A method, device, equipment and medium for predicting the loss of a ceiling fan lamp

Abstract

The present application relates to the field of object search, and in particular to a method, device, equipment and medium for predicting the search of a ceiling fan lamp. The method includes: obtaining desktop image information and indoor airflow information, then inputting the desktop image information into a trained recognition network model for training, obtaining object feature information and object annotation information, and then determining the object initial position and object prediction quality of the object in the desktop image information based on the object feature information and object annotation information, and then determining the separation point position of the object from the desktop based on the desktop image information, and combining the separation point position with the object initial position for analysis to obtain the object initial speed and the object initial direction, and then combining the indoor airflow information, the object initial speed and the object initial direction to predict the scattered position of the object, and generate the object drop position information. The present application has the effect of improving the search efficiency of the object.

Description

Technical Field

[0001] The present application relates to the field of object search, and more particularly to a method, device, equipment and medium for predicting the search of objects for a ceiling fan lamp. Background Art

[0002] Ceiling fan lamp, full name decorative ceiling fan lamp, is the perfect combination of lamp and ceiling fan. It has both the decorativeness of lamp and the practicality of fan.

[0003] At present, when people install ceiling fan lights, they usually install them right above the table in the living room to facilitate the user's daily life. However, after the ceiling fan lights are installed and started, if the user places some light objects on the table, the wind force generated by the ceiling fan lights will easily blow the objects to the surroundings of the living room or even some narrow corners, increasing the difficulty for the user to search for the object, thereby reducing the efficiency of object search. Summary of the invention

[0004] In order to improve the efficiency of searching for objects, the present application provides a method, device, equipment and medium for predicting the search for objects of a ceiling fan lamp.

[0005] In a first aspect, the present application provides a method for predicting the location of a ceiling fan lamp, using the following technical solution:

[0006] A method for predicting a found object of a ceiling fan lamp, comprising:

[0007] Get desktop image information and indoor airflow information;

[0008] Inputting the desktop image information into a trained recognition network model for training to obtain object feature information and object annotation information, wherein the object annotation information is used to indicate the object ratio of the object feature information;

[0009] Determining an object initial position and an object prediction quality of an object in the desktop image information based on the object feature information and the object annotation information;

[0010] Determine the separation point position of the object from the desktop based on the desktop image information, and combine the separation point position with the initial position of the object for analysis to obtain the initial speed and initial direction of the object;

[0011] The object scattering position is predicted by combining the indoor airflow information, the object initial speed and the object initial direction to generate the object drop position information.

[0012] By adopting the above technical solution, when an object falls from a desktop, desktop image information and indoor airflow information are obtained, and the indoor airflow information is the current size and direction of air flow in the room. The desktop image information is input into a trained recognition network model for training to obtain object feature information and object annotation information, and then the object initial position and object prediction quality of the object in the desktop image information are determined based on the object feature information and object annotation information. Then, the separation point position of the object leaving the desktop is determined based on the desktop image information, and the object initial position is combined with the separation point position for analysis to obtain the object initial speed and the object initial direction. Then, the indoor airflow information, the object initial speed and the object initial direction are combined to predict the scattered position of the object to obtain the object drop position information. The user searches for the object based on the object drop position information, thereby improving the object search efficiency.

[0013] In another possible implementation, combining and analyzing the separation point position with the object initial position to obtain the object initial velocity and the object initial direction includes:

[0014] Acquire the distance time information and distance movement information of the object from the initial position of the object to the position of the separation point;

[0015] The initial speed of the object and the initial direction of the object are obtained according to the distance time information and the distance movement information.

[0016] Through the above technical scheme, when the separation point position and the initial position of the object are combined for analysis, the distance time information and distance movement information taken by the object to move from the initial position of the object to the separation point position are obtained, and then the initial speed and initial direction of the object are obtained based on the distance time information and the distance movement information, thereby improving the accuracy of the data.

[0017] In another possible implementation, the step of obtaining the desktop image information and the indoor airflow information further includes:

[0018] The desktop image information is subjected to denoising processing, and the denoised desktop image information is subjected to image enhancement processing.

