Abstract: A method for GNN-based automatic bay zoning includes the following steps: S1, using a modified data packet to convert an output file of the hydrodynamic model into a .nc file that can be read by Python software; S2, reading the converted .nc file and performing data preprocessing; S3, using a tsfresh data packet to extract time series feature values of different features; S4, using a Delaunay triangulation algorithm and a four-way matrix or an eight-way matrix to determine spatial connectivity, and constructing an adjacency matrix; S5, constructing a convolutional GNN to learn bay characteristics and spatial connectivity; S6, using a Louvain algorithm or a Spectral Clustering algorithm to perform unsupervised classification of bay; S7, post-processing broken edges of bay zoning; and S8, outputting zoning results in the form of a .shp file to realize the automatic bay zoning.

Abstract: A method for early warning of algal bloom levels based on an Ordinal Forests model includes the following steps: S1, preprocessing water quality data from a system for online monitoring of water quality and water ecology; S2, determining an algal bloom level according to a chlorophyll a value of the pre-processed water quality data; S3, using a resampling method to solve the problem of imbalanced algal bloom level data, and synthesizing a dataset of balanced algal bloom levels; and S4, taking the newly synthesized dataset in the S3 as an input variable, constructing a model for early warning of algal bloom levels based on the Ordinal Forests model, and performing early warning of algal bloom levels through the trained model for early warning of algal bloom levels.

Abstract: Disclosed herein is a method and apparatus for deploying a self-moving device, an electronic device, and a non-transitory storage medium. The method includes acquiring position information of a target object in each region; determining an activity trajectory of the target object in each region according to the position information; determining a deployment position of the self-moving device in each region according to the activity trajectory; and controlling the self-moving device to move to the deployment position.

Abstract: Disclosed are a sleep detection method and an apparatus, an electronic device and a storage medium. The sleep detection method includes: collecting pressure information from a bed; detecting the pressure information collected within a continuous preset duration, and determining whether the pressure information includes a sleep parameter of a body sign from a sleeping human; and if the pressure information includes the parameter of the sleeping human body sign, turning on a sleep detection function to perform the sleep detection. The sleep detection method and the apparatus, the electronic device and the storage medium can be applied to an apparatus having a sleep detection function, such that the sleep detection function in the apparatus having the sleep detection function is automatically turned on without a manual operation of a user, thereby saving time and labor.

Abstract: An intelligent fusion and processing method for remote sensing products for water quality monitoring of estuaries and bays includes: S1. setting criteria for image retrieval, performing iterative image retrieval and downloading, and achieving batch downloading of remote sensing images automatically; S2. performing recursive call of an Acolite settings file in Python to directly perform batch atmospheric correction of multi-source remote sensing satellite data; S3. fusing multi-source remote sensing data products based on machine learning to generate a layer of high-frequency water quality parameter remote sensing products; S4. superimposing a layer of tidal boundary vectors for different water levels onto the layer of water quality parameter remote sensing products, and adding map elements to generate a thematic map of different water quality parameters; S5. performing intelligent statistical analysis of water quality parameters; and S6.

Abstract: A method for early warning of algal bloom levels based on an Ordinal Forests model includes the following steps: S1, preprocessing water quality data from a system for online monitoring of water quality and water ecology; S2, determining an algal bloom level according to a chlorophyll a value of the pre-processed water quality data; S3, using a resampling method to solve the problem of imbalanced algal bloom level data, and synthesizing a dataset of balanced algal bloom levels; and S4, taking the newly synthesized dataset in the S3 as an input variable, constructing a model for early warning of algal bloom levels based on the Ordinal Forests model, and performing early warning of algal bloom levels through the trained model for early warning of algal bloom levels.

Abstract: Disclosed are a method and apparatus for controlling a speech recognition device, an electronic device, and a storage medium. The method includes: recording, when the speech recognition device is in a dormant state, current time as first time in response to detecting that a target object stares at the speech recognition device; recording the current time as second time in response to detecting that the target object makes a speech; and awakening the speech recognition device in response to determining that an interval between the first time and the second time satisfies a preset condition, such that the speech recognition device enters a speech control mode.

