US2023169279A1PendingUtilityA1

System for providing dialogue guidance

61
Individually held — no corporate assignee on recordPriority: Sep 6, 2018Filed: Aug 29, 2022Published: Jun 1, 2023
Est. expirySep 6, 2038(~12.1 yrs left)· nominal 20-yr term from priority
Inventors:Daniel L. Coffing
G06F 40/56G06F 16/3329G06V 40/20G06F 40/20G06F 40/35
61
PatentIndex Score
0
Cited by
0
References
0
Claims

Abstract

Various aspects of the subject technology relate to a dialogue guidance system. The dialogue guidance system is configured to receive input data captured from a communication event among at least a first participant and a second participant. The input data may include one or more of text data, audio data, or video data. The dialogue guidance system is configured to identify, based on the input data, one of a sentiment or a disposition corresponding to the communication event, determine dialogue guidance for the first participant based on one of the sentiment or the disposition, and provide the dialogue guidance to the first participant.

Claims

exact text as granted — not AI-modified
1 . (canceled) 
     
     
         2 . An apparatus for dialogue guidance, the apparatus comprising:
 at least one memory; and   at least one processor, the at least one processor configured to:
 store a history of interactions involving a plurality of participants of the interactions; 
 analyze the history of interactions to identify at least one sentiment expressed by at least a subset of the plurality of participants through at least a subset of the interactions; 
 edit content of an excerpt of dialogue based on the at least one sentiment expressed by at least a subset of the plurality of participants to generate edited content for the excerpt of dialogue; and 
 provide an indication of the edited content for the excerpt of dialogue. 
   
     
     
         3 . The apparatus of  claim 2 , wherein the content of the excerpt of dialogue includes a string of text, and wherein, to edit the content to generate the edited content for the excerpt of dialogue, the at least one processor is configured to edit the string of text based on the at least one sentiment expressed by at least the subset of the plurality of participants to generate an edited string of text. 
     
     
         4 . The apparatus of  claim 2 , wherein the content of the excerpt of dialogue includes a spoken dialogue, and wherein, to edit the content to generate the edited content for the excerpt of dialogue, the at least one processor is configured to edit the spoken dialogue based on the at least one sentiment expressed by at least the subset of the plurality of participants to generate an edited spoken dialogue. 
     
     
         5 . The apparatus of  claim 2 , the at least one processor configured to:
 edit the content of the excerpt of dialogue to increase a likelihood of persuasiveness to at least the subset of the plurality of participants based on the at least one sentiment to generate the edited content for the excerpt of dialogue.   
     
     
         6 . The apparatus of  claim 2 , the at least one processor configured to:
 edit the content of the excerpt of dialogue based on the at least one sentiment without changing a topic of the excerpt of dialogue to generate the edited content for the excerpt of dialogue.   
     
     
         7 . The apparatus of  claim 2 , the at least one processor configured to:
 transmit the edited content for the excerpt of dialogue to a recipient device at a specified time to provide the edited content for the excerpt of dialogue.   
     
     
         8 . The apparatus of  claim 2 , wherein, to analyze the history of interactions to identify at least one sentiment, the at least one processor is configured to analyze at least one of a gaze of at least one of the plurality of participants, a respiratory response of the at least one of the plurality of participants, an audible response from the at least one of the plurality of participants, a disposition of the at least one of the plurality of participants, or a facial expression of the at least one of the plurality of participants. 
     
     
         9 . The apparatus of  claim 2 , wherein the at least one sentiment includes at least one disposition. 
     
     
         10 . The apparatus of  claim 2 , wherein, to analyze the history of interactions to identify at least one sentiment, the at least one processor is configured to analyze the history of interactions according to at least one rule for communication. 
     
     
         11 . The apparatus of  claim 2 , the at least one processor configured to:
 provide the edited content for the excerpt of dialogue as an audio clip to provide the edited content for the excerpt of dialogue.   
     
     
         12 . The apparatus of  claim 2 , the at least one processor configured to:
 provide the edited content for the excerpt of dialogue as a text string to provide the edited content for the excerpt of dialogue.   
     
     
         13 . The apparatus of  claim 2 , the at least one processor configured to:
 use at least one machine learning model to analyze the history of interactions to identify the at least one sentiment expressed by at least the subset of the plurality of participants through at least a subset of the interactions.   
     
     
         14 . The apparatus of  claim 13 , the at least one processor configured to:
 identify at least one reaction to the edited content for the excerpt of dialogue from at least one of the plurality of participants; and   update the machine learning model based on the at least one reaction and on the edited content for the excerpt of dialogue.   
     
     
         15 . The apparatus of  claim 2 , the at least one processor configured to:
 identify at least one reaction to the edited content for the excerpt of dialogue from at least one of the plurality of participants;   edit the edited content of the excerpt of dialogue further based on the at least one reaction to generate secondary edited content for the excerpt of dialogue; and   provide the secondary edited content for the excerpt of dialogue.   
     
     
         16 . A method for dialogue guidance, the method comprising:
 storing a history of interactions involving a plurality of participants of the interactions;   analyzing the history of interactions to identify at least one sentiment expressed by at least a subset of the plurality of participants through at least a subset of the interactions;   editing content of an excerpt of dialogue based on the at least one sentiment expressed by at least a subset of the plurality of participants to generate edited content for the excerpt of dialogue; and   providing an indication of the edited content for the excerpt of dialogue.   
     
     
         17 . The method of  claim 16 , wherein editing the content of the excerpt of dialogue based on the at least one sentiment to generate the edited content for the excerpt of dialogue includes editing the content of the excerpt of dialogue to increase a likelihood of persuasiveness to at least the subset of the plurality of participants based on the at least one sentiment. 
     
     
         18 . The method of  claim 16 , wherein editing the content of the excerpt of dialogue based on the at least one sentiment to generate the edited content for the excerpt of dialogue includes editing the content of the excerpt of dialogue based on the at least one sentiment without changing a topic of the excerpt of dialogue. 
     
     
         19 . The method of  claim 16 , wherein analyzing the history of interactions to identify the at least one sentiment includes using at least one machine learning model to analyze the history of interactions to identify the at least one sentiment. 
     
     
         20 . The method of  claim 19 , further comprising:
 identifying at least one reaction to the edited content for the excerpt of dialogue from at least one of the plurality of participants; and   updating the at least one machine learning model based on the at least one reaction and on the edited content for the excerpt of dialogue.   
     
     
         21 . The method of  claim 16 , further comprising:
 identifying at least one reaction to the edited content for the excerpt of dialogue from at least one of the plurality of participants;   editing the edited content of the excerpt of dialogue further based on the at least one reaction to generate secondary edited content for the excerpt of dialogue; and   providing the secondary edited content for the excerpt of dialogue.   
     
     
         22 . A non-transitory, computer-readable storage medium, having embodied thereon instructions executable by one or more processors to perform a method for dialogue guidance, the method comprising:
 storing a history of interactions involving a plurality of participants of the interactions;   analyzing the history of interactions to identify at least one sentiment expressed by at least a subset of the plurality of participants through at least a subset of the interactions;   editing content of an excerpt of dialogue based on the at least one sentiment expressed by at least a subset of the plurality of participants to generate edited content for the excerpt of dialogue; and   providing an indication of the edited content for the excerpt of dialogue.

Join the waitlist — get patent alerts

Track US2023169279A1 — get alerts on status changes and closely related new filings.

We store only your email — no account needed. See our privacy policy.