[0019] Through the above technical scheme, since the desktop image information in reality is often affected by the interference of imaging equipment and external environmental noise during the digitization and transmission process, it is necessary to use denoising technology to denoise the desktop image information in order to reduce the noise in the digital image and make the desktop image information more accurate. Then, the denoised desktop image information is enhanced to improve the visual effect of the desktop image information, making the image clearer, thereby achieving the effect of improving the recognition of the desktop image information.

[0020] In another possible implementation, the step of inputting the desktop image information into a trained recognition network model for training may also include:

[0021] Obtaining an object training sample, wherein the object training sample includes an object sample image and an object name and a unit object mass corresponding to the object sample image;

[0022] A recognition network model is created, and the recognition network model is trained based on the object training sample to obtain a trained recognition network model.

[0023] Through the above technical solution, before training the desktop image information, object sample images and the object names and unit object masses corresponding to the object sample images are collected as equipment training samples, and then a recognition network model is created, and the recognition network model is trained through the object training samples. Finally, a trained recognition network model is obtained, which facilitates the subsequent training of the desktop image information.

[0024] In another possible implementation manner, the determining the initial position of the object and the predicted quality of the object in the desktop image information further includes:

[0025] Acquire wind force information and distance information of the ceiling fan lamp, wherein the distance information of the ceiling fan lamp is the distance between the ceiling fan lamp and the object;

[0026] Determine the object wind force information according to the ceiling fan light wind force information and the ceiling fan light distance information;

[0027] Based on the predicted mass of the object, determining whether the wind force information of the object can blow the object off the table, and if so, generating an object scattering instruction, and controlling the alarm device to output an alarm signal in a preset manner;

[0028] The preset mode includes at least one of the following: a sound output mode and a light output mode.

[0029] Through the above technical scheme, when judging whether the wind force generated by the ceiling fan lamp can blow down an object, the wind force information and the distance information of the ceiling fan lamp are obtained, and then the wind force information of the object is determined based on the wind force information and the distance information of the ceiling fan lamp, that is, the wind force at the current location of the object, and then based on the predicted mass of the object, it is determined whether the wind force information of the object can blow the object off the table. If so, an object scattering instruction is generated, and the alarm device is controlled to output an alarm signal to inform the user that there is a risk of the object falling.

[0030] In another possible implementation, the method further includes:

[0031] Acquire environmental sound signals;

[0032] Amplifying the ambient sound signal to obtain amplified audio data;

[0033] The audio data is sent to a preset circuit for analysis, a light change instruction is generated, and the frequency change of the LED light is controlled according to the light change instruction.

[0034] Through the above technical scheme, the acquired ambient sound signal is amplified to obtain amplified audio data, and the audio data is sent to a preset circuit for analysis to generate a light change instruction to control the flashing frequency of the LED light, thereby improving the lighting atmosphere effect of the ceiling fan light.

[0035] In another possible implementation, the method further includes:

[0036] Acquire indoor image information;

[0037] It is determined based on the indoor image information whether there is a person within a preset time period. If not, a light-off instruction is generated to control the ceiling fan light to be turned off.

[0038] Through the above technical solution, when no one is indoors within a preset time period, if the ceiling fan light is still working, a light off instruction is generated to control the ceiling fan light to turn off, thereby achieving the effect of energy saving and emission reduction.

[0039] In a second aspect, the present application provides a device for predicting lost objects of a ceiling fan lamp, which adopts the following technical solution:

[0040] A device for predicting lost objects of a ceiling fan lamp, comprising:

[0041] An information acquisition module is used to acquire desktop image information and indoor airflow information;

[0042] An image training module, used for inputting the desktop image information into a trained recognition network model for training, and obtaining object feature information and object annotation information, wherein the object annotation information is used to indicate the object proportion of the object feature information;

[0043] A data determination module, configured to determine an object initial position and an object prediction quality of an object in the desktop image information based on the object feature information and the object annotation information;

[0044] An analysis module, configured to determine the separation point position of the object from the desktop based on the desktop image information, and combine the separation point position with the initial position of the object for analysis to obtain the initial speed and initial direction of the object;

[0045] The position prediction module is used to predict the scattered position of the object in combination with the indoor airflow information, the initial speed of the object and the initial direction of the object to generate the object falling position information.

