lamp can follow the book, thereby better meeting the user's lighting needs during the reading process.

[0160] Step S263: when the current application scenario is an electronic device operation scenario, determine the first target object based on the second configuration information.

[0161] In this way, since the first target object is determined based on the second configuration information, when the user operates the electronic device under the lighting of the desk lamp, the illumination direction of the spotlight source of the desk lamp can follow the position of the first target object configured in the second configuration information, thereby better meeting the lighting needs of the user in the process of operating the electronic device.

[0162] The present disclosure provides a method for controlling a desk lamp, which can be executed by a processor of a computer device. Figure 3A As shown, the method includes the following steps S301 to S308:

[0163] Step S301, obtaining a first image captured by a first image capturing component of the desk lamp.

[0164] Step S302: Based on the first image, identify the application scene of the desk lamp to obtain the current application scene.

[0165] Step S303: determining the lighting mode of the desk lamp based on the current application scenario.

[0166] Step S304, controlling the desk lamp to switch to the lighting mode.

[0167] Here, the above steps S301 to S304 correspond to steps S101 to S104 in the above embodiments respectively, and the implementation of the above steps S101 to S104 may be referred to during implementation.

[0168] Step S305, obtaining a third image captured by the second image capture component of the desk lamp; wherein, in a first direction, there is a first height difference between the second image capture component and the desktop currently used by the user, and the first direction is vertically downward.

[0169] Here, the second image acquisition component can be an image acquisition component set at any suitable position of the desk lamp. For example, the second image acquisition component can be set on the lamp head, the base and / or the connecting rod connecting the lamp head and the base, etc., and the embodiments of the present disclosure are not limited to this.

[0170] In some embodiments, the second image acquisition component and the first image acquisition component may be the same image acquisition component.

[0171] In some embodiments, the second image acquisition component and the first image acquisition component are two image acquisition components respectively arranged at different positions of the desk lamp. For example, the first image acquisition component can be arranged at the lamp head of the desk lamp, and the second image acquisition component can be arranged at the base of the desk lamp, or at a connecting rod for connecting the lamp head and the base.

[0172] The second image acquisition component can be used to acquire images of the environment in which the desk lamp is currently located to obtain a third image. It is understandable that, when a user uses the desk lamp, the third image can include the user currently using the desk lamp.

[0173] In some embodiments, after the third image is acquired, the third image may be corrected and / or subjected to perspective distortion according to actual needs. For example, when the second image acquisition component is a camera, the second image may be corrected and / or subjected to perspective distortion according to the intrinsic parameter coefficients of the camera.

[0174] In implementation, the number of the third images may be one or more than two, which is not limited here. When the number of the third images is more than two, the more than two third images may be a sequence of image frames captured by the image capture component.

[0175] The first height difference between the second image acquisition component and the desktop currently used by the user may be preset by the user, or may be detected by a distance sensor, a distance detector, etc., which are arranged at the location of the second image acquisition component.

[0176] Step S306: Based on the third image, determine a first distance between the user's eye and the second image acquisition component, and determine a first angle between a second direction extending from the eye to the second image acquisition component and the first direction.

[0177] Here, based on the third image, the first distance and the first angle may be determined in any suitable manner, and the embodiments of the present disclosure are not limited to this.

[0178] In some embodiments, the coordinates of the user's eye in the real physical world can be determined based on the coordinates of the user's eye in the third image and the camera intrinsic parameter coefficient of the second image acquisition component, so that the first distance between the user's eye and the second image acquisition component can be determined, and the first angle between the second direction extending from the eye to the second image acquisition component and the first direction can be determined.

[0179] For example, suppose the pixel width and height of the third image are w pix and h pix , the corresponding width and height of the real physical world are w and h respectively, then there is a mapping relationship between the third image and the physical world as shown in the following formula 1-1:

[0180]

[0181] Among them, z is the depth information from the physical plane to the pixel plane, f x 、f y 、c x and c y is the camera internal parameter coefficient. Assume that the coordinates of the user's eyes in the third image are (x pix ,y pix ), then the coordinates (x, y, z) of the eye in the physical space and the coordinates (x pix ,y pix ) have the following mapping relationship as shown in Formula 1-2:

[0182]

[0183] Based on the above formula 1-2, the coordinates (x, y, z) of the eye in the physical space can be calculated, and thus according to the coordinates (x, y, z) of the eye in the physical space, the distance d from the eye to the second image acquisition component in the physical space can be determined.

[0184] For example, the first distance d from the eye to the second image acquisition component in the physical space may be calculated in the manner shown in the following formula 1-3:

[0185]

[0186] Step S307: determining a second height difference between the eye and the second image acquisition component in the first direction based on the first distance and the first angle.

[0187] Here, since the ratio of the second height difference to the first distance is the cosine value of the first angle, the product of the first distance and the cosine value of the first angle is the second height difference.

[0188] Step S308: When it is determined that the second distance between the eye and the desktop is less than a preset distance threshold based on the first height difference and the second height difference, output first prompt information for prompting the user to adjust the sitting posture.

[0189] Here, the second distance between the eyes and the desktop currently used by the user is the sum of the first height difference and the second height difference. The preset distance threshold can be a suitable viewing distance that is beneficial to protecting the eyes and is pre-set by those skilled in the art according to actual conditions.

[0190] The first prompt information may be any suitable information for prompting the user to adjust the sitting posture. For example, the first prompt information may include but is not limited to at least one of voice prompt information, indicator light information, message reminder, vibration information, buzzer prompt information, etc.

[0191] In some embodiments, the information output component of the desk lamp can be controlled to output the first prompt information for prompting the user to adjust the sitting posture. The information output component may include but is not limited to at least one of a display screen, a speaker, an indicator light, a buzzer, etc.

[0192] In the disclosed embodiment, a third image captured by the second image acquisition component of the desk lamp is obtained; wherein, in the first direction, there is a first height difference between the second image acquisition component and the desktop currently used by the user, and the first direction is vertically downward; based on the third image, a first distance between the user's eyes and the second image acquisition component is determined, and a first angle between the second direction extending from the eye to the second image acquisition component and the first direction is determined; based on the first distance and the first angle, a second height difference between the eye and the second image acquisition component in the first direction is determined; when it is determined based on the first height difference and the second height difference that the second distance between the eye and the desktop is less than a preset distance threshold, a first prompt message for prompting the user to adjust the sitting posture is output. In this way, the second distance between the user's eyes and the desktop can be monitored in real time, and when the second distance is less than the preset distance threshold, the first prompt message is output to prompt the user to adjust the sitting posture, thereby urging the user to use the eyes more reasonably and enhancing the protection of the user's eyes.

[0193] In some embodiments, the above step S306 may include the following steps S311 to S313:

[0194] Step S311, determining a second angle between the optical axis direction of the second image acquisition component and the opposite direction of the second direction.

[0195] Step S312: determine a third angle between the optical axis direction and the first direction.

[0196] Step S313: determine the first angle based on the second angle and the third angle.

[0197] Here, any suitable geometric algorithm may be used to determine the second angle between the optical axis direction of the second image acquisition component and the opposite direction of the second direction, and the third angle between the optical axis direction and the first direction, which is not limited in the embodiments of the present disclosure.