Abstract: The disclosure relates to the field of intelligent home, and particularly to an indoor monitoring method, device and system, a storage medium and a camera device. The method includes: controlling a camera device to acquire monitoring images at consecutive times in a room; identifying a first monitoring image at a previous time and a second monitoring image at a current time, and identifying items corresponding to the first monitoring image and the second monitoring image and positions of the items, respectively; determining whether a position of an item changes according to the position of the item in the first monitoring image and the position of the item in the second monitoring image; and generating item record information of the item when it is determined that the position of the item changes, wherein the item record information represents movement of the item in the room.

Abstract: Disclosed is a smart magic cube controller. The smart magic cube controller includes: a controller body, the controller body has a plurality of surfaces, and at least one surface of the controller body is configured to be a display module; an posture sensing module; and a control module in signal connection with the posture sensing module, wherein the control module is configured to determine a current top surface of the controller body according to placement state information collected by the posture sensing module, and transmits, according to the determined current top surface, a scene mode control instruction corresponding to the current top surface, and when the display module is located on a surface, other than the current top surface and the bottom surface of the controller body, the control module is configured to control a display picture of the display module to be displayed upright.

Abstract: Disclosed are a method for controlling smart home and a device for controlling smart home. The method includes the following steps: a demand database and a habit database of a user for home appliances are built; according to the built demand database, demand models of different users are trained by using a neural network, and the demands of the users during different periods of time are predicted; and according to the built habit database and a prediction regarding the demands of the users, a home appliance execution policy conforming to the habits of the users are output by using a probability statistical algorithm, and the corresponding home appliances are controlled in advance.

Abstract: The disclosure provides a control method and a device for an air conditioner. The method includes: a first reward matrix is constructed according to multiple sets of target operating parameters of an air conditioner, a maximum expected benefit of performing a current action in a current state is calculated based on the first reward matrix and a Q-learning algorithm, wherein the current state is represented by a current indoor environment temperature and a current outdoor environment temperature; target action parameters under the maximum expected benefit are acquired, and operation of the air conditioner is controlled based on second target action parameters, wherein the second target action parameters at least include a second target operating frequency of the compressor, a second target opening degree of the electronic expansion valve and a second target rotating speed of the external fan.

Abstract: Door lock shielding cover, which includes a shielding cover body, an attraction member, and blocking portions. The shielding cover body is configured to be movably installed onto a lock panel of a smart door lock. The attraction member is installed on a side of the shielding cover body adjacent to the lock panel of the smart door lock. A plurality of through holes is defined in the attraction member. The blocking portions correspond to the through holes in a one-to-one manner. Each of the blocking portions is fixed to the shielding cover body through a connecting portion that penetrates the through hole, thereby fixing the attraction member to the shielding cover body. The fixing between the shielding cover body and the attraction member in the door lock shielding cover is firm and durable.

Abstract: Disclosed are a method for controlling an unmanned aerial vehicle, a method for controlling outbound and return trips of an unmanned aerial vehicle, an unmanned aerial vehicle, a medium, and a control system. The method for controlling an unmanned aerial vehicle includes: obtaining, in a process of flying along a target course sent by a first ground station, first positioning auxiliary information sent by the first ground station; adjusting a flight attitude according to the first positioning auxiliary information, to fly along the target course; in a case of determining that a ground station switching condition of the second ground station is satisfied, obtaining the second positioning auxiliary information sent by the second ground station; and adjusting the flight attitude according to the second positioning auxiliary information, to fly along the target course to reach the second location point.

