ARTIFICIAL INTELLIGENCE DEVICE FOR RECOGNIZING SPEECH AND METHOD THEREOF

    公开(公告)号:EP4439398A3

    公开(公告)日:2024-10-09

    申请号:EP24194223.4

    申请日:2020-05-08

    Inventor: MIN, Sunki

    Abstract: An embodiment of the present disclosure provides an artificial intelligence device for recognizing speech, the artificial intelligence device comprising: a memory for storing an intention mapping table including a mapping item obtained by mapping text and intention information; and a processor which receives first speech data, generates first intention information corresponding to the first speech data by using the intention mapping table and a natural language processing (NLP) engine, receives second speech data if speech recognition on the first speech data has failed, generates second intention information corresponding to the second speech data, and adds, to the intention mapping table, a mapping item including the second intention information and first text converted from the first speech data, if speech recognition on the second speech data has been successfully performed.

    METHOD FOR AUTOMATICALLY DOCUMENTING A LABORATORY WORKFLOW

    公开(公告)号:EP4432294A1

    公开(公告)日:2024-09-18

    申请号:EP23162094.9

    申请日:2023-03-15

    Applicant: Labtwin GmbH

    Abstract: The invention relates to a method for automatically documenting a laboratory workflow via a control system (1), wherein the laboratory workflow is performed by a first user (2) inside a laboratory, wherein the laboratory comprises different laboratory devices (3) used for the laboratory workflow, wherein the control system (1) receives unstructured workflow data (4) from the different laboratory devices (3), wherein the unstructured workflow data (4) comprises documenting information about the performance of the laboratory workflow, wherein the control system (1) automatically documents the laboratory workflow by filling out a predefined template, wherein the template comprises data fields for different classes of data, wherein the control system (1) comprises a classification engine (5), wherein the classification engine (5) comprises one or more trained AI models (6), wherein the classification engine (5) receives the unstructured workflow data (4), wherein the classification engine (5) applies the one or more trained AI models (6) to analyze the unstructured workflow data (4), to extract the documenting information and to classify the documenting information into a group of classes including the classes of data of the template, wherein one of the one or more trained AI model (6) outputs classification certainties describing a probability of the classification being correct for each class, wherein the control system (1) fills out the data fields of the template by inputting the extracted documenting information into the data fields based on matching the classification with the classes of data of the template if the classification certainty for a respective class is above a predefined threshold, wherein, if the classification certainty for a respective data field is not above the predefined threshold, the control system (1) prompts a second user (8) to classify the documenting information.

Patent Agency Ranking