Abstract: An optical lens includes: a first region, including a first incident surface and a first emergent surface that face each other, wherein the first incident surface is for, when a display panel is detected, receiving a first light ray from a plane region, and the first light ray exits from the first emergent surface after passing through the first region; a second region, connected to the first region, including a second incident surface and a second emergent surface that face each other, wherein the second incident surface is for, when the display panel is detected, receiving a second light ray that is from a curved-surface region and propagates in a first direction, and the second light ray exits from the second emergent surface in a second direction after passing through the second region; and the first emergent surface and the second emergent surface are located in a same plane.

Abstract: Provided is a method of training an image recognition model, the model is configured to detect a defect region in an image of a display substrate, the display substrate includes a display area and a connection area, and the method includes: acquiring a first training sample including images of n display substrates; dividing each of the images of n display substrates into a first sub image and a second sub image, the first sub image is an image of a display area, and the second sub image is an image of a connection area; inputting the first training sample into the image recognition model, the first training sample includes the first sub image and the second sub image; and adjusting at least one feature parameter of the image recognition model to reduce a difference between an output value of the model and a training value of the first training sample.

Abstract: Provided is a knowledge graph fusion method based on iterative completion, which includes: obtaining multiple knowledge graphs, and identifying each of entities of the multiple knowledge graphs; performing structure vector representation learning on each of entities to obtain a structure vector of each of entities, and performing entity name vector representation learning on each of entities to obtain an entity name vector of each of entities; determining a structural similarity between the entities according to the structure vector of each of entities, and determining an entity name similarity between the entities according to the entity name vector of each of entities; constructing a degree-aware-based co-attention network, and calculating an entity similarity between fused entities through the degree-aware-based co-attention network; and obtaining a high-confidence entity pair according to the entity similarity between the fused entities, and performing knowledge graph completion by iterative training to o

Abstract: The invention discloses a multi-triplets extraction method based on the entity relationship joint extraction model, comprises: performing segmentation processing on the target text, and tagging position, type and whether is involved with any relation or not of each word in the sentence; the joint extraction model of the entity relationship is established; the joint extraction model of the entity relationship is trained; the triple extraction is performed according to the joint extraction model of the entity relationship; the tri-part tagging scheme designed by the present invention is in the process of joint extraction of the entity relationship an entity that is not related to the target relationship can be excluded; the multi-triplets extraction method based on the entity relationship joint extraction model can be used to extract multiple triplets, and based on the model of the triplet extraction method of the present invention other models have stronger multi-triplets extraction capabilities.