2results about How to "No input required" patented technology

The invention provides a computer remote login identification system based on artificial intelligence, which relates to the field of information systems, and comprises the following contents: a mobile terminal application plug-in which is used for sending a control signal to a mobile terminal system and is interconnected with a cloud processor depending on a mobile terminal, the mobile terminal system controls the mobile terminal to execute the corresponding information acquisition module according to the control signal, keyword prompt information is acquired through pre-feature recognition of the mobile terminal system according to the content of information acquired by the information acquisition module, and the keyword prompt information is sent to the cloud processor by the mobile terminal; and the computer end application plug-in is used for being interconnected with the cloud processor. According to the method, the corresponding application plug-ins are used on the mobile terminal and the computer to obtain the remote unlocking instruction for the user to log in the computer on the mobile terminal in a mode of reducing the running pressure, the mode is simple, tedious input operation is not needed, and the operation efficiency is improved.

The application provides a method, device, equipment and medium for improving expression base expression capability, the method comprising: extracting initial semantic parameters of each frame of three-dimensional reconstruction data based on an initial expression parameterization model, and generating an initial parameterization result by driving a preset face model through a first expression base corresponding to the initial semantic parameters; comparing the initial parameterization result under each first expression base with the three-dimensional reconstruction data to determine whether the initial parameterization result and the three-dimensional reconstruction data match; if not, generating expression residual data according to error information of the initial parameterization result and the three-dimensional reconstruction data; adjusting the initial expression parameterization model using the expression residual data to obtain an adjusted second parameterization model, and driving the face model through a second expression base determined by the second parameterization model to generate a second parameterization result matching the three-dimensional reconstruction data. The application does not need manual input of external data, thereby improving efficiency.