8 results about "Object search" patented technology

This application discloses a smart home system based on security technology, relating to the fields of smart home and smart elderly care technology, including: a terminal acquisition layer, a network edge computing layer, a cloud platform layer, and an interactive application layer; the terminal acquisition layer integrates elderly care wristbands, environmental sensors, fall radar, smart cameras, door magnets, positioning tags, and companion robots; the cloud platform layer deploys a data fusion engine, an AI big data model, a video analysis module, and a positioning service engine. This invention achieves functions such as health anomaly monitoring and medication reminders, environmental safety early warning and automatic control, anti-wandering voice reminders, dangerous area protection, real-time positioning of people and objects, multimodal fall detection, voice control of home appliances and monitoring of abnormal electricity use, intelligent object search, AI big data model video retrieval, and community-linked missing person search. Through multimodal data fusion and AI big data model-driven interaction, it achieves proactive smart monitoring of the elderly's lives, improving the level of intelligence in elderly care monitoring and the user experience.

This invention provides a weakly supervised object detection method and system for images, comprising: feature extraction from the input image; performing self-refining enhancement features; extracting suggestions from the input image; extracting region features of the suggestions through an ROI Pooling layer; applying a fully connected layer to the region features to obtain a feature matrix; performing softmax and element-wise product on two different dimensions, class and suggestion, respectively, to obtain all suggestion scores; and obtaining the image score on class c. The suggestion score is associated with a saliency prior module, a multi-object search method, a refinement branch, a bounding box regression branch, and an area-guided weighting strategy. This invention directly uses the original image for training, effectively training an end-to-end object detection model without introducing additional high-complexity models into the main network; and it significantly outperforms existing algorithms in detecting non-rigid targets.

The application discloses an object positioning method, device and equipment, and belongs to the technical field of positioning. The method is executed by a first device, and the method comprises the following steps: acquiring first position information corresponding to a sought object in a first coordinate system, the first coordinate system being a coordinate system established based on the position of a second device and a reference direction, the second device being a device which respectively establishes a communication connection with the first device and the sought object; acquiring spatial relationship information between the first device and the second device, the spatial relationship information being used for indicating the relative position relationship between the first device and the second device; determining first direction information and first distance information of the sought object relative to the first device based on the first position information and the spatial relationship information; and positioning the sought object based on the first direction information and the first distance information. The second device is introduced to assist the positioning process of the sought object, so that the accuracy of the position of the sought object positioned can be ensured, and the accuracy of the object searching process can be ensured.

This disclosure describes systems and methods for multi-modal search-based object detection and electric grid object search. Annotations and bounding boxes for images in an image database are determined. A first subset of images is determined from the images that share annotations. A textual token representing the first subset of images is generated and stored in a search index. A second subset of images that share visual features is determined from image pixels enclosed by the bounding boxes. An image token is generated based on the second subset of images and the shared visual features. A user interface configured to receive a search query input is provided for display on a user device. Search tokens are generated based on the search query input. A candidate image is identified and provided for display within the user interface at a position within a respective region of a geographic map of an electric grid.

The application discloses an object searching method, device, medium and equipment, relates to the technical field of Internet, and the method comprises the following steps: in response to an object searching operation, an object searching request is sent to a server; first candidate object set information returned by the server is received, the first candidate object set information is obtained by performing object content searching on a database of the server based on a search keyword and a dialogue identifier in the object searching request; based on the search keyword and the dialogue identifier, object title searching is performed on a database of a client to determine second candidate object set information; and according to the first candidate object set information and the second candidate object set information, display information of at least one object to be displayed is determined to be displayed on the client. The application can search for an object whose title or content abstract matches a search keyword, and the efficiency of the searching behavior is realized.

A method comprising determining a plurality of commodity objects meeting a search intent according to a commodity object search request submitted by a user; analyzing the plurality of commodity objects to obtain a plurality of commodity object combinations, and generating text content in units of commodity object combinations, wherein the text content is used for showing recommendation reason information corresponding to the commodity object combinations; and providing, to a client, the commodity object combinations and the corresponding text content to be displayed in a commodity search result page of the client. According to the present disclosure, information displayed on the commodity search result page can guide shopping, thus improving the browsing efficiency of users.

This disclosure relates to an object search method, apparatus, electronic device, storage medium, and product, and pertains to the fields of intelligent interaction and artificial intelligence technologies. The object search method includes: acquiring a search instruction related to a user intent, and determining a first interface image corresponding to a first interface displayed by the electronic device, the search instruction being used to search for a target object on the electronic device; determining an operation sequence, the operation sequence being determined based on the search instruction and the first interface image, and including multiple operation steps for searching the target object; invoking a target function corresponding to the multiple operation steps based on a functional interface, and executing the multiple operation steps included in the operation sequence through the target function to acquire and display the target object. This disclosure reduces the latency of the electronic device automatically searching for a target object based on a search instruction, achieving one-step access to user services.

This application discloses an object query method, apparatus, and electronic device, relating to the field of artificial intelligence. The specific technical solution is as follows: A first interface displays first dialogue information, which is used to indicate the search for a first object. The first interface includes a preview image captured by a camera. Based on the first dialogue information and the preview image, an object search is performed, and first information is output. The first information includes at least one of the following: the relative position information of the first object relative to the user; and the relative position information between the first object and a second object in the preview image.