公开(公告)号：US11449525B2

公开(公告)日：2022-09-20

申请号：US16775024

申请日：2020-01-28

Applicant: salesforce.com, inc.

Inventor： Subrata Ashe

IPC: G06F7/00 ,  G06F16/27 ,  H04L67/10 ,  H04L67/02 ,  G06F16/21 ,  G06F16/9535 ,  G10L15/22 ,  G06F16/9032 ,  G06F16/2452

Abstract: Disclosed are systems, methods, apparatus and computer program products for facilitating voice-based interaction by a mobile device with an enterprise database. In some implementations, a command and a type of enterprise work record are identified in a first one or more voice signals obtained at the mobile device. One or more fields of the identified record type required by the enterprise database to be populated to carry out the identified command is determined. Field data can be identified in a second one or more voice signals obtained at the mobile device. Structured text data comprising the identified command, the identified record type and the identified field data can be sent to a server.

公开(公告)号：US11436636B2

公开(公告)日：2022-09-06

申请号：US14833300

申请日：2015-08-24

Applicant: Salesforce.com, Inc

Inventor： Byron Pitney ,  Jeffrey S. Cunning ,  Gabriel Joynt ,  Adam Fletcher ,  Srikant Rao

IPC: G06Q30/02

Abstract: In a method for communicating information about a service or product, a record can be retrieved from a database storing records of communications related to a second entity. The record can include information related to an identity of a first entity. The first entity can be defined, at a processor and based upon content of the record, as a member of a set designated to be sent the information about the product or service. The first entity can have previously engaged in a first communication related to the second entity. The second entity can be associated with the product or service. A second communication, which can include the information related to the identity of the first identity, can be sent from the processor to an advertising platform. A third communication, which can include the information about the product or service, can be sent from the processor to the advertising platform.

公开(公告)号：US11436481B2

公开(公告)日：2022-09-06

申请号：US16134957

申请日：2018-09-18

Applicant: salesforce.com, inc.

Inventor： Govardana Sachithanandam Ramachandran ,  Michael Machado ,  Shashank Harinath ,  Linwei Zhu ,  Yufan Xue ,  Abhishek Sharma ,  Jean-Marc Soumet ,  Bryan McCann

IPC: G06N3/08 ,  G06F16/35 ,  G06F40/00

Abstract: A method for natural language processing includes receiving, by one or more processors, an unstructured text input. An entity classifier is used to identify entities in the unstructured text input. The identifying the entities includes generating, using a plurality of sub-classifiers of a hierarchical neural network classifier of the entity classifier, a plurality of lower-level entity identifications associated with the unstructured text input. The identifying the entities further includes generating, using a combiner of the hierarchical neural network classifier, a plurality of higher-level entity identifications associated with the unstructured text input based on the plurality of lower-level entity identifications. Identified entities are provided based on the plurality of higher-level entity identifications.

公开(公告)号：US11436233B2

公开(公告)日：2022-09-06

申请号：US16258217

申请日：2019-01-25

Applicant: salesforce.com, inc.

Inventor： Arun Kumar Jagota

IPC: G06F16/2457 ,  G06F16/901 ,  G06F16/28 ,  G06F16/22

Abstract: A system creates graph of nodes connected by edges. Each node represents corresponding value of corresponding attribute and is associated with count of corresponding value. Each edge is associated with count of instances that values represented by corresponding connected nodes are associated with each other. The system identifies each node associated with first count as first set of keys, and deletes each node associated with first count. The system identifies each edge associated with second count as second set of keys, and deletes each edge associated with second count. The system identifies each node associated with third count as third set of keys, and deletes each node associated with third count. The system identifies each edge associated with fourth count as fourth set of keys, and deletes each edge associated with fourth count. The system uses each set of keys to search and match records.

公开(公告)号：US11436223B2

公开(公告)日：2022-09-06

申请号：US15419509

申请日：2017-01-30

Applicant: salesforce.com, inc.

Inventor： RamaLinga Raju Penmetsa ,  Prem Veeramani ,  Jeffrey Lallana Freschl ,  Jesse Collins ,  Ganesh Maganti

IPC: G06F16/2453

Abstract: Systems, methods, and computer-readable media for pinning query execution plans are described. A database system may obtain a query, and determine a organization identifier and/or user identifier associated with the query. The database system may identify an optimized plan among a set of query plans that correspond with the query, and may generate a query execution plan based on the query and the optimized plan. The database system may determine a pinned plan that is associated with the optimized plan, and may generate a query execution plan based on the pinned plan when the pinned plan is associated with the optimized plan and corresponds with the organization identifier and/or the user identifier. The database system may generate a query execution plan using optimization functions when the pinned plan is not associated with the pinned plan, or the organization identifier and/or the user identifier. Other embodiments may be described and/or claimed.