[0046] By adopting the above technical solution, when an object falls from a desktop, desktop image information and indoor airflow information are obtained, and the indoor airflow information is the current size and direction of air flow in the room. The desktop image information is input into a trained recognition network model for training to obtain object feature information and object annotation information, and then the object initial position and object prediction quality of the object in the desktop image information are determined based on the object feature information and object annotation information. Then, the separation point position of the object leaving the desktop is determined based on the desktop image information, and the object initial position is combined with the separation point position for analysis to obtain the object initial speed and the object initial direction. Then, the indoor airflow information, the object initial speed and the object initial direction are combined to predict the scattered position of the object to obtain the object drop position information. The user searches for the object based on the object drop position information, thereby improving the object search efficiency.

[0047] In a possible implementation, when the analysis module combines the separation point position with the object initial position for analysis to obtain the object initial speed and the object initial direction, it is specifically used to:

[0048] Acquire the distance time information and distance movement information of the object from the initial position of the object to the position of the separation point;

[0049] The initial speed of the object and the initial direction of the object are obtained according to the distance time information and the distance movement information.

[0050] In another possible implementation, the device further includes: an image processing module, wherein:

[0051] The image processing module is used to perform denoising on the desktop image information and perform image enhancement on the denoised desktop image information.

[0052] In another possible implementation, the device further includes: a sample acquisition module and a model creation module, wherein:

[0053] The sample acquisition module is used to acquire object training samples, wherein the object training samples include object sample images and object names and unit object masses corresponding to the object sample images;

[0054] The model creation module is used to create a recognition network model and train the recognition network model based on the object training sample to obtain a trained recognition network model.

[0055] In another possible implementation, the device further includes: a wind force acquisition module, a wind force determination module, and a blow-off judgment module, wherein:

[0056] The wind force acquisition module is used to acquire wind force information of the ceiling fan lamp and distance information of the ceiling fan lamp, wherein the distance information of the ceiling fan lamp is the distance between the ceiling fan lamp and the object;

[0057] The wind force determination module is used to determine the object wind force information according to the ceiling fan light wind force information and the ceiling fan light distance information;

[0058] The blow-off judgment module is used to determine whether the wind force information of the object can blow the object off the table based on the predicted mass of the object, and if so, generate an object scattering instruction to control the alarm device to output an alarm signal in a preset manner;

[0059] Among them, the preset mode includes at least one of the following: a sound output mode and a light output mode.

[0060] In another possible implementation, the device includes: a sound acquisition module, a sound processing module, and a frequency control module, wherein:

[0061] A sound acquisition module is used to acquire environmental sound signals;

[0062] A sound processing module, used to amplify the ambient sound signal to obtain amplified audio data;

[0063] The frequency control module is used to send the audio data to a preset circuit for analysis, generate a light change instruction, and control the frequency change of the LED light according to the light change instruction.

[0064] In another possible implementation, the device further includes: an indoor image acquisition module and a closing judgment module, wherein:

[0065] The indoor image acquisition module is used to acquire indoor image information;

[0066] The shutdown judgment module is used to determine whether there is a person within a preset time period based on the indoor image information. If not, a light shutdown instruction is generated to control the ceiling fan light to be turned off.

[0067] In a third aspect, the present application provides an electronic device, which adopts the following technical solution:

[0068] An electronic device, comprising:

[0069] at least one processor;

[0070] Memory;

[0071] At least one application, wherein the at least one application is stored in the memory and is configured to be executed by at least one processor, and the at least one application is configured to: execute the above-mentioned object-searching prediction method for the ceiling fan light.

[0072] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution:

[0073] A computer-readable storage medium includes: a computer program that can be loaded by a processor and execute the above-mentioned method for predicting the lost object of a ceiling fan lamp.

