Na C Cheng

20120254333, Oct 4, 2012

Apr 25, 2012

13/455862

Rajarathnam Chandramouli - Holmdel NJ, US
Xiaoling Chen - Sugar Land TX, US
Koduvayur P. Subbalakshmi - Holmdel NJ, US
Peng Hao - Cliffside Park NJ, US
Na Cheng - San Ramon CA, US
Rohan Perera - Phlidelphia PA, US

G06F 15/16

709206

A method and apparatus for automatically identifying harmful electronic messages, such as those presented in emails, on Craigslist or on Twitter, Facebook and other social media websites, features methodology for discriminating unwanted garbage communications (spam) and unwanted deceptive messages (scam) from wanted, truthful communications based upon patterns discernable from samples of each type of electronic communication. Methods are proposed that enable discrimination of wanted from unwanted communications in short electronic messages, such as on Twitter and for multilingual application.

20220318669, Oct 6, 2022

Apr 1, 2021

17/220567

- San Francisco CA, US
Na Cheng - Bellevue WA, US
Jayesh Govindarajan - Palo Alto CA, US

G06N 20/00
G06K 9/62

A computing system may receive a corpus of training data including a plurality of data entity schemas. A first data entity of a first set of data entities corresponding to a first data entity schema is associated with a topic characteristic based on a first set of attributes defined by the first data entity schema, and a first attribute of the first set of attributes is associated with a structural characteristic that is common across each of the first set of data entities. The system may identify a respective attribute type identifier for each attribute of the first set, generate an attribute embedding for each attribute using the attribute value and the identifier, generate an entity embedding based on each attribute embedding and parameterize the topic characteristic for each data entity and the structural characteristic for each attribute.

20220293094, Sep 15, 2022

Mar 15, 2021

17/202077

- San Francisco CA, US
Zachary Alexander - Berkeley CA, US
Victor Winslow Yee - Berkeley CA, US
Joseph R. Zeimen - San Francisco CA, US
Na Cheng - Bellevue WA, US
Chien-Sheng Wu - Mountain View CA, US
Wenhao Liu - Redwood City CA, US
Caiming Xiong - Menlo Park CA, US

G10L 15/16
H04L 12/58
G10L 15/22
G10L 15/08
G10L 15/06

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.

20230086302, Mar 23, 2023

Sep 20, 2021

17/479748

- San Francisco CA, US
Shubham Mehrotra - Santa Clara CA, US
Abhishek Sharma - Fremont CA, US
Shashank Harinath - Santa Clara CA, US
Na Cheng - Yarrow Point WA, US
Zineb Laraki - Atherton CA, US

G06F 40/263
G06F 40/58
G06K 9/62

A method that includes receiving an input at an interactive conversation service that uses an intent classification model. The method may further include generating, using an encoder model of the intent classification model, a set of output vectors corresponding to the input, where the encoder model is configured to determine a set of metrics corresponding to intent classifications. The method may further include determining, using an outlier detection model of the intent classification model, whether the input is in-domain or out-of-domain (OOD) based on a first vector of the set of output vectors satisfying a domain threshold relative to one or more of the intent classifications. The method may further include outputting, by the intent classification model, a second vector of the set of output vectors that indicates the set of metrics corresponding to the intent classifications or an indication that the input is OOD.

20210149921, May 20, 2021

Nov 15, 2019

16/685926

- San Francisco CA, US
Na Cheng - Dublin CA, US

G06F 16/28
G06F 16/21
G06N 7/00
G06N 3/00
G06F 17/27

Disclosed are some implementations of systems, apparatus, methods and computer program products for extracting state flow structures from a corpus of exchanges. The system generates vector representations of utterances of an entity common to the exchanges and uses the vector representations to cluster the utterances.The system labels the clusters and uses the labeled clusters to generate an exchange label sequence for each of the exchanges, where the exchange label sequence corresponds to a sequence of utterances generated by the entity. The system processes the exchange label sequences to generate a state flow structure, where each of the states is represented by a corresponding set of utterances.

20210149933, May 20, 2021

Apr 28, 2020

15/929364

- San Francisco CA, US
Weiping Peng - San Francisco CA, US
Na Cheng - Dublin CA, US
Feifei Jiang - San Mateo CA, US
Jacob Nathaniel Huffman - Oakland CA, US
Nandini Suresh Kumar - San Francisco CA, US
Khoa Le - San Francisco CA, US
Christopher Larry - San Francisco CA, US

salesforce.com, Inc. - San Francisco CA

G06F 16/31
H04L 12/58
G06F 16/34
G06F 16/35

Computing systems, database systems, and related methods are provided for recommending values for fields of database objects and dynamically updating a recommended value for a field of a database record in response to updated auxiliary data associated with the database record. One method involves obtaining associated conversational data, segmenting the conversational data, converting each respective segment of conversational data into a numerical representation, generating a combined numerical representation of the conversational data based on the sequence of numerical representations using an aggregation model, generating the recommended value based on the combined numerical representation of the conversational data using a prediction model associated with the field, and autopopulating the field of the case database object with the recommended value.

20210149949, May 20, 2021

Nov 15, 2019

16/685933

- San Francisco CA, US
Na Cheng - Dublin CA, US

G06F 16/61
G06F 7/08
G06F 40/30

Disclosed are some implementations of systems, apparatus, methods and computer program products for extracting topics from a corpus of exchanges. The system generates vector representations of utterances of an entity common to the exchanges and uses the vector representations to cluster the utterances. The system labels the clusters and uses the labeled clusters to generate an exchange label sequence for each of the exchanges, where each exchange label sequence corresponds to a sequence of utterances generated by the entity. The system processes the exchange label sequences to generate one or more subsets of the utterances, where each of the subsets corresponds to a particular topic.

20210149964, May 20, 2021

Nov 15, 2019

16/685909

- San Francisco CA, US
Anuprit Kale - El Cerrito CA, US
Zachary Alexander - Berkeley CA, US
Na Cheng - Dublin CA, US

G06F 16/9032
G06N 20/00
G06K 9/62
G06F 17/27

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.