1. Q&A robot:
Information retrieval and search
Keywords: tfidf, SVM, Naive Bayes RNN、CNN
knowledge graph
Storing knowledge and relationships between knowledge in a graphical database, converting Q&A into query statements, and enabling inference
Common implementation ideas
speech-to-text
Intent recognition, domain recognition, text classification
Slot filling: For example, a robot buying a plane ticket uses command body recognition to fill two positions of the ticket from {position} to {position}
Reply management and reply strategy
natural language generation
text-to-speech

2. Visual and Image Processing

image processing
Image processing aims to process the original image to apply a certain transformation. The goal is usually to improve the image or use it as input for a specific task, while the goal of computer vision is to describe and interpret the image. For example, typical image processing components such as noise reduction, contrast, or rotation operations can be performed at the pixel level.
machine vision
It mainly refers to visual research in the industrial field, such as the vision of autonomous robots used for detection and measurement. This indicates that in this field, image perception and control theory are often closely integrated with image processing through software and hardware to achieve efficient robot control or various real-time operations.