[0198] From the geometric relationship, it can be known that the first angle is the supplementary angle of the second angle plus the third angle, that is, the first angle is the angle obtained by subtracting the second angle and the third angle from the straight angle (180°).

[0199] For example, the second image acquisition component is a camera mounted on the connecting rod of a desk lamp, see Figure 3B As shown, BK is the desktop; MN is the base of the desk lamp, and the top N of the base is at a height of l relative to BK of the desktop. 0 NO is the connecting rod used to connect the lamp holder and the base. The length of the connecting rod is l 1 The angle between the image and the desktop is θ. The pixel height of the third image is h pix , which can be a fixed value at the factory. The camera is installed at point O on the light pole NO, and the projection of point O on the desktop is H. The vertical field of view of the camera is limited by rays OC and OD. Since the camera is fixedly installed on the light pole, the angle β between rays OC and ON is a fixed value. The vertical field of view (FOV) of the camera is fixed at the factory and is set to α; the main optical axis of the camera is ray OA, then ∠AOC=∠AOD=α / 2. Since point A is on the main optical axis, the vertical pixel coordinate of point A is h pix / 2. The user's eyes are located at point E, OE is the first distance between the user's eyes and the camera, and the vertical pixel coordinate of point E in the camera imaging is y pix , coordinate y pix It can be identified by the deep learning image recognition model. Extend EO in the opposite direction and intersect with the desktop at point K. The projection of point E on the desktop is B. Therefore, the second angle is ∠AOE = μ; the third angle is The first angle is ∠KEB=∠KOH; wherein ∠HON satisfies the following formula 1-4:

[0200] ∠HON=π / 2-θ (1-4);

[0201] ∠KOH satisfies the following formula 1-5:

[0202] ∠KOH=π-μ-α / 2-β-∠HON=π / 2+θ-μ-α / 2-β (1-5);

[0203] The first height difference OH satisfies the following formula 1-6:

[0204] OH=l 1 sin(θ)+l 0 (1-6).

[0205] In addition, since point D is a point on the upper edge of the image, the distance EA between point E and point A, and the distance DA between point D and point A satisfy the following formula 1-7:

[0206]

[0207] Among them, the vertical pixel coordinate of point D is 0, combined with the vertical pixel coordinate of point E mentioned above is y pix , the vertical pixel coordinate of point A is h pix / 2, therefore, it can be determined that the value μ of the second angle ∠AOE can satisfy the following formula 1-8:

[0208]

[0209] Therefore, the value μ of the second angle ∠AOE can be determined by the following formula 1-9:

[0210]

[0211] In this way, the distance EB from the user's eyes to the desktop can be determined as shown in the following formula 1-10:

[0212] EB=OH+OEcos(∠KEB)=l 1 sin(θ)+l 0 +OE·sin(μ+α / 2+β-θ) (1-10).

[0213] It should be noted that the angle β between the ray OC and the ray ON, and the angle θ between the connecting rod and the desktop can be factory settings, or can be determined by the user after adjustment according to actual needs, and the embodiments of the present disclosure are not limited to this.

[0214] In some embodiments, the inclination angle of the connecting rod of the desk lamp is fixed, that is, the angle θ between the connecting rod and the desktop can be fixed after factory setting. The angle θ between the connecting rod and the desktop can be obtained by reading the factory configuration information of the desk lamp.

[0215] In some embodiments, the inclination angle of the connecting rod of the desk lamp is adjustable, and the current inclination angle of the connecting rod can be obtained by an angle sensor disposed on the connecting rod, thereby determining the angle θ between the connecting rod and the desktop.

[0216] In some embodiments, the installation angle of the camera on the connecting rod is fixed, that is, the angle β between the ray OC and the ray ON is fixed after factory setting, and the angle β can be obtained by reading the factory configuration information of the desk lamp.

[0217] In some embodiments, the installation angle of the camera on the connecting rod may be adjustable, and the user may adjust the installation angle of the camera on the connecting rod according to actual needs. By setting an angle sensor at the camera, the current installation angle of the camera may be obtained to determine the angle β.

[0218] In some embodiments, the outputting of the first prompt information for prompting the user to adjust the sitting posture in step S308 may include the following steps S321 to S323:

[0219] Step S321, determining second prompt information; the second prompt information is used to instruct a preset language model to generate the first prompt information.

[0220] Here, the preset language model can be any suitable language model pre-set by technicians in this field according to actual conditions, such as at least one of the large language models ChatGPT-3.5, ChatGPT-4, etc.

[0221] The second prompt information may be pre-configured by the user, or may be a system default, or may be determined according to the current application scenario, which is not limited in the embodiments of the present disclosure.

[0222] The second prompt information may be any suitable information for instructing the language model to generate the first prompt information. The second prompt information may be implemented in a form including but not limited to at least one of instructions, voice, text, and the like.

[0223] For example, the second prompt information may include but is not limited to "generating prompt information for prompting the user to adjust the sitting posture according to the image", "generating prompt information for reminding the user in this image to adjust the sitting posture", etc.

[0224] Step S322: Send the third image and the second prompt information to the language model.

[0225] Here, the third image and the second prompt information can be sent directly to the language model, or the third image and / or the second prompt information can be pre-processed by image enhancement, image noise reduction, semantic error correction, etc. before being sent to the language model. The embodiments of the present disclosure are not limited to this.

[0226] In some embodiments, the speech model can be deployed in the processor of the desk lamp, so that the first prompt information generated based on the third image and the second prompt information can be generated by using the language model running locally on the processor. In this way, the communication cost can be reduced and the data transmission efficiency can be improved.

[0227] In some embodiments, the language model can be deployed in a server, and the processor of the desk lamp can send the third image and the second prompt information to the language model on the server, so that the language model running on the server generates the first prompt information based on the third image and the second prompt information. Since the computing resources on the server are usually abundant, the operating efficiency of the language model can be improved, and the processing pressure of the processor of the desk lamp can be reduced.

[0228] Step S323: in response to receiving the first prompt information generated by the language model based on the third image and the second prompt information, output the first prompt information.

[0229] Here, after receiving the third image and the second prompt information, the language model can generate and return the first prompt information for prompting the user to adjust the sitting posture according to the third image and the second prompt information.

[0230] After receiving the first prompt information returned by the language model, the processor executing the method can output the first prompt information. During implementation, the processor can directly output the first prompt information returned by the language model, or can reprocess the first prompt information returned by the language model before outputting it. The reprocessing of the first prompt information returned by the language model can include but is not limited to operations such as saving, adding some leading words, modal particles, etc.

[0231] In the above embodiment, a preset language model is used to generate the first prompt information for prompting the user to adjust the sitting posture. Since the language model can generate richer and more reasonable first prompt information in combination with the understanding of the third image, it can bring a better user experience to the user.

[0232] In some embodiments, the method may further include the following steps S331 to S333:

[0233] Step S331, obtaining multimedia information for interacting with a preset language model.

[0234] Step S332: sending the multimedia information to a language model.

[0235] Step S333: in response to receiving the response information generated by the language model based on the multimedia information, controlling the information output component of the desk lamp to output the response information.

