Abstract: Methods, systems, and apparatuses include receiving network data for nodes of a graph network of an online system. Logging data is received for entities associated with the nodes Weakly labeled data is generated by filtering the logging data using the network data. Training data is generated for a relationship scoring machine learning model. The relationship scoring machine learning model is trained to determine relationship scores for the nodes by using the training data. Input data is generated for the trained relationship scoring machine learning model. The trained relationship scoring machine learning model is coupled to an input of a recommendation system to provide a recommendation.

Abstract: System and method for time-aware deep learning are provided. A training data set including continuous-time data and a deep learning architecture are received. A trained deep learning model is generated using a temporal kernel approach. The temporal kernel approach includes constructing a temporal kernel based on the continuous-time data and composing the temporal kernel with a selected hidden layer of the deep learning architecture to generate a hidden output. The trained deep learning model is output for use in one or more machine learning tasks.

Abstract: The invention relates to the technical field of microstructure refinement and homogenization of bearing steel, and specifically relates to a high-carbon bearing steel and a method of preparing same. The high-carbon bearing steel of the invention has the following chemical composition: C: 0.80˜1.20 wt %, Cr: 0.40˜2.0 wt %, Mn: 0.15˜0.75 wt %, Si: 0.15˜0.75 wt %, Nb: 0˜0.20 wt %, Mo: 0˜0.20 wt %, V: 0˜0.20 wt %, P?0.015 wt %, S?0.01 wt %, the remaining is Fe and unavoidable impurities; the contents of Nb, Mo and V are not 0 at the same time. According to the invention, microalloying elements such as Nb, Mo and V, in combination with other elements, are added into the high-carbon bearing steel to effectively refine the bearing steel matrix and promote the precipitation of a large amount of nano-carbides, thereby enhancing the contact fatigue life of the high-carbon bearing steel.

Abstract: A panoramic stitching method, a panoramic stitching apparatus, an electronic device, and a storage medium are provided. The panoramic stitching method comprises acquiring captured images from cameras in a same scene; obtaining a remapping lookup table and a fusion lookup table generated based on a stitching model; and mapping and fusing the captured images based on the remapping lookup table and the fusion lookup table to obtain a panoramic stitched output image. The stitching model comprises a hemisphere and a cylinder, and an origin of a virtual camera coordinate system associated with the cameras is located at a center of a bottom surface of the hemisphere. The bottom surface is where the hemisphere is in contact with the cylinder. This method effectively reduces camera parallax and alignment errors, significantly enhancing the quality of panoramic stitching, which is particularly well-suited for open horizontal scenes, delivering exceptional visual stitching results.

Abstract: A system including one or more processors and one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, perform certain acts. The acts can include obtaining training data. The acts also can include training candidate recommendation models and an adversarial exposure model using the training data. The acts additionally can include generating recommendations based on a selected recommendation model of the candidate recommendation models. Other embodiments are described.

Abstract: The present disclosure provides a remotely controllable dynamic lighting device and an intelligent lighting system. The device comprises modules such as power supply module and lighting control module, along with a support structure, featuring solar power supply, diverse lighting effects with RGB light strips, and convenient assembly/disassembly. The intelligent lighting system achieves adaptive lighting effects, with dual-mode power supply and remote interaction capabilities, enhancing lighting experience to meet diverse scenario requirements.

Abstract: Systems and methods including one or more processors and one or more non-transitory computer readable media storing computing instructions that, when executed on the one or more processors, cause the one or more processors to perform: receiving a user request via a graphical user interface, the user request corresponding to a user search query for a product; determining whether a first processing machine of the system is operating in a first processing mode or a second processing mode; when the first processing machine is determined to be operating in the first processing mode, analyzing the user request via the first processing machine and using a process, to identify a candidate recommendation system to utilize by: determining a randomized strategy for one or more candidate recommendation systems based on a ratio of a number of the one or more candidate recommender systems, the randomized strategy to be stored in a collected history data; determining model parameters based on the collected history data; and

Abstract: Techniques for a social networking system involve analyzing members' interactions to enhance follow recommendations. The techniques include calculating the number of follows generated by a first member and the number of follows received by a second and third member. The platform then computes a weighted follow utility score for two member pairs: the first comprising the first and second members, and the second comprising the first and third members. These scores are determined by equally weighing the follows generated and received, along with a probability of the first member following the second or third member. While the probability suggests a preference for the second member, the ranking system places the third member pair higher. Consequently, the first member is advised to follow the third member, based on this ranking. Finally, this recommendation is displayed to the first member on an electronic device, guiding their social interactions on the platform.

Abstract: Techniques for a social networking system involve analyzing members' interactions to enhance follow recommendations. The techniques include calculating the number of follows generated by a first member and the number of follows received by a second and third member. The platform then computes a weighted follow utility score for two member pairs: the first comprising the first and second members, and the second comprising the first and third members. These scores are determined by equally weighing the follows generated and received, along with a probability of the first member following the second or third member. While the probability suggests a preference for the second member, the ranking system places the third member pair higher. Consequently, the first member is advised to follow the third member, based on this ranking. Finally, this recommendation is displayed to the first member on an electronic device, guiding their social interactions on the platform.

Abstract: The present disclosure provides a remotely controllable dynamic lighting device and an intelligent lighting system. The device comprises modules such as power supply module and lighting control module, along with a support structure, featuring solar power supply, diverse lighting effects with RGB light strips, and convenient assembly/disassembly. The intelligent lighting system achieves adaptive lighting effects, with dual-mode power supply and remote interaction capabilities, enhancing lighting experience to meet diverse scenario requirements.

