公开(公告)号：US20210150146A1

公开(公告)日：2021-05-20

申请号：US16687626

申请日：2019-11-18

Applicant: salesforce.com, inc.

Inventor： Zachary Alexander ,  Edgar Gerardo Velasco ,  Victor Winslow Yee ,  Na Cheng ,  Khoa Le

IPC: G06F40/30 ,  G06F16/33 ,  G06F16/332 ,  G06N20/00

Abstract: A system is configured to analyze a corpus of historical chat data to identify the list of “best” responses. As such, the user is not required to identify a list of canned responses for input into the system. The described system uses a context word embedding function and response word embedding function to generate context vectors and response vectors corresponding to the corpus of conversation data, and the vectors are represented by a respective context matrix and a response matrix. The system processes these matrices to generate scores for responses, clusters the responses, and identifies the responses corresponding to the best scores for each cluster.

公开(公告)号：US11379671B2

公开(公告)日：2022-07-05

申请号：US16687626

申请日：2019-11-18

Applicant: salesforce.com, inc.

Inventor： Zachary Alexander ,  Edgar Gerardo Velasco ,  Victor Winslow Yee ,  Na Cheng ,  Khoa Le

IPC: G06F40/30 ,  G06F16/33 ,  G06N20/00 ,  G06F16/332

Abstract: A system is configured to analyze a corpus of historical chat data to identify the list of “best” responses. As such, the user is not required to identify a list of canned responses for input into the system. The described system uses a context word embedding function and response word embedding function to generate context vectors and response vectors corresponding to the corpus of conversation data, and the vectors are represented by a respective context matrix and a response matrix. The system processes these matrices to generate scores for responses, clusters the responses, and identifies the responses corresponding to the best scores for each cluster.

公开(公告)号：US11790894B2

公开(公告)日：2023-10-17

申请号：US17202077

申请日：2021-03-15

Applicant: salesforce.com, inc.

Inventor： Yixin Mao ,  Zachary Alexander ,  Victor Winslow Yee ,  Joseph R. Zeimen ,  Na Cheng ,  Chien-Sheng Wu ,  Wenhao Liu ,  Caiming Xiong

IPC: G10L15/16 ,  H04L51/02 ,  G10L15/06 ,  G10L15/08 ,  G10L15/22 ,  G06F16/33 ,  G06F40/56

CPC classification number: G10L15/16 ,  G10L15/063 ,  G10L15/08 ,  G10L15/22 ,  H04L51/02 ,  G06F16/3344 ,  G06F40/56

Abstract: A system uses conversation engines to process natural language requests and conduct automatic conversations with users. The system generates responses to users in an online conversation. The system ranks generated user responses for the online conversation. The system generates a context vector based on a sequence of utterances of the conversation and generates response vectors for generated user responses. The system ranks the user responses based on a comparison of the context vectors and user response vectors. The system uses a machine learning based model that uses a pretrained neural network that supports multiple languages. The system determines a context of an utterance based on utterances in the conversation. The system generates responses and ranks them based on the context. The ranked responses are used to respond to the user.

公开(公告)号：US20220293094A1

公开(公告)日：2022-09-15

申请号：US17202077

申请日：2021-03-15

Applicant: salesforce.com, inc.

Inventor： Yixin Mao ,  Zachary Alexander ,  Victor Winslow Yee ,  Joseph R. Zeimen ,  Na Cheng ,  Chien-Sheng Wu ,  Wenhao Liu ,  Caiming Xiong

IPC: G10L15/16 ,  H04L12/58 ,  G10L15/22 ,  G10L15/08 ,  G10L15/06

Abstract: A system uses conversation engines to process natural language requests and conduct automatic conversations with users. The system generates responses to users in an online conversation. The system ranks generated user responses for the online conversation. The system generates a context vector based on a sequence of utterances of the conversation and generates response vectors for generated user responses. The system ranks the user responses based on a comparison of the context vectors and user response vectors. The system uses a machine learning based model that uses a pretrained neural network that supports multiple languages. The system determines a context of an utterance based on utterances in the conversation. The system generates responses and ranks them based on the context. The ranked responses are used to respond to the user.