[0236] Here, the multimedia information may include but is not limited to at least one of information collected by an information collection component of the desk lamp, information generated by a processor executing the method, and the like.

[0237] In some embodiments, the information acquisition component may include but is not limited to an audio acquisition component, a first image acquisition component, a second image acquisition component and / or a text input component, and the multimedia information may include but is not limited to audio information acquired by the audio acquisition component of the desk lamp, a fourth image acquired by the second image acquisition component and / or text information input by the user through the text input component. Among them, the audio acquisition component and the text input component can be set at any suitable position on the desk lamp, for example, the audio acquisition component can be set at at least one of the base, connecting rod, lamp head, etc. of the desk lamp. Here, the audio information may include but is not limited to at least one of the user's voice, environmental sound, recording played by the user, etc. The text information may be at least one of the text instructions, text questions, etc. input by the user. The fourth image may be any suitable image obtained by using the second image acquisition component to acquire an image of the environment in which the desk lamp is currently located. It can be understood that when a user uses the desk lamp, the fourth image may include the user currently using the desk lamp. In some embodiments, after the fourth image is acquired, the fourth image may be corrected and / or perspective distorted according to actual needs. For example, when the second image acquisition component is a camera, the fourth image may be corrected and / or subjected to perspective distortion according to the intrinsic parameter coefficients of the camera.

[0238] The response information generated by the language model based on the multimedia information can be a reply information to the user's voice and / or the input text information, or it can be a chat information generated for the current user's voice, environmental sound, recording played by the user, input text information and / or the fourth image, which is not limited here. In implementation, the implementation method of the response information can include but is not limited to at least one of voice prompt information, indicator light information, message reminder, vibration information, buzzer prompt information, etc.

[0239] For example, the user can ask questions to the desk lamp, the audio collection component can collect the voice information of the user's current question, the processor can send the voice information to the language model, the language model can generate corresponding reply information based on the voice information, and after receiving the reply information, the processor can control the information output component to output the reply information, thereby completing the dialogue interaction between the desk lamp and the user.

[0240] In some embodiments, the multimedia information may include information generated by the processor executing the method when it is detected that the user's behavior meets the preset behavior condition, and the response information generated by the language model based on the multimedia information may include prompt information for prompting the user to adjust the behavior. The preset behavior condition may include but is not limited to at least one of the second distance between the user's eyes and the desktop being less than a preset distance threshold, the user's pen holding posture being incorrect, and the user's writing concentration being low. During implementation, the preset behavior condition may be a factory default or may be set by the user according to actual needs, which is not limited here.

[0241] For example, when it is detected that the second distance between the user's eyes and the desktop is less than a preset distance threshold, the processor can generate second prompt information for instructing the language model to generate first prompt information, and send the second prompt information and the fourth image captured by the second image acquisition component to the language model, wherein the first prompt information is used to prompt the user to adjust the sitting posture, and the language model can generate first prompt information based on the second prompt information and the fourth image, and return the first prompt information as response information to the processor, so that the processor controls the information output component of the desk lamp to output the first prompt information.

[0242] For another example, when it is detected that the user has an incorrect pen-holding posture, the processor may generate fourth prompt information for instructing the language model to generate third prompt information, and send the fourth prompt information and the fourth image to the language model, wherein the third prompt information is used to prompt the user to adjust the pen-holding posture, and the language model may generate the third prompt information based on the fourth prompt information and the fourth image, and return the third prompt information as response information to the processor, so that the processor controls the information output component of the table light to output the third prompt information. The fourth prompt information can be any suitable information for instructing the language model to generate the third prompt information. The implementation form of the fourth prompt information may include but is not limited to at least one of instructions, voice, text, etc. For example, the fourth prompt information may include but is not limited to "generating prompt information prompting the user to adjust the pen-holding posture based on the image", "generating prompt information for reminding the user in this image to adjust the pen-holding posture", etc.

[0243] In the above embodiment, using a language model to generate and output response information based on multimedia information can provide users with a richer interactive experience, thereby better meeting user needs.

[0244] The present disclosure provides a desk lamp, such as Figure 4AAs shown, the desk lamp 400 includes: a base 410, a lighting assembly 420, a first image acquisition assembly 430, a control assembly (not shown in the figure), and a connecting portion 440 connecting the base 410 and the lighting assembly 420; wherein,

[0245] The control component is used to: obtain the first image captured by the first image acquisition component 430; based on the first image, identify the application scene of the desk lamp to obtain the current application scene; based on the current application scene, determine the lighting mode; control the lighting component 420 to switch to the lighting mode.

[0246] The connection part 440 may include but is not limited to at least one of a connecting rod, a connecting shaft, a supporting frame, etc.

[0247] It is understandable that the lighting assembly 420 can be accommodated in the lamp head of the desk lamp 400, or can directly serve as the lamp head of the desk lamp 400, which is not limited here.

[0248] The first image acquisition component 430 can be set at any suitable position of the desk lamp 400. In implementation, the first image acquisition component 430 can be set on the lighting component 420, the base 410 and / or the connecting portion 440, etc., and the embodiment of the present disclosure is not limited to this. For example, the lighting component 420 may include a spotlight source 421, and the first image acquisition component 430 may be set at an additional device of the spotlight source 421 (such as a lamp tube).

[0249] In some embodiments, see Figure 4A The lighting component 420 includes a spotlight source 421 and / or a floodlight source 422, and the control component is also used for at least one of the following: when the current application scenario is a writing scenario, determining the lighting mode to be a spotlight mode, wherein the spotlight mode represents that at least the spotlight source 421 is turned on; when the current application scenario is a reading scene, determining the lighting mode to be a floodlight mode, wherein the floodlight mode represents that at least the floodlight source 422 is turned on; when the current application scenario is an electronic device operation scenario, determining the lighting mode to be a floodlight mode.

[0250] In some embodiments, the control component is also used to: acquire a second image captured by the first image acquisition component 430 when the spotlight source 421 is turned on; determine a first illumination area to be irradiated based on the second image; and adjust an irradiation direction of the spotlight source 421 based on the first illumination area.

[0251] In some embodiments, the control component is also used to: identify the gesture corresponding to the target hand in the second image to obtain the current gesture of the target hand; when the current gesture is the first preset gesture, adjust the illumination direction of the spotlight source 421 based on the first illumination area.

[0252] In some embodiments, before identifying the gesture corresponding to the target hand in the second image and obtaining the current gesture of the target hand, the control component is also used to: detect the face in the second image to obtain at least one candidate face, at least one first candidate hand, and the imaging size of each candidate face in the second image; determine the target face from at least one candidate face based on the imaging size; and determine the target hand that belongs to the same person as the target face from at least one first candidate hand.

[0253] In some embodiments, the control component is also used to: perform human body semantic segmentation on the second image to obtain at least one candidate face, at least one first candidate hand, at least one human torso, and the imaging size of each candidate face in the second image; determine at least one second candidate hand that has a human torso connection with the target face from at least one first candidate hand; and when the second candidate hands include a left hand and a right hand, determine the target hand from the left hand and the right hand based on the preset first configuration information.

[0254] In some embodiments, the control component is further used to: determine a first target object to be identified; identify the first target object in the second image to obtain first position information of the first target object; and determine a first illumination area based on the first position information of the first target object.