公开(公告)号：US20220277141A1

公开(公告)日：2022-09-01

申请号：US17187608

申请日：2021-02-26

Applicant: salesforce.com, inc.

Inventor： Erik Lennart Nijkamp ,  Caiming Xiong

IPC: G06F40/279 ,  G06F40/58

Abstract: A machine learning based model generates a feature representation of a text sequence, for example, a natural language sentence or phrase. The system trains the machine learning based model by receiving an input text sequence and perturbing the input text sequence by masking a subset of tokens. The machine learning based model is used to predict the masked tokens. A predicted text sequence is generated based on the predictions of the masked tokens. The system processes the predicted text sequence using the machine learning based model to determine whether a token was predicted or an original token. The parameters of the machine learning based model are adjusted to minimize an aggregate loss based on prediction of the correct word for a masked token and a classification of a word as original or replaced.

公开(公告)号：US11429714B2

公开(公告)日：2022-08-30

申请号：US16299851

申请日：2019-03-12

Applicant: salesforce.com, inc.

Inventor： Christian Meyer ,  Chris Lawrence

IPC: G06F21/62 ,  G06F21/55 ,  G06N3/04 ,  G06K9/62 ,  G06N3/08 ,  G06F9/54

Abstract: A method of operating a privacy management system for managing personal data includes receiving a first input indicative of a first user activity in accessing personal data stored within a memory element. The method also includes creating an activity model based on the first input. The activity model is indicative of typical activity in accessing personal data stored in the memory element. The method further includes receiving a second input indicative of a second user activity in accessing personal data stored within the memory element. Also, the method includes recognizing, according to the activity model, the second user activity as being anomalous to the typical activity in accessing personal data stored in the memory element. Moreover, the method includes generating, as a result of recognizing the second user activity as being anomalous, a command that causes at least one of the client devices to perform an anomaly corrective action.

公开(公告)号：US20220269801A1

公开(公告)日：2022-08-25

申请号：US17184096

申请日：2021-02-24

Applicant: salesforce.com, inc.

Inventor： Jimmy Hua ,  Gang Shu ,  Chong Pang ,  Nidhi Baheti ,  Liuxizi Xu ,  Barkkarn Aravinda Arasakutti Vetrivelu ,  Jaisudha Gunasekaran ,  Sai Prashanth Lakshminaraayana ,  Ravi Lakkanna Gowda Honakere ,  Bijoy Sarkar ,  Frédéric Voituret

IPC: G06F21/62 ,  H04L29/08 ,  H04L29/06 ,  G06F16/953

Abstract: Methods, systems, and devices for data processing are described. According to the techniques described herein, an application server may be used for real-time provisioning for features for a user. The application server may validate requests from the user for feature activation or deactivation and after validation, may communicate with a provisioning server, which may be non-local to the user or the application server, to indicate validation and activation or deactivation of a feature for the user.

公开(公告)号：US11425245B2

公开(公告)日：2022-08-23

申请号：US16678530

申请日：2019-11-08

Applicant: salesforce.com, inc.

Inventor： Molly Mahar ,  Nicholas Beng Tek Geh

IPC: H04M3/42 ,  H04L51/02 ,  H04L51/046 ,  H04M3/53 ,  H04M3/523 ,  H04L51/234

Abstract: Described herein is a system and method for capturing data associated with actions attempted by an automated agent. The system described herein captures data associated with the actions attempted by an automated agent during the messaging session between an automated agent and the user and present a summary of the actions in a messaging platform. In an embodiment, the automated agent uploads data associated with actions attempted during the messaging session to a server. The server captures the data associated with the actions and generates a description of each action that was attempted. The server generates a summary including the description of each action. The summary of the actions are rendered in the messaging platform.

公开(公告)号：US20220261651A1

公开(公告)日：2022-08-18

申请号：US17479565

申请日：2021-09-20

Applicant: salesforce.com, inc.

Inventor： Gerald Woo ,  Doyen Sahoo ,  Chu Hong Hoi

IPC: G06N3/08 ,  G06N3/04

Abstract: A multi-view contrastive relational learning framework is provided. In the multi-view contrastive relational learning framework, contrastive learning is augmented with a multi-view learning signal. The auxiliary views guide an encoder of the underlying time series data's main view, by using an inter-sample similarity structure as a learning signal to learn representations which encode information from multiple views.