SYSTEMS AND METHODS FOR CONVERSATION ORCHESTRATION USING FINE-TUNED LARGE LANGUAGE MODELS

    公开(公告)号:US20240281619A1

    公开(公告)日:2024-08-22

    申请号:US18582984

    申请日:2024-02-21

    申请人: KORE.AI, INC.

    IPC分类号: G06F40/40

    CPC分类号: G06F40/40

    摘要: A virtual assistant server determines one or more use cases of one or more utterances received from one or more customer devices. The virtual assistant server executes one or more dialog flows corresponding to the one or more use cases of the one or more utterances, where the executing comprises providing one or more inputs to a fine-tuned large language model comprising: use case context, customer context, conversation context, business rules, and exit conditions. The virtual assistant server receives one or more outputs corresponding to the one or more inputs from the fine-tuned large language model, and determines one or more responses based on the one or more outputs. Subsequently, the virtual assistant server provides the one or more responses to the one or more customer devices.

    Systems and methods for recommending dialog flow modifications at a contact center

    公开(公告)号:US12058288B1

    公开(公告)日:2024-08-06

    申请号:US18105075

    申请日:2023-02-02

    申请人: KORE.AI, INC.

    IPC分类号: H04M3/00 G06F40/40 H04M3/51

    摘要: A contact center server manages conversation data for a plurality of conversations between agent devices and customer devices and provides to the agent devices, one or more automated response recommendations to one or more customer messages by executing one or more dialog flows. The contact center server, using a classification model, determines for each of the one or more customer messages when there are one or more changes between the corresponding one or more automated response recommendations and corresponding one or more agent responses. Further, the contact center server associates one or more tags to the one or more agent responses when the one or more changes are determined. Subsequently, the contact center server identifies one or more patterns in the one or more tags associated to the one or more agent responses and provides one or more flow modification recommendations to the one or more dialog flows to one or more enterprise user devices based on the identified one or more patterns.

    Systems and methods for comparing versions of a virtual assistant

    公开(公告)号:US11977880B2

    公开(公告)日:2024-05-07

    申请号:US17748168

    申请日:2022-05-19

    申请人: Kore.ai, Inc.

    IPC分类号: G06F8/71

    CPC分类号: G06F8/71

    摘要: A virtual assistant server receives a selection of at least two versions of a virtual assistant for comparison from a client device and compares metadata corresponding to each component of the at least two versions. The virtual assistant server presents to the client device, based on the compared metadata, a list of components of the at least two versions and a type of change made to one or more components of the list of components. The virtual assistant server receives from the client device, a selection corresponding to the one or more components of the list of components and presents to the client device, a comparison of definitions of the at least two versions of the selected one or more components of the list of components.

    Methods for managing automated discovery and knowledge sharing in one or more networks and devices thereof

    公开(公告)号:US11461417B2

    公开(公告)日:2022-10-04

    申请号:US16810522

    申请日:2020-03-05

    申请人: Kore.ai, Inc.

    摘要: A virtual assistant server receives a user input from a virtual assistant interface available on a client system associated with a user identified by a user identifier. Upon receiving the user input, the virtual assistant server creates a search network of repositories not associated with the user identifier by determining, for the received user input, a priority score of each repository not associated with the user identifier based on interactions of the user identifier through the virtual assistant interface. Further, the virtual assistant server searches, for the received user input, in a repository associated with the user identifier and in the repositories in the search network. Based on the searching, a group of one or more results corresponding to the received user input are identified and returned to the client system associated with the user identifier.

    SYSTEMS AND METHODS FOR RECOMMENDING DIALOG FLOW MODIFICATIONS AT A CONTACT CENTER

    公开(公告)号:US20240267464A1

    公开(公告)日:2024-08-08

    申请号:US18105075

    申请日:2023-02-02

    申请人: KORE.AI, INC.

    IPC分类号: H04M3/51 G06F40/40

    摘要: A contact center server manages conversation data for a plurality of conversations between agent devices and customer devices and provides to the agent devices, one or more automated response recommendations to one or more customer messages by executing one or more dialog flows. The contact center server, using a classification model, determines for each of the one or more customer messages when there are one or more changes between the corresponding one or more automated response recommendations and corresponding one or more agent responses. Further, the contact center server associates one or more tags to the one or more agent responses when the one or more changes are determined. Subsequently, the contact center server identifies one or more patterns in the one or more tags associated to the one or more agent responses and provides one or more flow modification recommendations to the one or more dialog flows to one or more enterprise user devices based on the identified one or more patterns.

    Methods for orchestrating an automated conversation in one or more networks and devices thereof

    公开(公告)号:US11823082B2

    公开(公告)日:2023-11-21

    申请号:US16868250

    申请日:2020-05-06

    申请人: Kore.ai, Inc.

    摘要: A virtual assistant server receives an utterance from an input mechanism. Upon receiving the utterance, the virtual assistant server, evaluates the utterance to identify a plurality of intents corresponding to the utterance and calculates common scores using natural language processing techniques for each of the identified plurality of intents. The virtual assistant server ranks the identified plurality of intents based on the calculated common scores and based on the ranking identifies a first winning intent and a second winning intent. Subsequently, the virtual assistant server prioritizes one of the first winning intent or the second winning intent to identify a final winning intent based on context information. The virtual assistant server executes the final winning intent and forwards a response to the input mechanism.