3results about How to "Smart experience" patented technology

This invention relates to the field of voice interaction in smart devices, and discloses a cascaded voice interaction method for moxibustion devices. The method collects user voice, preprocesses it to obtain effective voice frames and acoustic feature maps; inputs the feature maps into a first-level voice processing unit, runs a low-power wake-word detection and short command recognition model, and directly outputs control commands when short commands are recognized; if no short command is recognized, it calculates a complex intent tendency score, and if the score exceeds a threshold, it wakes up a second-level voice processing unit; the second-level unit runs a locally deployed lightweight large language model to perform end-to-end voice recognition and semantic understanding, and generates interactive commands based on a moxibustion knowledge base; finally, the commands are executed and the results are broadcast. This invention, through a two-level cascaded architecture, balances low power consumption and high intelligence, achieves offline complex semantic understanding, and improves the voice interaction experience in moxibustion scenarios.

The invention provides an equipment monitoring method and device, electronic equipment and a storage medium, and the method comprises the steps: determining a current state of a target scene corresponding to target equipment after the target equipment is controlled, and determining an expected state for the target scene; when the current state is not matched with the expected state, obtaining a target device weight of the target device, and determining a duration in which the current state is not matched with the expected state; determining distance information between the user and the target equipment; and determining deviation degree information of the target equipment according to the weight, the duration and the distance information of the target equipment, and monitoring the target equipment according to the deviation degree information. Through the embodiment of the invention, the accidental abnormal phenomenon and the continuous deviation state can be effectively distinguished on the basis of the multi-dimensional parameters, the running state of which equipment in the current scene control better meets the current actual demand can be intelligently judged, and more intelligent user experience can be brought to a user.

The invention provides a page componentization dynamic configuration method and system applied to an intelligent workbench, and relates to the technical field of computer software, and the method comprises the steps: obtaining a component selected by a user from a component library; in response to an action of dragging the selected component to the page canvas, analyzing user operation habits and component relevance by utilizing a machine learning algorithm, performing edge collision between the components, intelligently recommending the optimal placement position and size of the component on the page canvas, and completing layout of the page canvas; taking the page canvas after layout as an intelligent workbench, and dynamically mounting data of all components in the page canvas to obtain a rendered intelligent workbench page; on the basis of a machine learning algorithm, the positions and sizes of the components in the intelligent workbench are intelligently recommended, and better and more intelligent user experience is provided while more complex personalized requirements are met.