Abstract: A method for performing disaster recovery in a clustered environment comprises identifying, at a master device, a first indexer from a set of indexers to serve as a primary indexer for responding to queries pertaining to a subset of data. The method also comprises assigning, at the master device, a generation identifier indicating that the first indexer is the primary indexer for the subset of data. Responsive to an event prompting a change in a primary indexer designation for the subset of data, the method comprises identifying, at the master device, a second indexer from the set of indexers to serve as the primary indexer for responding to queries pertaining to the subset of data. Further, the method comprises assigning, at the master device, a new generation identifier indicating that the second indexer is the primary indexer for the subset of data.

Abstract: A corner marking method, a parameter calibration method, and an electronic device are provided. The corner marking method includes: acquiring a target image, the target image including at least a portion of a target chessboard; detecting corners in the target image; performing a chessboard reconstruction based on detected corners to acquire a reconstructed chessboard; if the reconstructed chessboard contains one or more of tagging squares, acquiring one of the tagging squares of the reconstructed chessboard as a reference square; acquiring an identification and orientation of the reference square based on a tag of the reference square; marking corners in the reconstructed chessboard based on the identification and orientation of the reference square. Even if the target image does not contain a complete target chessboard, the corner marking method described in the present disclosure is still capable of marking corners in the target image.

Abstract: An interface display method, an interface display apparatus, an electronic device and a medium are provided. The interface display method includes: for a list item in a data object list, creating an interface container proxy and arranging an interface data object of the list item in the interface container proxy; in response to a first update operation on a display interface, binding the interface container proxy to a corresponding interface container on the display interface if the first update operation is configured to instruct updating the list item to the display interface for display; and displaying the interface data object of the list item in the interface container proxy in a region that is on the display interface and that corresponds to the interface container according to a binding relationship between the interface container and the interface container proxy.

Abstract: A fresh-keeping vacuum bottle with two compartments for preserving freshness, specifically designed to tackle the technical challenges faced by existing similar products in packaging powder products like freeze-dried powder, for example, prone to moisture, and challenged to reuse and assemble as replacement bottles. The bottle mouth of the vacuum bottle body and the large circle are connected through snap fitting to create a lower liquid storage compartment. The large circle includes a fixed large circle, a rotating large circle, and an inner sleeve large circle, with the fixed large circle being connected through snap fitting to the mouth fixed on the bottle body. The rotating large circle rotates the sealing plug until the upper thru-hole of the rotating large circle, the middle thru-hole of the sealing plug, and the lower thru-hole of the fixed large circle are aligned sequentially to achieve dual-compartment mixing.

Abstract: A system including one or more processors and one or more non-transitory computer-readable media storing computing instructions configured to run on the one or more processors and perform generating one or more item relational graphs for one or more items based on historical user purchases; transforming, using spectral filtering, the one or more item relational graphs into one or more frequency signals to remove noise from the one or more frequency signals; constructing, using a machine learning model, one or more item pair label classifications for one or more item pairs of the one or more items; generating a respective similarity score for each of the one or more item pairs; outputting a top k results for the one or more item pairs ranked by the respective similarity scores; and re-ranking, using a re-ranking algorithm, the top k results of the one or more item pairs based on a user preference for display on a user interface of an electronic device of a user. Other embodiments are disclosed.

Abstract: A method for performing disaster recovery in a clustered environment comprises identifying, at a master device, a first indexer from a set of indexers to serve as a primary indexer for responding to queries pertaining to a subset of data. The method also comprises assigning, at the master device, a generation identifier indicating that the first indexer is the primary indexer for the subset of data. Responsive to an event prompting a change in a primary indexer designation for the subset of data, the method comprises identifying, at the master device, a second indexer from the set of indexers to serve as the primary indexer for responding to queries pertaining to the subset of data. Further, the method comprises assigning, at the master device, a new generation identifier indicating that the second indexer is the primary indexer for the subset of data.

Abstract: A method for performing disaster recovery in a clustered environment comprises identifying, at a master device, a first indexer from a set of indexers to serve as a primary indexer for responding to queries pertaining to a subset of data. The method also comprises assigning, at the master device, a generation identifier indicating that the first indexer is the primary indexer for the subset of data. Responsive to an event prompting a change in a primary indexer designation for the subset of data, the method comprises identifying, at the master device, a second indexer from the set of indexers to serve as the primary indexer for responding to queries pertaining to the subset of data. Further, the method comprises assigning, at the master device, a new generation identifier indicating that the second indexer is the primary indexer for the subset of data.

Abstract: The present disclosure provides an image sensor, which may include a driving layer, a negative electrode layer formed in the driving layer, a N-region layer formed above the negative electrode layer. The N-region layer includes multiple cylindrical structures formed of semiconductor materials. The image sensor may also include a light absorption layer formed above the N-region layer. The light absorption layer is composed of a multi-layer structure including a P-region layer formed using quantum dot semiconductor materials. The image sensor may further include a positive electrode layer formed above the light absorption layer and configured to receive incoming light signals.

Abstract: A method for performing disaster recovery in a clustered environment comprises identifying, at a master device, a first indexer from a set of indexers to serve as a primary indexer for responding to queries pertaining to a subset of data. The method also comprises assigning, at the master device, a generation identifier indicating that the first indexer is the primary indexer for the subset of data. Responsive to an event prompting a change in a primary indexer designation for the subset of data, the method comprises identifying, at the master device, a second indexer from the set of indexers to serve as the primary indexer for responding to queries pertaining to the subset of data. Further, the method comprises assigning, at the master device, a new generation identifier indicating that the second indexer is the primary indexer for the subset of data.