[0074] In summary, this application includes the following beneficial technical effects:

[0075] 1. When an object falls from the desktop, the desktop image information and indoor airflow information are obtained. The indoor airflow information is the current indoor air flow size and air flow direction. The desktop image information is input into the trained recognition network model for training to obtain object feature information and object labeling information. Then, the object initial position and object prediction quality of the object in the desktop image information are determined based on the object feature information and object labeling information. Then, the separation point position of the object leaving the desktop is determined based on the desktop image information, and the object initial position is combined with the separation point position for analysis to obtain the object initial speed and the object initial direction. Then, the indoor airflow information, the object initial speed and the object initial direction are combined to predict the scattered position of the object to obtain the object drop position information. The user searches for the object based on the object drop position information, thereby improving the object search efficiency and the effect of the ceiling fan light object search prediction efficiency and the equipment maintenance efficiency.

[0076] 2. When judging whether the wind force generated by the ceiling fan lamp can blow down an object, obtain the wind force information and the distance information of the ceiling fan lamp, and then determine the object's wind force information based on the wind force information and the distance information of the ceiling fan lamp, that is, the wind force at the current location of the object, and then determine whether the object's wind force information can blow the object off the table based on the predicted mass of the object. If so, generate an object scattering instruction, control the alarm device to output an alarm signal, and inform the user that there is a risk of the object falling. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] Figure 1 It is a flow chart of a method for predicting the object found by a ceiling fan lamp according to an embodiment of the present application;

[0078] Figure 2 It is a block diagram of a method for predicting a found object of a ceiling fan lamp according to an embodiment of the present application;

[0079] Figure 3 It is a schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0080] The following is combined with Figure 1-3 This application is described in further detail.

[0081] After reading this specification, those skilled in the art may make non-creative modifications to this embodiment as needed, but such modifications are protected by patent law as long as they are within the scope of the claims of this application.

[0082] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0083] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0084] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0085] The embodiment of the present application provides a method for predicting the loss of a ceiling fan lamp, which is executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiment of the present application. Figure 1 As shown, the method includes:

[0086] Step S10, obtaining desktop image information and indoor airflow information.

[0087] In an embodiment of the present application, a shooting tool is pre-installed on the side of the ceiling fan lamp close to the desktop to obtain desktop image information, and a wind direction and speed sensor is installed near the table in the room to obtain indoor airflow information.

[0088] Specifically, the shooting tools include cameras and monitors, and the working principle of the wind direction and speed sensor is to convert the wind speed into a voltage signal through a flow sensor, and its value is a functional relationship with the incoming wind speed. The two analog signals are then converted into digital signals by an A / D conversion chip and an operational amplifier, which are read and processed by the microcontroller as the transmitter of the main control unit. Then, the microcontroller sends the processed data packet to the receiver through the wireless module, and the receiver receives it with the wireless module. The receiver analyzes the collected data to record, save, and display the wind speed and direction.

[0089] Step S11, inputting the desktop image information into the trained recognition network model for training, obtaining object feature information and object annotation information, wherein the object annotation information is used to indicate the object ratio of the object feature information.

[0090] Specifically, feature vectors are extracted from the desktop image information. The contour shapes that objects can form in the image are different. Object features are extracted according to the difference categories to obtain object feature information. For example, object feature information of "0" indicates that the object is easy to blow off (paper, vegetable peels), and device feature information of "1" indicates that the object is not easy to blow off. At the same time, the proportional size of the object is detected to obtain the object annotation information. For example, the object annotation information of "1:10" indicates that the size of the object occupies 1 / 10 of the desktop.

[0091] Step S12, determining the object initial position and object prediction quality of the object in the desktop image information based on the object feature information and the object annotation information.

[0092] Specifically, the position of the object initially recognized is taken as the initial position of the object, and the object prediction quality is determined according to the type of the object and the ratio of the object to the desktop, wherein the type of the object is identified according to the object feature information, and the ratio of the object is determined according to the object annotation information.

[0093] Step S13, determining the separation point position where the object leaves the desktop based on the desktop image information, and combining the separation point position with the initial position of the object for analysis to obtain the initial speed and initial direction of the object.

