公开(公告)号：US20210374759A1

公开(公告)日：2021-12-02

申请号：US17154619

申请日：2021-01-21

Applicant: salesforce.com, inc.

Inventor： Prithvi Krishnan Padmanabhan ,  Amanda Grady

IPC: G06Q30/00 ,  G06T11/20 ,  H04W4/021

Abstract: Methods, systems, and devices supporting physical proximity graphing are described. Some systems may store a limited set of location information for a set of humans (e.g., refraining from tracking device location information to maintain user privacy). A system may send a survey to each person indicating a suggested list of people based on the location information. The people may provide feedback confirming whether encounters occurred with each suggested human. The system may use this information to generate a graph using hashed identifiers to obfuscate user identities, where the graph tracks connections between people (e.g., based on encounters within a time period). Based on a trigger event, the system may analyze the graph and identify a set of hashed identifiers connected to a person of interest (e.g., traversing multiple levels of the graph). The system may transmit messages to people corresponding to the identified set of hashed identifiers.

公开(公告)号：US20210374524A1

公开(公告)日：2021-12-02

申请号：US17098007

申请日：2020-11-13

Applicant: salesforce.com, inc.

Inventor： Yihao Feng ,  Caiming Xiong

IPC: G06N3/08 ,  G06K9/62 ,  G06N3/063

Abstract: Some embodiments of the current disclosure disclose methods and systems for detecting out-of-distribution (ODD) data. For example, a method for detecting ODD data includes obtaining, at a neural network composed of a plurality of layers, a set of training data generated according to a distribution. Further, the method comprises generating, via a processor, a feature map by combining mapping functions corresponding to the plurality of layers into a vector of mapping function elements and mapping, by the feature map, the set of training data to a set of feature space training data in a feature space. Further, the method comprises identifying, via the processor, a hyper-ellipsoid in the feature space enclosing the feature space training data based on the generated feature map. In addition, the method comprises determining, via the processor, the first test data sample is OOD data when a mapped first test data sample in the feature space is outside the hyper-ellipsoid.

公开(公告)号：US20210374520A1

公开(公告)日：2021-12-02

申请号：US16886470

申请日：2020-05-28

Applicant: salesforce.com, inc.

Inventor： Arthur Zhang ,  Joshua Correa

IPC: G06N3/08 ,  G06N7/00

Abstract: Systems, devices, and techniques are disclosed for recommendations using a transformer neural network. User activity data including items and actions associated with users and a catalog including descriptions of the items may be received. User vectors for the users, item vectors for the items and action vectors the actions may be generated by applying singular vector decomposition to the user activity data. Sequence vectors may be generated based on item vectors and the action vectors. Transformer vectors may be generated by applying a text-to-text transferring transformer to descriptions of the items. Similarity vectors may be generated based on the transformer vectors. Merged vectors may be generated by merging the sequence vector, transformer vector, and similarity vector for items. A set of probabilities may be determined by inputting the user vector for the user, merged vectors for the items, and sequence vectors for the actions to a transformer neural network.

公开(公告)号：US20210374353A1

公开(公告)日：2021-12-02

申请号：US17005316

申请日：2020-08-28

Applicant: salesforce.com, inc.

Inventor： Jianguo Zhang ,  Kazuma Hashimoto ,  Chien-Sheng Wu ,  Wenhao Liu ,  Richard Socher ,  Caiming Xiong

IPC: G06F40/30 ,  G10L15/16

Abstract: An online system allows user interactions using natural language expressions. The online system uses a machine learning based model to infer an intent represented by a user expression. The machine learning based model takes as input a user expression and an example expression to compute a score indicating whether the user expression matches the example expression. Based on the scores, the intent inference module determines a most applicable intent for the expression. The online system determines a confidence threshold such that user expressions indicating a high confidence are assigned the most applicable intent and user expressions indicating a low confidence are assigned an out-of-scope intent. The online system encodes the example expressions using the machine learning based model. The online system may compare an encoded user expression with encoded example expressions to identify a subset of example expressions used to determine the most applicable intent.

公开(公告)号：US20210373949A1

公开(公告)日：2021-12-02

申请号：US17390213

申请日：2021-07-30

Applicant: salesforce.com, inc.

