Abstract: The present disclosure provides a method and apparatus of generating a meeting summary, an electronic device and a readable storage medium. The method of generating the meeting summary includes: receiving a generation request for generating a meeting summary of a target meeting, extracting a meeting record file of the target meeting according to the generation request, where the meeting record file includes a meeting audio recording and display data, and the meeting audio recording and the display data are collected through an intelligent meeting interaction device, and parsing the meeting record file to generate the meeting summary of the target meeting, where the meeting summary includes a spoken text generated according to the meeting audio recording and display data, and a time of the display data corresponds to a time of the meeting audio recording.

Abstract: A speech instruction recognition method, an electronic device, and a non-transient computer readable storage medium. The speech instruction recognition method comprises: acquiring a target speech; processing the target speech to obtain a target speech vector corresponding to the target speech; performing speech recognition on the target speech to obtain a target speech text of the target speech, and processing the target speech text to obtain a target text vector corresponding to the target speech text; and inputting the target speech vector and the target text vector to a pre-trained instruction recognition model to obtain an instruction category corresponding to the target speech.

Abstract: A method for event extraction according to the disclosure includes: processing an object text using a preset extraction model to determine event information of the object text; wherein the event information includes an event element, and an event type and a role corresponding to the event element; and the extraction model includes a classification layer and an output layer; the classification layer is configured to determine a token attribute of a token in the object text; the token attribute includes whether the token is a start token of the event element of any event type and any role, and whether the token is an end token of the event element of any event type and any role; and the output layer is configured to determine the event element according to the token attribute of the token, and determine the event type and the role corresponding to the event element.

Abstract: A conference content display method, a conference system and a conference device. The method includes: determining speech text corresponding to speech information, which is collected by a terminal of a conference participant; and displaying conference content related to the speech text.

Abstract: The present application provides a summary generation model training method, apparatus, electronic device, and non-transitory computer readable storage medium. The summary generation model training method includes: obtaining a first vector set, where vectors in the first vector set are original encoding vectors which have been trained; generating a second vector set based on the first vector set, where the number of vectors in the second vector set is greater than the number of the vectors in the first vector set, and each vector in the second vector set is determined according to one or more vectors in the first vector set; and taking the vectors included in the first vector set and the vectors included in the second vector set as input encoding vectors to perform model training to obtain a summary generation model.

Abstract: A speech instruction recognition method, an electronic device, and a non-transient computer readable storage medium. The speech instruction recognition method comprises: acquiring a target speech; processing the target speech to obtain a target speech vector corresponding to the target speech; performing speech recognition on the target speech to obtain a target speech text of the target speech, and processing the target speech text to obtain a target text vector corresponding to the target speech text; and inputting the target speech vector and the target text vector to a pre-trained instruction recognition model to obtain an instruction category corresponding to the target speech.

Abstract: A method for event extraction according to the disclosure includes: processing an object text using a preset extraction model to determine event information of the object text; wherein the event information includes an event element, and an event type and a role corresponding to the event element; and the extraction model includes a classification layer and an output layer; the classification layer is configured to determine a token attribute of a token in the object text; the token attribute includes whether the token is a start token of the event element of any event type and any role, and whether the token is an end token of the event element of any event type and any role; and the output layer is configured to determine the event element according to the token attribute of the token, and determine the event type and the role corresponding to the event element.

Abstract: The present application provides a summary generation model training method, apparatus, electronic device, and non-transitory computer readable storage medium. The summary generation model training method includes: obtaining a first vector set, where vectors in the first vector set are original encoding vectors which have been trained; generating a second vector set based on the first vector set, where the number of vectors in the second vector set is greater than the number of the vectors in the first vector set, and each vector in the second vector set is determined according to one or more vectors in the first vector set; and taking the vectors included in the first vector set and the vectors included in the second vector set as input encoding vectors to perform model training to obtain a summary generation model.