[0255] In some embodiments, the control component is also used for one of the following: determining the first target object based on the current application scenario and / or preset second configuration information; identifying the gesture corresponding to the target hand in the second image to obtain the current gesture of the target hand, and determining the first target object based on the current gesture.

[0256] In some embodiments, the control component is also used for one of the following: when the current application scenario is a writing scenario, determining the first target object as the intersection between the user's line of sight and the desktop currently used by the user; when the current application scenario is a reading scene, determining the first target object as a book; when the current application scenario is an electronic device operation scene, determining the first target object based on the second configuration information.

[0257] In some embodiments, see Figure 4BThe desk lamp 400 also includes a second image acquisition component 450 and an information output component (not shown in the figure), and the control component is also used to: obtain a third image acquired by the second image acquisition component of the desk lamp; wherein, in a first direction, there is a first height difference between the second image acquisition component and the desktop currently used by the user, and the first direction is vertically downward; based on the third image, determine a first distance between the user's eyes and the second image acquisition component, and determine a first angle between a second direction extending from the eye to the second image acquisition component and the first direction; based on the first distance and the first angle, determine a second height difference between the eye and the second image acquisition component in the first direction; when it is determined that the second distance between the eye and the desktop is less than a preset distance threshold based on the first height difference and the second height difference, the control information output component outputs a first prompt message for prompting the user to adjust his sitting posture.

[0258] In some embodiments, the control component is also used to: determine a second angle between the optical axis direction of the second image acquisition component and the opposite direction of the second direction; determine a third angle between the optical axis direction and the first direction; and determine the first angle based on the second angle and the third angle.

[0259] In some embodiments, the control component is also used to: determine second prompt information, the second prompt information is used to instruct a preset language model to generate first prompt information; send the third image and the second prompt information to the language model; in response to receiving the first prompt information generated by the language model based on the third image and the second prompt information, the control information output component outputs the first prompt information.

[0260] In some embodiments, the control component is also used to: obtain multimedia information for interacting with a preset language model; send the multimedia information to the language model; and in response to receiving response information generated by the language model based on the multimedia information, control the information output component of the desk lamp to output the response information.

[0261] The embodiment of the present disclosure provides a multifunctional healthy eye protection desk lamp, which has at least the following functions:

[0262] 1) Provide high-quality lighting effects that meet national standards in terms of low blue light, low flicker, high color rendering, and excellent uniformity.

[0263] 2) Provide two basic lighting modes - floodlight mode and spotlight mode. Floodlight mode means that the desk lamp provides high-quality lighting in a larger area, which can provide lighting for writing documents, indoor walking activities, etc. Spotlight mode means that the desk lamp provides high-quality lighting in a smaller area, forming a clear lighting contrast inside and outside the illuminated area, thus providing an immersive lighting atmosphere, making it easier for people to concentrate on doing things that require brainpower.

[0264] 3) Provide a light-chasing function. In the spotlight mode, the illumination area of ​​the spotlight source can be set to move with the movement of the hand or the line of sight, so that the occupant (i.e. the user of the desk lamp) can concentrate on work in the spotlight mode without worrying about the lack of light in the current focus area. This function is referred to as the "light-chasing" function below.

[0265] 4) Based on the two basic lighting modes of floodlight mode and spotlight mode, a combination of lighting modes can also be performed. For example, a spotlight mode + weak floodlight mode is provided, in which the spotlight mode is used to provide an immersive lighting atmosphere, while the weak floodlight mode can improve the lighting contrast between the spotlight area and the outside of the area.

[0266] 5) Provide a sitting posture reminder function. People in front of a desk lamp, such as primary and secondary school students, can easily sit crookedly without realizing it. Over time, a crooked sitting posture will affect the health of the spine and indirectly affect the health of the eyes. The desk lamp in the disclosed embodiment provides a sitting posture reminder function, which can effectively alleviate this health problem.

[0267] 6) Provide an estimate of the distance between the human eye and the desktop (hereinafter referred to as the eye-desk distance). Some primary and secondary school students lower their heads unconsciously when writing, and their eyes are relatively close to the desktop, which increases the possibility of myopia or worsens the degree of myopia. In another case, some students already have myopia and have to keep their eyes very close to the desktop, but the students themselves do not know it, and some parents simply attribute it to the child's poor sitting posture, without thinking about the cause of myopia, thus easily missing the best intervention time. The desk lamp in the disclosed embodiment provides an eye-desk distance estimation function, which can effectively alleviate this problem.

[0268] 7) Provide automatic scene recognition function. The person sitting in front of the desk lamp can write, read, or do other things. Generally speaking, when doing something that consumes more brainpower and requires an immersive atmosphere, you can use the spotlight mode, while reading or other relaxing things can use the floodlight mode.

[0269] 8) Provide voice-controlled lights on and off and other voice control functions. Many families have not yet installed voice-controlled lighting or induction lighting, which means that sometimes they have to turn on the lights in the dark, but turning on the lights in the dark may lead to dangerous situations such as tripping. In addition, some families share study rooms and bedrooms. After children or adults use traditional table lamps or ordinary lighting lamps (such as LED lights on the ceiling), they need to turn off the lights before going to bed, but turning off the lights and going to bed will cause the problem of finding the bed in the dark, which may lead to dangerous situations such as tripping over the lamp. The table lamp in the embodiment of the present disclosure provides basic voice control functions, including voice-controlled lights on and off, which can effectively reduce the problem of turning on and off lights in the dark.

[0270] 9) Provide the function of wireless charging for mobile phones. Charging is a common requirement for modern mobile phones. The current mainstream charging method in China is still wired charging. The plugging and unplugging of wires and the adaptation of various interfaces are relatively troublesome. In comparison, wireless charging is more convenient. The desk lamp in the embodiment of the present disclosure provides a wireless charging function, which is multi-purpose. It is convenient for charging mobile phones and saves the need to purchase chargers separately, which is conducive to environmental protection.

[0271] 10) Provide an ambient brightness detection function. When the indoor lighting environment is too dark or too bright, it is usually not suitable for reading or writing, but people may not notice it or may notice it but not realize it. The desk lamp in the disclosed embodiment provides an ambient brightness detection function. When it detects that the indoor lighting environment is too dark or too bright, it can output corresponding prompt information for reminder.

[0272] 11) Provide real-time viewing and backtracking functions. The desk lamp in the disclosed embodiment can be bound to the user's mobile phone, for example, to the mobile phone of the student's parent, so that the parent can remotely observe in real time or remotely view the child's sitting posture, eye use and / or other learning conditions in front of the lamp afterwards.

[0273] 12) Provide homework upload function. After finishing the homework, students can directly use the camera on the desk lamp in the embodiment of the present disclosure (corresponding to the first image acquisition component and / or the second image acquisition component in the aforementioned embodiment) to upload the homework, and parents or teachers can see the homework.

