Abstract: According to the embodiments of the present disclosure, a method for conversion evaluation comprises: extracting a resource feature from resource-related data of a target resource; extracting an audience feature of the target audience group from audience-related data of a target audience group of the target resource, the target audience group being to be distributed with a recommended content item related to the target resource; and determining, based on the resource feature and the audience feature, a target predicted conversion rate for the target resource through a predetermined association between resource features, audience features and predicted conversion rates, the target predicted conversion rate indicating a predicted probability of the target audience group performing a conversion for the target resource. According to the scheme, the accuracy of the conversion rate evaluation may be improved, thereby improving distribution effect of the recommended content item for a resource.

Abstract: A handling robot (100), which relates to the field of warehouse logistics, comprises: a mobile chassis (10); a storage shelf (20) mounted to the mobile chassis (10), the storage shelf (20) comprising a plurality of layered plate components (21) distributed at different heights, each layered plate component (21) comprising a layered plate (210) for placing materials; a handling device (40), comprising a handling assembly (42), the handling assembly (42) being configured to handle a material to a layered plate (210) at the same height as the handling assembly (42), or to handle a material out of a layered plate (210) at the same height as the handling assembly (42); and a lift component (30), configured to drive the handling device (40) to lift relative to the storage shelf (20) so that the handling assembly (42) is at the same height as one layered plate (210).

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately, efficiently, and flexibly generating harmonized digital images utilizing a self-supervised image harmonization neural network. In particular, the disclosed systems can implement, and learn parameters for, a self-supervised image harmonization neural network to extract content from one digital image (disentangled from its appearance) and appearance from another from another digital image (disentangled from its content). For example, the disclosed systems can utilize a dual data augmentation method to generate diverse triplets for parameter learning (including input digital images, reference digital images, and pseudo ground truth digital images), via cropping a digital image with perturbations using three-dimensional color lookup tables (“LUTs”).

Abstract: Provided are a handling robot (600) and a handling assembly (100) thereof, and the handling assembly (100) includes a base component (10), a handling arm component (20), a hook (31) and a driving component (40). The handling arm component (20) is slidably mounted to the base component (10), and may perform a reciprocating linear movement on the base component (10). The driving component (40) is connected with the handling arm component (20), for driving the handling arm component (20) and the hook (31) to perform a reciprocating linear movement. Through the above structure, the handling assembly (100) pulling and pushing the material box (500) is realized without extending into two sides of the material box (500), thereby saving working space of the handling assembly (100), enabling the material boxes (500) of the warehousing to be placed next to each other, and improving the storage density of the warehouse.

Abstract: The present disclosure discloses a design method of a polymeric seawater desalination membrane based on a graph neural network, including the following steps: S1: constructing a knowledge graph of element-molecular group-molecular structure based on chemical knowledge, and constructing a molecular structure information data set; S2: obtaining related data of design and manufacture of a polymeric desalination membrane, establishing a seawater desalination membrane database, and performing characterization processing suitable for a graph neural network model with reference to analysis of the structure information data set to generate an adjacency matrix; S3: building the graph neural network; S4: outputting a design model of the polymeric seawater desalination membrane by training the graph neural network; and S5: predicting a chemical structure meeting seawater desalination membrane performance requirements for seawater desalination by using the design model of the polymeric seawater desalination membrane.

Abstract: A handling robot used in a field of warehouse logistics comprises a mobile chassis, and a storage shelf. The storage shelf is mounted to the mobile chassis and comprises a plurality of layered plate components distributed at different heights. The handling robot further comprises a handling device configured to transport a material to a layered plate of the plurality of layered plate components, and a lift component configured to drive the handling device to lift relative to the storage shelf.

Abstract: The present disclosure relates to the field of intelligent warehousing technologies, and provides a shelf and a warehousing system, to resolve a technical problem that it is difficult to control a spacing between adjacent goods on a shelf. The shelf includes a support frame and a first conveyor and a second conveyor arranged on the support frame. The first conveyor and the second conveyor form a goods conveying layer for conveying goods. The first conveyor is hinged with the support frame. The first conveyor is rotatably switched to a first limit position or a second limit position. When the first conveyor is at the first limit position, a second end of the first conveyor protrudes from an upper surface of the second conveyor, so that an end surface of the second end of the first conveyor is configured to block goods on the second conveyor.

Abstract: A transportation apparatus (30), includes a bracket (31), a telescopic apparatus (32) and a manipulator (33), where the bracket is mounted to a storage shelf (20), the telescopic apparatus is mounted to the bracket, the manipulator is mounted to the telescopic apparatus, and the telescopic apparatus is used for driving the manipulator to move along a horizontal first reference line (S5) or a horizontal second reference line (S6). The manipulator is driven to move on the first reference line and second reference line that are disposed orthogonally, and thereby the manipulator is able to load or unload goods at any position on the first reference line or second reference line, so as to avoid time being wasted on adjusting an angle of a transportation robot (100). The transportation apparatus has a high transportation efficiency.

Abstract: A goods loading or unloading control method is applicable to a goods loading or unloading device. The goods loading or unloading device includes a storage unit. The storage unit is provided with a goods outlet and a roller conveyor. The roller conveyor has an outer contour surface configured for rolling contact with goods in the storage unit. The roller conveyor is configured to rotate about a rotation axis thereof. The method includes: receiving a goods loading or unloading instruction; and controlling a rotation state of the roller conveyor according to the goods loading or unloading instruction, so as to convey goods outside the storage unit to outside of the goods outlet through the storage unit.

Abstract: The present disclosure provides a goods taking mechanism and a carrying device. The goods taking mechanism includes a fixed member, a first clamping plate, a second clamping plate, and a driving assembly, where the first clamping plate and the second clamping plate are oppositely mounted on the fixed member and are connected to the driving assembly, and the first clamping plate and the second clamping plate are movable relative to the fixed member under the action of the driving assembly, to act on two opposing sides of a to-be-moved object. The goods taking mechanism of the present disclosure can clamp to-be-moved objects of different sizes, which helps reduce the distance between the adjacent to-be-moved objects.