首页|"Processing Crowd-Sourced Information Using Machine Learning Based Language Mode ls" in Patent Application Approval Process (USPTO 20240303710)
"Processing Crowd-Sourced Information Using Machine Learning Based Language Mode ls" in Patent Application Approval Process (USPTO 20240303710)
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
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-A patent application by the inventors Prasad, Shishir Kumar (Fremont, CA, US); Putrevu, Jagannath (Danville, CA, US); Tan, Li (Fremont, CA, US); Tenneti, Tejaswi (San Carlos, CA, US); Wang, Haixun ( Bellevue, WA, US); Wu, Aomin (Scarsdale, NY, US), filed on March 5, 2024, was ma de available online on September 12, 2024, according to news reporting originati ng from Washington, D.C., by NewsRx correspondents. This patent application has not been assigned to a company or institution. The following quote was obtained by the news editors from the background informa tion supplied by the inventors: "Systems such as online systems often store larg e amounts of unstructured data. For example, a system may store a large corpus o f documents comprising unstructured data. An online system may receive user feed back representing unstructured text. Often such unstructured data includes infor mation that is useful to other users. Typical techniques for searching through s uch data include text search techniques. If the data comprises a large number of smAll documents, for example, documents representing user feedback, conventiona l text search techniques for processing the data can be inefficient. For example , several documents may match a search request, thereby requiring significant ma nual effort to process the search results."
NETL
NSTL
