Back to results
US 11,769,509 B2Granted
Speech-based contextual delivery of content
AssigneeMicroStrategy Incorporated
InventorsChristophe Touret, Eshika Manchanda
Life of this patent
Estimating the term…
Abstract
In some implementations, one or more computers receive audio data indicating an utterance of a first participant during a call with a second participant. The one or more computers obtain text of the utterance of the first participant. The one or more computers identify an information card associated with the utterance based on the text of the utterance of the first participant. The one or more computers provide information card data causing the identified information card to be provided, for presentation during the call, by a device associated with the second participant.
Claims20
A method performed by one or more computers, the method comprising:
- receiving, by the one or more computers, audio data indicating an utterance of a first participant during a call with a second participant;
- obtaining, by the one or more computers, text of the utterance of the first participant;
- storing, by the one or more computers, data indicating a set of keywords, wherein each keyword of the set of keywords is associated with at least one information card;
- identifying, by the one or more computers, a portion of the text of the utterance of the first participant that matches a particular keyword of the set of keywords;
- identifying, by the one or more computers, multiple information cards associated with the particular keyword;
- selecting, by the one or more computers, a first information card from the multiple information cards based at least in part on (i) a role or identity of the second participant, (ii) content retrieved from a database based on one or more words in the text of the utterance of the first participant other than the particular keyword, and (iii) content of one or more previous information cards that were presented during the call or one or more previous calls involving the first participant;
- populating, by the one or more computers, content of the first information card based on an authorization level of the second participant;
- and
- providing, by the one or more computers, information card data causing the first information card to be provided for presentation during the call by a device associated with the second participant.
6 more elements
A system comprising:
- one or more computers;
- and
- one or more computer-readable media storing instructions that, when executed by the one or more computers, cause the one or more computers to perform operations comprising:
- receiving, by the one or more computers, audio data indicating an utterance of a first participant during a call with a second participant;
- obtaining, by the one or more computers, text of the utterance of the first participant;
- storing, by the one or more computers, data indicating a set of keywords, wherein each keyword of the set of keywords is associated with at least one information card;
- identifying, by the one or more computers, a portion of the text of the utterance of the first participant that matches a particular keyword of the set of keywords;
- identifying, by the one or more computers, multiple information cards associated with the particular keyword;
- selecting, by the one or more computers, a first information card from the multiple information cards based at least in part on (i) a role or identity of the second participant (ii) content retrieved from a database based on one or more words in the text of the utterance of the first participant other than the particular keyword, and (iii) content of one or more previous information cards that were presented during the call or one or more previous calls involving the first participant;
- populating, by the one or more computers, content of the first information card based on an authorization level of the second participant;
- and
- providing, by the one or more computers, information card data causing the first information card to be provided for presentation during the call by a device associated with the second participant.
9 more elements
One or more non-transitory computer-readable media storing instructions that, when executed by the one or more computers, cause the one or more computers to perform operations comprising:
- receiving, by the one or more computers, audio data indicating an utterance of a first participant during a call with a second participant;
- obtaining, by the one or more computers, text of the utterance of the first participant;
- storing, by the one or more computers, data indicating a set of keywords, wherein each keyword of the set of keywords is associated with at least one information card;
- identifying, by the one or more computers, a portion of the text of the utterance of the first participant that matches a particular keyword of the set of keywords;
- identifying, by the one or more computers, multiple information cards associated with the particular keyword;
- selecting, by the one or more computers, a first information card from the multiple information cards based at least in part on (i) a role or identity of the second participant (ii) content retrieved from a database based on one or more words in the text of the utterance of the first participant other than the particular keyword, and (iii) content of one or more previous information cards that were presented during the call or one or more previous calls involving the first participant;
- populating, by the one or more computers, content of the first information card based on an authorization level of the second participant;
- and
- providing, by the one or more computers, information card data causing the first information card to be provided for presentation during the call by a device associated with the second participant.
6 more elements
Dependencies are inferred from the claim text.