-
公开(公告)号：US20230368773A1
公开(公告)日：2023-11-16
申请号：US18196113
申请日：2023-05-11
Applicant: LIVEPERSON, INC.
Inventor： Amit Mishra
IPC: G10L13/033 , G10L15/06
CPC classification number: G10L13/033 , G10L15/063 , G10L2015/0631
Abstract: Systems and method are provided for generating personal virtual agents. A computing device may receive communication request from a first device associated with a particular domain. In response, the computing device may facilitate a connection between the first device and a personal virtual agent that was generated for a user corresponding of, wherein the first device. The computing device may execute the personal virtual agent using a subsequent communication from the first device to generate a response. The computing device may generate an accuracy metric corresponding to the response generated by the personal virtual agent. The personal virtual agent may be trained using the accuracy metric to improve subsequent response generated by the personal virtual agent with respect to the user of the first device.
-
公开(公告)号：US12254880B2
公开(公告)日：2025-03-18
申请号：US18208367
申请日：2023-06-12
Applicant: LIVEPERSON, INC.
Inventor： Amit Mishra
Abstract: The present disclosure relates generally to systems, methods, instructions, and other aspects describing automated transcription and associated script generation. In one aspect, a method includes facilitating a voice bot segment of a two-way communication session, where the voice bot segment is between a customer device and a non-human bot agent, and transfer of the session to a human agent device as part of a human voice segment of the two-way communication session, wherein the transfer occurs following a failure of the non-human bot agent to resolve a customer issue. Accessing survey data describing the two-way communication session, wherein the survey data is associated with successful resolution of the customer issue and automatically processing transcript data from the two-way communication with the survey data to identify language data from the transcript associated with resolution of the customer issue. The non-human bot agent is then dynamically updated using the language data.
-
3.发明公开公开(公告)号：US20240304031A1
公开(公告)日：2024-09-12
申请号：US18600941
申请日：2024-03-11
Applicant: LIVEPERSON, INC.
Inventor： Amit Mishra
IPC: G06V40/20 , G06V10/764 , G06V10/774 , G06V10/82 , G06V20/40 , G09B21/00
CPC classification number: G06V40/20 , G06V10/764 , G06V10/774 , G06V10/82 , G06V20/46 , G09B21/00
Abstract: A communication assist service may extract one or more video frames during a communication session between a user device and a terminal device. The video frames may include a representation of a gesture provided by a user of the user device. The communication assist service may generate a feature vector from the video frames and execute a trained neural network configured to generate classify the semantic meaning of gesture. The neural network may output the semantic meaning of the gesture, which may be used to generate an appropriate communication response to the gesture. The communication assist service may facilitate transmission of the communication response to a device of the new communication session in real time.
-
公开(公告)号：US20230410801A1
公开(公告)日：2023-12-21
申请号：US18208367
申请日：2023-06-12
Applicant: LIVEPERSON, INC.
Inventor： Amit Mishra
CPC classification number: G10L15/22 , H04M3/58 , H04M3/5166 , H04M3/5175 , H04M3/42221 , G06F9/451 , G10L15/063 , G10L15/30 , H04M2201/405 , H04M2242/08 , G10L2015/0635 , G10L15/18
Abstract: The present disclosure relates generally to systems, methods, instructions, and other aspects describing automated transcription and associated script generation. In one aspect, a method includes facilitating a voice bot segment of a two-way communication session, where the voice bot segment is between a customer device and a non-human bot agent, and transfer of the session to a human agent device as part of a human voice segment of the two-way communication session, wherein the transfer occurs following a failure of the non-human bot agent to resolve a customer issue. Accessing survey data describing the two-way communication session, wherein the survey data is associated with successful resolution of the customer issue and automatically processing transcript data from the two-way communication with the survey data to identify language data from the transcript associated with resolution of the customer issue. The non-human bot agent is then dynamically updated using the language data.
-
Patent Agency Ranking
5.发明授权公开(公告)号：US11875195B2
公开(公告)日：2024-01-16
申请号：US18121675
申请日：2023-03-15
Applicant: LIVEPERSON, INC.