[0094] Step S14, predicting the object scattering position by combining the indoor airflow information, the object initial speed and the object initial direction, and generating the object drop position information.

[0095] Specifically, the indoor airflow information, the initial velocity of the object and the initial direction of the object are input into the simulation software to perform fluid dynamics simulation, simulate the falling motion trajectory of the object, thereby obtaining the scattered position of the object and generating the object falling position information.

[0096] The embodiment of the present application provides a method for predicting the object found by a ceiling fan lamp. When an object falls from a desktop, desktop image information and indoor airflow information are obtained, and the indoor airflow information is the current size and direction of air flow in the room. The desktop image information is input into a trained recognition network model for training to obtain object feature information and object annotation information. Then, the object initial position and the object prediction quality of the object in the desktop image information are determined based on the object feature information and the object annotation information. Then, the separation point position of the object leaving the desktop is determined based on the desktop image information, and the object initial position is combined with the separation point position for analysis to obtain the object initial speed and the object initial direction. Then, the indoor airflow information, the object initial speed and the object initial direction are combined to predict the scattered position of the object to obtain the object drop position information. The user searches for the object based on the object drop position information, thereby improving the object search efficiency, the effect of the ceiling fan lamp object finding prediction efficiency and the equipment maintenance efficiency.

[0097] In a possible implementation of the embodiment of the present application, step S13 specifically includes step S131 (not shown in the figure) and step S132 (not shown in the figure), wherein:

[0098] Step S131, obtaining the distance time information and distance movement information of the object from the initial position of the object to the separation point position.

[0099] In an embodiment of the present application, the initial position of the object is the position of the object on the desktop when the desktop image information is acquired, the separation point position is the position where the object leaves the desktop image information, the distance movement information is determined based on the path of the object moving from the initial position of the object to the separation point position, and the distance time information is the time taken for the object to move from the initial position of the object to the separation point position.

[0100] Step S132, obtaining the initial speed and the initial direction of the object according to the distance time information and the distance movement information.

[0101] In a possible implementation of the embodiment of the present application, step S10 further includes step S101 (not shown in the figure), wherein:

[0102] Step S101, performing denoising processing on the desktop image information, and performing image enhancement processing on the denoised desktop image information.

[0103] Specifically, noise can be understood as "factors that hinder people's sensory organs from understanding the received source information." For example, for a black and white picture, its plane brightness distribution is assumed to be f(x, y), then the brightness distribution R(x, y) that interferes with its reception can be called image noise. Common image noises include additive noise, multiplicative noise, quantization noise, and "salt and pepper" noise. Additive noise is unrelated to the image signal intensity, for example: "channel noise" introduced during the image transmission process, the noise of the TV camera scanning the image; multiplicative noise is related to the image signal and often changes with the change of the image signal, for example: the noise in the flying spot scanning image, the TV scanning raster, film grain, etc.; quantization noise is the main noise source of digital images, and its size shows the difference between the digital image and the original image; "salt and pepper" noise, for example: white spots on black images caused by image cutting, black spot noise on white images, errors introduced in the transform domain, and transformation noise caused by the inverse transformation of the image.

[0104] In a possible implementation of the embodiment of the present application, before step S11, the following steps are further included:

[0105] Obtain object training samples, where the object training samples include object sample images and object names and unit object masses corresponding to the object sample images.

[0106] A recognition network model is created, and the recognition network model is trained based on object training samples to obtain a trained recognition network model.

[0107] In a possible implementation of the embodiment of the present application, step S12 further includes step S121 (not shown in the figure), step S122 (not shown in the figure), and step S123 (not shown in the figure), wherein:

[0108] Step S121, obtaining wind force information of the ceiling fan lamp and distance information of the ceiling fan lamp, where the distance information of the ceiling fan lamp is the distance between the ceiling fan lamp and the object.

[0109] Specifically, the wind force information of the ceiling fan lamp is determined according to the wind force level of the current ceiling fan lamp.

