Abstract: The invention relates to a method for lane-changing prediction of a target vehicle, the method including: receiving a velocity and a position of the target vehicle; respectively obtaining, based on the velocity and the position of the target vehicle, a first lane-changing probability and a second lane-changing probability of the target vehicle by using a first machine learning model and a second machine learning model; and determining a possibility of lane changing of the target vehicle based on the first lane-changing probability and the second lane-changing probability, the first machine learning model and the second machine learning model being pre-trained and being different from each other. The invention further relates to a device for lane-changing prediction of a target vehicle, a computer storage medium, and a vehicle.

Abstract: A display substrate, a manufacturing method thereof and a display apparatus are provided. In the present disclosure, a first transistor group with oxide semiconductor as an active layer material is disposed on a side of a second transistor group with polysilicon as an active layer material away from the base, and an area enclosed by orthographic projections of the transistors in the first transistor group on the base is overlapped with an area enclosed by orthographic projections of the transistors in the second transistor group on the base. Stable performance of the transistors included can be ensured in a manufacturing process of the first transistor group and the second transistor group located in different layers, and at the same time, an area occupied by the driving circuit can be reduced so as to decrease a frame width of a display apparatus or improve resolution of the display apparatus.

Abstract: A system that manages a dialog between a user and an AI system using a hierarchically structured tree of topics. An illustrative application is collection of a personal history. A topic manager repeatedly selects a topic and requests the AI system to generate a question based on summary information stored in the associated topic node; this avoids sending the entire dialog to the AI system each time, which would be impossible for long conversations due to AI context window limitations. The AI system analyzes each response from the user to identify new topics to add to the tree, and to update the summary associated with each topic node. Vector embeddings of topic names may be used to place new topic nodes in the most relevant position in the tree. Topics may be selected using a biased tree walk that preferentially selects nodes that have been less explored in previous questions.