Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

3results about How to "Eliminate clutter" patented technology

Noise reducing eyewear

ActiveCN224387627Ureduce carryReduce the use effectGogglesEarplugsProtecting eyeEyewear
The utility model relates to the technical field of protective appliance especially is concerned on a kind of noise reduction goggles, including mirror frame and temple, the both ends of mirror frame are hinged respectively with temple, mirror frame is equipped with goggles lens, temple is equipped with noise reduction pendant, noise reduction pendant is equipped with adjusting mechanism, cotton thread and noise reduction earplug, one end of cotton thread is connected in adjusting mechanism, its other end is connected in noise reduction earplug, adjusting mechanism is installed in temple, and the length of cotton thread is adjusted, to release or retract noise reduction earplug. From the above, the efficient integration of the goggles and the noise reduction earplug is achieved, providing one-key retracting and automatic indexing function, significantly improving user experience and operation convenience, while ensuring the stability and safety of the equipment, suitable for a variety of high-noise scenes, meeting the user's needs in protecting eyes and hearing, also improving the practicability and aesthetics of the product.
Owner:SHENZHEN HANMAI TECHNOLOGY CO LTD

Short video recommendation algorithm based on causal inference and graph convolution network

PendingCN122240876AFully capture positive interestCapture negative feedback fullyDigital data information retrievalBiological models
To address the issue of user viewing behavior being easily influenced by confounding factors such as video duration in short video recommendation, leading to distorted interest modeling, this paper proposes a short video recommendation method based on causal inference and graph convolutional networks. First, a do-operator is introduced to explicitly intervene in users' historical behavior, weakening the confounding effect of duration bias on interest expression and obtaining more realistic preference signals. Second, positive and negative sample sets are constructed, and representation learning and aggregation are performed separately through differentiated graph convolutional networks to achieve multi-dimensional user preference modeling. Furthermore, graph propagation mechanisms and expert network design are combined to enhance the model's ability to characterize complex interest structures. Experimental results show that this method can effectively alleviate confounding bias and improve recommendation performance and model robustness.
Owner:LIAONING UNIVERSITY

Method and system for automatic processing of accessory results for multi-source remote sensing images

This invention relates to the field of image processing technology, specifically to an automated processing method and system for ancillary results of multi-source remote sensing imagery. The method includes: parsing and extracting core parameters such as side viewpoint, temporal phase, and data source type for each remote sensing image from the original metadata file set, generating a set of structured metadata objects; generating a set of standard scene numbers based on the data source type, track number, and image acquisition time information in the structured metadata object set; and batch-producing the full-scene image metadata files, projection information files, and coordinate information files for each remote sensing image based on the completed full-scene image set, standard scene number set, and structured metadata object set, thus obtaining an initial set of ancillary results. This invention, by parsing and extracting core parameters and generating a set of structured metadata objects, provides a unified, accurate, and machine-readable data source for all subsequent automated steps, eliminating production errors caused by misunderstandings of metadata at the source.
Owner:湖南省自然资源调查所