[0110] Step S122, determining the object wind information according to the ceiling fan light wind information and the ceiling fan light distance information.

[0111] Specifically, the object wind force information is the wind force generated by the ceiling fan lamp reaching the object.

[0112] Step S123, based on the predicted mass of the object, determine whether the wind force information of the object can blow the object off the table. If so, generate an object scattering instruction and control the alarm device to output an alarm signal in a preset manner.

[0113] Among them, the preset mode includes at least one of the following: a sound output mode and a light output mode.

[0114] Specifically, if the current wind force information of the object can blow the object away from the desktop, the electronic device transmits a control signal to the alarm device to control the alarm device to send out an alarm signal through sound and light output.

[0115] For example, devices that send out alarm signals by sound include: buzzers, bells, whistles, and sirens, etc., and devices that send out alarm signals by light output include: breathing lights, flashing lights, etc.

[0116] In a possible implementation of the embodiment of the present application, step S14 further includes: step S15 (not shown in the figure), step S16 (not shown in the figure) and step S17 (not shown in the figure), wherein:

[0117] Step S15, obtaining an ambient sound signal.

[0118] Specifically, the sound signal of the indoor environment is collected by the audio signal collection circuit, and then the sound signal is sent to the electronic device.

[0119] Step S16, amplify the ambient sound signal to obtain amplified audio data.

[0120] Specifically, the electronic device sends the sound signal to the audio signal amplifier circuit, amplifies the sound signal, obtains audio data after the sound signal is parsed, and returns the audio data to the electronic device.

[0121] Step S17, sending the audio data to a preset circuit for analysis, generating a light change instruction, and controlling the LED light frequency change according to the light change instruction.

[0122] Specifically, the electronic device transmits the audio data to the MCU control circuit for analysis. The MCU control circuit receives the amplified audio data, issues corresponding light change instructions according to the program settings, and transmits the light change instructions to the LED drive circuit. The LED drive circuit will also make corresponding adjustments to the LED currents of each LED light board, thereby realizing the frequency change of the LED light.

[0123] In a possible implementation of the embodiment of the present application, after step S14, the following steps are further included:

[0124] Get indoor image information.

[0125] Based on the indoor image information, determine whether there is anyone present within the preset time period. If not, generate a light-off instruction to control the ceiling fan light to turn off.

[0126] The above-mentioned embodiment introduces a method for predicting lost objects of a ceiling fan lamp from the perspective of a method flow, and the following embodiment introduces a device for predicting lost objects of a ceiling fan lamp from the perspective of a virtual module or a virtual unit. For details, please refer to the following embodiments.

[0127] The present application embodiment provides a device for predicting lost objects of a ceiling fan lamp, such as Figure 2 As shown, the device 20 may specifically include: an information acquisition module 21, an image training module 22, a data determination module 23, an analysis module 24 and a position prediction module 25, wherein:

[0128] An information acquisition module 21 is used to acquire desktop image information and indoor airflow information;

[0129] An image training module 22 is used to input desktop image information into a trained recognition network model for training, and obtain object feature information and object annotation information, where the object annotation information is used to indicate the object ratio of the object feature information;

[0130] A data determination module 23, for determining an object initial position and an object prediction quality of an object in the desktop image information based on the object feature information and the object annotation information;

[0131] An analysis module 24 is used to determine the separation point position of the object leaving the desktop based on the desktop image information, and analyze the separation point position in combination with the initial position of the object to obtain the initial speed and initial direction of the object;

[0132] The position prediction module 25 is used to predict the object scattering position by combining the indoor airflow information, the object initial speed and the object initial direction, and generate the object falling position information.

[0133] In a possible implementation of the embodiment of the present application, when the analysis module 24 combines the separation point position with the initial position of the object to analyze and obtain the initial speed and initial direction of the object, it is specifically used to:

[0134] Obtaining the distance time information and distance movement information of the object from the initial position of the object to the separation point position;

[0135] According to the distance time information and the distance movement information, the initial speed and the initial direction of the object are obtained.