Inventor： Amit Mishra , Thorsten Ohrstrom Sandgren
CPC classification number: G06F9/5077 , G06F9/505 , G06F9/45558 , G06F2009/45595
Abstract: Systems and method are provided for load balancing in distributed environments. A computing device may instantiate a first quantity of partitions within a processing node. The first set of partitions can be configured to support a service accessible by multiple user devices. The computing device may determine that a load value corresponding to the first quantity of partitions is greater than a threshold and in response, cause an autoscaler to instantiate a second quantity of partitions. The quantity of petitions in the second quantity of partitions may be determined based on the first quantity of partitions. The computing device may then modify the autoscaler based on an indication that the second quantity of partitions has been instantiated. Modifying the autoscaler can include adjusting the threshold to reduce a likelihood that a subsequent load value is greater than the threshold.
-
6.发明公开公开(公告)号：US20230297433A1
公开(公告)日：2023-09-21
申请号：US18121708
申请日：2023-03-15
Applicant: LIVEPERSON, INC.
Inventor： Amit Mishra , Thorsten Ohrstrom Sandgren
IPC: G06F9/50
CPC classification number: G06F9/505 , G06F9/5077
Abstract: Systems and method are provided for load balancing in distributed networks. A computing device uses historical resource allocation data associated with a service deployed within a distributed network to train a machine-learning model configured to generate a threshold processing load usable to determine when processing resources allocated to a service within a particular distributed network are to be increased. An autoscaler of the computing device may instantiate a first quantity of partitions within a processing node of the particular distributed network. The computing device may execute the machine-learning model using a load value associated with the first quantity of partitions to generate a threshold processing load. Upon receiving an updated load value that is greater than the threshold process load, the autoscaler may instantiate a second quantity of partitions and, in response, modify the autoscaler based on the updated load value.
-
公开(公告)号：US20240305744A1
公开(公告)日：2024-09-12
申请号：US18600926
申请日：2024-03-11
Applicant: LIVEPERSON, INC.
Inventor： Amit Mishra
CPC classification number: H04N7/15 , G06V10/25 , G06V10/44 , G06V10/82 , G06V2201/07
Abstract: A communication assist service may extract one or more video frames during a communication session between a user device and a terminal device. The video frames may include a representation of an object associated with an issue for which the communication session was established. The communication assist service may generate a feature vector from the video frames and execute a trained neural network configured to generate predictions associated with a resolution to the issue. The neural network may output predicted actions that if executed may resolve the issue or provide additional information that will improve a likelihood of resolving the issue. The communication assist service may then transmit the predicted actions to the terminal device in real time.
-
8.发明授权公开(公告)号：US11875190B2
公开(公告)日：2024-01-16
申请号：US18121708
申请日：2023-03-15
Applicant: LIVEPERSON, INC.
Inventor： Amit Mishra , Thorsten Ohrstrom Sandgren
CPC classification number: G06F9/505 , G06F9/5077
Abstract: Systems and method are provided for load balancing in distributed networks. A computing device uses historical resource allocation data associated with a service deployed within a distributed network to train a machine-learning model configured to generate a threshold processing load usable to determine when processing resources allocated to a service within a particular distributed network are to be increased. An autoscaler of the computing device may instantiate a first quantity of partitions within a processing node of the particular distributed network. The computing device may execute the machine-learning model using a load value associated with the first quantity of partitions to generate a threshold processing load. Upon receiving an updated load value that is greater than the threshold process load, the autoscaler may instantiate a second quantity of partitions and, in response, modify the autoscaler based on the updated load value.
-
9.发明公开公开(公告)号：US20230297441A1
公开(公告)日：2023-09-21
申请号：US18121675
申请日：2023-03-15
Applicant: LIVEPERSON, INC.
Inventor： Amit Mishra , Thorsten Ohrstrom Sandgren
IPC: G06F9/50
CPC classification number: G06F9/5077 , G06F9/505 , G06F9/45558
Abstract: Systems and method are provided for load balancing in distributed environments. A computing device may instantiate a first quantity of partitions within a processing node. The first set of partitions can be configured to support a service accessible by multiple user devices. The computing device may determine that a load value corresponding to the first quantity of partitions is greater than a threshold and in response, cause an autoscaler to instantiate a second quantity of partitions. The quantity of petitions in the second quantity of partitions may be determined based on the first quantity of partitions. The computing device may then modify the autoscaler based on an indication that the second quantity of partitions has been instantiated. Modifying the autoscaler can include adjusting the threshold to reduce a likelihood that a subsequent load value is greater than the threshold.
-
-
-
-
-
-
-
-
Search Results
9
records
(took 0.029 seconds)
