首页|Researchers Submit Patent Application, 'Computer-Based Systems Utilizing Speech Pattern Recognition Machine Learning Models And Methods Of Use Thereof', for App roval (USPTO 20240127806)
Researchers Submit Patent Application, 'Computer-Based Systems Utilizing Speech Pattern Recognition Machine Learning Models And Methods Of Use Thereof', for App roval (USPTO 20240127806)
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:“A computer network platform/system may include a group of computers (e.g., clients, servers, smartrouters) and other computing hardware d evices that are linked together through one or more communicationchannels to fa cilitate communication and/or resource-sharing, via one or more specifically programmed graphical user interfaces (GUIs) of the present disclosure, among a wide range of users.”As a supplement to the background information on this patent application, NewsRx correspondentsalso obtained the inventors’ summary information for this patent application: “In some embodiments,the present disclosure provides an exemplary technically improved computer-based system/method/thatincludes at least the fo llowing components/steps of receiving, by a processor, at least one transcribedspeech file of speech of at least one person; identifying, by the processor, a p lurality of utterance-delimitedmultiword units in the at least one transcribed speech file; wherein each utterance-delimited multiwordunit corresponds to an i dentified utterance in the speech delimited by pauses in the speech of the at le astone person; generating, by the processor, a plurality of utterance-based dat a vectors corresponding to theplurality of utterance-delimited multiword units by assigning a numerical data token to each word in eachutterance-delimited mul tiword unit; wherein each utterance-based data vector comprises a sequence of numerical data tokens; determining, by the processor, at least one utterance-delim ited multiword unit fromthe plurality of utterance-delimited multiword units ha ving question-indicative word patterns by inputtingthe plurality of utterance-b ased data vectors into at least one machine learning model, configured to identify the question-indicative word patterns by computing a probability of a word, g roups of words, or bothin each of the plurality of utterance-delimited multiwor d units; and identifying, by the processor, at leastone question in the at leas t one transcribed speech file of the speech of the at least one person using thequestion-indicative word patterns identified in the at least one utterance-deli mited multiword unit.
NETL
NSTL