[0136] In another possible implementation of the embodiment of the present application, the device 20 further includes: an image processing module, wherein:

[0137] The image processing module is used to perform denoising on the desktop image information and perform image enhancement on the denoised desktop image information.

[0138] In another possible implementation of the embodiment of the present application, the device 20 further includes: a sample acquisition module and a model creation module, wherein:

[0139] A sample acquisition module is used to acquire object training samples, where the object training samples include object sample images and object names and unit object masses corresponding to the object sample images;

[0140] The model creation module is used to create a recognition network model and train the recognition network model based on object training samples to obtain a trained recognition network model.

[0141] In another possible implementation of the embodiment of the present application, the device 20 further includes: a wind force acquisition module, a wind force determination module, and a blow-off judgment module, wherein:

[0142] A wind force acquisition module is used to obtain wind force information of the ceiling fan lamp and distance information of the ceiling fan lamp, where the distance information of the ceiling fan lamp is the distance between the ceiling fan lamp and the object;

[0143] A wind force determination module, used to determine the wind force information of the object according to the wind force information of the ceiling fan lamp and the distance information of the ceiling fan lamp;

[0144] A blow-off judgment module is used to determine whether the wind force information of the object can blow the object off the table based on the predicted mass of the object. If so, an object scattering instruction is generated to control the alarm device to output an alarm signal in a preset manner;

[0145] Among them, the preset mode includes at least one of the following: a sound output mode and a light output mode.

[0146] In another possible implementation of the embodiment of the present application, the device 20 includes: a sound acquisition module, a sound processing module and a frequency control module, wherein:

[0147] A sound acquisition module is used to acquire environmental sound signals;

[0148] The sound processing module is used to amplify the ambient sound signal to obtain amplified audio data;

[0149] The frequency control module is used to send the audio data to the preset circuit for analysis, generate the light change instruction, and control the frequency change of the LED light according to the light change instruction.

[0150] In another possible implementation of the embodiment of the present application, the device 20 further includes: an indoor image acquisition module and a closing judgment module, wherein:

[0151] An indoor image acquisition module is used to acquire indoor image information;

[0152] The judgment closing module is used to determine whether there is a person within a preset time period based on the indoor image information. If not, a light closing instruction is generated to control the ceiling fan light to turn off.

[0153] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0154] The present application also introduces an electronic device from the perspective of a physical device, such as Figure 3 As shown, Figure 3 The electronic device 300 shown includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 300 does not constitute a limitation on the embodiments of the present application.

[0155] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0156] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0157] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0158] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above method embodiment.

[0159] The electronic devices include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs, desktop computers, etc. It can also be a server, etc. Figure 3 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0160] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0161] The above are only some implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for predicting the object found by a ceiling fan lamp, characterized in that: include Get desktop image information and indoor airflow information; Inputting the desktop image information into a trained recognition network model for training to obtain object feature information and object annotation information, wherein the object annotation information is used to indicate the object ratio of the object feature information; Among them, obtaining object feature information and object annotation information includes: Extracting feature vectors from the desktop image information, extracting object features according to the difference categories, and obtaining object feature information, wherein the object feature information is used to indicate whether the object is easy to be blown off; Determining an object initial position and an object prediction quality of an object in the desktop image information based on the object feature information and the object annotation information; Wherein, determining the initial position of the object and the predicted quality of the object in the desktop image information includes: The position of the object initially recognized is taken as the initial position of the object, and the predicted quality of the object is determined according to the type of the object and the ratio of the object to the desktop, wherein the type of the object is identified according to the object feature information, and the ratio of the object ratio is determined according to the object labeling information; Determine the separation point position of the object from the desktop based on the desktop image information, and combine the separation point position with the initial position of the object for analysis to obtain the initial speed and initial direction of the object; Predicting the object's falling position by combining the indoor airflow information, the object's initial velocity, and the object's initial direction to generate object falling position information; The determining of the initial position of the object and the predicted quality of the object in the desktop image information further includes: Acquire wind force information and distance information of the ceiling fan lamp, wherein the distance information of the ceiling fan lamp is the distance between the ceiling fan lamp and the object; Determine the object wind force information according to the ceiling fan light wind force information and the ceiling fan light distance information; Based on the predicted mass of the object, determining whether the wind force information of the object can blow the object off the table, and if so, generating an object scattering instruction, and controlling the alarm device to output an alarm signal in a preset manner; The preset mode includes at least one of the following: a sound output mode and a light output mode.