Abstract: The disclosure relates to the field of intelligent home, and particularly to an indoor monitoring method, device and system, a storage medium and a camera device. The method includes: controlling a camera device to acquire monitoring images at consecutive times in a room; identifying a first monitoring image at a previous time and a second monitoring image at a current time, and identifying items corresponding to the first monitoring image and the second monitoring image and positions of the items, respectively; determining whether a position of an item changes according to the position of the item in the first monitoring image and the position of the item in the second monitoring image; and generating item record information of the item when it is determined that the position of the item changes, wherein the item record information represents movement of the item in the room.

Abstract: Disclosed are a method for controlling an unmanned aerial vehicle, a method for controlling outbound and return trips of an unmanned aerial vehicle, an unmanned aerial vehicle, a medium, and a control system. The method for controlling an unmanned aerial vehicle includes: obtaining, in a process of flying along a target course sent by a first ground station, first positioning auxiliary information sent by the first ground station; adjusting a flight attitude according to the first positioning auxiliary information, to fly along the target course; in a case of determining that a ground station switching condition of the second ground station is satisfied, obtaining the second positioning auxiliary information sent by the second ground station; and adjusting the flight attitude according to the second positioning auxiliary information, to fly along the target course to reach the second location point.

Abstract: Disclosed are a sleep detection method and an apparatus, an electronic device and a storage medium. The sleep detection method includes: collecting pressure information from a bed; detecting the pressure information collected within a continuous preset duration, and determining whether the pressure information includes a sleep parameter of a body sign from a sleeping human; and if the pressure information includes the parameter of the sleeping human body sign, turning on a sleep detection function to perform the sleep detection. The sleep detection method and the apparatus, the electronic device and the storage medium can be applied to an apparatus having a sleep detection function, such that the sleep detection function in the apparatus having the sleep detection function is automatically turned on without a manual operation of a user, thereby saving time and labor.

Abstract: Disclosed are a method for controlling smart home and a device for controlling smart home. The method includes the following steps: a demand database and a habit database of a user for home appliances are built; according to the built demand database, demand models of different users are trained by using a neural network, and the demands of the users during different periods of time are predicted; and according to the built habit database and a prediction regarding the demands of the users, a home appliance execution policy conforming to the habits of the users are output by using a probability statistical algorithm, and the corresponding home appliances are controlled in advance.

Abstract: Disclosed is a smart magic cube controller. The smart magic cube controller includes: a controller body (1), the controller body (1) has a plurality of surfaces, and at least one surface of the controller body (1) is configured to be a display module (2); an posture sensing module (3); and a control module (4) in signal connection with the posture sensing module (3), wherein the control module (4) is configured to determine a current top surface of the controller body (1) according to placement state information collected by the posture sensing module (3), and transmits, according to the determined current top surface, a scene mode control instruction corresponding to the current top surface, and when the display module (2) is located on a surface, other than the current top surface and the bottom surface of the controller body (1), the control module (4) is configured to control a display picture of the display module (2) to be displayed upright.

Abstract: The disclosure provides a control method and a device for an air conditioner. The method includes: a first reward matrix is constructed according to multiple sets of target operating parameters of an air conditioner, a maximum expected benefit of performing a current action in a current state is calculated based on the first reward matrix and a Q-learning algorithm, wherein the current state is represented by a current indoor environment temperature and a current outdoor environment temperature; target action parameters under the maximum expected benefit are acquired, and operation of the air conditioner is controlled based on second target action parameters, wherein the second target action parameters at least include a second target operating frequency of the compressor, a second target opening degree of the electronic expansion valve and a second target rotating speed of the external fan.

Abstract: Door lock shielding cover, which includes a shielding cover body, an attraction member, and blocking portions. The shielding cover body is configured to be movably installed onto a lock panel of a smart door lock. The attraction member is installed on a side of the shielding cover body adjacent to the lock panel of the smart door lock. A plurality of through holes is defined in the attraction member. The blocking portions correspond to the through holes in a one-to-one manner. Each of the blocking portions is fixed to the shielding cover body through a connecting portion that penetrates the through hole, thereby fixing the attraction member to the shielding cover body. The fixing between the shielding cover body and the attraction member in the door lock shielding cover is firm and durable.