4results about How to "Interactive humanization" patented technology

The invention discloses a blind person auxiliary interaction method and system based on a multi-modal large model and a storage medium, and belongs to the technical field of artificial intelligence, and the method comprises the steps: obtaining a user voice instruction and an external environment image, and carrying out the preprocessing of the obtained data; inputting the preprocessed data into a pre-trained multi-modal large model to obtain an environment understanding result; integrating the environment understanding result into feedback information for voice output, and adjusting output intonations according to environment characteristics; the acquisition method of the pre-trained multi-modal large model comprises the following steps: acquiring historical multi-modal data; and inputting the historical multi-modal data into a pre-constructed multi-modal large model, carrying out fine tuning on the trained multi-modal large model through a base layer in a frozen model to obtain a trained multi-modal large model, fusing multi-modal information through the multi-modal large model, accurately identifying a user intention and a corresponding object in a complex environment, and carrying out real-time identification on the user intention and the corresponding object in the complex environment. Therefore, accurate scene description is fed back.

This invention discloses a multi-mode AI-powered smart memo and call reminder method, offering three scene switching modes: Boss Mode, Butler Mode, and Ox-Horse Mode. It supports user-defined AI greetings to the user and integrates memo, family birthday, anniversary, public holiday, calendar, and phone alarm functions. Users can freely choose reminder methods such as incoming calls, system notifications, and ringtone / vibration. Call reminders support AI voice interaction, allowing users to directly read out tasks, mark completions, postpone reminders, and schedule the next task. Birthdays and holidays can be accompanied by personalized call messages, and the alarm clock supports wake-up calls. This invention achieves compliant reminders by reading system do-not-disturb, mute, and volume permissions. Data is encrypted locally and synchronized with the cloud. With rich scenarios, user-friendly interaction, and complete and unified functions, it is suitable for smart reminders and schedule management on various mobile terminals.

The present invention proposes an industrial software data parsing system and method based on large language model AI technology, introduces large language model AI technology in the industrial Internet control process, identifies industrial software data parsing large language instructions through the AI ​​model of LLM, extracts classification keywords and performs intelligent analysis, and clusters the instructions, so that the system can better understand the industrial software data parsing instructions. Secondly, the present invention pushes the instructions to different industrial software data extraction parties through natural language processing of large language model AI technology, and obtains industrial software data of various types from different locations of the system such as native digital factories, industrial process control modules, and industrial product output modules for centralized analysis, and then optimizes and outputs natural language processing through large language model AI technology, so that the system's control platform interaction is humanized and the convenience and readability of data analysis are improved.

The invention relates to a method for predicting the consciousness level of an L3-level driving takeover driver, and the method comprises the steps: dividing a takeover road into three sections according to environment factors and a current task condition; respectively acquiring the environmental factor probability, the environmental factor relative importance, the scene awareness prediction probability and the environmental complexity of each section; and based on the environmental factor probability, the environmental factor relative importance, the scene awareness prediction probability and the environmental complexity, obtaining the scene awareness level of a single section, and summing to obtain the scene awareness level of the driver of the takeover road. The situation awareness level prediction value of the driver in the takeover process is obtained based on the prediction method, so that the automatic driving system can better know the alertness degree of the driver in different road sections and send out a takeover request in time, and therefore traffic accidents caused by driving misoperation are reduced; and intelligent cooperation between the automatic driving system and the driver is further realized, and intelligent and humanized interaction is carried out.