首页|Researchers Submit Patent Application, 'Systems And Methods For Levaraging Machi ne Learning To Enable User-Specific Real-Time Information Services For Identifia ble Objects Within A Video Stream', for Approval (USPTO 20240259640)
Researchers Submit Patent Application, 'Systems And Methods For Levaraging Machi ne Learning To Enable User-Specific Real-Time Information Services For Identifia ble Objects Within A Video Stream', for Approval (USPTO 20240259640)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
News editors obtained the following quote from the background information suppli ed by the inventors:“This disclosure is directed to identifying objects in a me dia stream. In particular, techniques are disclosed for leveraging machine learn ing to enable user-specific real-time information services for objects identified in a media stream.”As a supplement to the background information on this patent application, NewsRx correspondentsalso obtained the inventors’ summary information for this patent application: “Manually searching forinformation related to the people and obje cts visible within live and/or recorded video streams, especiallydiscontinued c ommercial products, requires a significant investment in time and effort. This o ften resultsin a break in focus of the video stream and takes the user’s attent ion away from the event/video streambeing watched. It also requires quite a bit of existing knowledge from each individual end-user in orderto uncover the inf ormation or services currently available regarding the real-world object itself (such asspecifically which handbag or dress someone is wearing, precisely which brand and model watch/digitaldevice a character in a movie is using, or the re al-world name of a lesser-known actor appearing brieflywithin a scene). By bein g able to receive real-time, user-specific information services related to each andevery identifiable object on screen, each individual experiencing a video st ream (and even multiple colocatedindividuals watching the same video stream to gether) could receive information about objects inthe video stream that are of interest to them. For example, each user may receive reviews and purchasinginfo rmation for identified objects, professional histories of actors or persons, or even comparisons ofthe object with the user’s existing equipment (e.g., compari son of a new smartphone with the user’scurrent smartphone). This provides signi ficantly enhanced value and personal satisfaction compared withtraditional, non -enhanced viewing experiences. This enhanced accessibility to object-specific in formationproducts and services would also be likely to increase the marketing a nd product placement values of theconstant stream of consumer products discerni ble in real-time and recorded broadcasts. This may alsosignificantly reduce the information and knowledge barriers required for the majority of end-users to interact with those products/services they desire during a fleeting moment of inte rest or inspiration.
NETL
NSTL
