公开(公告)号：ZA202103455B

公开(公告)日：2022-08-31

申请号：ZA202103455

申请日：2021-05-21

Applicant: IBM

Inventor： BYAMUGISHA JOAN ,  YOUNG RICHARD ,  KURIEN TOBY ,  KHAN NAWEED AGHMAD ,  MOLAPO MALETSABISA

Abstract: Method, systems, and apparatus to facilitate navigation in a known environment. Communication and tracking between a receiver device and one or more beacons are provided to identify a current position of the receiver device. A direction to a next waypoint of a current path is determined based on the identified current position and a haptic feedback system is signaled to provide continuous haptic feedback to orient a user in the identified direction.

公开(公告)号：ZA202001992B

公开(公告)日：2021-05-26

申请号：ZA202001992

申请日：2020-05-04

Applicant: IBM

Inventor： KURIEN TOBY ,  YOUNG RICHARD ,  MOLAPO MALETSABISA ,  AKHALWAYA ISMAIL YUNUS

Abstract: Language models may be run with an input set of words in a given sentence. Each of the language models can predict a set of next candidate words to follow the input set or words. Based on the sets of next candidate words predicted by the language models and an actual next word, language guidance can be provided.

公开(公告)号：ZA202103618B

公开(公告)日：2022-09-28

申请号：ZA202103618

申请日：2021-05-27

Applicant: IBM

Inventor： MOLAPO MALETSABISA ,  MOODLEY CHANE SIMONE ,  MAKHANYA SIBUSISIWE AUDREY ,  MAPIYE DARLINGTON SHINGIRIRAI

Abstract: Method and systems for identifying dangers in an accessible environment. Computer vision and video analysis is performed on one or more images and/or video of the accessible environment to generate a series of still frames for a database of training images and natural language processing (NLP) is performed on one or more written reports to generate textual parameters. An online image similarity search is performed using the textual parameters to generate additional images for the database of training images and a risk/danger prediction model is generated based on the database of training images. One or more potential dangers are identified, and one or more warnings are generated using the risk/danger prediction model.