[0274] The multifunctional healthy eye protection desk lamp provided by the embodiment of the present disclosure includes a base, a connecting rod, a lamp head, a floodlight source and its additional devices, a spotlight source and its additional devices, an embedded computer (corresponding to the control component in the aforementioned embodiment), a light-chasing camera (corresponding to the first image acquisition component in the aforementioned embodiment), a sitting posture detection camera (corresponding to the second image acquisition component in the aforementioned embodiment), a voice input and output device (corresponding to the audio acquisition component in the aforementioned embodiment), a network communication device, a light-chasing power device, a reminder device (corresponding to the information output component in the aforementioned embodiment), a wireless charging device, an ambient brightness detection module, a light emitting diode (LED) lamp driver, a power supply device, etc.; wherein,

[0275] Base: refers to the lamp holder placed on a desktop or other flat surface, used to support the entire desk lamp body.

[0276] Connecting rod: refers to the connecting part between the base and the lamp holder. The connecting rod can be one section or multiple sections, and the multiple sections can generally rotate with each other.

[0277] Lamp holder: refers to the shell used to accommodate the floodlight source and its accessories and the spotlight source and its accessories.

[0278] Floodlight source and its additional devices: refers to the light source used to generate floodlight and the additional devices that optimize the lighting effect of the floodlight source. The floodlight source is usually a light strip with multiple LED lamp beads connected in series and / or in parallel, which can emit light after being connected to a compliant power supply. Of course, the floodlight source can also be provided by other light sources such as incandescent lamps, fluorescent lamps, etc. The additional devices of the floodlight source may include reflective films, light guide plates, diffuser plates, heat sinks, control buttons and other objects. The additional devices of the floodlight source can change the direction of light, improve the uniformity of light, adjust the color temperature and brightness, etc.

[0279] Spotlight source and its additional devices: refers to the light source used to generate spotlight and additional devices to optimize the spotlight effect. Spotlight source is usually a single high-power LED lamp bead with a lens. Of course, it can also be undertaken by multiple LED lamp beads, or by other light sources such as incandescent lamps. Additional devices of spotlight source can include lamp tube, heat sink, control buttons and other objects, among which the lamp tube can improve the spotlight effect.

[0280] Embedded computer: refers to a computing device with certain computing, storage, and communication capabilities, which generally includes processors, memory, storage, and other components. Embedded computers can process image and voice information input, as well as network communications and other operations.

[0281] Light-chasing camera: refers to a camera used to capture images of hands, books, etc. (corresponding to the first image or the second image in the above-mentioned embodiment). In some embodiments, the light-chasing camera can be the same camera as the sitting posture detection camera to save costs.

[0282] Sitting posture detection camera: refers to a camera used to collect images of a person's body (corresponding to the third image in the aforementioned embodiment).

[0283] Voice input and output device: refers to electronic devices used to convert human voice into electrical signals and convert electrical signals into sound, such as microphones, sound cards, speakers, etc.

[0284] Network communication device: refers to electronic devices used to connect to the Internet, such as network cards, wireless LAN chips, Bluetooth chips, etc.

[0285] Light chasing power device: refers to the motor or servo used to control the direction of the spotlight source.

[0286] Reminder device: used to output reminder information. For example, when the sitting posture of the person in front of the lamp is incorrect or the distance between the eyes and the desk is too close, the user can be reminded through a voice output device. In order to reduce the sound interference to the user, the user can also be reminded through devices such as an LCD screen and a light-emitting button.

[0287] Wireless charging device: used to provide wireless charging function.

[0288] Ambient brightness detection device: used to detect ambient brightness.

[0289] LED driver: used to power floodlights and spotlights, and / or provide brightness and color temperature control.

[0290] Power supply device: refers to the electronic device used to provide electrical energy for the desk lamp.

[0291] Figure 5A A schematic diagram of the structure of a desk lamp provided in an embodiment of the present disclosure is shown in FIG. Figure 5A As shown, the desk lamp 500 at least includes a base 510, a connecting rod 520, a floodlight source 530, a spotlight source 540, a floodlight servo 550 for controlling the direction of the floodlight source 530, a spotlight servo 560 for controlling the direction of the spotlight source 540, a tracking camera 570, and a sitting posture detection camera 580.

[0292] The following is a description of the implementation process of some functions of the desk lamp provided by the embodiment of the present disclosure.

[0293] Process 1: Gesture light tracking function.

[0294] 1) In spotlight mode, the tracking camera collects photos of hands or books on the table.

[0295] 2) The embedded computer recognizes the position of the hand or book from the photo.

[0296] 3) The embedded computer controls the light-chasing power device to drive the spotlight source to rotate a certain angle, so that the illumination area of ​​the spotlight source includes the position of the hand or the book (the book here can also include the exercise book), or the illumination of the spotlight area light source is centered on the position of the hand or the book.

[0297] Figure 5B and Figure 5C A schematic diagram of the illumination area of ​​a spotlight source of a desk lamp provided in an embodiment of the present disclosure, such as Figure 5B and Figure 5C As shown, the embedded computer can control the light-chasing power device (eg, the focusing servo 560 ) to rotate at different angles, so that the focusing light source 540 has different irradiation areas (eg, irradiation area 561 and irradiation area 562 ).

[0298] Considering that only relying on the position of a single hand or book may not fully reflect the true intention of the person sitting in front of the desk lamp, for example, if there are multiple hands or multiple books on the table at the same time, choosing which hand or book to track is a problem. Or if the person uses his hands to get other items beside him, it does not make much sense to track the hand at this time. Therefore, in some embodiments, a setting function for the user's dominant hand can be provided. When the user sets the dominant hand to the left hand, the left hand will be tracked; when the user sets the dominant hand to the right hand, the right hand will be tracked. The hand to be tracked is hereinafter referred to as the "hand to be tracked" (corresponding to the target hand in the aforementioned embodiment).

[0299] In some implementations, when the user just sits down, the characteristics of the user's left or right hand and body characteristics can be identified and remembered through the relationship between the body sitting posture and the hands. In the subsequent final process, if other people's hands appear on the table at the same time, the embedded computer will use the deep learning image recognition model to determine which hand belongs to the user's dominant hand, and then determine to track this hand.

[0300] In some implementations, when the hand to be tracked reaches for other objects or performs other actions, if the hand leaves the table or is out of the camera's field of view, tracking is suspended.

[0301] In some embodiments, when a hand and a book appear at the same time, at least one of the following two tracking logics can be used: one is to use the scene automatic recognition function. If a writing scene is recognized, the hand is tracked; if a reading scene is recognized, the book is tracked; if it is other scenes that are difficult to judge, the user manually switches to track the hand, the book, or not track; the second is to provide a manual setting function, and the user can choose to track the hand, the book, or not track.

[0302] In some embodiments, the user can set the tracking of a specific gesture (such as an OK gesture) and ignore other gestures. In this way, when the user makes this specific gesture, the embedded computer automatically adjusts the spotlight source to the specified position. For other gestures, the embedded computer may not control the spotlight to turn, thereby greatly reducing the misjudgment of gestures.

[0303] It should be noted that the above-mentioned implementation modes can be used in combination or individually.

[0304] In some embodiments, when the occupant does not need the gesture light chasing function, such as when the occupant feels that the gesture light chasing will interfere with his or her thinking, the desk lamp in the disclosed embodiment can provide a quick stop gesture light chasing function. For example, a stop gesture (such as a clenched fist) can be set, and when the stop gesture is detected, the gesture light chasing is stopped; when a start gesture (such as an OK gesture) is detected, the gesture light chasing is turned on. For another example, a first button can be set on the additional device of the focusing light source to turn off and on the gesture light chasing. It should be noted that the start gesture here and the start gesture below can correspond to the first preset gesture in the aforementioned embodiment.

