-
公开(公告)号：US11172063B2
公开(公告)日：2021-11-09
申请号：US15986787
申请日：2018-05-22
Inventor： Conor McGann , Ioana Grigoropol , Mariya Orshansky , Ankit Pat
Abstract: A system and method for engaging in an automated dialog with a user. A processor retrieves a preset dialog flow that includes various blocks directing the dialog with the user. The processor provides a prompt to the user based on a current block of the dialog flow, receives an action from the user in response to the prompt, and retrieves a classification/decision tree corresponding to the dialog flow. The classification tree has a plurality of nodes mapped to the blocks of the dialog flow. Each of the nodes represents a user intent. The processor computes a probability for each of the nodes based on the action from the user. A particular one of the nodes is then selected based on the computed probabilities. A target block of the dialog flow is further identified based on the selected node, and a response is output in response to the identified target block.
-
公开(公告)号：US11019205B2
公开(公告)日：2021-05-25
申请号：US16819072
申请日：2020-03-14
Inventor： Conor McGann , Ioana Grigoropol , Mariya Orshansky , Ankit Pat
Abstract: A method for engaging in an automated dialog with a user that includes: retrieving a preset dialog flow that includes various blocks directing the dialog with the user; providing a prompt to the user based on a current block of the dialog flow; receiving an action from the user in response to the prompt; and retrieving a classification tree corresponding to the dialog flow. The classification tree has a plurality of nodes mapped to the blocks of the dialog flow representing user intents. The processor computes a probability for each of the nodes based on the action from the user. A particular one of the nodes is then selected based on the computed probabilities. A target block of the dialog flow is identified based on the selected node, and a response is output in response to the identified target block.
-
Patent Agency Ranking
公开(公告)号：US20180336896A1
公开(公告)日：2018-11-22
申请号：US15986787
申请日：2018-05-22
Inventor： Conor McGann , Ioana Grigoropol , Masha Orshansky , Ankit Pat
CPC classification number: H04M3/4936 , G06F17/18 , H04M3/4935 , H04M2203/355 , H04M2203/556
Abstract: A system and method for engaging in an automated dialog with a user. A processor retrieves a preset dialog flow that includes various blocks directing the dialog with the user. The processor provides a prompt to the user based on a current block of the dialog flow, receives an action from the user in response to the prompt, and retrieves a classification/decision tree corresponding to the dialog flow. The classification tree has a plurality of nodes mapped to the blocks of the dialog flow. Each of the nodes represents a user intent. The processor computes a probability for each of the nodes based on the action from the user. A particular one of the nodes is then selected based on the computed probabilities. A target block of the dialog flow is further identified based on the selected node, and a response is output in response to the identified target block.
-
公开(公告)号：US20200267260A1
公开(公告)日：2020-08-20
申请号：US16819072
申请日：2020-03-14
Inventor： Conor McGann , Ioana Grigoropol , Mariya Orshansky , Ankit Pat
Abstract: A method for engaging in an automated dialog with a user that includes: retrieving a preset dialog flow that includes various blocks directing the dialog with the user; providing a prompt to the user based on a current block of the dialog flow; receiving an action from the user in response to the prompt; and retrieving a classification tree corresponding to the dialog flow. The classification tree has a plurality of nodes mapped to the blocks of the dialog flow representing user intents. The processor computes a probability for each of the nodes based on the action from the user. A particular one of the nodes is then selected based on the computed probabilities. A target block of the dialog flow is identified based on the selected node, and a response is output in response to the identified target block.
-
公开(公告)号：US20180338041A1
公开(公告)日：2018-11-22
申请号：US15986766
申请日：2018-05-22
Inventor： Conor McGann , Ioana Grigoropol , Masha Orshansky , Ankit Pat
CPC classification number: H04M3/4936 , G06F17/18 , H04M3/4935 , H04M2203/355 , H04M2203/556
Abstract: A system and method for engaging in an automated dialog with a user. A processor retrieves a preset dialog flow that includes various blocks directing the dialog with the user. The processor provides a prompt to the user based on a current block of the dialog flow, receives an action from the user in response to the prompt, and retrieves a classification/decision tree corresponding to the dialog flow. The classification tree has a plurality of nodes mapped to the blocks of the dialog flow. Each of the nodes represents a user intent. The processor computes a probability for each of the nodes based on the action from the user. A particular one of the nodes is then selected based on the computed probabilities. A target block of the dialog flow is further identified based on the selected node, and a response is output in response to the identified target block.
-
公开(公告)号：US11734648B2
公开(公告)日：2023-08-22
申请号：US16890508
申请日：2020-06-02
Inventor： Jessica Li , Leor Grebler , Ankit Pat , William Zhao
IPC: G10L15/26 , G06Q10/10 , G06N3/08 , G06F40/295 , G06F18/2113
CPC classification number: G06Q10/10 , G06F18/2113 , G06F40/295 , G06N3/08 , G10L15/26
Abstract: A system and method are presented relating to emotion-based action recommendations. The present invention may include a recommender engine that analyzes several pieces of information and using artificial intelligence derived models, provides a course of action for a contact center agent and the probability and estimations behind the recommendation as a justification. System inputs include cost of the item or service being troubleshooted, estimated costs for different resolutions, cost of each escalation level of the interaction, history of previous interactions, agent costs, history of the current interaction, acoustic events and sentiment or primary detected emotions of the customer's transcript. The recommended course of action, rationale, and authorization can be provided as output. The system may record whether the agent followed the recommendation to improve further recommendations.
-
公开(公告)号：US20210374671A1
公开(公告)日：2021-12-02
申请号：US16890508
申请日：2020-06-02
Inventor： Jessica Li , Leor Grebler , Ankit Pat , William Zhao
IPC: G06Q10/10 , G06K9/62 , G10L15/26 , G06F40/295 , G06N3/08
Abstract: A system and method are presented relating to emotion-based action recommendations. The present invention may include a recommender engine that analyzes several pieces of information and using artificial intelligence derived models, provides a course of action for a contact center agent and the probability and estimations behind the recommendation as a justification. System inputs include cost of the item or service being troubleshooted, estimated costs for different resolutions, cost of each escalation level of the interaction, history of previous interactions, agent costs, history of the current interaction, acoustic events and sentiment or primary detected emotions of the customer's transcript. The recommended course of action, rationale, and authorization can be provided as output. The system may record whether the agent followed the recommendation to improve further recommendations.
-
-
-
-
-
-
Search Results
7
records
(took 0.014 seconds)
