A computer system configured for autonomous learning of entity values is provided. The computer system includes a memory that stores associations between entities and fields of response data. The computer system also includes a processor configured to receive a request to process an intent; generate a request to fulfill the intent; transmit the request to a fulfillment service; receive, from the fulfillment service, response data specifying values of the fields; identify the values of the fields within the response data; identify the entities via the associations using the fields; store, within the memory, the values of the fields as values of the entities; and retrain a natural language processor using the values of the entities.

A computer system configured for autonomous learning of entity values is provided. The computer system includes a memory that stores associations between entities and fields of response data. The computer system also includes a processor configured to receive a request to process an intent; generate a request to fulfill the intent; transmit the request to a fulfillment service; receive, from the fulfillment service, response data specifying values of the fields; identify the values of the fields within the response data; identify the entities via the associations using the fields; store, within the memory, the values of the fields as values of the entities; and retrain a natural language processor using the values of the entities.

An apparatus and computer implemented method that include obtaining, into a computer, text of a patent, automatically finding and extracting, using the computer, a set of claim text from the patent text, identifying, using the computer, text of independent claims from the set of claim text, displaying in a first row on a computer monitor the text of the independent claims, automatically determining a plurality of preliminary scope-concept phrases from the text of the independent claims, displaying in a second row on the computer monitor the text of the plurality of preliminary scope-concept phrases, eliciting and receiving user input to specify a first one of the plurality of preliminary scope-concepts phrases, and highlighting each occurrence of the specified first one of the plurality of preliminary scope-concept phrases in a plurality of the independent claims displayed in the first row. A scope concept builder tool is also provided.

An apparatus and computer implemented method that include obtaining, into a computer, text of a patent, automatically finding and extracting, using the computer, a set of claim text from the patent text, identifying, using the computer, text of independent claims from the set of claim text, displaying in a first row on a computer monitor the text of the independent claims, automatically determining a plurality of preliminary scope-concept phrases from the text of the independent claims, displaying in a second row on the computer monitor the text of the plurality of preliminary scope-concept phrases, eliciting and receiving user input to specify a first one of the plurality of preliminary scope-concepts phrases, and highlighting each occurrence of the specified first one of the plurality of preliminary scope-concept phrases in a plurality of the independent claims displayed in the first row. A scope concept builder tool is also provided.

A computer-implemented method, a computer system and a computer program product reduce bandwidth requirements of a virtual collaboration session. The method includes capturing session data from a virtual collaboration session. The session data is selected from a group consisting of video data, audio data, an image of a screen of a connected device and text data. The method also includes connecting to a live blog platform. The method further includes transmitting a text transcription of the virtual collaboration session to the live blog platform. The text transcription is generated by scanning the audio data using a speech-to-text algorithm. In addition, the method includes classifying a topic in the virtual collaboration session based on importance. Lastly, the method includes transmitting a multimedia file related to the topic to the live blog platform in response to the topic being classified as important. The multimedia file is extracted from the session data.

A computer-implemented method, a computer system and a computer program product reduce bandwidth requirements of a virtual collaboration session. The method includes capturing session data from a virtual collaboration session. The session data is selected from a group consisting of video data, audio data, an image of a screen of a connected device and text data. The method also includes connecting to a live blog platform. The method further includes transmitting a text transcription of the virtual collaboration session to the live blog platform. The text transcription is generated by scanning the audio data using a speech-to-text algorithm. In addition, the method includes classifying a topic in the virtual collaboration session based on importance. Lastly, the method includes transmitting a multimedia file related to the topic to the live blog platform in response to the topic being classified as important. The multimedia file is extracted from the session data.

Systems, methods, and apparatuses for contextual natural language understanding are detailed. An exemplary method includes receiving a user utterance provided by a user within a multi-turn chat dialog between the user and a conversational agent; providing to a contextual natural language understanding framework: the user utterance, and contextual information associated with one or more previous turns of the multi-turn chat dialog, the contextual information associated with each turn of the one or more previous turns including a previous intent, a previous dialog act, and an elicited slot; and obtaining, from the contextual natural language understanding framework, an intent classification and one or more slot labels.

Systems, methods, and apparatuses for contextual natural language understanding are detailed. An exemplary method includes receiving a user utterance provided by a user within a multi-turn chat dialog between the user and a conversational agent; providing to a contextual natural language understanding framework: the user utterance, and contextual information associated with one or more previous turns of the multi-turn chat dialog, the contextual information associated with each turn of the one or more previous turns including a previous intent, a previous dialog act, and an elicited slot; and obtaining, from the contextual natural language understanding framework, an intent classification and one or more slot labels.

A business flow creation support device 1 includes a generation unit 11 that receives an effect and a sentence indicating what is desired to be realized, which are input by a user, and generates a flow including a plurality of clauses obtained by morphologically analyzing the sentence, a presentation unit 12 that acquires scores indicating to which fields the effect and words included in the clauses are close, respectively, and presents, to the user, a template of a business flow in a field having a high total score, and a creation support unit 14 that support creation of the business flow corresponding to the effect and the sentence.

A business flow creation support device 1 includes a generation unit 11 that receives an effect and a sentence indicating what is desired to be realized, which are input by a user, and generates a flow including a plurality of clauses obtained by morphologically analyzing the sentence, a presentation unit 12 that acquires scores indicating to which fields the effect and words included in the clauses are close, respectively, and presents, to the user, a template of a business flow in a field having a high total score, and a creation support unit 14 that support creation of the business flow corresponding to the effect and the sentence.