[0305] Process 2: Line of sight light tracking function.

[0306] 1) The sitting posture monitoring camera collects images of the head, especially the eyes.

[0307] 2) The embedded computer uses a deep learning model to identify the direction of the eye's gaze.

[0308] 3) Generate a straight line pointing to the desktop along the line of sight.

[0309] 4) Determine the intersection of the straight line and the desktop. This intersection is the center of the spotlight area.

[0310] 5) The embedded computer controls the light-chasing power device to drive the spotlight source to rotate a certain angle so that the spotlight area is aligned with the center.

[0311] It should be noted that the human sight may exceed the maximum range of the spotlight source. If it exceeds this range, it can be ignored.

[0312] In some embodiments, when the occupant does not need the sight-chasing light function, such as when the ambient light is relatively bright or the occupant feels that sight-chasing light will interfere with thinking, the desk lamp in the disclosed embodiment can provide a function to quickly stop the sight-chasing light function. For example, a stop gesture (such as five fingers open) can be set, and when the stop gesture is detected, the sight-chasing light function is stopped; when a start gesture (such as a V-sign gesture) is detected, the sight-chasing light function is turned on. For another example, a second button can be provided on the additional device of the spotlight source to turn off and on sight-chasing light. The second button and the first button for controlling the start of gesture-chasing light mentioned above can be the same button or a different button, which is not limited here.

[0313] Process three: Sitting posture reminder function.

[0314] 1) The sitting posture detection camera collects the sitting posture image of the sitting person.

[0315] 2) The embedded computer uses a deep learning sitting posture recognition model to process and recognize human sitting posture images.

[0316] 3) The deep learning sitting posture recognition model gives the sitting posture recognition results, such as left leaning, right leaning, forward leaning or normal.

[0317] 4) The embedded computer translates the sitting posture recognition result into sound and plays it out through the voice output device; or translates the sitting posture recognition result into text and displays it on a screen such as an LCD screen; or lights up some light-emitting buttons, so that the user can perceive it.

[0318] Process 4: Provide an estimate of the distance between the human eye and the desktop (hereinafter referred to as "eye-desk distance").

[0319] 1) The sitting posture detection camera collects the sitting posture image and eye image of the sitting person.

[0320] 2) The embedded computer uses a deep learning model to identify the key parts of the human body, especially the location of the eyes in the image.

[0321] 3) The embedded computer relies on some initialization parameters (such as the intrinsic parameters of the camera, the position and angle of the camera installed on the lamp body, etc.) to calculate the pixel position of the eye in the image, the direction of the eye's line of sight (the perpendicular bisector of the line connecting the two eyes), the actual distance between the intersection of the line of sight and the desktop in the image and the desktop, thereby determining the eye-desk distance in physical space.

[0322] 4) The embedded computer transmits the calculated eye-table distance to the cloud, and parents can view it at any time. In addition, if the eye-table distance is too small, which is harmful to vision health, the embedded computer can also remind on the spot.

[0323] Process 5: Automatic scene recognition.

[0324] 1) The light-chasing camera collects the current scene image.

[0325] 2) The embedded computer uses a deep learning image recognition model to identify objects in the captured images.

[0326] 3) Generally, if the user's "hand to be followed" is detected to hold a pen-like object, the current scene is considered to be in writing mode; if the user's "hand to be followed" is not detected to hold a pen-like object, but a book is found, the current scene is considered to be in reading mode; if neither the pen-like object nor the book is detected, then it can be considered to be another scene.

[0327] Process six: Turn lights on and off by voice and other voice control functions.

[0328] The process of the desk lamp executing voice commands is as follows:

[0329] 1) The user issues a voice command within the sensing range of the voice input device, such as "Zhima, turn on the light".

[0330] 2) The voice input device collects voice signals and converts them into digital signals.

[0331] 3) The embedded computer receives the digital signal and uses the deep learning speech recognition model to interpret the command of the digital signal.

[0332] 4) The embedded computer determines whether the current voice command is consistent with the current state and scene, and if so, executes it. For example, if the desk lamp is already on at the moment, the on command can be ignored; if the desk lamp is already off at the moment, the on command can be executed.

[0333] The process of the desk lamp issuing voice reminders is as follows:

[0334] 1) When each functional module in the embedded computer thinks that a sound reminder is needed, it will generate a corresponding voice reminder command. For example, if the sitting posture reminder function module thinks that the sitting posture is too crooked and lasts for a period of time, it can issue a voice reminder command to let the sitting posture improve.

[0335] 2) For a voice reminder instruction, the embedded computer can call a pre-stored voice playback file from the memory and play it through the voice output device, or it can convert the text content of the voice reminder instruction into a voice signal in real time through a text-to-speech deep learning model and play it through the voice output device.

[0336] Process seven: Mobile phone wireless charging function.

[0337] 1) The user turns on the wireless charging switch on the desk lamp.

[0338] 2) The user places the mobile phone on the base of the desk lamp or on a suitable reserved position.

[0339] 3) The wireless charging device senses the phone and starts charging it.

[0340] Process 8: Ambient brightness detection function

[0341] 1) The ambient brightness detection device monitors the current ambient brightness in real time and transmits the signal to the embedded computer.

[0342] 2) The embedded computer determines whether the current ambient brightness exceeds a specified threshold. If so, it issues a reminder that the ambient brightness is too low or too high.

[0343] Process 9: Real-time viewing and backtracking functions

[0344] 1) The user downloads the application associated with the desk lamp to the mobile phone and installs it. The application includes various forms such as mobile phone applications, WeChat applets, H5 web applications, etc.

[0345] 2) The user opens the application, completes user registration, and then binds the current lamp to the mobile phone.

[0346] 3) The user opens and logs in to the application, clicks on the current desk lamp, and can view the real-time shooting content of the current desk lamp's tracking camera and sitting posture monitoring camera, view the sitter's concentration index, sitting posture health, eye health and other indicators, and can also browse and view historical records.

[0347] 4) The user opens and logs in to the application, clicks the backtracking function, clicks the current desk lamp and a past time point, and can playback the screen to see the user's past sitting posture, eye usage, and other content.

[0348] Process 10: Homework upload function.

[0349] 1) After finishing their homework, students place it under the tracking camera.

[0350] 2) Then click a button to take a photo and upload it.

[0351] The embedded computer takes a photo of the current job, crops it appropriately, and then uploads it to the cloud.

[0352] The desk lamp in the disclosed embodiment, on the one hand, provides a spotlight mode and a light chasing function in the spotlight mode, which is more convenient for immersive learning and work and helps to improve concentration; on the other hand, it provides a sitting posture reminder function based on a deep learning image recognition model, which helps the user maintain a healthy sitting posture; on the third hand, it provides an eye-desk distance detection function, which can play a good role in protecting the eyes.

[0353] The user can use the desk lamp provided by the embodiment of the present disclosure to improve eye health and sitting posture when studying, doing homework, reading, operating a mobile phone and / or tablet computer, etc. at home.