2. The method according to claim 1, characterized in that The combining and analyzing the separation point position and the object initial position to obtain the object initial velocity and the object initial direction includes: Acquire the distance time information and distance movement information of the object from the initial position of the object to the position of the separation point; The initial speed of the object and the initial direction of the object are obtained according to the distance time information and the distance movement information.

3. The method according to claim 1, characterized in that The step of obtaining the desktop image information and the indoor airflow information further includes: The desktop image information is subjected to denoising processing, and the denoised desktop image information is subjected to image enhancement processing.

4. The method according to claim 1, characterized in that: The step of inputting the desktop image information into a trained recognition network model for training also includes: Obtaining an object training sample, wherein the object training sample includes an object sample image and an object name and a unit object mass corresponding to the object sample image; A recognition network model is created, and the recognition network model is trained based on the object training sample to obtain a trained recognition network model.

5. The method according to claim 1, characterized in that The method further comprises: Acquire environmental sound signals; Amplifying the ambient sound signal to obtain amplified audio data; The audio data is sent to a preset circuit for analysis, a light change instruction is generated, and the frequency change of the LED light is controlled according to the light change instruction.

6. The method according to claim 1, characterized in that The method further comprises: Acquire indoor image information; It is determined based on the indoor image information whether there is a person within a preset time period. If not, a light-off instruction is generated to control the ceiling fan light to be turned off.

7. A device for predicting lost objects of a ceiling fan lamp, characterized in that: include: An information acquisition module is used to acquire desktop image information and indoor airflow information; An image training module, used for inputting the desktop image information into a trained recognition network model for training, and obtaining object feature information and object annotation information, wherein the object annotation information is used to indicate the object proportion of the object feature information; Wherein, when acquiring object feature information and object annotation information, the image training module is specifically used to: Extracting feature vectors from the desktop image information, extracting object features according to the difference categories, and obtaining object feature information, wherein the object feature information is used to indicate whether the object is easy to be blown off; A data determination module, configured to determine an object initial position and an object prediction quality of an object in the desktop image information based on the object feature information and the object annotation information; Wherein, when determining the initial position of the object and the predicted quality of the object in the desktop image information, the data determination module is specifically used to: The position of the object initially recognized is taken as the initial position of the object, and the predicted quality of the object is determined according to the type of the object and the ratio of the object to the desktop, wherein the type of the object is identified according to the object feature information, and the ratio of the object ratio is determined according to the object labeling information; An analysis module, configured to determine the separation point position of the object from the desktop based on the desktop image information, and combine the separation point position with the initial position of the object for analysis to obtain the initial speed and initial direction of the object; A position prediction module, used to predict the scattered position of the object by combining the indoor airflow information, the initial speed of the object and the initial direction of the object, and generate the object falling position information; The device further comprises: a wind force acquisition module, a wind force determination module and a blow-off judgment module, wherein: The wind force acquisition module is used to acquire wind force information of the ceiling fan lamp and distance information of the ceiling fan lamp, wherein the distance information of the ceiling fan lamp is the distance between the ceiling fan lamp and the object; The wind force determination module is used to determine the object wind force information according to the ceiling fan light wind force information and the ceiling fan light distance information; The blow-off judgment module is used to determine whether the wind force information of the object can blow the object off the table based on the predicted mass of the object, and if so, generate an object scattering instruction to control the alarm device to output an alarm signal in a preset manner; Among them, the preset mode includes at least one of the following: a sound output mode and a light output mode.

8. An electronic device, characterized in that: The electronic device includes: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the object-searching prediction method for a ceiling fan lamp as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed in a computer, the computer is caused to execute the object-searching prediction method for a ceiling fan lamp according to any one of claims 1 to 6.

Images