-
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
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
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：US11327979B2
公开(公告)日：2022-05-10
申请号：US16708925
申请日：2019-12-10
Applicant: salesforce.com, inc.
Inventor： Jayesh Govindarajan , Nicholas Beng Tek Geh , Ammar Haris , Zachary Alexander , Scott Thurston Rickard, Jr. , Clifford Z. Huang
IPC: G06F16/00 , G06F16/2457 , G06F16/9032 , G06F16/903 , G06N20/00 , G06N20/20
Abstract: A multi-tenant system stores a hierarchy of machine-learned models, wherein each machine-learned model is configured to receive as input a set of search results and generate as output scores for ranking the set of search results. Each machine-learned model is associated with a set of dimensions. The system evaluates search query performance. Performance below a threshold causes a new model to be generated and added to the hierarchy of models. Upon execution of a new search query associated with the same set of dimensions as the newly created model, the new model is used to rank that search query's search results.
-
公开(公告)号：US11086471B2
公开(公告)日：2021-08-10
申请号：US15608618
申请日：2017-05-30
Applicant: salesforce.com, inc.
Inventor： Greg Thomas Pascale , Zachary Alexander , Scott Thurston Rickard, Jr.
IPC: G06F3/0481 , G06F16/34 , G06F16/248 , G06N3/10 , G06T11/20 , G06N20/00
Abstract: A user provides a description of a neural network to a visualization tool. The visualization tool displays a user interface that includes a visual of the neural network based on the description. If the user interacts with a node or connection, for example by placing a cursor on the node/connection in the user interface, the user interface displays information associated with the node/connection. If the user selects a node of a layer, the neural network is applied to an input that corresponds to the selection and the user interface displays the propagation of the input through the neural network. Additionally, the user interface displays results from applying the neural network to the input.
-
公开(公告)号：US11061955B2
公开(公告)日：2021-07-13
申请号：US16233420
申请日：2018-12-27
Applicant: salesforce.com, inc.
Inventor： Zachary Alexander , Naren M. Chittar , Alampallam R. Ramachandran , Anuprit Kale , Tiffany McKenzie , Sitaram Asur , Jacob Nathaniel Huffman
IPC: G06F16/35 , G06T11/20 , G06N20/00 , G06F16/332 , G06F16/33
Abstract: A data processing system analyzes a corpus of conversation data collected at an interactive conversation service to train an intent classification model. The intent classification model generates vectors based on the corpus of conversation data. A set of intents is selected and an intent seed input for each intent of the set of intents is input into the model to generate an intent vector corresponding to each intent. Vectors based on user inputs are generated and compared to the intent vectors to determine the intent.
-
Patent Agency Ranking
公开(公告)号：US20210149964A1
公开(公告)日：2021-05-20
申请号：US16685909
申请日：2019-11-15
Applicant: salesforce.com, inc.
Inventor： Yuanxin Wang , Anuprit Kale , Zachary Alexander , Na Cheng
IPC: G06F16/9032 , G06N20/00 , G06K9/62 , G06F17/27
Abstract: Disclosed are some implementations of systems, apparatus, methods and computer program products for integrating question generation and answer retrieval in a question answer system. The system generates a question using a set of documents and determines whether it is semantically distinct from questions in a question-answer repository. After determining that the question is semantically distinct from questions in the question-answer repository, the system adds the question to the question-answer repository. Upon receipt of a user-submitted question, the system uses the question-answer repository to identify a semantically similar question. The system retrieves an answer corresponding to the identified question from the question-answer repository and provides the answer in response to the user-submitted question.
-
公开(公告)号：US10803127B2
公开(公告)日：2020-10-13
申请号：US15601806
申请日：2017-05-22
Applicant: salesforce.com, inc.
IPC: G06F16/907 , G06F16/31 , G06F16/335 , G06F16/33 , G06N3/08 , G06N3/04 , G06F40/30
Abstract: A record management system retrieves relevance information through an information retrieval model that models relevance between users, queries, and records based on user interaction data with records. Relevance information between different elements of the record management system are determined through a set of learned transformations in the information retrieval model. The record management system can quickly retrieve relevance information between different elements of the record management system given the set of learned transformations in the information retrieval model, without the need to construct separate systems for different types of relevance information. Moreover, even without access to contents of records, the record management system can determine relevant records for a given query based on user interaction data and the determined relationships between users, queries, and records learned through the information retrieval model.
-
公开(公告)号：US10552432B2
公开(公告)日：2020-02-04
申请号：US15730660
申请日：2017-10-11
Applicant: salesforce.com, inc.
Inventor： Jayesh Govindarajan , Nicholas Beng Tek Geh , Ammar Haris , Zachary Alexander , Scott Thurston Rickard, Jr. , Clifford Z. Huang
IPC: G06F17/30 , G06F16/2457 , G06F16/9032 , G06F16/903 , G06N20/00
Abstract: A multi-tenant system stores a hierarchy of machine-learned models, wherein each machine-learned model is configured to receive as input a set of search results and generate as output scores for ranking the set of search results. Each machine-learned model is associated with a set of dimensions. The system evaluates search query performance. Performance below a threshold causes a new model to be generated and added to the hierarchy of models. Upon execution of a new search query associated with the same set of dimensions as the newly created model, the new model is used to rank that search query's search results.
-
公开(公告)号：US20180101537A1
公开(公告)日：2018-04-12
申请号：US15730660
申请日：2017-10-11
Applicant: salesforce.com, inc.
Inventor： Jayesh Govindarajan , Nicholas Beng Tek Geh , Ammar Haris , Zachary Alexander , Scott Thurston Rickard, JR. , Clifford Z. Huang
IPC: G06F17/30
CPC classification number: G06F16/24578 , G06F16/2457 , G06F16/90324 , G06F16/90348 , G06N20/00
Abstract: A multi-tenant system stores a hierarchy of machine-learned models, wherein each machine-learned model is configured to receive as input a set of search results and generate as output scores for ranking the set of search results. Each machine-learned model is associated with a set of dimensions. The system evaluates search query performance. Performance below a threshold causes a new model to be generated and added to the hierarchy of models. Upon execution of a new search query associated with the same set of dimensions as the newly created model, the new model is used to rank that search query's search results.
-
30.发明申请公开(公告)号：US20180096372A1
公开(公告)日：2018-04-05
申请号：US15721346
申请日：2017-09-29
Applicant: salesforce.com, inc.
Inventor： Scott Thurston Rickard, JR. , Elizabeth Rachel Balsam , Tracy Morgan Backes , Zachary Alexander
CPC classification number: G06N5/022 , G06N3/08 , G06N5/003 , G06N7/005 , G06N20/00 , G06N20/10 , G06N20/20 , G06Q30/0201 , G06Q30/0203 , G06Q30/0204
Abstract: An online system stores objects representing potential transactions of an enterprise. The online system uses predictor models to determine an aggregate score based on values of the objects associated with a time interval, for example, a month. Each object is configured to take one of a plurality of states. The online system stores historical data describing activities associated with potential transaction objects and uses the stored data for generating the predictor models. The online system categorizes the objects into bins based on states of the objects. The online system may generate different predictions for each category. The online system may use machine learning based models as predictor models. The online system extracts features describing potential transaction objects and provides these as input to the predictor model.
-
-
-
-
-
-
-
-
-
Search Results
30
records
(took 0.017 seconds)