[0354] Figure 6 A schematic diagram of the structure of a control device for a desk lamp provided in an embodiment of the present disclosure is shown in FIG. Figure 6 As shown, the control device 600 of the desk lamp includes: a first acquisition module 610, a first identification module 620, a first determination module 630 and a first control module 640, wherein:

[0355] A first acquisition module 610, configured to acquire a first image acquired by a first image acquisition component of the desk lamp;

[0356] A first recognition module 620, configured to recognize an application scenario of the desk lamp based on the first image to obtain a current application scenario;

[0357] A first determination module 630, configured to determine a lighting mode of the desk lamp based on the current application scenario;

[0358] The first control module 640 is used to control the desk lamp to switch to the lighting mode.

[0359] In some embodiments, the first determination module is also used for at least one of the following: when the current application scenario is a writing scene, determining that the lighting mode of the desk lamp is a spotlight mode; wherein the spotlight mode represents that at least the spotlight light source of the desk lamp is turned on; when the current application scenario is a reading scene, determining that the lighting mode of the desk lamp is a floodlight mode; wherein the floodlight mode represents that at least the floodlight light source of the desk lamp is turned on; when the current application scenario is an electronic device operation scene, determining that the lighting mode of the desk lamp is the floodlight mode.

[0360] In some embodiments, the device also includes: a second acquisition module, used to acquire a second image captured by the first image acquisition component when the spotlight source of the desk lamp is turned on; a second determination module, used to determine a first illumination area to be irradiated based on the second image; and a first adjustment module, used to adjust the illumination direction of the spotlight source based on the first illumination area.

[0361] In some embodiments, the device also includes: a first recognition module, used to recognize the gesture corresponding to the target hand in the second image to obtain the current gesture of the target hand; the first adjustment module is also used to adjust the illumination direction of the spotlight source based on the first illumination area when the current gesture is a first preset gesture.

[0362] In some embodiments, the device also includes: a first detection module, used to detect faces in the second image to obtain at least one candidate face, at least one first candidate hand, and the imaging size of each candidate face in the second image; a third determination module, used to determine the target face from the at least one candidate face based on the imaging size; and a fourth determination module, used to determine the target hand that belongs to the same person as the target face from the at least one first candidate hand.

[0363] In some embodiments, the first detection module is also used to: perform human body semantic segmentation on the second image to obtain at least one candidate face, at least one first candidate hand, at least one human torso, and the imaging size of each candidate face in the second image; the fourth determination module is also used to: determine at least one second candidate hand that has a human torso connection with the target face from the at least one first candidate hand; and when the second candidate hands include a left hand and a right hand, determine the target hand from the left hand and the right hand based on the preset first configuration information.

[0364] In some embodiments, the second determination module is further used to: determine a first target object to be identified; identify the first target object in the second image to obtain first position information of the first target object; and determine the first illumination area based on the first position information of the first target object.

[0365] In some embodiments, the second determination module is also used for one of the following: determining the first target object based on the current application scenario and / or preset second configuration information; identifying the gesture corresponding to the target hand in the second image to obtain the current gesture of the target hand, and determining the first target object based on the current gesture.

[0366] In some embodiments, the second determination module is also used for one of the following: when the current application scenario is a writing scene, determining the first target object as the intersection between the user's line of sight and the desktop currently used by the user; when the current application scenario is a reading scene, determining the first target object as a book; when the current application scenario is an electronic device operation scene, determining the first target object based on the second configuration information.

[0367] In some embodiments, the device also includes: a third acquisition module, used to acquire a third image captured by the second image acquisition component of the desk lamp; wherein, in a first direction, there is a first height difference between the second image acquisition component and the desktop currently used by the user, and the first direction is vertically downward; a fifth determination module, used to determine, based on the third image, a first distance between the user's eyes and the second image acquisition component, and determine a first angle between a second direction extending from the eyes to the second image acquisition component and the first direction; a sixth determination module, used to determine, based on the first distance and the first angle, a second height difference between the eyes and the second image acquisition component in the first direction; an output module, used to output a first prompt message for prompting the user to adjust his sitting posture when it is determined that the second distance between the eyes and the desktop is less than a preset distance threshold based on the first height difference and the second height difference.

[0368] In some embodiments, the fifth determination module is also used to: determine a second angle between the optical axis direction of the second image acquisition component and the opposite direction of the second direction; determine a third angle between the optical axis direction and the first direction; and determine the first angle based on the second angle and the third angle.

[0369] In some embodiments, the output module is also used to: determine second prompt information; the second prompt information is used to instruct a preset language model to generate the first prompt information; send the third image and the second prompt information to the language model; in response to receiving the first prompt information generated by the language model based on the third image and the second prompt information, output the first prompt information.

[0370] In some embodiments, the device also includes: a fourth acquisition module, used to acquire multimedia information for interacting with a preset language model; a sending module, used to send the multimedia information to the language model; and a second control module, used to control the information output component of the desk lamp to output the response information in response to receiving the response information generated by the language model based on the multimedia information.

[0371] The description of the above device embodiment is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment. For technical details not disclosed in the device embodiment of the present disclosure, please refer to the description of the method embodiment of the present disclosure for understanding.

[0372] If the technical solution of this application involves personal information, the product using the technical solution of this application has clearly informed the personal information processing rules and obtained the individual's voluntary consent before processing the personal information. If the technical solution of this application involves sensitive personal information, the product using the technical solution of this application has obtained the individual's separate consent before processing the sensitive personal information, and at the same time meets the "explicit consent" requirement. For example, on personal information collection devices such as cameras, clear and prominent signs are set to inform that the personal information collection scope has been entered and personal information will be collected. If the individual voluntarily enters the collection scope, it is deemed that he or she agrees to the collection of his or her personal information; or on the device that processes personal information, the personal information processing rules are notified by obvious signs / information, and the individual's authorization is obtained through pop-up information or by asking the individual to upload his or her personal information; among them, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the type of personal information processed.

[0373] It should be noted that in the embodiments of the present disclosure, if the control method of the desk lamp described above is implemented in the form of a software function module and is sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiments of the present disclosure is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM), a magnetic disk or an optical disk. In this way, the embodiments of the present disclosure are not limited to any specific combination of hardware and software.

[0374] An embodiment of the present disclosure provides a computer device, including a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and the processor implements the steps in the above method when executing the program.

[0375] An embodiment of the present disclosure provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method are implemented.

[0376] The present disclosure provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and when the computer program is read and executed by a computer, some or all of the steps in the above method are implemented. The computer program product can be implemented specifically by hardware, software or a combination thereof. In an optional embodiment, the computer program product is specifically embodied as a computer storage medium, and in another optional embodiment, the computer program product is specifically embodied as a software product, such as a software development kit (Software Development Kit, SDK) and the like.

[0377] It should be noted here that the description of the above storage medium, computer program product and device embodiments is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment. For technical details not disclosed in the storage medium, computer program product and device embodiments of the present disclosure, please refer to the description of the method embodiment of the present disclosure for understanding.