Inventor： Bhinav Sura ,  Dilip Devaraj ,  Rajavardhan Sarkapally ,  Kirankumar Kakanuru Gowdru

IPC: G06F9/48

Abstract: A scheduling application is used to acquire into memory of a first processing system running on a computer system, a first jobs load for execution by the first processing system, the first jobs load stored in a database's table and having a first load size, the database associated with the computer system. The scheduling application is used to acquire into memory of a second processing system, a second jobs load for execution by a second processing system. The second jobs load being included in the table and having a second load size being balanced with the first load size and including jobs not in the first jobs load. In the first processing system's memory, jobs in the first jobs load are scheduled for execution by the first processing system. In the second processing system's memory, jobs in the second jobs load are scheduled for execution by the second processing system.

公开(公告)号：USD937288S1

公开(公告)日：2021-11-30

申请号：US29743881

申请日：2020-07-24

Applicant: salesforce.com, inc.

Designer： Diana Berlin ,  Nate Botwick ,  John Arlan Brock ,  Matthew Chan ,  Andrew Chung ,  Ben Cronin ,  Justin Edmund ,  David Engelberg ,  Merwan Hade ,  Christopher De La Iglesia ,  Anh Khuc ,  Norris Lee ,  Christopher Masterson ,  Kyle Meyer ,  Pedram Razavi ,  Yang Su

公开(公告)号：US11190511B2

公开(公告)日：2021-11-30

申请号：US16261217

申请日：2019-01-29

Applicant: salesforce.com, inc.

Inventor： Jagadeesh Kunda ,  Ariel Anant Chavan ,  Qian Han ,  Yifan Wang ,  Kamran Riaz Khan ,  Vishal Agarwal

IPC: H04L29/06 ,  G06F21/45

Abstract: Techniques are disclosed relating to generating authentication information independent of user input. In some embodiments, an authentication application repeatedly performs operations to authenticate a client application to one or more hosts of a server system during an automated tasks. In some such embodiments, an instance of the operations includes receiving, from the client application, a request to generate authentication information. In response to the request, the authentication application may retrieve authentication data for the user and, independent of user input, generate an item of authentication information based on the authentication data. The authentication application may then output the item of authentication information to the client application, where the item of authentication information is usable by the client application to authenticate to at least one of the one or more hosts.

公开(公告)号：US11190509B2

公开(公告)日：2021-11-30

申请号：US15960321

申请日：2018-04-23

Applicant: salesforce.com, inc.

Inventor： Matthew Wong ,  Alan Vangpat ,  Sean Tubbs ,  Sarah Lui ,  William C. Mortimore, Jr. ,  Itzik Koren

IPC: H04L29/06 ,  G06F21/62

Abstract: Techniques are disclosed relating to user authentication. In some embodiments, a computing system maintains an exception handler of a software development platform. The exception handler is executable to process a particular type of exception that causes an authentication of users of applications running on the software development platform. The computing system may receive, at the exception handler, an indication of the particular type of exception thrown by a particular application. In response to receiving the indication of the particular type of exception, the exception handler issues to a web browser interacting with the application, a request that the web browser redirect to an authentication server configured to perform an authentication of a user of the particular application. The computing system receives, from the authentication server, a result of the performed authentication and returns the result to the particular application.

公开(公告)号：US11190344B2

公开(公告)日：2021-11-30

申请号：US16425729

申请日：2019-05-29

Applicant: salesforce.com, inc.

Inventor： Prasad Peddada ,  Taher Elgamal

IPC: H04L9/14 ,  H04L9/08 ,  H04L9/30 ,  H04L9/32

Abstract: A method is disclosed. The method includes, in a client device, acquiring first and second asymmetric cryptographic key pairs for a user, where each key pair includes a public key and a corresponding private key, securing the private key of the second key pair in a cryptographic processor, and splitting the private key of the first key pair into plural private key fragments, so that a sum of the plural private key fragments equals the private key of the first key pair. The method further includes storing at least one of the plural private key fragments on the client device, and registering the user with an identity service not hosted on the client device. Registering the user includes providing to the identity service, for use in securely authenticating the user, the public keys of the first and second key pairs, and the plural private key fragment(s) excluding the at least one private key fragment secured on the client device.

公开(公告)号：US20210367874A1

公开(公告)日：2021-11-25

申请号：US17164810

申请日：2021-02-01

Applicant: salesforce.com, inc.

Inventor： Shauli Gal ,  Satish Raghunath ,  Kartikeya Chandrayana ,  Gabriel Tavridis ,  Kevin Wang

IPC: H04L12/26 ,  H04L12/24

Abstract: A data-driven approach to network performance diagnosis and root-cause analysis is presented. By collecting and aggregating data attribute values across multiple components of a content delivery system and comparing against baselines for points of inspection, network performance diagnosis and root-cause analysis may be prioritized based on impact on content delivery. Recommended courses of action may be determined and provided based on the tracked network performance analysis at diagnosis points.