[0378] It should be noted that Figure 7 is a schematic diagram of a hardware entity of a computer device in an embodiment of the present disclosure, such as Figure 7 As shown, the hardware entity of the computer device 700 includes: a processor 701, a communication interface 702 and a memory 703, wherein:

[0379] Processor 701 generally controls the overall operation of computer device 700 .

[0380] The communication interface 702 enables the computer device to communicate with other terminals or servers through a network.

[0381] The memory 703 is configured to store instructions and applications executable by the processor 701, and can also cache data to be processed or processed by the processor 701 and various modules in the computer device 700 (for example, image data, audio data, voice communication data, and video communication data), which can be implemented through flash memory (FLASH) or random access memory (Random Access Memory, RAM).

[0382] It should be understood that "one embodiment" or "an embodiment" mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present disclosure. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in the various embodiments of the present disclosure, the size of the serial number of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present disclosure. The serial numbers of the embodiments of the present disclosure are for description only and do not represent the advantages and disadvantages of the embodiments.

[0383] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0384] In the several embodiments provided in the present disclosure, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0385] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0386] In addition, all functional units in the embodiments of the present disclosure may be integrated into one processing unit, or each unit may be separately configured as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0387] A person skilled in the art can understand that all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM), magnetic disks or optical disks, etc., various media that can store program codes.

[0388] Alternatively, if the above-mentioned integrated unit of the present disclosure is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present disclosure can essentially or in other words, the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0389] The above description is only an implementation mode of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed in the present disclosure should be included in the protection scope of the present disclosure.

Claims

1. A method for controlling a desk lamp, characterized in that: The method comprises: Acquire a first image captured by a first image acquisition component of the desk lamp; Based on the first image, identifying an application scene of the desk lamp to obtain a current application scene; Based on the current application scenario, determining a lighting mode of the desk lamp; Control the desk lamp to switch to the lighting mode.

2. The method according to claim 1, characterized in that The determining the lighting mode of the desk lamp based on the current application scenario includes at least one of the following: In the case where the current application scenario is a writing scenario, determining that the lighting mode of the desk lamp is a spotlight mode; wherein the spotlight mode represents turning on at least a spotlight light source of the desk lamp; In the case where the current application scenario is a reading scenario, determining that the illumination mode of the desk lamp is a floodlight mode; wherein the floodlight mode represents turning on at least the floodlight source of the desk lamp; When the current application scenario is an electronic device operation scenario, the lighting mode of the desk lamp is determined to be the floodlight mode.

3. The method according to claim 1 or 2, characterized in that: The method further comprises: When the spotlight source of the desk lamp is turned on, acquiring a second image captured by the first image acquisition component; determining a first illumination area to be irradiated based on the second image; Based on the first illumination area, an illumination direction of the spotlight source is adjusted.

4. The method according to claim 3, characterized in that The method further comprises: Recognize the gesture corresponding to the target hand in the second image to obtain the current gesture of the target hand; The adjusting the irradiation direction of the spotlight source based on the first illumination area includes: When the current gesture is a first preset gesture, the illumination direction of the spotlight source is adjusted based on the first illumination area.

5. The method according to claim 4, characterized in that Before recognizing the gesture corresponding to the target hand in the second image to obtain the current gesture of the target hand, the method further includes: Detecting a human face in the second image to obtain at least one candidate human face, at least one first candidate hand, and an imaging size of each of the candidate human faces in the second image; Determining a target human face from the at least one candidate human face based on the imaging size; A target hand belonging to the same person as the target face is determined from the at least one first candidate hand.

6. The method according to claim 5, characterized in that The detecting of the human face in the second image to obtain at least one candidate human face, at least one first candidate hand, and the imaging size of each candidate human face in the second image includes: Performing human body semantic segmentation on the second image to obtain at least one candidate face, at least one first candidate hand, at least one human body trunk, and an imaging size of each candidate face in the second image; The step of determining, from the at least one first candidate hand, a target hand that belongs to the same person as the target face, comprises: Determine, from the at least one first candidate hand, at least one second candidate hand that is connected to the target face by a human body trunk; In the case that the second candidate hands include a left hand and a right hand, the target hand is determined from the left hand and the right hand based on preset first configuration information.

7. The method according to any one of claims 3 to 6, characterized in that The step of determining a first illumination area to be irradiated based on the second image includes: determining a first target object to be identified; Identify the first target object in the second image to obtain first position information of the first target object; The first illumination area is determined based on the first position information of the first target object.

8. The method according to claim 7, characterized in that The determining of the first target object to be identified includes one of the following: Determine the first target object based on the current application scenario and / or preset second configuration information; The gesture corresponding to the target hand in the second image is recognized to obtain the current gesture of the target hand, and the first target object is determined based on the current gesture.

9. The method according to claim 8, characterized in that The determining the first target object based on the current application scenario and / or the preset second configuration information includes one of the following: In the case where the current application scene is a writing scene, determining the first target object as an intersection between the user's sight line and the desktop currently used by the user; When the current application scenario is a reading scenario, determining that the first target object is a book; In a case where the current application scenario is an electronic device operation scenario, the first target object is determined based on the second configuration information.

10. The method according to any one of claims 1 to 9, characterized in that The method further comprises: Acquire a third image captured by the second image acquisition component of the desk lamp; wherein, in a first direction, there is a first height difference between the second image acquisition component and the desktop currently used by the user, and the first direction is vertically downward; Based on the third image, determining a first distance between the eye of the user and the second image acquisition component, and determining a first angle between a second direction extending from the eye to the second image acquisition component and the first direction; Determine a second height difference between the eye and the second image acquisition component in the first direction based on the first distance and the first angle; When it is determined that the second distance between the eye and the desktop is less than a preset distance threshold based on the first height difference and the second height difference, first prompt information for prompting the user to adjust the sitting posture is output.

11. The method according to claim 10, characterized in that The determining of a first angle between a second direction extending from the eye to the second image acquisition component and the first direction comprises: Determine a second angle between the optical axis direction of the second image acquisition component and the opposite direction of the second direction; Determining a third angle between the optical axis direction and the first direction; The first angle is determined based on the second angle and the third angle.

12. The method according to any one of claims 1 to 11, characterized in that The method further comprises: Acquiring multimedia information for interacting with a preset language model; sending the multimedia information to the language model; In response to receiving the response information generated by the language model based on the multimedia information, the information output component of the desk lamp is controlled to output the response information.

13. A desk lamp, characterized in that: include: A base, an illumination component, a first image acquisition component, a control component, and a connecting portion connecting the base and the illumination component; wherein, The control component is used to: obtain a first image acquired by the first image acquisition component; based on the first image, identify the application scene of the desk lamp to obtain the current application scene; Based on the current application scenario, a lighting mode is determined; and the lighting component is controlled to switch to the lighting mode.

14. A control device for a desk lamp, characterized in that: include: A first acquisition module, used to acquire a first image acquired by a first image acquisition component of the desk lamp; A first recognition module, configured to recognize an application scenario of the desk lamp based on the first image to obtain a current application scenario; A first determination module, configured to determine a lighting mode of the desk lamp based on the current application scenario; The first control module is used to control the desk lamp to switch to the lighting mode.

15. A computer device comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, wherein: When the processor executes the program, the steps in the method according to any one of claims 1 to 12 are implemented.

16. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 12 are implemented.

Images